Дисертації з теми "Autonomous and connected vehicles"
Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Autonomous and connected vehicles.
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 дисертацій для дослідження на тему "Autonomous and connected vehicles".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Wei, Jian. "Hybrid mobile computing for connected autonomous vehicles." Thesis, Aston University, 2018. http://publications.aston.ac.uk/37533/.
Анотація:
With increasing urbanization and the number of cars on road, there are many global issues on modern transport systems. Autonomous driving and connected vehicles are the most promising technologies to tackle these issues. The so-called integrated technology connected autonomous vehicles (CAV) can provide a wide range of safety applications for safer, greener and more efficient intelligent transport systems (ITS). As computing is an extreme component for CAV systems, various mobile computing models including mobile local computing, mobile edge computing and mobile cloud computing are proposed. However it is believed that none of these models fits all CAV applications, which have highly diverse quality of service (QoS) requirements such as communication delay, data rate, accuracy, reliability and/or computing latency. In this thesis, we are motivated to propose a hybrid mobile computing model with objective of overcoming limitations of individual models and maximizing the performances for CAV applications. In proposed hybrid mobile computing model three basic computing models and/or their combinations are chosen and applied to different CAV applications, which include mobile local computing, mobile edge computing and mobile cloud computing. Different computing models and their combinations are selected according to the QoS requirements of the CAV applications. Following the idea, we first investigate the job offloading and allocation of computing and communication resources at the local hosts and external computing centers with QoS aware and resource awareness. Distributed admission control and resource allocation algorithms are proposed including two baseline non-cooperative algorithms and a matching theory based cooperative algorithm. Experiment results demonstrate the feasibility of the hybrid mobile computing model and show large improvement on the service quality and capacity over existing individual computing models. The matching algorithm also largely outperforms the baseline non-cooperative algorithms. In addition, two specific use cases of the hybrid mobile computing for CAV applications are investigated: object detection with mobile local computing where only local computing resources are used, and movie recommendation with mobile cloud computing where remote cloud resources are used. For object detection, we focus on the challenges of detecting vehicles, pedestrians and cyclists in driving environment and propose three methods to an existing CNN based object detector. Large detection performance improvement is obtained over the KITTI benchmark test dataset. For movie recommendation we propose two recommendation models based on a general framework of integrating machine learning and collaborative filtering approach. The experiment results on Netflix movie dataset show that our models are very effective for cold start items recommendation.
2
Anantharaman, Gokul Arvind. "Cooperative Collision Avoidance for Connected and Autonomous Vehicles." The Ohio State University, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=osu1543424841946961.
3
Garro, Alexandra. "Connected Vehicle Co-Simulation for Autonomous Vehicles in Airsim using Ns-3." DigitalCommons@CalPoly, 2021. https://digitalcommons.calpoly.edu/theses/2332.
Анотація:
Vehicle-to-everything (V2X) communications enables vehicles to communicate directly with each other, as well as roadside infrastructure. Vehicle-to-vehicle (V2V) communication, a subset of V2X communication, enables the vehicle to not solely rely on on-board sensors and allows the vehicle to share information directly to any nearby vehicles. Information shared between vehicles may include a vehicle's position, velocity, and direction, as well as other data. As these are safety-critical applications, rigorous security assessments are needed, yet it can be very expensive, dangerous, and complex to test security vulnerabilities of autonomous vehicles. Therefore, we aim to leverage realistic open-sourced simulators to carry out testing for multiple features, such as security attacks as well as cooperative autonomous driving algorithms. Since there is no open-sourced simulator capable of visually and physically simulating a vehicle and accurately representing its network, this thesis aims to combine a vehicle simulator and network simulator in real-time. Specifically, we incorporate Network Simulator 3 (Ns-3) and Unreal Engine's plugin, Airsim. To run this type of simulation accurately requires high computation power and time, and these requirements can cause delays between the two simulators. To handle the delays during simulation, we propose a system using a time step synchronization technique to pair Airsim and Ns-3. We further elaborate on our incorporation of delaying network packets that arrive earlier than the ideal packet delay. Additionally, we validate our system by demonstrating proof-of-concept attacks. Specifically, we simulate a replay attack and a jamming attack on our system, as well as show that a sybil attack is possible.
4
Obenauf, Austin William. "CONNECTED AND AUTONOMOUS VEHICLES EFFECTS ON EMERGENCY RESPONSE TIMES." UKnowledge, 2019. https://uknowledge.uky.edu/ce_etds/84.
Анотація:
Emergency response times have been shown to be directly correlated with mortality rates of out-of-hospital patients. Studies have been conducted to show the relationship between time and mortality rates until patients receive the proper treatment. With more cardiac arrests and other life threatening illnesses occurring in the United States, more emergency calls will be required as well. As of today, technological advancements have been made to reduce response times, but human factors still require certain procedures, causing delays in the run time and increasing the rate of mortality. Here we show the results of emergency response times with the market penetration of connected and autonomous vehicles. With connected and autonomous vehicles, the average time emergency vehicles spend on the roadways can be significantly decreased. Safety procedures with human drivers can be eliminated, giving the emergency vehicle a proper right-of-way through virtual emergency lanes and removing the need to slow down and avoid vehicles at intersections or during periods of heavy congestion. Our results show a three minute decrease in response time under full market penetration of the technology, reducing the mortality rate and increasing the potential to save lives.
5
Sridhar, Srivatsan. "Cooperative Perception in Autonomous Ground Vehicles using a Mobile Robot Testbed." Thesis, Virginia Tech, 2017. http://hdl.handle.net/10919/88742.
Анотація:
With connected and autonomous vehicles, no optimal standard or framework currently exists, outlining the right level of information sharing for cooperative autonomous driving. Cooperative Perception is proposed among vehicles, where every vehicle is transformed into a moving sensor platform that is capable of sharing information collected using its on-board sensors. This helps extend the line of sight and field of view of autonomous vehicles, which otherwise suffer from blind spots and occlusions. This increase in situational awareness promotes safe driving over a short range and improves traffic flow efficiency over a long range.
This thesis proposes a methodology for cooperative perception for autonomous vehicles over a short range. The problem of cooperative perception is broken down into sub-tasks of cooperative relative localization and map merging. Cooperative relative localization is achieved using visual and inertial sensors, where a computer-vision based camera relative pose estimation technique, augmented with position information, is used to provide a pose-fix that is subsequently updated by dead reckoning using an inertial sensor. Prior to map merging, a technique for object localization using a monocular camera is proposed that is based on the Inverse Perspective Mapping technique. A mobile multi-robot testbed was developed to emulate autonomous vehicles and the proposed method was implemented on the testbed to detect pedestrians and also to respond to the perceived hazard. Potential traffic scenarios where cooperative perception could prove crucial were tested and the results are presented in this thesis.MS
6
Tamilarasan, Santhosh. "Use of Connected Vehicle Technology for Improving Fuel Economy and Driveability of Autonomous Vehicles." The Ohio State University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=osu1543787677995516.
7
Dabboussi, Abdallah. "Dependability approaches for mobile environment : Application on connected autonomous vehicles." Thesis, Bourgogne Franche-Comté, 2019. http://www.theses.fr/2019UBFCA029.
Анотація:
Les véhicules autonomes et connectés (VAC) doivent avoir une exigence de fiabilité et de sécurité adéquate dans un environnement incertain aux circonstances complexes. La technologie des capteurs, les actionneurs et l'intelligence artificielle (IA) améliorent constamment leurs performances, ce qui permet un développement continu des véhicules autonomes et une automatisation accrue de la tâche de conduite. Les VAC présentent de nombreux avantages dans la vie humaine, tels que l’augmentation de la sécurité routière, la réduction de la pollution et la fourniture d’une mobilité autonome aux non-conducteurs. Cependant, ces composants avancés créent un nouvel ensemble de défis en matière de sécurité et de fiabilité. Il est donc nécessaire d’évaluer ces technologies avant leur mise en œuvre.Nous étudions dans cette thèse la fiabilité du VAC dans son ensemble, en nous concentrant sur les capteurs et le système de communication. Pour cela, une analyse fonctionnelle a été réalisée pour le système VAC. Notre approche scientifique pour l'analyse de la fiabilité du VAC a été structurée avec des méthodes combinant des approches quantitatives et qualitatives (telles que l'analyse fonctionnelle interne et externe, l'analyse préliminaire des risques (APR) et l'analyse des modes de défaillance, de leurs effets et de leur criticité (AMDEC), etc. Afin de prouver nos résultats, une simulation a été réalisée à l'aide de la probabilité d'analyse d'arbre de défaillance (ADD) et elle a été réalisée pour valider l'approche proposée. Les données (taux d'échec) utilisées proviennent d'une base de données professionnelle concernant le type de composants présentés dans le système. À partir de ces données, un modèle probabiliste de dégradation a été proposé. Le calcul de probabilité a été effectué par rapport à un moment d'utilisation de référence. Par la suite, une analyse de sensibilité a été suggérée concernant les paramètres de fiabilité et des propositions de restructuration ont été élaborées pour les composants.CAV fournit des services de communication entre véhicules : véhicules à véhicules (V2V) ou avec infrastructures côté rue : véhicules à infrastructures (V2I). La technologie des “Communications dédiées à courte portée” (DSRC = Dedicated Short Range Communications) utilise plusieurs canaux pour fournir une variété d'applications de sécurité. Les applications de sécurité nécessitent des transmissions appropriées et fiables, tandis que les applications non liées à la sécurité exigent des performances et une vitesse élevée. Aujourd’hui, la diffusion de messages de sécurité de base (Basic safety message, BSM) est l’un des services fondamentaux des véhicules connectés. Pour cela, un modèle analytique destiné à évaluer la fiabilité des services de diffusion V2V relatifs à la sécurité basée sur IEEE 802.11 dans le système DSRC sur autoroute a été proposé. Enfin, une amélioration du modèle proposé a été faite afin d'accroître la fiabilité de la connexion V2V, en tenant compte de nombreux facteurs tels que la portée de transmission, la densité du véhicule, la distance de sécurité sur l'autoroute, le taux d'erreur de paquets, l'influence de bruit et les taux de défaillants pour les équipements de communications.L'évaluation de ces problèmes conduit à une analyse de sensibilité liée aux paramètres de fiabilité, ce qui contribue à davantage d'innovation dans les domaines de l'ingénierie automobileConnected and Autonomous vehicles (CAV) must have adequate reliability and safety requirements in uncertain environments with complex circumstances. Sensor technology, actuators and artificial intelligence (AI) are constantly and rapidly evolving, thus enabling further development of self-driving vehicles, and increasing the automation of driving. CAV shows many benefits in human life such as increasing road safety, reducing pollution, and providing independent mobility to non-drivers. However, these advanced components create a new set of challenges concerning safety and dependability. Hence, it is necessary to evaluate these technologies before implementation.We study in this thesis the reliability of CAV as a whole, focusing on sensors and the communication system. For that purpose, a functional analysis was done for the CAV system.Our scientific approach for the analyzing the CAV reliability, was structured with methods that combine quantitative and qualitative approaches such as functional analysis for both internal and external, Preliminary Risk Analysis (PRA), and failure modes and effects criticality analysis (FMECA), in addition to other analysis techniques.To prove our results, a simulation was done using the Fault Tree analysis (FTA) probability in order to validate the proposed approach. The data (Failure ratio) used were from a professional database related to the type of components presented in the system. Using this data, a probabilistic model of degradation was proposed. A probability calculation was performed in relation to a reference time of use. Thereafter a sensitivity analysis was suggested concerning the reliability parameters and redesign proposals developed for the components.CAV provide several communication models: vehicles to vehicle (V2V), or with Road Side Infrastructure: vehicle to infrastructure (V2I). Dedicated Short Range Communication (DSRC) employs a multichannel approach to cater for a variety of safety and non-safety applications. Safety applications necessitate appropriate and reliable transmissions, while non-safety applications require performance and high speed. Broadcasting of Basic Safety Messages (BSM) is one of the fundamental services in today’s connected vehicles. For that, an analytical model to evaluate the reliability of IEEE 802.11 based V2V safety-related broadcast services in DSRC system on highway was proposed. Finally, an enhancement on the proposed model was made in order to increase the reliability of the V2V connection, taking into consideration many factors such as transmission range, vehicle density, and safety headway distance on highway, packet error rate, noise influence, and failures rates of communication equipment.Evaluating these problems leads to a sensitivity analysis related to reliability parameters, which helps further innovation in CAV and automobile engineering
8
Zeng, Tengchan. "Joint Communication, Control, and Learning for Connected and Autonomous Vehicles." Diss., Virginia Tech, 2021. http://hdl.handle.net/10919/104216.
