Dissertations / Theses on the topic 'Autonomous Vehicle Network'
To see the other types of publications on this topic, follow the link: Autonomous Vehicle Network.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Autonomous Vehicle Network.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
BRUCE, WILLIAM, and OTTER EDVIN VON. "Artificial Neural Network Autonomous Vehicle : Artificial Neural Network controlled vehicle." Thesis, KTH, Maskinkonstruktion (Inst.), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-191192.
Full textAbstract:
This thesis aims to explain how a Artificial Neural Network algorithm could be used as means of control for a Autonomous Vehicle. It describes the theory behind the neural network and Autonomous Vehicles, and how a prototype with a camera as its only input can be designed to test and evaluate the algorithms capabilites, and also drive using it. The thesis will show that the Artificial Neural Network can, with a image resolution of 100 × 100 and a training set with 900 images, makes decisions with a 0.78 confidence level.Denna rapport har som mal att beskriva hur en Artificiellt Neuronnatverk al- goritm kan anvandas for att kontrollera en bil. Det beskriver teorin bakom neu- ronnatverk och autonoma farkoster samt hur en prototyp, som endast anvander en kamera som indata, kan designas for att testa och utvardera algoritmens formagor. Rapporten kommer visa att ett neuronnatverk kan, med bildupplos- ningen 100 × 100 och traningsdata innehallande 900 bilder, ta beslut med en 0.78 sakerhet.
2
Moore, Christopher, Dylan Crocker, Garret Coffman, and Bryce Nguyen. "Telemetry Network for Ground Vehicle Navigation." International Foundation for Telemetering, 2011. http://hdl.handle.net/10150/595750.
Full textAbstract:
ITC/USA 2011 Conference Proceedings / The Forty-Seventh Annual International Telemetering Conference and Technical Exhibition / October 24-27, 2011 / Bally's Las Vegas, Las Vegas, NevadaThis paper describes a short distance telemetry network which measures and relays time, space, and position information among a group of ground vehicles. The goal is to allow a lead vehicle to be under human control, or perhaps controlled using advanced autonomous path planning and navigation tools. The telemetry network will then allow a series of inexpensive, unmanned vehicles to follow the lead vehicle at a safe distance. Ultrasonic and infrared signals will be relayed between the vehicles, to allow the following vehicles to locate their position, and track the lead vehicle.
3
Schmiterlöw, Maria. "Autonomous Path Following Using Convolutional Networks." Thesis, Linköpings universitet, Datorseende, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-78670.
Full textAbstract:
Autonomous vehicles have many application possibilities within many different fields like rescue missions, exploring foreign environments or unmanned vehicles etc. For such system to navigate in a safe manner, high requirements of reliability and security must be fulfilled. This master's thesis explores the possibility to use the machine learning algorithm convolutional network on a robotic platform for autonomous path following. The only input to predict the steering signal is a monochromatic image taken by a camera mounted on the robotic car pointing in the steering direction. The convolutional network will learn from demonstrations in a supervised manner. In this thesis three different preprocessing options are evaluated. The evaluation is based on the quadratic error and the number of correctly predicted classes. The results show that the convolutional network has no problem of learning a correct behaviour and scores good result when evaluated on similar data that it has been trained on. The results also show that the preprocessing options are not enough to ensure that the system is environment dependent.
4
Darr, Matthew John. "DEVELOPMENT AND EVALUATION OF A CONTROLLER AREA NETWORK BASED AUTONOMOUS VEHICLE." UKnowledge, 2004. http://uknowledge.uky.edu/gradschool_theses/192.
Full textAbstract:
Through the work of researchers and the development of commercially availableproducts, automated guidance has become a viable option for agricultural producers.Some of the limitations of commercially available technologies are that they onlyautomate one function of the agricultural vehicle and that the systems are proprietary toa single machine model.The objective of this project was to evaluate a controller area network (CAN bus)as the basis of an automated guidance system. The prototype system utilized severalmicrocontroller-driven nodes to act as control points along a system wide CAN bus.Messages were transferred to the steering, transmission, and hitch control nodes from atask computer. The task computer utilized global positioning system data to determinethe appropriate control commands.Infield testing demonstrated that each of the control nodes could be controlledsimultaneously over the CAN bus. Results showed that the task computer adequatelyapplied a feedback control model to the system and achieved guidance accuracy levelswell within the range sought. Testing also demonstrated the system's ability tocomplete normal field operations such as headland turning and implement control.
5
Magnusson, Filip. "Evaluating Deep Learning Algorithms for Steering an Autonomous Vehicle." Thesis, Linköpings universitet, Programvara och system, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-153450.
Full textAbstract:
With self-driving cars on the horizon, vehicle autonomy and its problems is a hot topic. In this study we are using convolutional neural networks to make a robot car avoid obstacles. The robot car has a monocular camera, and our approach is to use the images taken by the camera as input, and then output a steering command. Using this method the car is to avoid any object in front of it. In order to lower the amount of training data we use models that are pretrained on ImageNet, a large image database containing millions of images. The model are then trained on our own dataset, which contains of images taken directly by the robot car while driving around. The images are then labeled with the steering command used while taking the image. While training we experiment with using different amounts of frozen layers. A frozen layer is a layer that has been pretrained on ImageNet, but are not trained on our dataset. The Xception, MobileNet and VGG16 architectures are tested and compared to each other. We find that a lower amount of frozen layer produces better results, and our best model, which used the Xception architecture, achieved 81.19% accuracy on our test set. During a qualitative test the car avoid collisions 78.57% of the time.
6
Garratt, Matthew Adam, and m. garratt@adfa edu au. "Biologically Inspired Vision and Control for an Autonomous Flying Vehicle." The Australian National University. Research School of Biological Sciences, 2008. http://thesis.anu.edu.au./public/adt-ANU20090116.154822.
Full textAbstract:
This thesis makes a number of new contributions to control and sensing for unmanned vehicles. I begin by developing a non-linear simulation of a small unmanned helicopter and then proceed to develop new algorithms for control and sensing using the simulation. The work is field-tested in successful flight trials of biologically
inspired vision and neural network control for an unstable rotorcraft. The techniques are more robust and more easily implemented on a small flying vehicle than previously attempted methods.¶
Experiments from biology suggest that the sensing of image motion or optic
flow in insects provides a means of determining the range to obstacles and terrain. This biologically inspired approach is applied to control of height in a helicopter, leading to the Worlds first optic flow based terrain following controller for an unmanned helicopter in forward flight. Another novel optic flow based controller is developed for the control of velocity in hover. Using the measurements of height from other sensors, optic flow is used to provide a measure of the helicopters lateral and longitudinal velocities relative to the ground plane. Feedback of these velocity measurements enables automated hover with a drift of only a few cm per second, which is sufficient to allow a helicopter to land autonomously in gusty conditions
with no absolute measurement of position.¶
New techniques for sensor fusion using Extended Kalman Filtering are developed to estimate attitude and velocity from noisy inertial sensors and optic flow measurements. However, such control and sensor fusion techniques can be computationally
intensive, rendering them difficult or impossible to implement on a small
unmanned vehicle due to limitations on computing resources. Since neural networks can perform these functions with minimal computing hardware, a new technique of control using neural networks is presented. First a hybrid plant model consisting of exactly known dynamics is combined with a black-box representation of the unknown dynamics. Simulated trajectories are then calculated for the plant using an optimal controller. Finally, a neural network is trained to mimic the optimal controller. Flight test results of control of the heave dynamics of a helicopter confirm
the neural network controllers ability to operate in high disturbance conditions and suggest that the neural network outperforms a PD controller. Sensor fusion and control of the lateral and longitudinal dynamics of the helicopter are also shown to
be easily achieved using computationally modest neural networks.