Анотація:
The use of connected and autonomous ground and aerial vehicles is a promising solution to reduce accidents, improve the traffic efficiency, and provide various services ranging from delivery
of goods to monitoring. Different from the current connected vehicles and autonomous vehicles,
connected and autonomous vehicles (CAVs) combine autonomy and wireless connectivity and
use both sensors and communication systems to increase their situational awareness and for their
decision-making. However, in order to reap all the benefits of deploying CAVs, one must consider
the interconnection between communication, control, and learning mechanisms for the CAV system design. The key goal of this dissertation is, thus, to develop foundational science that can be used for the design, analysis, and optimization of CAV systems while jointly taking into account
the synergies among communication, control, and learning systems. First, a joint communication
and control system design is developed for non-coordinated CAVs when performing autonomous
path tracking. In particular, the maximum time delay requirements are derived to guarantee the
stability of the controller when tracking two typical road scenarios (i.e., straight line and circular
curve). Tools from optimization theory and risk theory are then used to jointly optimize the
control system and power allocation for the communication network so as to maximize the number
of vehicular links that meet the controller's delay requirements. Second, the joint control and
communication design framework is extended to two coordinated CAVs applications, i.e., CAV
platoons and unmanned aerial vehicle (UAV) swarms. Third, a distributed machine learning algorithm, i.e., federated learning (FL), is proposed for a swarm of connected and autonomous UAVs to execute tasks, such as coordinated trajectory planning and cooperative target recognition. In particular, a rigorous convergence analysis for FL is performed to show how wireless factors impact the FL convergence performance, and the design of UAV swarm networks is optimized to
reduce the convergence time. Fourth, a new FL framework, called dynamic federated proximal
(DFP) algorithm, is proposed for designing the autonomous controller of CAVs while considering
the mobility of CAVs, the wireless fading channels, as well as the unbalanced and non independent and identically distributed data across CAVs. To improve the convergence of the proposed DFP algorithm, a contract-theoretic incentive mechanism is also proposed. Fifth, a wireless-enabled asynchronous federated learning (AFL) framework is proposed for urban air mobility (UAM) aircraft to collaboratively learn the turbulence prediction model. In particular, to characterize how UAM aircraft leverage wireless connectivity for AFL, a stochastic geometry based spatial model is developed and the wireless connectivity performance is analyzed. Then, a rigorous convergence analysis is performed for the proposed AFL framework to identify how fast the UAM aircraft converge to using the optimal turbulence prediction model. Sixth, based on the concordance order from stochastic ordering theory, a dependence control mechanism is proposed to improve the overall reliability of wireless networks for CAVs. Finally, to determine the optimal cache placement for CAVs, a novel spatio-temporal caching framework is proposed where the notion of graph motifs, i.e., the spatio-temporal communication patterns in wireless networks, is used. In conclusion, the frameworks presented in this dissertation will provide key fundamental guidelines to design, analyze, and optimize CAV systems.Doctor of Philosophy
The evolution of transportation systems has always been the key to the progress of human societies. Recently, technology advances in sensing, autonomy, computing, and wireless connectivity ushered in the era of connected and autonomous vehicles (CAVs). In essence, CAVs rely on the data collected from sensors and wireless communication systems to automatically make the operation decision. If designed properly, the deployment of CAVs can improve the safety and the driving experience, increase the fuel efficiency and road capacity, as well as provide various services ranging from delivery of goods to monitoring. To reap all these benefits of deploying CAVs, one must address a number of technique challenges related to the wireless connectivity, autonomy, and autonomous learning for CAV systems. In particular, for CAV connectivity, the challenges include building a low latency and highly reliable network, using proper models for mobile radio channels, and determining the effective content dissemination strategy. At the control level, key considerations include guaranteeing stability and robustness for the controller when faced with measurement errors and wireless imperfections and rapidly adapting the CAV to dynamic environments. Meanwhile, when CAVs use machine learning to complete their tasks (e.g., object detection and environment monitoring), insufficient training data, privacy concerns, communication overhead, and limited energy are among the main challenges. Therefore, this dissertation develops the foundational science needed to design, analyze, and optimize CAVs while jointly taking into account the challenges within the wireless network, controller, and leaning mechanism design. To this end, various frameworks for the joint communication, control, and learning design and wireless network optimizations are proposed for different CAV applications. The results show that, using the proposed frameworks, the performance of CAVs can be optimized with more reliable communication systems, more stable controller, and improved learning mechanism, enabling intelligent transportation systems for the future smart cities.
9
Ghiasi, Amir. "Connected Autonomous Vehicles: Capacity Analysis, Trajectory Optimization, and Speed Harmonization." Scholar Commons, 2018. https://scholarcommons.usf.edu/etd/7295.
Анотація:
Emerging connected and autonomous vehicle technologies (CAV) provide an opportunity to improve highway capacity and reduce adverse impacts of stop-and-go traffic. To realize the potential benefits of CAV technologies, this study provides insightful methodological and managerial tools in microscopic and macroscopic traffic scales. In the macroscopic scale, this dissertation proposes an analytical method to formulate highway capacity for a mixed traffic environment where a portion of vehicles are CAVs and the remaining are human-driven vehicles (HVs). The proposed analytical mixed traffic highway capacity model is based on a Markov chain representation of spatial distribution of heterogeneous and stochastic headways. This model captures not only the full spectrum of CAV market penetration rates but also all possible values of CAV platooning intensities that largely affect the spatial distribution of different headway types. Numerical experiments verify that this analytical model accurately quantifies the corresponding mixed traffic capacity at various settings. This analytical model allows for examination of the impact of different CAV technology scenarios on mixed traffic capacity. We identify sufficient and necessary conditions for the mixed traffic capacity to increase (or decrease) with CAV market penetration rate and platooning intensity. These theoretical results caution scholars not to take CAVs as a sure means of increasing highway capacity for granted but rather to quantitatively analyze the actual headway settings before drawing any qualitative conclusion.
In the microscopic scale, this study develops innovative control strategies to smooth highway traffic using CAV technologies. First, it formulates a simplified traffic smoothing model for guiding movements of CAVs on a general one-lane highway segment. The proposed simplified model is able to control the overall smoothness of a platoon of CAVs and approximately optimize traffic performance in terms of fuel efficiency and driving comfort. The elegant theoretical properties for the general objective function and the associated constraints provides an efficient analytical algorithm for solving this problem to the exact optimum. Numerical examples reveal that this exact algorithm has an efficient computational performance and a satisfactory solution quality. This trajectory-based traffic smoothing concept is then extended to develop a joint trajectory and signal optimization problem. This problem simultaneously solves the optimal CAV trajectory function shape and the signal timing plan to minimize travel time delay and fuel consumption. The proposed algorithm simplifies the vehicle trajectory and fuel consumption functions that leads to an efficient optimization model that provides exact solutions. Numerical experiments reveal that this algorithm is applicable to any signalized crossing points including intersections and work-zones. Further, the model is tested with various traffic conditions and roadway geometries. These control approaches are then extended to a mixed traffic environment with HVs, connected vehicles (CVs), and CAVs by proposing a CAV-based speed harmonization algorithm. This algorithm develops an innovative traffic prediction model to estimate the real-time status of downstream traffic using traffic sensor data and information provided by CVs and CAVs. With this prediction, the algorithm controls the upstream CAVs so that they smoothly hedge against the backward deceleration waves and gradually merge into the downstream traffic with a reasonable speed. This model addresses the full spectrum of CV and CAV market penetration rates and various traffic conditions. Numerical experiments are performed to assess the algorithm performance with different traffic conditions and CV and CAV market penetration rates. The results show significant improvements in damping traffic oscillations and reducing fuel consumption.
10
Alhuttaitawi, Saif. "Intersection coordination for Autonomous Vehicles." Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20936.
Анотація:
Connected Autonomous Vehicles require intelligent autonomous intersection management for safe and efficient operation. Given the uncertainty in vehicle trajectory, intersection management techniques must consider a safety buffer among the vehicles, which must also account for the network and computational delay, queue and determine the best solution to avoid traffic congestions (smart intersection management), in this paper we model traffic by using Poisson distribution method then add a birth-death processes for each state and combine both two in one queuing system (The Markovian chain) to model the traffic.Also, this paper will compare some autonomous vehicles communication techniques in intersections to draw the best scenario for autonomous vehicle network communication in order to reduce the traffic congestion in an intersection.The Connected Autonomous Vehicles and a normal autonomous vehicle, as well from the third line of the intersection a mix between the both will be provided into the intersection.The last section is about applying the results from the first and second research question into a simulator and compare the simulation results to approve the advantage of using the next generation of transportation technology (The connected autonomous vehicles) over the normal conventional vehicles.
11
Chen, Qi. "Cooperative Perception for Connected Autonomous Vehicle Edge Computing System." Thesis, University of North Texas, 2020. https://digital.library.unt.edu/ark:/67531/metadc1707376/.
Анотація:
This dissertation first conducts a study on raw-data level cooperative perception for enhancing the detection ability of self-driving systems for connected autonomous vehicles (CAVs). A LiDAR (Light Detection and Ranging sensor) point cloud-based 3D object detection method is deployed to enhance detection performance by expanding the effective sensing area, capturing critical information in multiple scenarios and improving detection accuracy. In addition, a point cloud feature based cooperative perception framework is proposed on edge computing system for CAVs. This dissertation also uses the features' intrinsically small size to achieve real-time edge computing, without running the risk of congesting the network. In order to distinguish small sized objects such as pedestrian and cyclist in 3D data, an end-to-end multi-sensor fusion model is developed to implement 3D object detection from multi-sensor data. Experiments show that by solving multiple perception on camera and LiDAR jointly, the detection model can leverage the advantages from high resolution image and physical world LiDAR mapping data, which leads the KITTI benchmark on 3D object detection. At last, an application of cooperative perception is deployed on edge to heal the live map for autonomous vehicles. Through 3D reconstruction and multi-sensor fusion detection, experiments on real-world dataset demonstrate that a high definition (HD) map on edge can afford well sensed local data for navigation to CAVs.
12
Shaikh, Palwasha Waheed. "Intelligent Infrastructures for Charging Reservation and Trip Planning of Connected Autonomous Electric Vehicles." Thesis, Université d'Ottawa / University of Ottawa, 2021. http://hdl.handle.net/10393/42735.
Анотація:
For an environmentally sustainable future, electric vehicle (EV) adoption rates have been growing exponentially around the world. There is a pressing need for constructing smart charging infrastructures that can successfully integrate the large influx of connected and autonomous EVs (CAEVs) into the smart grids. To fulfill the aspiration of massive deployment of autonomous mobility on demand (AMoD) services, the proposed fast and secure framework will need to address the long charging times and long waiting times of static charging. It will also need to consider dynamic wireless charging as a viable solution for the CAEVs on the move. In this thesis, a novel three-layer charging system design of static and dynamic wireless charging that can operate with the existing wired charging infrastructure and standards for Intelligent Transportation System (ITS) is presented. This internet of things (IoT) application is accompanied by a proposed handshake protocol with light-weight request message frames. It employs vehicle to infrastructure (V2I) and vehicle to grid (V2G) communications for fulfilling charging requests of CAEVs with the shortest possible route to the destination. The charging requests of the CAEV users are fulfilled by dynamically distributing the request over the three different types of charging equipment. Further, the requests are serviced and billed privately and securely using two different proposed payment schemes with the encrypted virtual currency. The hardware independent system can detect misalignment of the CAEVs on the wireless charging pads and the speed issue errors in dynamic wireless charging systems as well as avoid free-riders. Additionally, the proposed dynamic wireless charging network (DWCN) design specification tool is analyzed. The suggestions made by the tool for building a DWCN can enable implementers to achieve the desired charging delivery performance at the lowest cost possible. Finally, the presented system is simulated, and this verified and validated simulator is revealed to make reservations and plan trips with minimum waiting times, travel costs, and battery consumption per vehicle trip. The system results proved 90.25% charge delivery efficiency. This system is then compared with alternative system designs to help showcase its ability to aid implementers and analysts in making design choices with the simulation.
13
Lause, Federico Valentin III. "Adapting Crash Modification Factors for the Connected and Autonomous Vehicle Environment." UKnowledge, 2019. https://uknowledge.uky.edu/ce_etds/90.
Анотація:
The Crash Modification Factor (CMF) clearinghouse can be used to estimate benefits for specific highway safety countermeasures. It assists safety professionals in the allocation of investments. The clearinghouse contains over 7000 entries of which only 446 are categorized as intelligent transportation systems or advanced technology, but none directly address connected or autonomous vehicles (CAVs). Further, the effectiveness of highway safety countermeasures is assumed to remain constant over time, an assumption that is particularly problematic as new technologies are introduced. For example, for the existing fleet of human-driven vehicles, installation of rumble strip can potentially reduce “run-off-road” crashes by 40%. If specific CAV technologies, e.g., lane-tracking, can work without rumble strips, and say, half of all cars are so equipped, only half of the fleet will benefit, reducing the benefits of rumble strips by a commensurate amount. Benefits of the two improvements, e.g., rumble strips and automated vehicles, should not be double-counted. As there will still be human-driven and/or non-connected vehicles in the fleet, conventional countermeasures are still necessary, although returns on conventional safety investments may be significantly overestimated. This is important as safety investments should be optimized and geared to future, not past fleets. Moreover, as CMFs are based on historical events, the types of crashes experienced by human-driven, un-connected cars are likely to be much different in the future. This research presents methods to estimate the safety benefits that autonomous vehicles have to offer and the changes needed in CMFs as a result of their adoption. This will primarily be achieved by modifying and enhancing a tool co-developed by the Fellow that estimates the safety benefits of different levels of autonomy. This tool, ddSAFCAT, estimates CAV safety benefits using real-world data for crashes, market penetration, and effectiveness.
14
Fakharian, Qom Somaye. "Multi-Resolution Modeling of Managed Lanes with Consideration of Autonomous/Connected Vehicles." FIU Digital Commons, 2016. http://digitalcommons.fiu.edu/etd/2559.
Анотація:
Advanced modeling tools and methods are essential components for the analyses of congested conditions and advanced Intelligent Transportation Systems (ITS) strategies such as Managed Lanes (ML). A number of tools with different analysis resolution levels have been used to assess these strategies. These tools can be classified as sketch planning, macroscopic simulation, mesoscopic simulation, microscopic simulation, static traffic assignment, and dynamic traffic assignment tools. Due to the complexity of the managed lane modeling process, this dissertation investigated a Multi-Resolution Modeling (MRM) approach that combines a number of these tools for more efficient and accurate assessment of ML deployments.
This study clearly demonstrated the differences in the accuracy of the results produced by the traffic flow models incorporated into different tools when compared with real-world measurements. This difference in the accuracy highlighted the importance of the selection of the appropriate analysis levels and tools that can better estimate ML and General Purpose Lanes (GPL) performance. The results also showed the importance of calibrating traffic flow model parameters, demand matrices, and assignment parameters based on real-world measurements to ensure accurate forecasts of real-world traffic conditions. In addition, the results indicated that the real-world utilization of ML by travelers can be best predicated with the use of dynamic traffic assignment modeling that incorporates travel time, toll, and travel time reliability of alternative paths in the assignment objective function. The replication of the specific dynamic pricing algorithm used in the real-world in the modeling process was also found to provide the better forecast of ML utilization.
With regards to Connected Vehicle (CV) operations on ML, this study demonstrated the benefits of using results from tools with different modeling resolution to support each other’s analyses. In general, the results showed that providing toll incentives for Cooperative Adaptive Cruise Control (CACC)-equipped vehicles to use ML is not beneficial at lower market penetrations of CACC due to the small increase in capacity with these market penetrations. However, such incentives were found to be beneficial at higher market penetrations, particularly with higher demand levels.
15
Adler, Martin, Stefanie Peer, and Tanja Sinozic. "Autonomous, connected, electric shared vehicles (ACES) and public finance: An explorative analysis." Elsevier, 2019. http://epub.wu.ac.at/7200/1/main.pdf.
Анотація:
This paper discusses the implications of autonomous-connected-electric-shared vehicles (ACES) for public finance, which have so far been widely ignored in the literature. In OECD countries, 5-12% of federal and up to 30% of local tax revenues are currently collected from fuel and vehicle taxation. The diffusion of ACES will significantly reduce these important sources of government revenues and affect transport-related government expenditures, unless additional policies are introduced to align the new technological context with the tax revenue requirements. We argue that the realization of socioeconomic benefits of ACES depends on the implementation of tailored public finance policies, which can take advantage of the increase in data availability from the further digitalization of transportation systems. In particular, the introduction of road tolls in line with "user Pays" and "polluter Pays" principles will become more feasible for policy. Moreover, innovation in taxation schemes to fit the changing technological circumstances may alter the relative importance of levels of governance in transport policy making, likely shifting power towards local, in particular urban, governmental levels. We finally argue that, given the risk of path-dependencies and lock-in to sub-optimal public finance regimes if policies are implemented late, further research and near-term policy actions taken during the diffusion process of ACES are required.