7
Matson, Nathan C. "Communications network design, simulation, and analysis for an autonomous unmanned vehicle system." Thesis, Monterey California. Naval Postgraduate School, 2011. http://hdl.handle.net/10945/33993.
Full textAbstract:
Approved for public release; distribution is unlimited.In this thesis, we designed, simulated, and analyzed a wireless communications system for an autonomous unmanned vehicle system. The system used for the design context is the Unmanned Vehicle (UV) Sentry, which is a system of autonomous unmanned vehicles that can be tasked for a variety of missions that involve the patrolling and protecting of a geographical region. Accordingly, the communications network needs to allow for flexibility of the vehicle topography to enable large amounts of delay intolerant sensor data to be transmitted between nodes and a capability that allows vehicles to act as relays for other vehicles. To meet these requirements, a medium access control (MAC) relay protocol based on the IEEE 802.16 standard was developed. To evaluate the performance of the protocol, Simulink was used to model the performance of the protocol as it was implemented in a specific UV Sentry scenario. Several network parameters were chosen as factors for the model, and these factors were systematically varied to yield a full factorial design of experiments. The network quality of service parameters for the tests were then analyzed to determine the best communication network configuration for the UV Sentry scenario and to illuminate the tradeoffs between the factors.
8
Tekin, Mim Kemal. "Vehicle Path Prediction Using Recurrent Neural Network." Thesis, Linköpings universitet, Statistik och maskininlärning, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166134.
Full textAbstract:
Vehicle Path Prediction can be used to support Advanced Driver Assistance Systems (ADAS) that covers different technologies like Autonomous Braking System, Adaptive Cruise Control, etc. In this thesis, the vehicle’s future path, parameterized as 5 coordinates along the path, is predicted by using only visual data collected by a front vision sensor. This approach provides cheaper application opportunities without using different sensors. The predictions are done by deep convolutional neural networks (CNN) and the goal of the project is to use recurrent neural networks (RNN) and to investigate the benefits of using reccurence to the task. Two different approaches are used for the models. The first approach is a single-frame approach that makes predictions by using only one image frame as input and predicts the future location points of the car. The single-frame approach is the baseline model. The second approach is a sequential approach that enables the network the usage of historical information of previous image frames in order to predict the vehicle’s future path for the current frame. With this approach, the effect of using recurrence is investigated. Moreover, uncertainty is important for the model reliability. Having a small uncertainty in most of the predictions or having a high uncertainty in unfamiliar situations for the model will increase success of the model. In this project, the uncertainty estimation approach is based on capturing the uncertainty by following a method that allows to work on deep learning models. The uncertainty approach uses the same models that are defined by the first two approaches. Finally, the evaluation of the approaches are done by the mean absolute error and defining two different reasonable tolerance levels for the distance between the prediction path and the ground truth path. The difference between two tolerance levels is that the first one is a strict tolerance level and the the second one is a more relaxed tolerance level. When using strict tolerance level based on distances on test data, 36% of the predictions are accepted for single-frame model, 48% for the sequential model, 27% and 13% are accepted for single-frame and sequential models of uncertainty models. When using relaxed tolerance level on test data, 60% of the predictions are accepted by single-frame model, 67% for the sequential model, 65% and 53% are accepted for single-frame and sequential models of uncertainty models. Furthermore, by using stored information for each sequence, the methods are evaluated for different conditions such as day/night, road type and road cover. As a result, the sequential model outperforms in the majority of the evaluation results.
9
Youmans, Elisabeth A. "Neural network control of space vehicle orbit transfer, intercept, and rendezvous maneuvers." Diss., This resource online, 1995. http://scholar.lib.vt.edu/theses/available/etd-06062008-162101/.
Full text
10
Flores, Javier Alejandro. "Autonomous vehicle navigation a comparative study of classical logic and neural network technique /." To access this resource online via ProQuest Dissertations and Theses @ UTEP, 2009. http://0-proquest.umi.com.lib.utep.edu/login?COPT=REJTPTU0YmImSU5UPTAmVkVSPTI=&clientId=2515.
Full text
11
Bauman, Cheryl Lynn. "Autonomous Navigation of a Ground Vehicle to Optimize Communication Link Quality." Thesis, Virginia Tech, 2006. http://hdl.handle.net/10919/36302.
Full textAbstract:
The wireless technology of today provides combat systems with the potential to communicate mission critical data to every asset involved in the operation. In such a dynamic environment, the network must be able maintain communication by adapting to subsystems moving relative to each other. A theoretical and experimental foundation is developed that allows an autonomous ground vehicle to serve as an adaptive communication node in a larger network. The vehicle may perform other functions, but its primary role is to constantly reposition itself to maintain optimal link quality for network communication. Experimentation with existing wireless network hardware and software led to the development, implementation, and analysis of two main concepts that provided a signal optimization solution. The first attracts the communication ground vehicle to the network subsystems with weaker links using a vector summation of the signal-to-noise ratio and network subsystem position. This concept continuously generates a desired waypoint for repositioning the ground vehicle. The second concept uses a-priori GIS data to evaluate the desired vehicle waypoint determined by the vector sum. The GIS data is used primarily for evaluating the viewshed, or line-of-sight, between two network subsystems using elevation data. However, infrastructure and ground cover data are also considered in navigation planning. Both concepts prove to be powerful tools for effective autonomous repositioning for maximizing the communication link quality.Master of Science
12
Freudinger, Lawrence C., Filiberto Macias, and Harold Cornelius. "Frequency Agile Transceiver for Advanced Vehicle Data Links." International Foundation for Telemetering, 2009. http://hdl.handle.net/10150/605968.
Full textAbstract:
ITC/USA 2009 Conference Proceedings / The Forty-Fifth Annual International Telemetering Conference and Technical Exhibition / October 26-29, 2009 / Riviera Hotel & Convention Center, Las Vegas, NevadaEmerging and next-generation test instrumentation increasingly relies on network communication to manage complex and dynamic test scenarios, particularly for uninhabited autonomous systems. Adapting wireless communication infrastructure to accommodate challenging testing needs can benefit from reconfigurable radio technology. Frequency agility is one characteristic of reconfigurable radios that to date has seen only limited progress toward programmability. This paper overviews an ongoing project to validate a promising chipset that performs conversion of RF signals directly into digital data for the wireless receiver and, for the transmitter, converts digital data into RF signals. The Software Configurable Multichannel Transceiver (SCMT) enables four transmitters and four receivers in a single unit, programmable for any frequency band between 1 MHz and 6 GHz.
13
Lindberg, Jonas, and Källman Isak Wolfert. "Vehicle Collision Risk Prediction Using a Dynamic Bayesian Network." Thesis, KTH, Matematisk statistik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-273629.
Full textAbstract:
This thesis tackles the problem of predicting the collision risk for vehicles driving in complex traffic scenes for a few seconds into the future. The method is based on previous research using dynamic Bayesian networks to represent the state of the system. Common risk prediction methods are often categorized into three different groups depending on their abstraction level. The most complex of these are interaction-aware models which take driver interactions into account. These models often suffer from high computational complexity which is a key limitation in practical use. The model studied in this work takes interactions between drivers into account by considering driver intentions and the traffic rules in the scene. The state of the traffic scene used in the model contains the physical state of vehicles, the intentions of drivers and the expected behaviour of drivers according to the traffic rules. To allow for real-time risk assessment, an approximate inference of the state given the noisy sensor measurements is done using sequential importance resampling. Two different measures of risk are studied. The first is based on driver intentions not matching the expected maneuver, which in turn could lead to a dangerous situation. The second measure is based on a trajectory prediction step and uses the two measures time to collision (TTC) and time to critical collision probability (TTCCP). The implemented model can be applied in complex traffic scenarios with numerous participants. In this work, we focus on intersection and roundabout scenarios. The model is tested on simulated and real data from these scenarios. %Simulations of these scenarios is used to test the model. In these qualitative tests, the model was able to correctly identify collisions a few seconds before they occur and is also able to avoid false positives by detecting the vehicles that will give way.Detta arbete behandlar problemet att förutsäga kollisionsrisken för fordon som kör i komplexa trafikscenarier för några sekunder i framtiden. Metoden är baserad på tidigare forskning där dynamiska Bayesianska nätverk används för att representera systemets tillstånd. Vanliga riskprognosmetoder kategoriseras ofta i tre olika grupper beroende på deras abstraktionsnivå. De mest komplexa av dessa är interaktionsmedvetna modeller som tar hänsyn till förarnas interaktioner. Dessa modeller lider ofta av hög beräkningskomplexitet, vilket är en svår begränsning när det kommer till praktisk användning. Modellen som studeras i detta arbete tar hänsyn till interaktioner mellan förare genom att beakta förarnas avsikter och trafikreglerna i scenen. Tillståndet i trafikscenen som används i modellen innehåller fordonets fysiska tillstånd, förarnas avsikter och förarnas förväntade beteende enligt trafikreglerna. För att möjliggöra riskbedömning i realtid görs en approximativ inferens av tillståndet givet den brusiga sensordatan med hjälp av sekventiell vägd simulering. Två olika mått på risk studeras. Det första är baserat på förarnas avsikter, närmare bestämt att ta reda på om de inte överensstämmer med den förväntade manövern, vilket då skulle kunna leda till en farlig situation. Det andra riskmåttet är baserat på ett prediktionssteg som använder sig av time to collision (TTC) och time to critical collision probability (TTCCP). Den implementerade modellen kan tillämpas i komplexa trafikscenarier med många fordon. I detta arbete fokuserar vi på scerarier i korsningar och rondeller. Modellen testas på simulerad och verklig data från dessa scenarier. I dessa kvalitativa tester kunde modellen korrekt identifiera kollisioner några få sekunder innan de inträffade. Den kunde också undvika falsklarm genom att lista ut vilka fordon som kommer att lämna företräde.
14
Тарасов, О. Є. "Інтелектуальна система автоматичного керування автомобілем у віртуальній моделі навколишнього середовища." Thesis, Чернігів, 2021. http://ir.stu.cn.ua/123456789/25133.
Full textAbstract:
Тарасов, О. Є. Інтелектуальна система автоматичного керування автомобілем у віртуальній моделі середовища : випускна кваліфікаційна робота : 121 "Інженерія програмного забезпечення" / О. Є. Тарасов ; керівник роботи О. В. Трунова ; НУ "Чернігівська політехніка", кафедра технологій та програмної інженерії. – Чернігів, 2021. – 82 с.Кваліфікаційна робота передбачає дослідження сучасного стану розвитку галузі безпілотних автомобілів, а також основних технологій, які в ній застосовуються; дослідження можливостей використання віртуальних середовищ для перевірки ефективності роботи систем автоматичного керування автомобілем; розробку системи автоматичного керування автомобілем та оцінку ефективності її роботи у віртуальній моделі навколишнього середовища. Віртуальне середовище повинно являти собою модель реального світу зі змінними довколишніми умовами: погодою, ландшафтом, часом доби. При виборі перевага має надаватися тим варіантам, в яких дорожня інфраструктура реалізована більш детально та реалістично. Розроблювана система має складатися з частин, що повинні виконувати наступні функції: - підсистема збору даних: отримання даних з віртуального середовища, їх зберігання у сховищі даних; - підсистема обробки даних: підготовка зібраних даних для реалізації системи автоматичного керування; реалізація обраних технологій на основі зібраних даних; - підсистема керування: інтеграція реалізованої системи автоматичного керування до віртуального середовища.
Qualification work involves the study of the current state of development of the unmanned vehicle industry, as well as the main technologies used in it; research of possibilities of use of virtual environments for check of efficiency of work of systems of automatic control of the car; development of an automatic car control system and evaluation of its efficiency in a virtual model of the environment. The virtual environment should be a model of the real world with changing environmental conditions: weather, landscape, time of day. When choosing, preference should be given to those options in which the road infrastructure is implemented in more detail and realistically. The developed system should consist of parts that must perform the following functions: - data collection subsystem: obtaining data from the virtual environment, storing them in the data warehouse; - data processing subsystem: preparation of collected data for the implementation of automatic control system; implementation of selected technologies based on collected data; - control subsystem: integration of the implemented automatic control system into the virtual environment.
15
Jönsson, Jonatan, and Felix Stenbäck. "Monte-Carlo Tree Search in Continuous Action Spaces for Autonomous Racing : F1-tenth." Thesis, Högskolan i Halmstad, Akademin för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-42442.
Full textAbstract:
Autonomous cars involve problems with control and planning. In thispaper, we implement and evaluate an autonomous agent based ona Monte-Carlo Tree Search in continuous action space. To facilitatethe algorithm, we extend an existing simulation framework and usea GPU for faster calculations. We compare three action generatorsand two rewards functions. The results show that MCTS convergesto an effective driving agent in static environments. However, it onlysucceeds at driving slow speeds in real-time. We discuss the problemsthat arise in dynamic and static environments and look to future workin improving the simulation tool and the MCTS algorithm. See code, https://github.com/felrock/PyRacecarSimulator
16
Stepien, Hubert, and Martin Bilger. "Diverse Time Redundant Triplex Parallel Convolutional Neural Networks for Unmanned Aerial Vehicle Detection." Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-54596.