16
McManus, Ian Patrick. "The Impact of Cyberattacks on Safe and Efficient Operations of Connected and Autonomous Vehicles." Thesis, Virginia Tech, 2021. http://hdl.handle.net/10919/104891.
Анотація:
The landscape of vehicular transportation is quickly shifting as emerging technologies continue to increase in intelligence and complexity. From the introduction of Intelligent Transportation Systems (ITS) to the quickly developing field of Connected and Autonomous Vehicles (CAVs), the transportation industry is experiencing a shift in focus. A move to more autonomous and intelligent transportation systems brings with it a promise of increased equity, efficiency, and safety. However, one aspect that is overlooked in this shift is cybersecurity.
As intelligent systems and vehicles have been introduced, a large amount of research has been conducted showing vulnerabilities in them. With a new connected transportation system emerging, a multidisciplinary approach will be required to develop a cyber-resilient network. Ensuring protection against cyberattacks and developing a system that can handle their consequences is a key objective moving forward. The first step to developing this system is understanding how different cyberattacks can negatively impact the operations of the transportation system.
This research aimed to quantify the safety and efficiency impacts of an attack on the transportation network. To do so, a simulation was developed using Veins software to model a network of intelligent intersections in an urban environment. Vehicles communicated with Road-Side Units (RSUs) to make intersection reservations – effectively simulating CAV vehicle network. Denial of Service (DoS) and Man in the Middle (MITM) attacks were simulated by dropping and delaying vehicle's intersection reservation requests, respectively. Attacks were modeled with varying degrees of severity by changing the number of infected RSUs in the system and their attack success rates.
Data analysis showed that severe attacks, either from a DoS or MITM attack, can have significant impact on the transportation network's operations. The worst-case scenario for each introduced an over 20% increase in delay per vehicle. The simulation showed also that increasing the number of compromised RSUs directly related to decreased safety and operational efficiency. Successful attacks also produced a high level of variance in their impact. One other key finding was that a single compromised RSU had very limited impact on the transportation network.
These findings highlight the importance of developing security and resilience in a connected vehicle environment. Building a network that can respond to an initial attack and prevent an attack's dissemination through the network is crucial in limiting the negative effects of the attack. If proper resilience planning is not implemented for the next generation of transportation, adversaries could cause great harm to safety and efficiency with relative ease. The next generation of vehicular transportation must be able to withstand cyberattacks to function. Understanding their impact is a key first step for engineers and planners on the long road to ensuring a secure transportation network.Master of Science
The landscape of transportation is quickly shifting as transportation technologies continue to increase in intelligence and complexity. The transportation industry is shifting its focus to Connected and Autonomous Vehicles (CAVs). The move to more autonomous and intelligent transportation systems brings with it a promise of increased transportation equity, efficiency, and safety. However, one aspect that is often overlooked in this shift is cybersecurity. As intelligent systems and vehicles have been introduced, a large amount of research has been conducted showing cyber vulnerabilities in them. With a new connected transportation system emerging, a multidisciplinary approach will be required to prevent and handle attacks. Ensuring protection against cyberattacks is a key objective moving forward. The first step to developing this system is understanding how different cyberattacks can negatively impact the operations of the transportation system. This research aimed to measure the safety and efficiency impacts of an attack on the transportation network. To do so, a simulation was developed to model an intelligent urban road network. Vehicles made reservations at each intersection they passed – effectively simulating an autonomous vehicle network. Denial of Service (DoS) and Man in the Middle (MITM) attacks were simulated by dropping, and delaying vehicle's intersection reservation requests, respectively. These cyberattacks were modeled with varying degrees of severity to test the different impacts on the transportation network. Analysis showed that severe attacks can have significant impact on the transportation network's operations. The worst-case scenario for each attack introduced an over 20% increase in delay per vehicle. The simulation showed also that increasing the number of attacked intersections directly related to decreased safety and operational efficiency. Successful attacks also produced a high level of variance in their impact. One other key finding was that a single compromised RSU had very limited impact on the transportation network. These findings highlight the importance of developing security and resilience in a connected vehicle environment. Building a transportation network that can respond to an initial attack and prevent it from impacting the entire network is crucial in limiting the negative effects of the attack. If proper resilience planning is not implemented for CAVs, hackers could cause great harm to safety and efficiency with relative ease. The next generation of vehicular transportation must be able to withstand cyberattacks to function. Understanding their impact is a key first step for engineers and planners on the long road to ensuring a secure transportation network.
17
Brasier, Richard. "Efficient autonomy: Identifying energy efficiency opportunities with the introduction of autonomous and connected vehicles." Thesis, Brasier, Richard (2015) Efficient autonomy: Identifying energy efficiency opportunities with the introduction of autonomous and connected vehicles. Other thesis, Murdoch University, 2015. https://researchrepository.murdoch.edu.au/id/eprint/30759/.
Анотація:
Much of the scientific and policy analysis of autonomous vehicles advocates their safety and accessibility. This dissertation seeks to contribute to broadening academic discourse by examining the energy efficiency opportunities of the introduction of autonomous vehicles and vehicle communication technology. As the global market for autonomous vehicles develops, the impacts on society are beginning to be investigated including the impact on energy efficiency. This dissertation will contribute to this discourse by examining platooning and automated intersection management as techniques for improving efficiency as a result of the introduction of autonomous vehicles. In addition, this dissertation will analyse how society is likely to adapt to autonomous vehicles being introduced into the market and the how it may impact the energy efficiency of transportation networks. This examination demonstrates that there is great scope for energy efficiency as society and systems adapt to this technological change.
18
Bouchouia, Mohammed. "Multi layered Misbehavior Detection for a connected and autonomous vehicle." Electronic Thesis or Diss., Institut polytechnique de Paris, 2023. http://www.theses.fr/2023IPPAT018.
Анотація:
De nos jours, le domaine des véhicules, y compris les véhicules autonomes et les villes intelligentes, est en train de se développer pour moderniser la vie humaine dans une ville où tout est connecté : les humains grâce à un smartphone, les infrastructures, les voitures et les motos. Dans un tel système, les informations sont échangées, traitées et utilisées pour le bon fonctionnement de toute entité dans le système. Cependant, la dépendance accrue à la communication véhiculaire en fait également une cible d'attaques de sécurité, ce qui pourrait entraîner la diffusion d'informations fausses ou manipulées provenant de sources malveillantes. Cela pourrait constituer une menace pour le bon fonctionnement du système et pourrait potentiellement entraîner des accidents. Pour résoudre ce problème, il est crucial de valider et de vérifier la communication pour garantir son exactitude et prévenir les attaques malveillantes. Nous avons pour objectif de formuler la détection de comportements anormaux pour les véhicules connectés et autonomes de niveau 4/5 d'automatisation. Dans notre thèse, nous proposons une architecture multicouche pour la détection de comportements anormaux avec un apprentissage automatique pour sécuriser la communication, les capteurs et les composants internes des véhicules connectés et autonomes. Cette architecture nous permet de proposer un nouveau modèle de réseau de neurones basé sur l'apprentissage par renforcement pour la détection de comportements anormaux. Nous avons montré dans un environnement simulé, à travers une évaluation, que notre modèle est capable de détecter des comportements anormaux nouveaux et fonctionne mieux que les algorithmes de l'état de l'art. De plus, nous abordons la fuite de données dans les communications véhiculaires et proposons une méthode de validation croisée pour éviter cette fuite dans les applications d'apprentissage automatique. Lors de l'évaluation des résultats de notre thèse, nous avons développé une simulation pour les environnements de véhicules, capable d'injecter et de détecter des comportements anormaux. Enfin, les idées développées dans cette thèse ont donné lieu à plusieurs publicationsIn recent years, the vehicular field has undergone significant advancements with the development of autonomous vehicles and smart cities. These advancements have brought about a modernization of human life, where everything is interconnected - from individuals through smartphones to infrastructure, cars, and motorcycles. In such a system, information is exchanged and processed, and used to ensure the proper functioning of all entities. However, the increased reliance on V2X communication also makes it a target for security attacks, which could lead to the dissemination of false or manipulated information from malicious sources. This could pose a threat to the proper functioning of the system and can potentially result in accidents. To address this problem, it is crucial to validate and verify the communication to ensure its accuracy and prevent malicious attacks. We aim to formulate misbehavior and misbehavior detection for connected and autonomous vehicles of level 4/5 automation. In our thesis, we propose a multi-layered architecture for the detection of abnormal behaviors with automatic learning to secure the connected and autonomous vehicles' communications, sensors, and internal components. The architecture allows us to propose a novel reinforcement learning based neural architecture for the detection of misbehaviors where we showed in a simulated environment, through evaluation, that the model is capable of detecting novel misbehaviors and performs better than current state-of-the-art algorithms. Furthermore, we tackle data leakage in V2X data and propose a cross-validation method to avoid said leakage in machine learning applications. We also developed a simulation for vehicular environments capable of injecting and detecting misbehaviors for the evaluation of our thesis results. The ideas developed in this research have resulted in several publications and have the potential to significantly enhance the security and reliability of vehicular systems
19
Rahimi, Tariq Rahim. "Potential Impacts of Connected Vehicles in Urban Traffic: A Case Study." University of Toledo / OhioLINK, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1525457750006016.
20
Loulou, Hassan. "Verifying Design Properties at Runtime Using an MDE-Based Approach Models @Run.Time Verification-Application to Autonomous Connected Vehicles." Thesis, Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLS405.
Анотація:
Un véhicule autonome et connecté (ACV – pour Autonomous Connected Vehicle ) est un système cyber-physique où le monde réel et l’espace numérique virtuel se fusionnent. Ce type de véhicule requiert un processus de validation rigoureuse commençant à la phase de conception et se poursuivant même après le déploiement du logiciel. Un nouveau paradigme est apparu pour le monitorat continu des exécutions des logiciels afin d'autoriser des adaptations automatiquement en temps réel, systématiquement lors d’une détection de changement dans l'environnement d'exécution, d’une panne ou d’un bug. Ce paradigme s’intitule : « Models@Run.time ». Cette thèse s’inscrit dans le cadre des ACVs et plus particulièrement dans le contexte des véhicules qui collaborent et qui partagent leurs données d’une manière sécurisée. Plusieurs approches de modélisation sont déjà utilisées pour exprimer les exigences relatives au contrôle d'accès afin d’imposer des politiques de sécurité. Toutefois, leurs outils de validation ne tiennent pas compte les impacts de l'interaction entre les exigences fonctionnelles et les exigences de sécurité. Cette interaction peut conduire à des violations de sécurité inattendues lors de l'exécution du système ou lors des éventuelles adaptations à l’exécution. En outre, l’estimation en temps réel de l’état de trafic utilisant des données de type crowdsourcing pourrait être utilisée pour les adaptations aux modèles de coopération des AVCs. Cette approche n'a pas encore été suffisamment étudiée dans la littérature. Pour pallier à ces limitations, de nombreuses questions doivent être abordées:• L'évolution des exigences fonctionnelles du système doit être prise en compte lors de la validation des politiques de sécurité ainsi que les scénarios d'attaque doivent être générés automatiquement.• Une approche pour concevoir et détecter automatiquement les anti-patrons (antipatterns) de sécurité doit être développée. En outre, de nouvelles reconfigurations pour les politiques de contrôle d'accès doivent également être identifiées, validées et déployées efficacement à l'exécution.• Les ACVs doivent observer et analyser leur environnement, qui contient plusieurs flux de données dite massives (Big Data) pour proposer de nouveaux modèles de coopération, en temps réel.Dans cette thèse, une approche pour la surveillance de l'environnement des ACVs est proposée. L’approche permet de valider les politiques de contrôle d'accès et de les reconfigurer en toute sécurité. La contribution de cette thèse consiste à:• Guider les Model Checkers de sécurité pour trouver automatiquement les scénarios d'attaque dès la phase de conception.• Concevoir des anti-patterns pour guider le processus de validation, et développer un algorithme pour les détecter automatiquement lors des reconfigurations des modèles.• Construire une approche pour surveiller en temps réel les flux de données dynamiques afin de proposer des adaptations de la politique d'accès lors de l'exécution.L’approche proposée a été validée en utilisant plusieurs exemples liés aux ACVs, et les résultats des expérimentations prouvent la faisabilité de cette approcheAutonomous Connected Vehicles (ACVs) are Cyber-physical systems (CPS) where the computationalworld and the real one meet. These systems require a rigorous validation processthat starts at design phase and continues after the software deployment. Models@Runtimehas appeared as a new paradigm for continuously monitoring software systems execution inorder to enable adaptations whenever a change, a failure or a bug is introduced in the executionenvironment. In this thesis, we are going to tackle ACVs environment where vehicles tries tocollaborate and share their data in a secure manner.Different modeling approaches are already used for expressing access control requirementsin order to impose security policies. However, their validation tools do not consider the impactsof the interaction between the functional and the security requirements. This interaction canlead to unexpected security breaches during the system execution and its potential runtimeadaptations. Also, the real-time prediction of traffic states using crowd sourcing data could beuseful for proposition adaptations to AVCs cooperation models. Nevertheless, it has not beensufficiently studied yet. To overcome these limitations, many issues should be addressed:• The evolution of the system functional part must be considered during the validation ofthe security policy and attack scenarios must be generated automatically.• An approach for designing and automatically detecting security anti-patterns might bedeveloped. Furthermore, new reconfigurations for access control policies also must befound, validated and deployed efficiently at runtime.• ACVs need to observe and analyze their complex environment, containing big-datastreams to recommend new cooperation models, in near real-time.In this thesis, we build an approach for sensing the ACVs environment, validating its accesscontrol models and securely reconfiguring it on the fly. We cover three aspects:• We propose an approach for guiding security models checkers to find the attack scenariosat design time automatically.• We design anti-patterns to guide the validation process. Then, we develop an algorithmto detect them automatically during models reconfigurations. Also, we design a mechanismfor reconfiguring the access control model and we develop a lightweight modularframework for an efficient deployment of new reconfigurations.• We build an approach for the real-time monitoring of dynamic data streams to proposeadaptations for the access policy at runtime.Our proposed approach was validated using several examples related o ACVs. the results ofour experimentations prove the feasibility of this approach
21
Lakshmanan, Vinith Kumar. "Cooperative control of eco-driving trajectories for a fleet of electric connected and autonomous vehicles". Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPAST068.