Full textAbstract:
Safe airspace of airports worldwide is crucial to ensure that passengers, workers, and airplanes are safe from external threats, whether malicious or not. In recent years, several airports worldwide experienced intrusions into their airspace by unmanned aerial vehicles. Based on this observation, there is a need for a reliable detection system capable of detecting unmanned aerial vehicles with high accuracy and integrity. This thesis proposes time redundant triplex parallel diverse convolutional neural network architectures trained to detect unmanned aerial vehicles to address the aforementioned issue. The thesis aims at producing a system capable of real-time performance coupled with previously mentioned networks. The hypothesis in this method will result in lower mispredictions of objects other than drones and high accuracy compared to singular convolutional neural networks. Several improvements to accuracy, lower mispredictions, and faster detection times were observed during the performed experiments with the proposed system. Furthermore, a new way of interpreting the intersection over union results for all neural networks is introduced to ensure the correctness and reliability of results. Lastly, the system produced by this thesis is analyzed from a dependability viewpoint to provide an overview of how this contributes to dependability research.
17
Silva, Joelson Coelho da. "Uma proposta de controle neural adaptativo para a navegação de veículos autônomos." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 1999. http://hdl.handle.net/10183/18631.
Full textAbstract:
Os equipamentos robóticos foram inicialmente criados para atuarem em ambientes industriais fechados. Com o passar do tempo, melhorias foram conquistadas. Atualmente, não se limitam mais à realização de tarefas simples e repetitivas em locais especialmente preparados. Novos equipamentos, capazes de atuarem em ambientes abertos e de realizarem as mais diversas atividades, estão sendo desenvolvidos. Para tanto, é necessário que seus sistemas de controle realizem uma efetiva interação com o mundo onde estão inseridos. Fazem-se necessários, portanto, novos sistemas controladores com capacidade de uma contínua adaptação ao ambiente dinâmico onde operam. As redes neurais artificiais, devido a sua capacidade de tratamento de problemas não lineares – matematicamente difíceis de serem resolvidos, estão sendo empregadas no controle destes processos. O gerenciamento da trajetória de um veículo móvel em ambientes abertos ou fechados é um procedimento altamente não-linear, logo, a aplicação das redes neurais artificiais é bastante promissora. Apesar de sua grande versatilidade, as redes neurais artificiais têm sido utilizadas apenas como sistemas de mapeamento. A grande maioria delas necessita de uma fase de treinamento para que possam armazenar a diversidade de estados possíveis do sistema. Quando atuam, elas simplesmente mapeiam os seus valores de entrada (estado atual) nas soluções previamente armazenadas. Contudo, esta não é a melhor abordagem para os sistemas abertos, ou seja, para os processos cujas situações e possibilidades não podem ser totalmente enumeradas e que podem ser mutáveis no decorrer do tempo. Este trabalho apresenta uma metodologia de controle neural adaptativo para guiar um veículo móvel até o seu destino em ambientes contendo obstáculos fixos ou móveis. Diferentemente das abordagens tradicionais, não existe a necessidade de um treinamento prévio da rede. A rede neural artificial escolhida promove uma contínua adaptação do sistema enquanto atua. Neste processo, são utilizados sensores que fornecem subsídios para que a rede possa gerar, adaptativamente, soluções parciais que façam com que o veículo autônomo se aproxime cada vez mais do seu objetivo, até, finalmente, atingi-lo.The robotic equipments were created initially to actuate in closed industrial environments. Improvements have been acquieved in this area. Nowadays, they are no longer limited to perform simple and repetitive tasks in controlled places. New equipments, capable of acting in open environments and doing the most several activities, are being developed. For so much, it is necessary that its control systems accomplish an effective interaction with the world where they are inserted. Therefore, new systems controllers with capacity of a continuous adaptation to the dynamic environments are essential. Artificial neural networks, due to their capacity of dealing wit non-linear problems – mathematically difficult to be solved – are being used to control these kind of processes. Guide a mobile vehicle through an open or controlled environments is a highly non-linear procedure; therefore, the use of an artificial neural nets is quite promising. In spite of its great versatility, they have just been used as mapping systems. Most of them need a training phase so that they can store the diversity of system’s possible states. When they actuate, they simply map their input values (current state) to the solutions previously stored. However, this is not the best approach for open systems, i.e. systems whose situations and possibilities cannot be totally enumerated and that can change in time. This work presents an adaptive neural control methodology to guide a mobile vehicle to its target in environments with fixed or mobile obstacles. Differently from the traditional approaches, the need of a previous training phase of the neural network doesn't exist. The chosen model of artificial neural net promotes a continuous adaptation of the system while it actuates. Sensors are used to provide informations to the net. This way it generates partial solutions that makes the autonomous vehicle gets closer of its goal, until, finally, reach it.
18
Rahman, Quazi Marufur. "Performance monitoring of deep learning vision systems during deployment." Thesis, Queensland University of Technology, 2022. https://eprints.qut.edu.au/229733/1/Quazi%20Marufur_Rahman_Thesis.pdf.
Full textAbstract:
This thesis investigates how to monitor the performance of deep learning vision systems in mobile robots. It conducts state-of-the-art research to validate the real-time performance of mobile robots such as self-driving cars. This research is significant for deploying visual sensor-dependent autonomous vehicles in our daily lives. This knowledge will alert a mobile robot about its performance degradation to take preventive measures to reduce the risk of hazardous consequences for the robot, its surroundings and any person involved.
19
Berggren, Filip, and Jakob Engström. "Autonoma fordon – En jämförelse av tekniker för identifiering av utryckningsfordon." Thesis, KTH, Skolan för industriell teknik och management (ITM), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-264433.
Full textAbstract:
Kraven på säkerhet och effektivitet ökar ständigt inom fordonsindustrin. För att uppfylla dessa strävar fordonstillverkare efter att uppnå en högre grad av autonomi, detta innebär dock att många problem måste lösas. Denna rapport behandlar ett av dessa, autonoma fordons möjlighet att identifiera utryckningsfordon. Målet är att presentera ett förslag på vilken teknik som anses mest lämpad för autonoma fordon att kommunicera med utryckningsfordon. Arbetet grundade sig i en förstudie där standarden ITS G5, IEEE 802.11g, ZigBee samt mobilnät analyserades utifrån deras tekniska specifikationer. Utifrån analysen presenterades tre situationer där de olika teknikernas användning ansågs begränsade, i tunnlar, i tät trafik samt på långa avstånd vid höga hastigheter. Dessa situationer ställde krav på teknikerna inom bland annat svarstid, räckvidd, överföringsförmåga samt möjlighet till direktkommunikation mellan fordonen. Utifrån dessa krav ställdes en jämförelsematris upp där de olika teknikernas prestanda jämfördes. Resultatet visar att ITS G5 och ZigBee har bäst prestanda på egen hand medan en kombination av mobilnät och ITS G5 uppnår högst prestanda.The demand for safety and effectivity continuously increases within the automotive industry. One way to meet these demands is to achieve a higher level of autonomy, but to achieve the highest levels of autonomy there is a few problems to be solved along the way. This report treats one of these, an autonomous vehicle’s ability to identify emergency vehicles. The report, based on a pilot study, analyses the ITS G5 standard, IEEE 802.11g, Zigbee and mobile networks based on their technological specifications. From the analysis three situations are identified where the technologies are considered limited. These limitations are, but not limited to, reach, latency, data rates and ability to communicate vehicle to vehicle (V2V). The four technologies are then compared by these limitations in a matrix. The result shows that ITS G5 and ZigBee has the best performance by its own but the combination of mobile networks and ITS G5 shows the highest possible performance.
20
Strandell, Erstorp Elias. "Evaluation of the LSTS Toolchain for Networked Vehicle Systems on KTH Autonomous Maritime Vehicles." Thesis, KTH, Marina system, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-185273.
Full textAbstract:
The department of Naval Architecture at the Royal Institute of Technology is in posession of one Autonomous Underwater Vehicle (AUV) and a second is under construction. A project for doing hydrographic mapping using an Autonomous Surface Vehicle (ASV) is also initiated. These projects raises the need for a software to easily send commands to vehicles and to review collected data. The ability to use each vehicle as a node in a network of vehicles is also requested. This thesis examines a software toolchain developed at the Underwater Systems and Technology Laboratory (LSTS) in Portugal for mission planning and control of networked autonomous vehicles. The toolchain constitutes primarily of Neptus, which provides an operator with a user interface for realtime control and feedback from vehicles, and DUNE. DUNE is a software running on-board vehicles and communicates with Neptus over a wireless network. As a first step, and as a limitation to this thesis, the toolchain has been used to control an autonomous rover. An autopilot receives waypoints in form of latitude/longitude coordinates from DUNE and periodically sends position and various sensor readings back. DUNE is running on a GNU/Linux computer and is responsible for storing a mission of multiple waypoints and to keep track of the progress. DUNE forwards vehicle location and sensor data to Neptus for feedback in the user interface and generation of plots. In conclusion the author was able to create and execute missions of an arbitrary number of waypoints. Graphs of basically any sensor reading could be generated through the Mission Review and Analysis tool contained by Neptus. Implementing the toolchain on the departments marine vehicles releases valuable time during field tests and will in the future provide a way for experimentation with deliberate planning tools; the next natural step toward complete autonomy.
21
Lebre, Marie-Ange. "De l'impact d'une décision locale et autonome sur les systèmes de transport intelligent à différentes échelles." Thesis, Lyon, 2016. http://www.theses.fr/2016LYSEI007/document.
Full textAbstract:
Cette thèse présente des applications véhiculaires à différentes échelles : de la petite qui permet d'effectuer des tests réels de communication et de service ; à des plus grandes incluant plus de contraintes mais permettant des simulations sur l'ensemble du réseau. Dans ce contexte nous soulignons l'importance d'avoir et de traiter des données réelles afin de pouvoir interpréter correctement les résultats. A travers ces échelles nous proposons différents services utilisant la communication V2V et V2I. Nous ne prétendons pas prendre le contrôle du véhicule, notre but est de montrer le potentiel de la communication à travers différents services. La petite échelle se focalise sur un service à un feu de circulation permettant d'améliorer les temps de parcours et d'attente, et la consommation en CO2 et en carburant. La moyenne échelle se situant sur un rond-point, permet grâce à un algorithme décentralisé, d'améliorer ces mêmes paramètres, mais montre également qu'avec une prise de décision simple et décentralisée, le système est robuste face à la perte de paquet, à la densité, aux comportements humains ou encore aux taux d'équipement. Enfin à l'échelle d'une ville, nous montrons que grâce à des décisions prises de manière locale et décentralisée, avec seulement un accès à une information partielle dans le réseau, nous obtenons des résultats proches des solutions centralisées. La quantité de données transitant ainsi dans le réseau est considérablement diminuée. Nous testons également la réponse de ces systèmes en cas de perturbation plus ou moins importante tels que des travaux, un acte terroriste ou une catastrophe naturelle. Les modèles permettant une prise de décision locale grâce aux informations délivrées autour du véhicule montrent leur potentiel que se soit avec de la communication avec l'infrastructure V2I ou entre les véhicules V2VIn this thesis we present vehicular applications across different scales: from small scale that allows real tests of communication and services; to larger scales that include more constraints but allowing simulations on the entire network. In this context, we highlight the importance of real data and real urban topology in order to properly interpret the results of simulations. We describe different services using V2V and V2I communication. In each of them we do not pretend to take control of the vehicle, the driver is present in his vehicle, our goal is to show the potential of communication through services taking into account the difficulties outlined above. In the small scale, we focus on a service with a traffic light that improves travel times, waiting times and CO2 and fuel consumption. The medium scale is a roundabout, it allows, through a decentralized algorithm, to improve the same parameters. It also shows that with a simple and decentralized decision-making process, the system is robust to packet loss, density, human behavior or equipment rate. Finally on the scale of a city, we show that local and decentralized decisions, with only a partial access to information in the network, lead to results close to centralized solutions. The amount of data in the network is greatly reduced. We also test the response of these systems in case of significant disruption in the network such as roadworks, terrorist attack or natural disaster. Models, allowing local decision thanks to information delivered around the vehicle, show their potential whatsoever with the V2I communication or V2V
22
Hallqvist, Erik, and Sebastian Håkansson. "Networked control of autonomous ground vehicles." Thesis, KTH, Skolan för elektro- och systemteknik (EES), 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-199347.
Full text
23
Ehrlin, E., and M. Törnqvist. "Networked control of autonomous ground vehicles." Thesis, KTH, Skolan för elektro- och systemteknik (EES), 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-199313.
Full text
24
Athari, Kayvan. "Networked control of autonomous ground vehicles." Thesis, KTH, Skolan för elektro- och systemteknik (EES), 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-199389.
Full text
25
Bakutis, Vladas, and Qiao Jin. "Networked Control of Autonomous Ground Vehicles." Thesis, KTH, Skolan för elektro- och systemteknik (EES), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-200572.
Full text
26
Orihuela, Swartling Johanna, and Magnus Pontusson. "Cooperative networked control of autonomous ground vehicles." Thesis, KTH, Skolan för elektro- och systemteknik (EES), 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-199264.
Full text
27
Lycke, Jens, and Fredrik Svensson. "Cooperative networked control of autonomous ground vehicles." Thesis, KTH, Skolan för elektro- och systemteknik (EES), 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-199265.
Full text
28
Bsaybes, Sahar. "Models and algorithms for fleet management of autonomous vehicles." Thesis, Université Clermont Auvergne (2017-2020), 2017. http://www.theses.fr/2017CLFAC114/document.
Full textAbstract:
Résumé indisponibleThe VIPAFLEET project aims at developing a framework to manage a fleet of IndividualPublic Autonomous Vehicles (VIPA). We consider a fleet of cars distributed at specifiedstations in an industrial area to supply internal transportation, where the cars can beused in different modes of circulation (tram mode, elevator mode, taxi mode). The goalis to develop and implement suitable algorithms for each mode in order to satisfy all therequests either under an economic point aspect or under a quality of service aspect, thisby varying the studied objective functions.We model the underlying online transportation system as a discrete event basedsystem and propose a corresponding fleet management framework, to handle modes,demands and commands. We consider three modes of circulation, tram, elevator andtaxi mode. We propose for each mode appropriate online algorithms and evaluate theirperformance, both in terms of competitive analysis and practical behavior by computationalresults. We treat in this work, the pickup and delivery problem related to theTram mode and the Elevator mode the pickup and delivery problem with time windowsrelated to the taxi mode by means of flows in time-expanded networks
29
Smart, Royce Raymond, and roycesmart@hotmail com. "Evolutionary Control of Autonomous Underwater Vehicles." RMIT University. Aerospace, Mechanical and Manufacturing Engineering, 2009. http://adt.lib.rmit.edu.au/adt/public/adt-VIT20090331.143104.