Анотація:
Les véhicules électriques connectés et autonomes (CAV) qui maximisent l'efficacité énergétique peuvent être considérés comme une approche intégrée pour répondre aux différentes tendances, notamment la transition verte et numérique, dans l'industrie automobile. Les stratégies d'économie d'énergie pour les CAV peuvent être classées en écoroutage (ER) et écoconduite (ED). Avec l'augmentation de la pénétration des CAV, ces véhicules peuvent coopérer plutôt que de se disputer le droit de passage, ce qui donne naissance aux véhicules coopératifs connectés et automatisés (CCAV). En fonction du niveau d'information partagé et de la motivation pour l'efficacité énergétique, les stratégies d'ED des CCAV peuvent être catégorisées comme Non Coopératives (NC), Coopératives (C) et Coopératives Centralisées (CC). Les objectifs principaux de cette thèse sont d'évaluer expérimentalement une stratégie de base connue de NC-ED pour un seul CCAV, d'obtenir des solutions analytiques d'ED pour une flotte de CCAV électriques avec différents niveaux de coopération pour des scénarios de peloton et d'intersection sans signalisation, et d'évaluer l'influence des différents niveaux de coopération sur la consommation d'énergie de la flotte. La thèse présente en premier lieu une stratégie NC-ED connue pour un seul CAV qui constitue la base de cette recherche. L'ED est formulé comme un Problème de Commande Optimale (OCP), pour un scénario de suivi de voiture et sans contraintes, et résolu par le Principe du Minimum de Pontryagin (PMP). La stratégie de suivi de voiture NC-ED de base prédit le mouvement du véhicule d'avant en cas d'accélération constante (CA) afin de permettre des solutions analytiques. Dans cette thèse, des modèles de prédiction plus sophistiqués du véhicule d'avant, à savoir le CA-AB et le EDM-LOSP, sont développés en l'absence de communication V2V. Les résultats indiquent que le véhicule ego utilisant l'EDM-LOSP est plus performant que le CA-AB avec un gain d'énergie de 4 %, tandis que le CA-AB est plus performant de 4,5 % que le CA de base sur des trajets urbains.Le scénario de base NC-ED de suivi de voiture est étendu à un scénario ED en peloton. Un OCP est formulé pour les trois niveaux de coopération et des solutions analytiques sont obtenues à l'aide du PMP. Les pelotons utilisant les trois stratégies de coopération sont évalués par rapport à un scénario de référence utilisant un régulateur de vitesse adaptatif dans un environnement de simulation. Les résultats indiquent une économie d'énergie plus importante avec des niveaux de coopération plus élevés. Le peloton CC-ED présente une économie d'énergie meilleure de 2,5 %, sur un cycle WLTC High, par rapport au peloton NC-ED. Cette thèse présente en outre un OCP formulé pour un ensemble de CCAVs traversant en toute sécurité une intersection sans signalisation en minimisant la consommation d'énergie. L'OCP est formulé pour deux niveaux de coopération : NC-ED et C-ED. L'OCP est résolu à l'aide de PMP, des solutions sont présentés. Les deux stratégies sont évaluées par rapport à l'IDM comme référence pour différents débits. Les résultats indiquent que la stratégie C-ED est la plus performante, avec un gain énergétique de 23,7 %. Enfin, cette thèse présente une approche expérimentale de mise en œuvre de la stratégie de référence NC-ED dans une voiture électrique Renault Zoé. Les solutions ED sont mises en œuvre via une tablette, qui affiche la vitesse optimale calculée pour que le conducteur puisse la suivre dans les secondes suivantes. La mise en œuvre de l'algorithme se compose de deux parties : un profil de vitesse prévu au début du voyage et un profil de vitesse ED calculé en temps réel afin de conseiller le conducteur. Dans ce travail, les profils de conduite sont analysés a posteriori pour étudier l'impact des hypothèses faites au début d'un voyage. Les résultats indiquent l'importance d'avoir des informations précises sur le trafic et les feux de circulationElectric Connected and Autonomous Vehicles (CAVs) that maximize energy efficiency can be considered an integrated approach to meet the various trends, mainly green and digital transition, in the automotive industry. Energy-saving strategies for CAVs on the vehicle level can be categorized into Eco-Routing (ER) and Eco-Driving (ED). With increased penetration of CAVs, such vehicles can cooperate rather than compete for right of way, giving rise to Cooperative Connected and Automated Vehicles (CCAVs). Based on the level of information shared and the motivation for energy efficiency, the behavior of CCAVs can be categorized into Non-Cooperative (NC), Cooperative (C), and Centralized Cooperative (CC) ED strategies. Each CCAV optimizes for itself in NC-ED and shares only its instantaneous states with its neighbors, while in C-ED, it shares its future intentions. Each CCAV's control action optimizes for the entire group in the CC-ED.The main objectives of this thesis are to experimentally assess a known baseline NC-ED strategy for a single CAV; to obtain analytical eco-driving solutions for a fleet of electric CCAVs, with varying levels of cooperation, for platooning and un-signalized intersection scenarios; and to evaluate the influence of the varying levels of cooperation, namely, NC-ED, C-ED, and CC-ED, on fleet energy consumption. The thesis first introduces a known NC-ED strategy for a single CAV that forms the basis for this thesis. ED is formulated as an optimal control problem for an unconstrained and car-following scenario and solved using Pontryagin's Minimum Principle (PMP). The baseline NC-ED car-following strategy predicts the lead vehicle's motion under Constant Acceleration (CA) to facilitate analytical closed-form solutions. In a chapter of this thesis, more sophisticated lead vehicle prediction models, namely Constant Acceleration-Average Braking (CA-AB) and EDM-LOS based Predictor (EDM-LOSP), are developed in the absence of V2V communication. The results distinguished the performance of the predictors in urban routes, where the ego vehicle using EDM-LOSP performed better than CA-AB with 4 % energy gain, while CA-AB had 4.5 % over the baseline CA. The baseline NC-ED car-following scenario is extended to a platooning ED scenario. An OCP is formulated for the three levels of cooperation, and analytical solutions are obtained using PMP. Platoons with the three cooperative strategies are evaluated against a baseline using Adaptive Cruise Control in a simulation environment. The results indicate higher energy saving with increased levels of cooperation. The CC-ED platoon performed best with 2.5 % energy saving over the NC-ED platoon on a WLTC High cycle. This thesis further presents an OCP formulated for a set of CCAVs safely crossing an un-signalized intersection while minimizing energy consumption. The OCP is formulated for two levels of cooperation: NC-ED and C-ED. The conflicts that arise in an intersection are analyzed and transformed into constraints. The OCP with the constraints is solved using PMP, and analytical solutions are presented. The two strategies are evaluated against Intelligent Driver Model (IDM) as a baseline for various flow rates. The results indicate that C-ED performs best, with 23.7 % energy gains over IDM. Finally, this thesis presents an experimental implementation of the baseline NC-ED strategy in a Renault Zoe electric car. The ED solutions are implemented via a tablet, that displays the computed optimal speed for the driver to follow in the next second. The implementation of the algorithm consists of two parts: an ED speed profile predicted at the trip's start under certain assumptions and an ED speed profile computed in real-time advising the driver. In this work, the driven profiles are analyzed a posteriori to study the impact of the assumptions made at the start of a trip. The results indicate the importance of having accurate information on traffic and traffic light behavior
22
Almobayedh, Hamad Bader. "Simulation of the Impact of Connected and Automated Vehicles at a Signalized Intersection." University of Dayton / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1557207826602638.
23
Narasimhan, Ramakrishnan Akshra. "Design and Evaluation of Perception System Algorithms for Semi-Autonomous Vehicles." The Ohio State University, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=osu1595256912692618.
24
He, Mingzhe, and Xinyu Lin. "Connected Tyres : Real-time Tyre Monitoring System for Fleet& Autonomous Vehicles with Tyre WearEstimation through Sensor Fusion." Thesis, KTH, Fordonsdynamik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-290080.
Анотація:
Tyres are one crucial part for vehicles, as they are the only contact pointbetween the vehicle and the road. Intelligent tyres are a trending new subjectin the tyre industry. They are designed to monitor various tyre states and sendthis information to both drivers and remote servers. The master thesis focuseson the proposal of a real-time tyre monitoring system for fleet and autonomousvehicles. It includes developing a tyre wear model and analysis of the currenttyre pressure monitoring functionality by leveraging the connectivity of fleetvehicles equipped with a Volvo web cloud service. The tyre wear model indirectlymonitors the tread depth of the vehicles all four tyres by identifyingcharacteristics between worn and fresh tyres. The two characteristics are identifiedby monitoring and analyzing vehicle speed and braking signals. The twocharacteristics is input to a voting scheme which decides when a worn tyre isdetected. The test vehicle was a Volvo XC40 with three types of tyres: wintertyres, summer tyres and worn summer tyres. The wear model gives 90 %accuracy to 10 set of test data, randomly selected from all dataset at HälleredProving Ground (Sweden). The connectivity realizes the data transmissionfrom the raw data of onCAN and FlexRay signals stored in a Volvo web cloudservice to the tyre monitoring fleet system. The signals are filtered and resampled,leaving the required signals of the tyre pressure monitor system andthe tyre wear model. Two signals, Calibration Status and iTPMS Status, areused to perform a statistical analysis on tyre pressure by categorizing the calibrationstatus and the tyre pressure conditions.The project outcome is an interfacebuilt on MATLAB GUI for demonstration of vehicle identification andtyre health conditions, with the embedded tyre wear model and connectivity.Däck är en viktig del för fordon, eftersom de är den enda kontaktpunktenmellan fordonet och vägen. Intelligenta däck är ett trendigt nytt ämne i däckindustrin.De är utformade för att övervaka olika däcktillstånd och skicka dennainformation till både förare och fjärrservrar. Examensarbetet är inriktat på ettförslag till ett däckövervakningssystem i realtid för fordonsflottor och autonomafordon och inkluderar en däckslitagesmodell och anslutning. Det inkluderaratt utveckla en slitagemodell och analys av den aktuella däcktrycksövervakningsfunktionengenom att studera Volvos fordonspark som är utrustade medVolvos webbmolntjänst. Däckens slitagemodell övervakar indirekt slitbanedjupetpå alla fyra däck genom att identifiera egenskaper mellan slitna och nyadäck. De två egenskaperna identifieras genom att övervaka och analysera fordonshastighet och bromssignaler. De två egenskaperna är inmatade i ett röstningsschemasom avgör när ett slitet däck upptäcks. Testfordonet var en VolvoXC40 med tre typer av däck, vinterdäck samt nya och slitna sommardäck.Modellen ger 90 % noggrannhet för 10 uppsättningar testdata, slumpmässigtvalda från alla dataset på Hällered provbana (Sverige). Anslutningen genomfördataöverföringen av rådata från onCAN och FlexRay-signaler lagrade ienVolvoswebbmolntjänst till däcksövervakningssystemet. Signalerna filtrerasoch samplas på nytt för att skapa de nödvändiga signalerna till däcktrycksövervakningssystemetoch däckslitagemodellen. Två signaler, kalibreringsstatusoch iTPMS-status, används för att utföra en statistisk analys av däcktrycketgenom att kategorisera kalibreringsstatus och däcktrycksförhållanden. Projektetsresultat är ett gränssnitt byggt på MATLAB GUI för demonstration avfordonsidentifiering och däcktillstånd. med inbäddad däckslitagemodell ochanslutning.
25
Kherroubi, Zine el abidine. "Novel off-board decision-making strategy for connected and autonomous vehicles (Use case highway : on-ramp merging)." Thesis, Lyon, 2020. http://www.theses.fr/2020LYSE1331.
Анотація:
L'insertion sur autoroute est un défi pour réaliser une conduite entièrement automatisée (Niveau 4 de conduite autonome). La combinaison des technologies de communication et de conduite autonome, qui sous-tend la notion de Connected Autonomous Vehicles (CAV), peut améliorer considérablement les performances de sécurité lors de l'insertion sur autoroute. Cependant, même avec l'émergence des véhicules CAVs, certaines contraintes clés doivent être prises en compte afin de réaliser une insertion sécurisée sur autoroute. Tout d'abord, les véhicules conduits par des conducteurs humains seront toujours présents sur la route, et il faudra peut-être des décennies avant que tous les véhicules commercialisés ne soient entièrement autonomes et connectés. Aussi, les capteurs embarqués des véhicules peuvent fournir des données inexactes ou incomplètes en raison des limites des capteurs et des angles morts, en particulier dans de telles situations de conduite critiques. Afin de résoudre ces problèmes, la présente thèse propose une nouvelle solution utilisant une unité de bord de route (Road-Side Unit (RSU)) permettant une insertion entièrement automatisée sur autoroute pour véhicules connectés et automatisés. Notre approche est basée sur un réseau de neurones artificiels (ANN) pour prédire l'intention des conducteurs. Cette prédiction est utilisée comme état d'entrée pour un agent Deep Reinforcement Learning (DRL) qui fournit l'accélération longitudinale pour le véhicule qui s'insère. Afin d'y parvenir, nous montrons d'abord comment l'unité Road-Side Unit peut-être utilisée pour améliorer la perception dans la zone d'insertion sur autoroute. Ensuite, nous proposons un modèle de reconnaissance d'intention du conducteur qui peut prédire le comportement des véhicules conduits par des conducteurs humains sur la voie principale de l'autoroute, avec une précision de 99%. Nous utilisons la sortie de ce modèle comme état d'entrée pour entrainer un agent Twin Delayed Deep Deterministic Policy Gradients (TD3) qui apprend une politique de conduite « sûre » et « coopérative » pour effectuer l'insertion sur autoroute. Nous montrons que notre stratégie de prise de décision améliore les performances par rapport aux solutions proposées dans l'état de l'artMerging in the highway on-ramp is a significant challenge toward realizing fully automated driving (level 4 of autonomous driving). The combination of communication technology and autonomous driving technology, which underpins the notion of Connected Autonomous Vehicles (CAVs), may improve greatly safety performances when performing highway on-ramp merging. However, even with the emergence of CAVs vehicles, some keys constraints should be considered to achieve a safe on-ramp merging. First, human-driven vehicles will still be present on the road, and it may take decades before all the commercialized vehicles will be fully autonomous and connected. Also, on-board vehicle sensors may provide inaccurate or incomplete data due to sensors limitations and blind spots, especially in such critical situations. To resolve these issues, the present thesis introduces a novel solution that uses an off-board Road-Side Unit (RSU) to realize fully automated highway on-ramp merging for connected and automated vehicles. Our proposed approach is based on an Artificial Neural Network (ANN) to predict drivers’ intentions. This prediction is used as an input state to a Deep Reinforcement Learning (DRL) agent that outputs the longitudinal acceleration for the merging vehicle. To achieve this, we first show how the road-side unit may be used to enhance perception in the on-ramp zone. We then propose a driver intention model that can predict the behavior of the human-driven vehicles in the main highway lane, with 99% accuracy. We use the output of this model as an input state to train a Twin Delayed Deep Deterministic Policy Gradients (TD3) agent that learns « safe » and « cooperative » driving policy to perform highway on-ramp merging. We show that our proposed decision-making strategy improves performance compared to the solutions proposed previously
26
Monteuuis, Jean-Philippe. "Resilience by design & failures forecasting for a connected autonomous vehicle." Thesis, Institut polytechnique de Paris, 2020. http://www.theses.fr/2020IPPAT003.