Full textAbstract:
The goal of Evolutionary Robotics (ER) is the development of automatic processes for the synthesis of robot control systems using evolutionary computation. The idea that it may be possible to synthesise robotic control systems using an automatic design process is appealing. However, ER is considerably more challenging and less automatic than its advocates would suggest. ER applies methods from the field of neuroevolution to evolve robot control systems. Neuroevolution is a machine learning algorithm that applies evolutionary computation to the design of Artificial Neural Networks (ANN). The aim of this thesis is to assay the practical characteristics of neuroevolution by performing bulk experiments on a set of Reinforcement Learning (RL) problems. This thesis was conducted with the view of applying neuroevolution to the design of neurocontrollers for small low-cost Autonomous Underwater Vehicles (AUV). A general approach to neuroevolution for RL problems is presented. The is selected to evolve ANN connection weights on the basis that it has shown competitive performance on continuous optimisation problems, is self-adaptive and can exploit dependencies between connection weights. Practical implementation issues are identified and discussed. A series of experiments are conducted on RL problems. These problems are representative of problems from the AUV domain, but manageable in terms of problem complexity and computational resources required. Results from these experiments are analysed to draw out practical characteristics of neuroevolution. Bulk experiments are conducted using the inverted pendulum problem. This popular control benchmark is inherently unstable, underactuated and non-linear: characteristics common to underwater vehicles. Two practical characteristics of neuroevolution are demonstrated: the importance of using randomly generated evaluation sets and the effect of evaluation noise on search performance. As part of these experiments, deficiencies in the benchmark are identified and modifications suggested. The problem of an underwater vehicle travelling to a goal in an obstacle free environment is studied. The vehicle is modelled as a Dubins car, which is a simplified model of the high-level kinematics of a torpedo class underwater vehicle. Two practical characteristics of neuroevolution are demonstrated: the importance of domain knowledge when formulating ANN inputs and how the fitness function defines the set of evolvable control policies. Paths generated by the evolved neurocontrollers are compared with known optimal solutions. A framework is presented to guide the practical application of neuroevolution to RL problems that covers a range of issues identified during the experiments conducted in this thesis. An assessment of neuroevolution concludes that it is far from automatic yet still has potential as a technique for solving reinforcement problems, although further research is required to better understand the process of evolutionary learning. The major contribution made by this thesis is a rigorous empirical study of the practical characteristics of neuroevolution as applied to RL problems. A critical, yet constructive, viewpoint is taken of neuroevolution. This viewpoint differs from much of the reseach undertaken in this field, which is often unjustifiably optimistic and tends to gloss over difficult practical issues.
30
Schennings, Jacob. "Deep Convolutional Neural Networks for Real-Time Single Frame Monocular Depth Estimation." Thesis, Uppsala universitet, Avdelningen för systemteknik, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-336923.
Full textAbstract:
Vision based active safety systems have become more frequently occurring in modern vehicles to estimate depth of the objects ahead and for autonomous driving (AD) and advanced driver-assistance systems (ADAS). In this thesis a lightweight deep convolutional neural network performing real-time depth estimation on single monocular images is implemented and evaluated. Many of the vision based automatic brake systems in modern vehicles only detect pre-trained object types such as pedestrians and vehicles. These systems fail to detect general objects such as road debris and roadside obstacles. In stereo vision systems the problem is resolved by calculating a disparity image from the stereo image pair to extract depth information. The distance to an object can also be determined using radar and LiDAR systems. By using this depth information the system performs necessary actions to avoid collisions with objects that are determined to be too close. However, these systems are also more expensive than a regular mono camera system and are therefore not very common in the average consumer car. By implementing robust depth estimation in mono vision systems the benefits from active safety systems could be utilized by a larger segment of the vehicle fleet. This could drastically reduce human error related traffic accidents and possibly save many lives. The network architecture evaluated in this thesis is more lightweight than other CNN architectures previously used for monocular depth estimation. The proposed architecture is therefore preferable to use on computationally lightweight systems. The network solves a supervised regression problem during the training procedure in order to produce a pixel-wise depth estimation map. The network was trained using a sparse ground truth image with spatially incoherent and discontinuous data and output a dense spatially coherent and continuous depth map prediction. The spatially incoherent ground truth posed a problem of discontinuity that was addressed by a masked loss function with regularization. The network was able to predict a dense depth estimation on the KITTI dataset with close to state-of-the-art performance.
31
Stenberg, Josefin, and Sabina Syed. "Optimal Multi-Commodity Network Flow of Autonomous Vehicles in Urban Traffic." Thesis, KTH, Skolan för teknikvetenskap (SCI), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-297491.
Full textAbstract:
The focus of this thesis was to find, visualize and analyze the optimal flow of autonomous vehicles in urban traffic with respect to fuel consumption using linear optimization. Two different formulations based on multi-commodity network flow were implemented which resulted in a static and a dynamic model of the traffic. The static model was applied to Kungsholmen, an urban district in central Stockholm, Sweden, while the dynamic model was considered on a small-scale. These models led to large linear programs which were solved by applying different algorithms to the problems in various software. The results suggested that the developed models were adequate approximations of the urban traffic flow for the chosen parameter set-ups. It was concluded that the traffic in a system of autonomous vehicles may be optimally planned using similar models as formulated in this study.
32
Manara, Luca. "Investigating Antenna Placement on Autonomous Mining Vehicle." Thesis, KTH, Skolan för informations- och kommunikationsteknik (ICT), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-204908.
Full textAbstract:
Future mines will benefit from connected intelligent transport system technologies. Autonomous mining vehicles will improve safety and productivity while decreasing the fuel consumption. Hence, it is necessary for Scania to increase the know-how regarding the design of vehicular communication systems for the harsh mine environment. The scope of this work is to examine the requirements for the antenna placement of a future autonomous mining truck and propose suitable antenna types and positions. By using the electromagnetic simulator suite CST Microwave Studio, the research estimates the impact of a simplified autonomous mining vehicle geometry on basic antenna radiation patterns. Some simulated antenna configurations are assessed with radiation pattern measurements. In order to radiate enough power towards the area surrounding the vehicle and guarantee reliable communications, the truck requires omnidirectional antennas in centered locations, or alternatively one patch antenna for each side. The method used to solve the problem is also assessed: flexibility provided by the simulation method is emphasized, whereas some relevant limitations are discussed. Hardware requirements, availability of the models and limited results provided by the software can make the simulation phase not suitable to evaluate the antenna placement.Framtidens gruvor kommer att gynnas av sammankopplade, intelligenta transportsystem. Autonoma gruvfordon kommer att förbättra säkerhet och produktivitet, och samtidigt minska bränslekonsumtion. Därför är det nödvändigt för Scania att öka kunskapen om design av kommunikationssystem för fordon i hård gruvmiljö. Målet för detta projekt är att undersöka kraven för antennplacering hos ett framtida autonomt gruvfordon och att ge förslag på passande antenntyper och -positioner. Det elektromagnetiska simuleringsverktyget CST Microwave Studio används för att uppskatta påverkan från en förenklad fordonsgeometri på grundläggande antennstrålningsmönster. Utvalda antennkonfigurationer utvärderas genom undersökningar av dess strålningsmönster. För att kunna stråla ut tillräcklig effekt i området kring fordonet och garantera tillförlitlig kommunikation krävs centralt placerade runtstrålande antenner, eller alternativt en patchantenn till varje sida. Problemlösningsmetoden utvärderas också: Flexibiliteten simuleringsmetoden ger betonas, medan några relevanta begränsningar diskuteras. Hårdvarukrav, tillgängligheten av modeller och begränsade resultat från mjukvaran kan bidra till att göra simuleringen olämplig för att utvärdera antennplaceringen.
33
ANDERSSON, SANTIAGO GABRIEL, and MARTIN FAVRE. "Analysis and Evaluation of Recurrent Neural Networks in Autonomous Vehicles." Thesis, KTH, Skolan för industriell teknik och management (ITM), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-217336.
Full textAbstract:
Once upon a time cars were driven by the pure will and sweat of decent humans. Today technology has reached the point in which complex systems can drive the car with little or no human interaction at all. Whilst it does take away the sweet Sunday drive, one has to consider the positives. Over 90% of all vehicle accidents can be credited to the driver. City traffic can be optimised to avoid congestion. Additionally extending the morning nap to the car ride to work is truly something to strive for. One of the way autonomous driving can be achieved is through Artificial Neural Networks. These systems teaches a model how do drive a car through vast and vast amounts of data consisting of the state and the correct action. No manual logic required! One of the many issues these systems face is that the model only analyses the current state and has no inherent memory, just a million small independent decisions. This creates issues in situations like overtaking as it requires a longer plan to safely pass the other vehicle. This thesis investigates utilising the Recurrent Neural Networks which are designed to analyse sequences of states instead of a single one with hopes that this may alleviate the sequential hassles. This is done by modifying an 1/12 scale RC-car by mounting a camera in the front. The images were used to control both steering or velocity in three separate tests which simulates normal driving situations in which the sequence of events contain information. In all three scenarios three different networks were tested. One ordinary single-state model, a model evaluating 5 states and model evaluating 25. Additionally as a ground truth a human drove the same tests. These were qualitatively compared and evaluated. The test results showed that there indeed sometimes were an improvement in utilising recurrent neural networks but additional and more repeatable tests are required to define when and why.Traditionellt har bilar körts av antsändiga människor. Teknologin har idag dock kommit till den punkten då komplexa system kan köra med minimal eller full avsaknad av mänsklig interaktion. Medan det visserligen tar bort den trevliga söndagsturen så måste man tänka på fördelarna. I över 90% av alla fordonsolyckor är orsaken grundad i föraren. Stadstrafik kan bli optimerad för att undvika trafikstockningar. Dessutom att förlämga ens morgontur med hela bilresan till jobbet är verkligen något att sträva efter. Ett av sätten man kan uppnå autonom körning är genom artificiella neurala nätverk. Dessa system lär en modell hur man kör med hjälp av stora mängder data som består av ett tillstånd och dess korrekta handling. Minimal mängd manuell design krävd. En av de flera problem som Artificiella Neurala Nätverk har är att de inte har något minne, utan tar bara en stor mängd individuella beslut. Detta kan skapa problem i situationer som omkörning då det kräver en längre plan för att säkert ta sig runt andra bilen. Den här uppsatsen undersöker `Recurrent´ Neurala Nätverk som är designade för att analysera sekvenser av tillstånd iställer för ett enkelt tillstånd med hopp om att det kommer lindra de skventiella problemen. Detta är gjort genom att modifiera en 1/12 i skala radiostyrd bil med en kamera på framsidan. Dessa bilder används för att kontrollera både styrning eller hastighet i tre separata experiment som simulerar vanliga körningsscenarion i vilka sekvensen av tillstånd innehåller information. I alla tre experiment testades tre olika nätverk. Dessa analyserar respektibe 1, 5 och 25 tillstånd. Utöver dessa gjordes även experiment med en mänsklig förare som grundreferens. Resultaten jämfördes och evaluerades kvalitativt. Slutresultatet visade att det fanns tillfällen då det var bättre att analysera flera tillstånd, men att fler och mer repeterbara tester behövs för att kunna slå fast när och varför.
34
Lyu, Yiru. "Behavior Prediction of Surrounding Vehicles in a Road Network for Autonomous Driving." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-263236.
Full textAbstract:
To ensure the safety of the road system, an autonomous vehicle should have a good understanding of its surrounding environment. This thesis designs a framework for trajectory prediction of surrounding vehicles on a highway road system based on their historical information such as past positions, velocities and their neighbouring vehicles. The framework consists of a long short-term memory (LSTM) networks with a encoder-decoder structure that handles this sequence-to-sequence prediction problem. In order to account for uncertainty, confidence values are assigned to different maneuvers based on a maneuver classification network, so the final output of the framework is several possible future trajectories with particular probabilities. The experiments using NGSIM Us-101 and I-80 datasets show that this framework outperforms a simply stacked LSTM-dense network. Besides, the suitable input features for the framework are also analyzed in this thesis.För att säkerställa hög säkerhet i vägnätverket, ska ett autonomt fordon ha en god förståelse för sin omgivande miljö samt kunna resonera om hur den kommer utvecklas med tiden. Detta arbete innefattar ett ramverk för rörelsemönsterprediktion för omgivande fordon i ett motorvägssystem baserat på deras historik, såsom tidigare positioner, hastigheter och närliggande fordon. Ramverket består av ett långoch korttidsminnesbaserat neuralt nätverk (Long Short Term Memory, LSTM) med en kodaroch avkodarstruktur som hanterar detta sekvens-till-sekvens-prediktionsproblem. För att ta hänsyn till osäkerhet associeras osäkerhetsvärden till de olika predikterade rörelsemönstren baserat på ett manöver-klassificeringsnätverk, så att ramverkets slutliga utdata är flera möjliga framtida banor med associerade sannolikheter. Experimenten är baserade på data från NGSIM US-101 och I-80 och resultaten visar att detta ramverk överträffar ett enkelt staplat LSTM nätverk. Utöver detta analyseras även indatat till nätverket för att utvärdera de olika insignalernas påverkan på prediktionernas prestanda.
35
Richard, Mark G. "Cooperative control of distributed autonomous systems with applications to wireless sensor networks." Thesis, Monterey, Calif. : Naval Postgraduate School, 2009. http://edocs.nps.edu/npspubs/scholarly/theses/2009/Jun/09Jun%5FRichard.pdf.
Full textAbstract:
Thesis (M.S. in Mechanical Engineering)--Naval Postgraduate School, June 2009.Thesis Advisor(s): Lee, Deok Jin ; Kaminer, Issac I. "June 2009." Description based on title screen as viewed on 13 July 2009. Author(s) subject terms: Unmanned Aerial Vehicle, UAV, extremum seeking, simulink, high bandwidth communication links, SNR Model, coordinated control, cooperative control, decentralized control, wireless sensor network. Includes bibliographical references (p. 51). Also available in print.