Анотація:
Les véhicules autonomes dotés d'un niveau d'automatisation 5 conduiront de manière autonome dans tous les scénarios routiers tels que les autoroutes, les routes enneigées, les zones urbaines ou les embouteillages. L'intégration de la communication V2X, en tant que nouvelle source de perception du véhicule, pourrait supprimer les limitations de la perception locale en communiquant avec un piéton caché par un obstacle ou en détectant à l'avance la présence d'un véhicule caché par un brouillard épais. Cependant, cette communication V2X peut constituer une nouvelle source d'attaques menaçant la perception du véhicule. Les contre-mesures actuelles ne sont pas conçues pour toutes les architectures de véhicules autonomes, car elles requièrent l'assistance du conducteur ou fonctionnent avec un ensemble spécifique de capteurs. La thèse vise donc à proposer une architecture de perception générique et résiliante aux défaillances pour tous les types de véhicules connectés et autonomes. Dans cette thèse, nous proposons une architecture de perception générique nommée GPA avec son algorithme de perception résiliante aux défaillances (FRPA). Nous proposons une nouvelle méthode d'analyse de menaces et d'évaluation des risques nommée SARA, qui identifie et évalue le risque d'attaques ciblant les véhicules connectés et automatisés de niveau 5. Pour identifier où et comment ces attaques ont lieu, nous proposons un modèle d'attaquant et un modèle d'objectifs de sécurité pour tous les systèmes de perception automobile. Nous avons implémenté deux modules de notre algorithme FRPA: un module classification des défaillances basé sur une méthode de Machine Learning et un module de corrélation V2X-Capteur en considérant trois sources d'information: radar, camera et V2X. Nous avons mis en évidence plusieurs nouvelles attaques dans le cycle de perception et soulevé le besoin de nouvelles contre-mesures de sécurité centrées sur l'intégrité physique des infrastructures routières et sur les algorithmes de perception fiables. De plus, nos contre-mesures basées sur l'apprentissage automatique et la corrélation entre capteurs sont très précises pour détecter et classifier les défaillances de perception (score de précision supérieur à 90 %). Enfin, les idées développées dans la thèse ont abouti à 10 brevets déposés et à plusieurs publicationsAutonomous vehicles with an automation level 5 will drive autonomously in any road scenarios such as highways, snowy roads, urban areas, or traffic jams. The integration of V2X communication, as a new source of perception for the vehicle could remove the limitations of local perception by communicating with an occluded pedestrian or by detecting in advance the presence of a vehicle under a heavy mist. However, this V2X communication may be a new source of attacks threatening the vehicle perception. Current countermeasures are not designed for all autonomous vehicles because these countermeasures require the driver assistance or work with a specific set of sensors. Therefore, the thesis aims to propose a generic failure resilient perception architecture for all types of connected and autonomous vehicles supporting different kinds of sensors. In this thesis, we propose a generic perception architecture named GPA with its failure resilient perception algorithm (FRPA). We propose a new threat analysis and risk assessment method named SARA that identifies and assess the risk of attacks targeting connected and automated vehicles with an automation level 5. To identify where and how these attacks occur, we propose an attacker and a security goal model for all automotive perception systems. We implemented two modules of our failures resilient perception algorithm (FRPA): a Machine Learning based Failure Classifier and a V2X-Sensor Correlation Module considering three kinds of source: camera, radar, and V2X. We highlighted several new attacks in the perception pipeline and raise the need for new security countermeasures such as the physical integrity of road infrastructures and trustworthy perception algorithms. Besides, our countermeasures based on machine learning and sensor correlation showed very accurate results to detect and classifies perception failures (over 90% accuracy score). Finally, the ideas developed in the thesis resulted in 10 filled patents and several publications
27
Sala, Sanmartí Marcel. "Modeling present and future freeway management strategies : variable speed limits, lane-changing and platooning of connected autonomous vehicles." Doctoral thesis, Universitat Politècnica de Catalunya, 2019. http://hdl.handle.net/10803/668562.
Анотація:
Freeway traffic management is necessary to improve capacity and reduce congestion, especially in metropolitan freeways where the rush period lasts several hours per day. Traffic congestion implies delays and an increase in air pollutant emissions, both with harmful effects to society. Active management strategies imply regulating traffic demand and improving freeway capacity. While both aspects are necessary, the present thesis only addresses the supply side.
Part of the research in traffic flow theory is grounded on empirical data. Today, in order to extend our knowledge on traffic dynamics, detailed and high-quality data is needed. To that end, the thesis presents a pioneering data collection campaign, which was developed in a freeway accessing Barcelona. In a Variable Speed Limits (VSL) environment, different speed limits where posted, in order to observe their real and detailed effects on traffic. All the installed surveillance instruments were set to capture data in the highest possible level of detail, including video recordings, from where to count lane-changing maneuvers. With this objective, a semi-automatic method to reliably count lane changes form video recordings was developed and is presented in the thesis.
Data analysis proved that the speed limit fulfillment was only relevant in sections with enforcement devices. In these sections, it is confirmed that, the lower the speed limit, the higher the occupancy to achieve a given flow. In contrast, the usually assumed mainline metering effect of low speed limits was not relevant. This might be different in case of stretch enforcement. These findings mean that, on the one hand, VSL strategies aiming to restrict the mainline flow on a freeway by using low speed limits will need to be applied carefully, avoiding conditions as the ones presented here. On the other hand, VSL strategies trying to get the most from the increased vehicle storage capacity of freeways under low speed limits might be rather promising.
Results also show that low speed limits increase the speed differences across lanes for moderate demands. This, in turn, also increases the lane changing rates. In contrast, lower speed limits widen the range of flows under uniform lane flow distributions, so that, even for moderate to low demands, the under-utilization of any lane can be avoided. Further analysis of lane-changing activity allowed unveiling that high lane-changing rates prevent achieving the highest flows. This inverse relationship is modeled in the thesis using a stochastic model based on Bayesian inference. This model could be used as a control tool, in order to determine which level of lane-changing activity can be allowed to achieve a desired capacity with some level of reliability.
Previous results identify drivers' fulfillment of traffic regulations as a weak point in order to maximize the benefits of current management strategies, like VSL or lane-changing control. This is likely to change in the near future with the irruption of Autonomous Vehicles (AV) in freeways. V2X communications will allow directly actuating on individual vehicles with high accuracy. This will open the door to new management strategies based on simultaneous communication to groups of AVs and extremely short reaction times, like platooning, which stands out as a strategy with a huge potential to improve freeway traffic. Strings of AVs traveling at extremely short gaps (i.e. platoons) allow achieving higher capacities and lower energy consumption rates. In this context, the thesis presents a parsimonious macroscopic model for AVs platooning in mixed traffic (i.e. platoons of AVs travelling together with human driven vehicles). The model allows determining the average platoon length and reproducing the overall traffic dynamics leading to higher capacities. Results prove that with a 50% penetration rate of AVs in the lane, capacity could reach 3400 veh/h/lane under a cooperative platooning strategy.Per tal de millorar la capacitat i reduir la congestió a les autopistes cal gestionar el trànsit de manera activa. Les estratègies de gestió activa del trànsit són d’especial importància en autopistes metropolitanes. La congestió provoca retards i un increment del consum de combustible que va lligat a unes majors emissions de gasos contaminants, tots amb efectes perniciosos per la societat. La gestió activa del transit requereix regular la demanda i millorar la capacitat de la via. Encara que tots dos aspectes son necessaris, la present tesis només analitza la gestió de l’oferta. Part de la recerca en l’anàlisi i la teoria del trànsit es basa en dades empíriques. Per satisfer el requeriment de dades detallades i d’alta qualitat, aquesta tesis presenta una campanya pionera de recol·lecció de dades. Les dades es van recollir a l’autopista B-23 d’accés a Barcelona. Tots els instruments de mesura es van configurar per tal de registrar les dades amb el major nivell de detall possible, incloent les càmeres de videovigilància, d’on es varen extreure els comptatges de canvi de carril. Amb aquest objectiu, es va desenvolupar una metodologia semiautomàtica per comptar canvis de carril a partir de gravacions de trànsit, que es presenta en el cos de la tesi. L’anàlisi de les dades obtingudes ha demostrat que el compliment dels límits de velocitat només resulta rellevant en aquelles seccions que compten amb un radar. És en aquestes seccions on s’ha confirmat que com menor és el límit de velocitat, major es l’ocupació per a un flux donat. Per contra, la hipòtesi habitual de que uns límits de velocitat baixos produeixen una restricció del flux no es va observar de forma rellevant. Aquest comportament podria esser diferent en el cas d’implantar un radar de tram. Els resultats obtinguts també mostren com les diferències de velocitats entre carrils s’incrementen per a límits de velocitat baixos i en condicions de demanda moderada. Això, alhora, incrementa el nombre de canvis de carril. Per contra, els límits de velocitat baixos contribueixen a una distribució de flux més uniforme entre carrils, de forma que es pot evitar la infrautilització de carrils. L’anàlisi més detallat de l’activitat de canvi de carril demostra que una taxa elevada de canvis de carril impedeix assolir fluxos grans de circulació. En la tesi, aquesta relació inversa entre la taxa de canvis de carril i el flux màxim de trànsit a l’autopista s’ha modelat de forma estocàstica utilitzant un model basat en la inferència Bayesiana. Aquest model es pot utilitzar com una eina de control, per tal de determinar quina taxa de canvi de carril es pot permetre si es vol assolir una capacitat determinada amb una determinada probabilitat de compliment. En vista dels resultats previs, la falta de compliment de les normes de trànsit per part dels conductors s’identifica com un punt dèbil a l’hora de maximitzar els beneficis de les actuals estratègies de gestió del transit. Això probablement canviarà en el futur pròxim amb la irrupció dels Vehicles Autònoms (VA) a les autopistes. Els sistemes de comunicació V2X permetran actuar individualment sobre cada vehicle amb una gran precisió. Això obrirà la porta a noves estratègies de gestió, basades en la comunicació simultània entre diferents grups de VA i en temps de reacció extremadament curts, com per exemple és el “platooning”, que destaca pel seu gran potencial per millorar el trànsit en autopista. Els “platons” son cadenes de VA viatjant amb uns espaiaments extremadament curts que permeten assolir capacitats mes elevades i un menor consum energètic. En aquest context, la tesi presenta un model macroscòpic parsimoniós per a “platons” de VA en condicions de transit mixt, és a dir, compartint la infraestructura amb vehicles tradicionals. El model permet determinar la longitud mitjana del “platons” i reproduir el trànsit global dinàmiques que condueixen a majors capacitats. Els resultats demostren que amb un 50% la velocitat de penetració dels AV al carril, la capacitat podria arribar als 3.400 vehicles / h / carril sota una estratègia cooperativa de “platooning”
28
Gupta, Shobhit. "Look-Ahead Optimization of a Connected and Automated 48V Mild-Hybrid Electric Vehicle." The Ohio State University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=osu1554478434629481.
29
Wang, Yuan-Fang. "Computer Vision Analysis for Vehicular Safety Applications." International Foundation for Telemetering, 2015. http://hdl.handle.net/10150/596451.
Анотація:
ITC/USA 2015 Conference Proceedings / The Fifty-First Annual International Telemetering Conference and Technical Exhibition / October 26-29, 2015 / Bally's Hotel & Convention Center, Las Vegas, NVIn this paper, we present our research on using computer-vision analysis for vehicular safety applications. Our research has potential applications for both autonomous vehicles and connected vehicles. In particular, for connected vehicles, we propose three image analysis algorithms that enhance the quality of a vehicle's on-board video before inter-vehicular information exchange takes place. For autonomous vehicles, we are investigating a visual analysis scheme for collision avoidance during back up and an algorithm for automated 3D map building. These algorithms are relevant to the telemetering domain as they involve determining the relative pose between a vehicle and other vehicles on the road, or between a vehicle and its 3D driving environment, or between a vehicle and obstacles surrounding the vehicle.
30
Mladenovic, Milos. "Development of Sustainable Traffic Control Principles for Self-Driving Vehicles: A Paradigm Shift Within the Framework of Social Justice." Diss., Virginia Tech, 2014. http://hdl.handle.net/10919/64806.
Анотація:
Developments of commercial self-driving vehicle (SDV) technology has a potential for a paradigm shift in traffic control technology. Contrary to some previous research approaches, this research argues that, as any other technology, traffic control technology for SDVs should be developed having in mind improved quality of life through a sustainable developmental approach. Consequently, this research emphasizes upon the social perspective of sustainability, considering its neglect in the conventional control principles, and the importance of behavioral considerations for accurately predicting impacts upon economic or environmental factors. The premise is that traffic control technology can affect the distribution of advantages and disadvantages in a society, and thus it requires a framework of social justice.
The framework of social justice is inspired by John Rawls' Theory of Justice as fairness, and tries to protect the inviolability of each user in a system. Consequently, the control objective is the distribution of delay per individual, considering for example that the effect of delay is not the same if a person is traveling to a grocery store as opposed to traveling to a hospital. The notion of social justice is developed as a priority system, with end-user responsibility, where user is able to assign a specific Priority Level for each individual trip with SDV. Selected Priority Level is used to determine the right-of-way for each self-driving vehicle at an intersection. As a supporting mechanism to the priority system, there is a structure of non-monetary Priority Credits. Rules for using Priority Credits are determined using knowledge from social science research and through empirical evaluation using surveys, interviews, and web-based experiment. In the physical space, the intersection control principle is developed as hierarchical self-organization, utilizing communication, sensing, and in-vehicle technological capabilities. This distributed control approach should enable robustness against failure, and scalability for future expansion. The control mechanism has been modeled as an agent-based system, allowing evaluation of effects upon safety and user delay. In conclusion, by reaching across multiple disciplines, this development provides the promise and the challenge for evolving SDV control technology. Future efforts for SDV technology development should continue to rely upon transparent public involvement and understanding of human decision-making.Ph. D.
31
Mennie, James J. "A Culture/Climate Examination of Autonomous Vehicle Technology In The United States." Scholar Commons, 2018. https://scholarcommons.usf.edu/etd/7546.
Анотація:
Autonomous Vehicle are coming. But mass adoption is at least ten years away according to consensus compiled from interviews conducted with industry thought lenders. Questions remain as to what technology those vehicles will contain as there is no universal platform for autonomous vehicle technology, since manufacturers, hardware and software companies are developing their own proprietary products. A/V technology is expected to improve productivity, and provide a plethora of societal benefits, but while we await the closure of the time gap the US will lose almost 40,000 citizens each year with traffic fatalities.
Connected vehicle technology, which is currently completing pilot studies, has been shown to reduce automobile accidents. This technology is not as complex as autonomous vehicle technology and is available now. Semi-autonomous vehicles which is Level 1 through Level 3 on the Society of Automobile Executives (SAE) scale is available on American automobiles today and has proven to be very popular amongst consumers.
Technology convergence of semi-autonomous vehicle and connected vehicles can bridge the time gap until mass adoption of autonomous vehicle and contribute to reducing annual traffic fatalities. Combining these technologies will give drivers additional safety features thus providing them with the opportunity of making better decisions.
32
Karray, Khaled. "Cyber-security of connected vehicles : contributions to enhance the risk analysis and security of in-vehicle communications." Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLT023.
Анотація:
Au cours de la dernière décennie, les progrès technologiques ont rendu la voiture de plus en plus autonome et connectée au monde extérieur. D'un autre côté, cette transformation technologique a soumis les véhicules modernes à des cyber-attaques avancées. Les architectures cyber-physiques des systèmes automobiles n'ont pas été conçues dans un souci de sécurité. Avec l'intégration de plates-formes connectées dans ces systèmes cyber-physiques, le paysage des menaces a radicalement changé. Dernièrement, plusieurs atteintes à la sécurité visant différents constructeurs automobiles ont été signalées principalement par la communauté scientifique. Cela fait de la sécurité une préoccupation essentielle, avec un impact important, en particulier sur la future conduite autonome. Afin de remédier à cela, une ingénierie de sécurité rigoureuse doit être intégrée au processus de conception d'un système automobile et de nouvelles méthodes de protections adaptées aux spécificités des systèmes véhiculaire doivent être introduites. La modélisation des menaces et l'analyse des risques sont des éléments essentiels de ce processus. Pour ce faire, les arbres d’attaque se sont avérés un moyen raisonnable de modéliser les étapes d’attaque et d’aider le concepteur à évaluer les risques. Néanmoins, étant donné la diversité des architectures, élaborer des arbres d’attaque pour toutes les architectures peut rapidement devenir un fardeau. Cette thèse aborde la problématique de la sécurité des véhicules connectés. L'approche présentée consiste à améliorer la méthodologie d'évaluation de la sécurité par la génération automatique d'arbres d'attaques pour assister à l'étape d'analyse de risques. On propose aussi de nouvelle méthodes de protections des réseaux internes véhiculaires capables de faire face aux attaques cyberphysiques existantesDuring the last decade, technological advances have made the car more and more connected to the outside world. On the flip side, thistechnological transformation has made modern vehicles subject to advanced cyber attacks. The cyber-physical architectures of automotive systems were not designed with security in mind. With the integration of connected platforms into these cyberphysical systems, the threat landscape has radically changed. Lately, multiple security breaches targeting different car manufacturers have been reported mainly by the scientific community. This makes security a critical concern, with a high impact especially on future autonomous driving. In order to address this gap, rigorous security engineering needs to be integrated into the design process of an automotive system and new protection methods adapted to the specificities of the vehicle systems must be introduced. Threat modeling and risk analysis are essential building blocks of this process. In this context, attack trees proved to be a reasonably good way to model attack steps. Nevertheless, given the diversity of architectures, it can quickly become a burden to draw attack trees for all architectures. This thesis tackles the issues of security of connected vehicles. The proposed approach allows enhancing the threat analysis with the automated generation of attack tree used to assist in the risk assessment step. We also propose novel and efficient protection mechanisms for in-vehicle communication networks capable of coping with existing cyber-physical attacks
33
Azmat, Muhammad, Sebastian Kummer, Moura Lara T, Gennaro Federico Di, and Rene Moser. "Future Outlook of Highway Operations with Implementation of Innovative Technologies Like AV, CV, IoT and Big Data." MDPI, 2019. http://dx.doi.org/10.3390/logistics3020015.
Анотація:
In the last couple of decades, there has been an unparalleled growth in number of people who can afford motorized vehicles. This is increasing the number of vehicles on roads at an alarming rate and existing infrastructure and conventional methods of traffic management are becoming inefficient both on highways and in urban areas. It is very important that our highways are up and running 24/7 as they not only provide a passage for human beings to move from one place to another, but also are the most important mode for intercity or international transfer of goods. There is an utter need of adapting the new world order, where daily processes are driven with the help of innovative technologies. It is highly likely that technological advancements like autonomous or connected vehicles, big data and the Internet of things can provide highway operators with a solution that might resolve unforeseeable challenges. This investigative exploratory research identifies and highlights the impact of new technological advancements in the automotive industry on highways and highway operators. The data for this research was collected on a Likert scale type online survey, from different organizations around the world (actively or passively involved in highway operations). The data was further tested for its empirical significance with non-parametric binomial and Wilcoxon signed rank tests, supported by a descriptive analysis. The results of this study are in line with theoretical and conceptual work done by several independent corporations and academic researchers. It is evident form the opinions of seasoned professionals that these technological advancements withhold the potential to resolve all potential challenges and revolutionize highway operations.
34
Bechihi, Adel. "Joint design of control algorithms and communication protocols for Connected and Automated Vehicles." Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPAST203.
Анотація:
Dans cette thèse, nous nous adressons le problème du contrôle de systèmes multi-agents connectés via des modèles réalistes de systèmes de communication. Nous traitons principalement les systèmes de véhicules connectés et automatisés (CAVs) communiquant via des systèmes de communication 5G qui permettent deux types de communication : la communication directe entre les nœuds, connue sous le nom de communication véhicule-à-véhicule (V2V), et la communication à travers l'infrastructure réseau, qui est la manière traditionnelle de communiquer dans les réseaux cellulaires.La thèse traite de trois problèmes : premièrement, nous analysons les propriétés de stabilité et de convergence de l'algorithme du consensus pour agents d'intégrateurs du premier ordre en utilisant un schéma d'accès multiple par répartition temporelle (TDMA) pour partager les ressources du réseau d'un canal de communication partagé. La stabilité exponentielle du système considéré est démontrée, et une borne explicite dépendant des paramètres du système de communication est fournie pour estimer la vitesse de convergence. Ensuite, nous abordons le problème du contrôle de formation d'un groupe de véhicules connectés dans un contexte de communication 5G. Nous proposons un algorithme d'allocation de ressources pour sélectionner les utilisateurs émetteurs afin d'atteindre la formation souhaitée tout en respectant les contraintes imposées par le couche de communication. Enfin, nous étudions les propriétés de stabilité des filtres de Kalman pour les systèmes hybrides, précisément, des systèmes avec une dynamique en temps continu observée à travers des mesures en temps discret. La stabilité d'entrée-à-état (ISS) est démontrée pour de tels systèmes en utilisant une fonction de Lyapunov appropriée. Ce résultat peut être considéré comme une première étape dans l'analyse de la robustesse du système global, car il permet de prendre en compte les effets des erreurs de communication sur la stabilité du système contrôléIn this thesis, we address the problem of control of multi-agent systems connected over realistic models of communication systems. We mainly focus on systems of connected and automated vehicles (CAVs) that communicate through a 5G communication system, which allows two types of communication: direct communication between nodes, known as Vehicle-to-Vehicle (V2V) communications, and communication through the network infrastructure, which is the traditional way of communication in cellular networks.The thesis discusses three problems: first, we analyze the stability and convergence properties of the consensus algorithm of first-order integrator agents using a time-division multiple access (TDMA) scheme to share the network resources of a broadcast shared communication channel. Exponential stability of the considered system is proved, and an explicit bound depending on the communication system parameters is provided to estimate the convergence rate. Second, we treat the problem of formation control of a float of connected vehicles in a 5G communication context. We propose a resource allocation algorithm to select the transmitting users to achieve the desired formation while satisfying the constraints imposed by the communication system. Finally, we study the stability properties of Kalman filters for hybrid systems, i.e., systems with continuous-time dynamics observed through discrete-time measurements. Input-to-state stability (ISS) is proved for such systems relying on an appropriate Lyapunov function. This result can be considered as a first step in the robustness analysis of the overall system since it allows to treat the effects of communication errors on the controlled system stability
35
Valenti, Giammarco. "Cooperative ADAS and driving, bio-inspired and optimal solutions." Doctoral thesis, Università degli studi di Trento, 2022. http://hdl.handle.net/11572/336890.
Анотація:
Mobility is a topic of great interest in research and engineering since critical aspects such as safety, traffic efficiency, and environmental sustainability still represent wide open challenges for researchers and engineers. In this thesis, at first, we address the cooperative driving safety problem both from a centralized and decentralized perspective. Then we address the problem of optimal energy management of hybrid vehicles to improve environmental sustainability, and finally, we develop an intersection management systems for Connected Autonomous Vehicle to maximize the traffic efficiency at an intersection. To address the first two topics, we define a common framework. Both the cooperative safety and the energy management for Hybrid Electric Vehicle requires to model the driver behavior. In the first case, we are interested in evaluating the safety of the driver’s intentions, while in the second case, we are interested in predicting the future velocity profile to optimize energy management in a fixed time horizon. The framework is the Co-Driver, which is, in short, a bio-inspired agent able both to model and to imitate a human driver. It is based on a layered control structure based on the generation of atomic human-like longitudinal maneuvers that compete with each other like affordances. To address driving safety, the Co-Driver behaves like a safe driver, and its behavior is compared to the actual driver to understand if
he/she is acting safely and providing warnings if not. In the energy management problem, the Co-Driver aims at imitating the driver to predict the future velocity. The Co-Driver generates a set of possible maneuvers and selects one of them, imitating the action selection process of the driver. At first, we address the problem of safety by developing and investigating a framework for Advanced Driving
Assistance Systems (ADAS) built on the Co-Driver. We developed and investigated this framework in an innovative context of new intelligent road infrastructure, where vehicles and roads communicate. The
infrastructure that allows the roads to interact with vehicles and the environment is the topic of a research project called SAFESTRIP. This project is about deploying innovative sensors and communication devices on the road that communicate with all vehicles. Including vehicles that are equipped with Vehicle-To-Everything (V2X) technology and vehicles that are not, using an interface (HMI) on smart-phones.
Co-Driver-based ADAS systems exploit connections between vehicles and (smart) roads provided by SAFESTRIP to cover several safety-critical use cases: pedestrian protection, wrong-way vehicles on-ramps, work-zones on roads and intersections. The ADAS provide personalized warning messages that account for the adaptive driver behavior to maximize the acceptance of the system. The ability of the framework to predict human drivers’ intention is exploited in a second application to improve environmental sustainability. We employ it to feed with the estimated speed profile a novel online Model
Predictive Control (MPC) approach for Hybrid Electric Vehicles, introducing a state-of-the-art electrochemical model of the battery. Such control aims at preserving battery life and fuel consumption through equivalent costs. We validated the approach with actual driving data used to simulate vehicles and the power-train dynamics. At last, we address the traffic efficiency problem in the context of autonomous vehicles crossing an intersection. We propose an intersection management system for Connected Autonomous Vehicles based on a bi-level optimization framework. The motion planning of the vehicle is provided by a simplified optimal control problem, while we formulate the intersection management problem (in terms of order and timing) as a Mixed Integer Non-Linear Programming. The latter approximates a linear problem with a powerful piecewise linearization technique. Therefore, thanks to this technique, we can bound the error and employ commercial solvers to solve the problem (fast enough). Finally, this framework is validated in simulation and compared with the "Fist-Arrived First-Served" approach to show the impact of the proposed algorithm.
36
Boukhalfa, Mohamed Fouzi. "Low latency radio and visible light communications for autonomous driving." Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS164.
Анотація:
Le sujet de cette thèse porte sur les réseaux sans fil véhiculaires et, plus précisément, sur l’utilisation de la transmission radio et de la communication par la lumière (VLC) pour améliorer la sécurité des véhicules. La thèse est motivée par les problèmes de fiabilité et d’évolutivité de la norme IEEE 802.11p. L’idée est d’évoluer vers de nouvelles techniques, et d’associer la transmission radio à la communication en VLC pour permettre une communication hybride. La première partie de la thèse concerne la mise au point de techniques d’accès radio à faible latence dans les réseaux véhiculaires. L’idée de la solution est de mélanger les techniques TDMA classiques et des mécanismes avancés de protocoles à compétition utilisant des signalements actifs. Cette solution a été spécifié, évalué et comparé à d’autres solutions de la littérature. Nous avons également introduit dans cette partie un schéma d’accès spécial pour les paquets d’urgence de haute priorité, tout en garantissant un accès fiable et à faible latence. La seconde partie de la thèse concerne la communication par lumière visible pour le contrôle de peloton. Pour cela, nous avons proposé et développé un algorithme qui sélectionne la communication radio, proposée dans la première partie, et la communication par lumière visible en se basant sur l’état du canal radio et d’alignement du pelotonThe subject of this thesis is vehicle wireless networks and, more specifically, the use of radio transmission and Visible Light Communication (VLC) to improve vehicle safety. The thesis is motivated by the reliability and scalability issues of the IEEE 802.11p standard. The idea is to move towards new techniques, especially in future 803.11bd standards, and to combine radio transmission with VLC to enable hybrid communication. The first part of the thesis concerns the development of a low latency radio access technique in vehicular networks. The idea of the solution is to combine classical TDMA techniques and advanced mechanisms of competitive protocols using active signaling. This solution has been specified, evaluated, and compared to other solutions from literature. This part also introduces a special access scheme for high priority emergency packets, while ensuring reliable and low latency access. The second part of the thesis concerns visible light communication for platoon control. The idea is to develop an algorithm to select the radio communication, proposed in the first part, and visible light communication based on the radio channel conditions and platoon alignment
37
Solano, Araque Edwin. "De l’ergonomie automobile à l’optimisation de la conduite automatisée. Application à l’écoconduite des véhicules électriques." Thesis, Orléans, 2020. http://www.theses.fr/2020ORLE3059.
Анотація:
Cette thèse se focalise sur l'étude de l’écoconduite (pratique de conduite visant à réduire l’impact environnemental de l’utilisation du véhicule) et, en particulier, des éco-manœuvres de conduite, avec prise en compte des contraintes d'infrastructure et de trafic, ainsi que des contraintes d'agrément de conduite. De plus, nous considérons, lors de la conception de l'algorithme, des principes inspirés de la cognition humaine, afin de renforcer l'efficacité et la bonne modularité. La facilité de calibration de l'algorithme est un autre aspect pris en considération. L'ensemble de l'exposé se focalise sur les véhicules électriques à batterie. Cependant, les principes proposés peuvent être adaptés pour leur application sur d'autres types de groupe motopropulseur.Ces travaux s’orientent sur trois grandes lignes. La première, l'Ergonomie de conduite, a permis de déterminer des critères d'agrément de conduite ; une modélisation du conducteur permettant de tenir compte des aspects ergonomiques est proposée. De même, nos hypothèses sont confrontées au comportement d’un conducteur en situation réelle, en appliquant une méthodologie innovante pour l'analyse d'enregistrements de roulages réels. Ensuite, une Modélisation énergétique du véhicule et des manœuvres de conduite est présentée, ainsi qu'une analyse du potentiel et l’origine du gain associé à différentes stratégies d'éco-conduite. Finalement un Algorithme de commande est proposé pour la réalisation d'éco-manœuvres de conduite, avec prise en compte des critères d'agrément. La structure globale de l'algorithme, basée sur les principes cognitifs, est constitué de plusieurs sous-systèmes le rendant modulaire et capable de répondre aux contraintes de calcul en temps réel et de mise au point, propres au milieu industrielIn the framework of this dissertation, we will focus on Eco-driving and, particularly on eco-maneuvers, taking into account constraints associated to infrastructure and traffic, as well as with drivability. Additionally, we will take inspiration on Cognitive Principles for the algorithm design; it will allow to reinforce algorithm’s effectiveness and modularity. Easiness of calibration will also be an important concern for our work. Our whole discussion focuses on Battery Electric Vehicles. However, the proposed principles may be adapted for their application for other types of powertrain.Our work treats three main topics: on one side, Driving Ergonomics, allowing to determine some criteria on drivability ; we will also propose a modelling of the driver allowing to take into account ergonomics considerations. Finally, we will assess our hypothesis with respect with driver behavior on real situations, by applying an innovative methodology for the analysis of actual driving records. Next we will focus on Energy Model of the vehicle and of driving maneuvers, as well as to the assessment of energy gain potential associated to several Eco-driving strategies; the origin of these gains is also studied. Finally, we propose a Control Algorithm allowing to execute driving eco-maneuvers, while taking into account drivability criteria. The global algorithm structure is based on cognitive principles presented earlier. These function consists of several subsystems, which improves its modularity, and enforces its potential to operate within real-time constraints, and simplifies calibrations ; these both are major advantages for an industrial application
38
El, Mawas Zaynab. "Localisation coopérative tolérante aux fautes : apport de l'apprentissage pour le diagnostic." Electronic Thesis or Diss., Université de Lille (2022-....), 2023. http://www.theses.fr/2023ULILB039.
Анотація:
La mobilité autonome et connectée est devenue un enjeu socio-économique majeur. Cependant, la sûreté et la sécurité des véhicules autonomes sont des freins au déploiement de ce type de véhicules. Dans ce contexte, les travaux de cette thèse ont pour objectifs d'une part de contribuer au développement de méthodes de diagnostic des défauts des capteurs et d'autre part de mettre en oeuvre une coopération entre les véhicules pour améliorer les performances de la localisation des véhicules autonomes.Concernant l'aspect diagnostic, nous proposons de coupler des techniques basées à la fois sur des modèles et des données afin de produire une solution de localisation coopérative tolérante aux défauts capteurs. Étant donnée la nature stochastique des mesures, nous avons choisi le formalisme informationnel, qui fournit des mesures de dissimilarité entre des distributions de probabilité appelées divergences. Dans le cadre de cette thèse, nous utilisons ainsi la divergence de Jensen-Shannon pour synthétiser des indicateurs de défauts, les résidus. Le seuillage de ces résidus permet alors de détecter et d'isoler les défauts capteurs. Par ailleurs, l'apport de l'apprentissage a été étudié pour la prise de décision du diagnostic. Deux modèles, l'un pour la détection et l'autre pour l'isolation, ont été entraînés, avec différents outils de l'apprentissage machine (perceptron multi-couches, arbre de décision et régression logistique).La coopération entre les véhicules a mené à la mise en place d'une architecture décentralisée pour la fusion de données multi-capteurs et le diagnostic. Cet aspect coopératif inter-véhicules permet une redondance informationnelle contribuant à l'amélioration des performances de l'estimation de la pose et du diagnostic. Les données issues de cette architecture ont permis de mettre en place un paradigme fédéré pour l'apprentissage.Les méthodes proposées ont été développées, testées et évaluées sur un ensemble de scénarios avec des défauts capteurs réels et injectés. Ces scénarios ont été créés en utilisant une base de données réelles acquises à l'aide d'une plateforme robotique conçue durant la thèse. Cet équipement de la plateforme PRETIL est constitué de trois robots communicants et instrumentésAutonomous and connected mobility has become a major socio-economic challenge. However, the safety and security of autonomous vehicles are barriers to the deployment of this type of vehicle. In this context, the aim of this thesis is to contribute to the development of sensor fault diagnosis methods, and to implement inter-vehicle cooperation to improve the localization performance of these autonomous vehicles.Concerning the diagnostic aspect, we propose to couple both model- and data-based techniques to produce a sensor fault-tolerant cooperative localization solution. Given the stochastic nature of the measurements, we have chosen the informational formalism, which provides measures of dissimilarity between probability distributions called divergences. In this thesis, we use the Jensen-Shannon divergence to synthesize fault indicators, the residuals. Thresholding these residuals enables us to detect and isolate sensor faults. We have also studied the contribution of learning to diagnostic decision-making. Two models, one for detection and the other for isolation, were trained, using different machine learning tools (multi-layer perceptron, decision tree and logistic regression).Inter-vehicle cooperation has led to the implementation of a decentralized architecture for multi-sensor data fusion and diagnosis. This inter-vehicle cooperative aspect enables informational redundancy, contributing to improved performance in pose estimation and diagnosis. The data generated by this architecture has been used to implement a federated learning paradigm.The proposed methods were developed, tested and evaluated on a set of scenarios with real and injected sensor faults. These scenarios were created using a database of real data acquired with a robotic platform designed during the thesis. The PRETIL platform comprises three communicating and instrumented robots
39
RAVIGLIONE, FRANCESCO. "Open Platforms for Connected Vehicles." Doctoral thesis, Politecnico di Torino, 2022. https://hdl.handle.net/11583/2973988.
40
Pérez, Tellez Adriel, and Jonas Roth. "Mobile autonomous ground vehicles." Thesis, KTH, Skolan för elektro- och systemteknik (EES), 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-199348.
41
Arutselvan, Kuralamudhan. "Assistive Autonomous Ground Vehicles." Thesis, KTH, Skolan för elektro- och systemteknik (EES), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-200530.
42
Kim, Bumsik. "Modeling Automated Vehicles and Connected Automated Vehicles on Highways." Diss., Virginia Tech, 2021. http://hdl.handle.net/10919/103012.
Анотація:
The deployment of Automated Vehicles (AV) is starting to become widespread throughout transportation, resulting in the recognition and awareness by legislative leaders of the potential impact on transportation operations. To assist transportation operators in making the needed preparations for these vehicles, an in-depth study regarding the impact of AV and Connected Automated Vehicles (CAV) is needed. In this research, the impact of AV and CAV on the highway setting is studied. This study addresses car-following models that are currently used for simulating AV and CAV. Diverse car-following models, such as the Intelligent Driver Model (IDM), the IDM with traffic adaptive driving Strategy (SIDM), the Improved IDM (IIDM), the IIDM with Constant-Acceleration Heuristic (CAH), and the MIcroscopic model for Simulation of Intelligent Cruise control (MIXIC) were examined with the state-of-the-art vehicle trajectory data. The Highway Drone dataset (HighD) were analyzed through the implementation of genetic algorithm to gain more insight about the trajectories of these vehicles. In 2020, there is no commercially available gully automated vehicle available to the public, although many companies are conducting in field testing. This research generated AV trajectories based on the actual vehicle trajectories from the High-D dataset and adjusts those trajectories to account for ideal AV operations. The analysis from the fitted trajectory data shows that the calibrated IIDM with CAH provides a best fit on AV behavior. Next, the AV and CAV were modeled in microscopic perspective to show the impact of these vehicles on a corridor. The traffic simulation software, VISSIM, modified by implementing an external driver model to govern the interactions between Legacy Vehicles (LV), AV, and CAV on a basic and merging highway segment as well as a model of the Interstate 95 corridor south of Richmond, Virginia. From the analysis, this research revealed that the AV and CAV could increase highway capacity significantly. Even with a small portion of AV or CAV, the roadway capacity increased. On I-95, CAV performed better than AV because of Cooperative Adaptive Cruise Control (CACC) and platooning due to CAV's ability to coordinate movement through communication; however, in weaving segments, CAV underperformed AV. This result indicates that the CAV algorithms would need to be flexible in order to maintain flow in areas with weaving sections. Lastly, diverse operational conditions, such as different heavy vehicle market penetration and different aggressiveness were examined to support traffic operators transition to the introduction of AV and CAV. Based on the analysis, the study concludes that the different aggressiveness could mitigate congestion in all cases if the proper aggressiveness level is selected considering the current traffic condition. Overall, the dissertation provides guidance to researchers, traffic operators, and lawmakers to model, simulate, and evaluate AV and CAV on highways.Doctor of Philosophy
The deployment of Automated Vehicles (AV) is starting to become widespread throughout transportation, resulting in the recognition and awareness by legislative leaders of the potential impact on transportation operations. To assist transportation operators in making the needed preparations for these vehicles, an in-depth study regarding the impact of AV and Connected Automated Vehicles (CAV) is needed. In this research, the impact of AV and CAV on the highway setting is studied. This study addresses car-following models that are currently used for simulating AV and CAV. Diverse car-following models, such as the Intelligent Driver Model (IDM), the IDM with traffic adaptive driving Strategy (SIDM), the Improved IDM (IIDM), the IIDM with Constant-Acceleration Heuristic (CAH), and the MIcroscopic model for Simulation of Intelligent Cruise control (MIXIC) were examined with the state-of-the-art vehicle trajectory data. The Highway Drone dataset (HighD) were analyzed through the implementation of genetic algorithm to gain more insight about the trajectories of these vehicles. In 2020, there is no commercially available gully automated vehicle available to the public, although many companies are conducting in field testing. This research generated AV trajectories based on the actual vehicle trajectories from the High-D dataset and adjusts those trajectories to account for ideal AV operations. The analysis from the fitted trajectory data shows that the calibrated IIDM with CAH provides a best fit on AV behavior. Next, the AV and CAV were modeled in microscopic perspective to show the impact of these vehicles on a corridor. The traffic simulation software, VISSIM, modified by implementing an external driver model to govern the interactions between Legacy Vehicles (LV), AV, and CAV on a basic and merging highway segment as well as a model of the Interstate 95 corridor south of Richmond, Virginia. From the analysis, this research revealed that the AV and CAV could increase highway capacity significantly. Even with a small portion of AV or CAV, the roadway capacity increased. On I-95, CAV performed better than AV because of Cooperative Adaptive Cruise Control (CACC) and platooning due to CAV's ability to coordinate movement through communication; however, in weaving segments, CAV underperformed AV. This result indicates that the CAV algorithms would need to be flexible in order to maintain flow in areas with weaving sections. Lastly, diverse operational conditions, such as different heavy vehicle market penetration and different aggressiveness were examined to support traffic operators transition to the introduction of AV and CAV. Based on the analysis, the study concludes that the different aggressiveness could mitigate congestion in all cases if the proper aggressiveness level is selected considering the current traffic condition. Overall, the dissertation provides guidance to researchers, traffic operators, and lawmakers to model, simulate, and evaluate AV and CAV on highways.
43
Aygun, Bengi. "Distributed Adaptation Techniques for Connected Vehicles." Digital WPI, 2016. https://digitalcommons.wpi.edu/etd-dissertations/336.
Анотація:
"In this PhD dissertation, we propose distributed adaptation mechanisms for connected vehicles to deal with the connectivity challenges. To understand the system behavior of the solutions for connected vehicles, we first need to characterize the operational environment. Therefore, we devised a large scale fading model for various link types, including point-to-point vehicular communications and multi-hop connected vehicles. We explored two small scale fading models to define the characteristics of multi-hop connected vehicles. Taking our research into multi-hop connected vehicles one step further, we propose selective information relaying to avoid message congestion due to redundant messages received by the relay vehicle. Results show that the proposed mechanism reduces messaging load by up to 75% without sacrificing environmental awareness. Once we define the channel characteristics, we propose a distributed congestion control algorithm to solve the messaging overhead on the channels as the next research interest of this dissertation. We propose a combined transmit power and message rate adaptation for connected vehicles. The proposed algorithm increases the environmental awareness and achieves the application requirements by considering highly dynamic network characteristics. Both power and rate adaptation mechanisms are performed jointly to avoid one result affecting the other negatively. Results prove that the proposed algorithm can increase awareness by 20% while keeping the channel load and interference at almost the same level as well as improve the average message rate by 18%. As the last step of this dissertation, distributed cooperative dynamic spectrum access technique is proposed to solve the channel overhead and the limited resources issues. The adaptive energy detection threshold, which is used to decide whether the channel is busy, is optimized in this work by using a computationally efficient numerical approach. Each vehicle evaluates the available channels by voting on the information received from one-hop neighbors. An interdisciplinary approach referred to as entropy-based weighting is used for defining the neighbor credibility. Once the vehicle accesses the channel, we propose a decision mechanism for channel switching that is inspired by the optimal flower selection process employed by bumblebees foraging. Experimental results show that by using the proposed distributed cooperative spectrum sensing mechanism, spectrum detection error converges to zero."
44
Bridgelall, Raj. "Pavement Performance Evaluation Using Connected Vehicles." Diss., North Dakota State University, 2015. http://hdl.handle.net/10365/25000.
Анотація:
Roads deteriorate at different rates from weathering and use. Hence, transportation agencies must assess the ride quality of a facility regularly to determine its maintenance needs. Existing models to characterize ride quality produce the International Roughness Index (IRI), the prevailing summary of roughness. Nearly all state agencies use Inertial Profilers to produce the IRI. Such heavily instrumented vehicles require trained personnel for their operation and data interpretation. Resource constraints prevent the scaling of these existing methods beyond 4% of the network. This dissertation developed an alternative method to characterize ride quality that uses regular passenger vehicles. Smartphones or connected vehicles provide the onboard sensor data needed to enable the new technique. The new method provides a single index summary of ride quality for all paved and unpaved roads. The new index is directly proportional to the IRI. A new transform integrates sensor data streams from connected vehicles to produce a linear energy density representation of roughness. The ensemble average of indices from different speed ranges converges to a repeatable characterization of roughness. The currently used IRI is undefined at speeds other than 80 km/h. This constraint mischaracterizes roughness experienced at other speeds. The newly proposed transform integrates the average roughness indices from all speed ranges to produce a speed-independent characterization of ride quality. This property avoids spatial wavelength bias, which is a critical deficiency of the IRI. The new method leverages the emergence of connected vehicles to provide continuous characterizations of ride quality for the entire roadway network. This dissertation derived precision bounds of deterioration forecasting for models that could utilize the new index. The results demonstrated continuous performance improvements with additional vehicle participation. With practical traversal volumes, the achievable precision of forecast is within a few days. This work also quantified capabilities of the new transform to localize roadway anomalies that could pose travel hazards. The methods included derivations of the best sensor settings to achieve the desired performances. Several case studies validated the findings. These new techniques have the potential to save agencies millions of dollars annually by enabling predictive maintenance practices for all roadways, worldwide.Mountain Plains Consortium (MPC)
45
Pedreira, Carabel Carlos Javier. "Terrain Mapping for Autonomous Vehicles." Thesis, KTH, Datorseende och robotik, CVAP, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-174132.
Анотація:
Autonomous vehicles have become the forefront of the automotive industry nowadays, looking to have safer and more efficient transportation systems. One of the main issues for every autonomous vehicle consists in being aware of its position and the presence of obstacles along its path. The current project addresses the pose and terrain mapping problem integrating a visual odometry method and a mapping technique. An RGB-D camera, the Kinect v2 from Microsoft, was chosen as sensor for capturing information from the environment. It was connected to an Intel mini-PC for real-time processing. Both pieces of hardware were mounted on-board of a four-wheeled research concept vehicle (RCV) to test the feasibility of the current solution at outdoor locations. The Robot Operating System (ROS) was used as development environment with C++ as programming language. The visual odometry strategy consisted in a frame registration algorithm called Adaptive Iterative Closest Keypoint (AICK) based on Iterative Closest Point (ICP) using Oriented FAST and Rotated BRIEF (ORB) as image keypoint extractor. A grid-based local costmap rolling window type was implemented to have a two-dimensional representation of the obstacles close to the vehicle within a predefined area, in order to allow further path planning applications. Experiments were performed both offline and in real-time to test the system at indoors and outdoors scenarios. The results confirmed the viability of using the designed framework to keep tracking the pose of the camera and detect objects in indoor environments. However, outdoor environments evidenced the limitations of the features of the RGB-D sensor, making the current system configuration unfeasible for outdoor purposes.Autonoma fordon har blivit spetsen för bilindustrin i dag i sökandet efter säkrare och effektivare transportsystem. En av de viktigaste sakerna för varje autonomt fordon består i att vara medveten om sin position och närvaron av hinder längs vägen. Det aktuella projektet behandlar position och riktning samt terrängkartläggningsproblemet genom att integrera en visuell distansmätnings och kartläggningsmetod. RGB-D kameran Kinect v2 från Microsoft valdes som sensor för att samla in information från omgivningen. Den var ansluten till en Intel mini PC för realtidsbehandling. Båda komponenterna monterades på ett fyrhjuligt forskningskonceptfordon (RCV) för att testa genomförbarheten av den nuvarande lösningen i utomhusmiljöer. Robotoperativsystemet (ROS) användes som utvecklingsmiljö med C++ som programmeringsspråk. Den visuella distansmätningsstrategin bestod i en bildregistrerings-algoritm som kallas Adaptive Iterative Closest Keypoint (AICK) baserat på Iterative Closest Point (ICP) med hjälp av Oriented FAST och Rotated BRIEF (ORB) som nyckelpunktsutvinning från bilder. En rutnätsbaserad lokalkostnadskarta av rullande-fönster-typ implementerades för att få en tvådimensionell representation av de hinder som befinner sig nära fordonet inom ett fördefinierat område, i syfte att möjliggöra ytterligare applikationer för körvägen. Experiment utfördes både offline och i realtid för att testa systemet i inomhus- och utomhusscenarier. Resultaten bekräftade möjligheten att använda den utvecklade metoden för att spåra position och riktning av kameran samt upptäcka föremål i inomhusmiljöer. Men utomhus visades begränsningar i RGB-D-sensorn som gör att den aktuella systemkonfigurationen är värdelös för utomhusbruk.
46
Dever, Christopher W. (Christopher Walden) 1972. "Parametrized maneuvers for autonomous vehicles." Thesis, Massachusetts Institute of Technology, 2004. http://hdl.handle.net/1721.1/30328.
Анотація:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Mechanical Engineering, 2004.Includes bibliographical references (p. 197-209).
This thesis presents a method for creating continuously parametrized maneuver classes for autonomous vehicles. These classes provide useful tools for motion planners, bundling sets of related vehicle motions based on a low-dimensional parameter vector that describes the fundamental high-level variations within the trajectory set. The method follows from a relaxation of nonlinear parametric programming necessary conditions that discards the objective function, leaving a simple coordinatized feasible space including all dynamically admissible vehicle motions. A trajectory interpolation algorithm uses projection and integration methods to create the classes, starting from arbitrary user-provided maneuver examples, including those obtained from standard nonlinear optimization or motion capture of human-piloted vehicle flights. The interpolation process, which can be employed for real-time trajectory generation, efficiently creates entire maneuver sets satisfying nonlinear equations of motion and nonlinear state and control constraints without resorting to iterative optimization. Experimental application to a three degree-of-freedom rotorcraft testbed and the design of a stable feedforward control framework demonstrates the essential features of the method on actual hardware. Integration of the trajectory classes into an existing hybrid system motion planning framework illustrates the use of parametrized maneuvers for solving vehicle guidance problems. The earlier relaxation of strict optimality conditions makes possible the imposition of affine state transformation constraints, allowing maneuver sets to fit easily into a mixed integer-linear programming path planner.
(cont.) The combined scheme generalizes previous planning techniques based on fixed, invariant representations of vehicle equilibrium states and maneuver elements. The method therefore increases the richness of available guidance solutions while maintaining problem tractability associated with hierarchical system models. Application of the framework to one and two-dimensional path planning examples demonstrates its usefulness in practical autonomous vehicle guidance scenarios.
by Christopher Walden Dever.
Ph.D.
47
RAHMAN, SHAHNUR. "Visual Perception in Autonomous Vehicles." Thesis, KTH, Hållbarhet och industriell dynamik, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-189346.
Анотація:
The human factor accounts for nine out of ten out of all traffic accidents, and because more vehicles are being deployed on the roads, the number of accidents will increase. Because of this, various automated functions have been implemented in vehicles in order to minimize the human factor in driving. In recent year, this development has accelerated and vehicles able to perform the complete driving task without any human assistance have begun to emerge from different projects around the world. However, the autonomous vehicle still has many barriers to overcome before safe driving in traffic becomes a reality. One of these barriers is the difficulty to visually perceive the surrounding. This is partly because of the fact that something can cover the camera sensors, but it is also problematic to translate the perceived data, that the sensors are collecting, into something valuable for the passenger. The situation could be improved if wireless communications were available to the autonomous vehicle. Instead of trying to understand the surrounding by the use of camera sensors, the autonomous vehicle could obtain the necessary data via wireless communication, which was the subject of this study. The study showed that wireless communication will be significant for the autonomous vehicle in the future. The conclusion is based on the fact that wireless communication was a solution in other transport systems that have had the similar barrier as for the autonomous vehicle. There are also plans on managing the barrier via wireless communication in pilot projects related to autonomous vehicles.Den mänskliga faktorn står för nio av tio utav alla trafikolyckor, och eftersom att allt fler fordon kommer ut på vägarna så leder det till att olycksantalet ökar. På grund av detta så har olika automatiserade funktioner applicerats i fordonet för att undvika den mänskliga faktorn i körningen. Denna utveckling har accelererat och fordon som ska kunna utföra hela det dynamiska framförandet utan mänsklig assistans har börjat utvecklas i olika projekt runt om i världen. Dock så har det autonoma fordonet många barriärer kvar att övervinna, för säkert framförande, varav en av dessa barriärer är fordonets förmåga att visuellt uppfatta omgivningen. Dels genom att något kan täcka kamerasensorerna men även att kunna omsätta det sensorerna uppfattar till något värdefullt för passageraren. Situationen skulle dock kunna förbättras om trådlös kommunikation gjordes tillgänglig för det autonoma fordonet. Istället för att försöka uppfatta omgivningen via kamerasensorer, skulle det autonoma fordonet kunna få den information som behövs via trådlös kommunikation, vilket är vad denna studie behandlade. Studien visade att trådlös kommunikation kommer att ha en betydelse för det autonoma fordonet i framtiden. Slutsatsen grundar sig på att trådlös kommunikation varit en lösning inom andra transportsystem som haft en liknande barriär som för det autonoma fordonet. Man planerar dessutom på att hantera det autonoma fordonets barriär via trådlös kommunikation i pilotprojekt i dagsläget
48
Hultgren, Andree, and Muhammed Memedi. "Autonomous Vehicles With Obstacle Avoidance." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-254202.
Анотація:
Autonomous ground vehicles are becoming prevalent in this modern society due to economical and environmental benefits. This paper investigates trajectory tracking control for a two-wheel autonomous vehicle first, and then a decentralised control approach is implemented where each vehicle can maintain a formation with other vehicles. Collision avoidance is also taken into account, where both moving and stationary obstacles are considered. This enables arbitrary fleets of vehicles to manoeuvre in a set formation without colliding with each other or other obstacles. The proposed controllers are presented theoretically and verified using simulation examples.
49
Li, Kaibo. "Modular connected machines system for electrified vehicles." Thesis, Lille 1, 2020. http://www.theses.fr/2020LIL1I046.
Анотація:
Le système de Machines Connectées Modulaires (MCM) est un type même système multi-machine, dans lequel plusieurs machines électriques sont intégrées dans un module. Il possède une zone à haute efficacité plus large, une meilleure capacité de tolérance aux pannes et de nombreux modes de fonctionnement. Il a des perspectives possibles dans le domaine des véhicules électrifiés. L'objectif de cette thèse est de développer différents systèmes MCM pour véhicules électrifiés.Pour cela, cette thèse organise tout d'abord le modèle et la commande d'un véhicule à base de MCM via la Représentation Energétique Macroscopique (REM). L'utilisation de la REM met l'accent sur les couplages importants, qui distribuent de l'énergie. Par le biais de règles d'inversion, la REM souligne la nécessité d'introduire des critères de répartition de l'énergie dans la structure de commande. Ensuite, une méthode de calcul rapide de la cartographie de rendement pour différentes machines électriques est proposée. L'élimination de la préconception de machine électrique permet de gagner beaucoup de temps, ce qui jette les bases du dimensionnement de MCM. En suite, une méthode de dimensionnement basée sur plusieurs objectifs est proposée, pour assurer une zone à haute efficacité plus large, une densité de couple plus grande et un volume d'aimant permanent moins important. Les intérêts de différents MCM pour différents véhicules sont comparés et analysés. Enfin, deux stratégies de répartition de la puissance au sein du MCM sont développées sur la base de la stratégie d'efficacité optimale. Elles sont comparées en termes d'efficacité et de condition de fonctionnement. Une configuration Hardware-In-the-Loop (HIL) à échelle réduite est établie et les stratégies sont validées en temps réelModular Connected Machines (MCM) system is one kind of multi-machine system, where several machines are integrated into a module. It has wider high-efficiency area, better fault tolerance ability and numerous operation modes, and is perspective in the fields of electrified vehicles. The objective of this PhD subject is to develop different MCM systems for electrified vehicles.For this, this PhD thesis firstly organizes the model and control of a MCM-based vehicle by Energetic Macroscopic Representation (EMR). The use of EMR emphasizes the important couplings, which distribute energy. Through inversion rules, EMR highlights the necessity for introducing energy distribution criteria in the control structure. Then a fast efficiency map estimation method for different EMs are proposed. The elimination of Electrical Machine (EM) pre-design saves a lot of time, which lays a foundation for MCM sizing. Next, a multi-objective-based sizing method for a MCM is proposed, which can ensure lager high-efficiency area, larger torque density and less usage amount of Permanent Magnet (PM). The interest of different MCM systems for different vehicles are compared and analysed. Finally, two kinds of power split strategies of a MCM system are developed. They are compared in terms of efficiency and EM operating property. A reduced-scale Hardware-In-the-Loop (HIL) setup is established and the strategies are validated in real-time
50
Gong, Xuwei. "Security Threats and Countermeasures for Connected Vehicles." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-259494.
Анотація:
With the rapid development of connected vehicles, automotive security has become one of the most important topics. To study how to protect the security of vehicle communication, we analyze potential threats for connected vehicles and discuss countermeasures to mitigate these threats. In this thesis, we examine 25 services that connected vehicles can provide. Entities, connections, and message flows in these services are investigated and synthesized into a vehicle network structure. The 25 services are divided into six use cases including: infotainment service, remote monitoring, device control, Vehicle-toeverything (V2X), diagnostics service, and in-vehicle Intrusion Detection System (IDS). We establish communication models for these use cases and analyze the potential threats based on Confidentiality, Integrity and Availability (CIA) criteria. We discuss possible countermeasures that can mitigate these threats based on existing network security techniques. Each alternative countermeasure’s advantages and limitations are presented. To filter possible attacks, we investigate and design firewalls in four components of a vehicle: Dedicated Short-Range Communications (DSRC) module, gateway, Telematic Control Unit (TCU), and Human-Machine Interface (HMI). We also simulate a firewall for an HMI application by building a communication model in Python.Med den snabba utvecklingen av anslutna fordon har bilsäkerhet blivit ett av de viktigaste ämnena. För att studera hur man skyddar säkerheten för fordonskommunikation analyserar vi potentiella hot mot anslutna fordon och diskuterar motåtgärder för att mildra dessa hot. I denna avhandling undersöker vi 25 tjänster som anslutna fordon kan tillhandahålla. Entiteter, anslutningar och meddelandeflöden i dessa tjänster undersöks och syntetiseras i en fordonsnätverksstruktur. De 25 tjänsterna är indelade i sex användarvägar, inklusive: infotainment service, fjärrövervakning, enhetskontroll, Fordon-tillallt (V2X), diagnostikservice och IDS-system (Intrusion Detection System). Vi etablerar kommunikationsmodeller för dessa användningsfall och analyserar de potentiella hot som baseras på CIA-kriterier (Confidentiality, Integrity and Availability). Vi diskuterar eventuella motåtgärder som kan mildra dessa hot baserat på befintliga nätverkssäkerhetstekniker. Varje alternativ motåtgärds fördelar och begränsningar presenteras. För att filtrera eventuella attacker undersöker vi och utformar brandväggar i fyra delar av ett fordon: Dedicated Short-Range Communications (DSRC) -modul, gateway, Telematic Control Unit (TCU) och Human Machine Interface (HMI). Vi simulerar också en brandvägg för en HMI-applikation genom att bygga en kommunikationsmodell i Python.