36
Sparrenhök, Jonny. "Influential Learning : Knowledge Sharing between Artificial Neural Networks for Autonomous Vehicles." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-301643.
Full textAbstract:
Autonomous vehicles may be a part of our future no matter if we like it or not. The technology developed for self-driving have already outperformed humans in multiple aspects but involves systems that are prone to failure. Machine learning techniques have proven to enhance the performance of these autonomous vehicles by efficiently analyzing and learning from data gathered through embedded systems. A popular approach to enhance performance in autonomous systems is to incorporate cameras and use computer vision techniques to extract useful information from the images. The potential use cases of applying such techniques are many including object detection, tracking, segmentation, motion estimation and scene understanding. Numerous implementation methods have been proposed with the ambition to optimize these techniques in order to utilize their full potential and help autonomous systems maneuver as accurate as possible. Velocity and steering angle are important aspects of autonomous vehicles, however since the vehicles can reach high velocities it is also of great importance that the systems act quickly in addition to being accurate. This thesis evaluates an approach that involves combining machine learning models in a way that enables one of the models to be influenced by the others with knowledge unobtainable by itself. While learning to estimate a steering angle one of the models is simultaneously taught to mimic auxiliary models that have achieved state-of-the-art performance in tasks related to image segmentation and optical flow. The machine learning models used are convolutional neural networks and the intention is for one of the neural networks to acquire the knowledge of the optimal direction to steer a vehicle. The project conducted in this thesis shows that the performance on gathered test data can be significantly improved with the proposed approach while all used neural networks are able to handle the data. After training has been conducted the auxiliary neural networks can be discarded and therefore this approach achieves the same processing time and memory size as if they were not involved.Autonoma fordon kan komma att bli en del av vår framtid oavsett om vi så önskar eller inte. Den teknik som har utvecklats för ändamålet är redan idag bättre i flertalet aspekter på att hantera fordon än vad människor är. Implementationer av autonoma fordon bygger ofta på maskininlärning där en modell lär sig att manövrera fordonet med hjälp av data som samlas in genom inbyggda system. En vanligt tillvägagångssätt för att förbättra dessa autonoma fordon är att använda sig av kameror, där de insamlade bilderna kan behandlas och utvärderas av modeller skapade för att främja datorseende. Det finns många användningsområden där datorseende kan appliceras inom autonoma fordon bland annat objektigenkänning, lokalisering, rörelseuppskattning och scenförståelse. Åtskilliga implementationer har föreslagits med ambitionen att optimera dessa modeller och utnyttja deras fulla potential så att autonoma system kan mönvrera ett fordon på bästa möjliga sätt. Det är inte bara styrning och hastighet som är viktigt för dessa modeller, det är också av stor betydelse att dessa system agerar snabbt då fordonen ofta rör sig i höga hastigheter. Den här uppsatsen utvärderar ett tillvägagångssätt som involverar en kombination av några av de främsta maskininlärnings modellerna inom optiskt flöde och bildsegmentering. Samtidigt som en av dessa modeller lär sig att manövrera styrning av fordonet så lär den sig att imitera modeller som tidigare har visat väldigt bra resultat inom andra uppgifter som är relaterade till datorseende i autonoma fordon. De modeller som är involverade är faltningsnätverk och imitationen sker med avsikten att den modell som är avsedd att lära sig styra fordonet ska ta del av den kunskap som indikerar styrvinkel ifrån de andra nätverken. Projektet som utförs i samband med den här uppsatsen visar att modellen blir signifikant förbättrad på att utvärdera styrvinkel för de fallen där alla faltningsnätverk klarar av att hantera datan. Efter träning förkastar modellen hjälpnätverken och uppnår därför samma behandlingstid och minnesanvändning som ett nätverk där dessa inte involveras.
37
Janet, Jason Andre. "Pattern analysis, tracking and control for autonomous vehicles using neural networks." Raleigh, NC : North Carolina State University, 1998. http://www.lib.ncsu.edu/etd/public/etd-45309999852811/etd.pdf.
Full text
38
Wineman, Patrick L. "Technical benefits and cultural barriers of networked Autonomous Undersea Vehicles." Thesis, Massachusetts Institute of Technology, 2013. http://hdl.handle.net/1721.1/79538.
Full textAbstract:
Thesis (S.M.)--Massachusetts Institute of Technology, Engineering Systems Division, 2013.Cataloged from PDF version of thesis.
Includes bibliographical references (p. 44-45).
The research presented in this thesis examines the technical benefits to using a collaborative network of Autonomous Undersea Vehicles (AUVs) in place of individual vehicles. Benefits could be achieved in the areas of reduced power consumption, improved positional information and improved acoustic communication bandwidth. However, current culture of AUV development may impede this approach. The thesis uses the Object Process Methodology (OPM) and principles of System Architecture to trace the value of an AUV system from the scientist who benefits from the data to the vehicle itself. Sections 3 and 4 outline the needs for an AUV system as they currently exist and describe the key physics-based limitations of operations. Section 5 takes a broader look at the system goal as data delivery, not just the deployment of a vehicle, and introduces the concept of networked AUV. Section 6 describes a potential evolution of networked AUVs in increasing autonomy and collaboration. Finally, Section 7 examines AUV development cultures that could impede, or foster, networked vehicles.
by Patrick L. Wineman.
S.M.
39
Risan, Øyvind. "Virtual (floating) Context Sharing between Vehicles : Generating and Sharing Context Information within an Autonomous Network of Vehicles." Thesis, Norges teknisk-naturvitenskapelige universitet, Institutt for telematikk, 2010. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-11319.
Full textAbstract:
This thesis investigates some of the potential within Intelligent Transportation Systems and Inter-Vehicle Communication. The aim is to find a method for spreading information throughout an ad hoc network of vehicles with as little impact on the available resources as possible.Two problems are identified and investigated. The first problem is determining the border of a known set of vehicle positions. This is solved by producing a list of edges that encircles vehicles which contain the same information. These edges form a border that can be used to reduce the amount of data needed to represent the status in that particular area. By reducing the amount of data the load on the limited transmission capacity can be reduced.Based on mathematical calculations relating to the relative position of vehicles, an algorithm was devised to detect and order the vehicles that contribute to the border of an area. It is possible to alter the shape of the border by removing selected points on the border. This makes it possible to make the border convex instead of concave. The behaviour of this border finding algorithm is illustrated by a java program. The graphical representation also displays some of the mechanisms used to determine the border.The second problem is related to how information can be distributed efficiently to all vehicles within a network. As there are limited capacities in most vehicle-to-vehicle-networks there is a need to focus on reducing the overall load in such networks. The aim is to distribute the available information to every vehicle in the network as efficiently as possible, without acting at the expense of speed and flexibility.The choice of information exchange method has a serious effect on the transmission load, and the amount of interference that is present in the network. Pure flooding is the most basic and elementary of the methods available. The two main strengths of this method are the reactive behaviour, and the ability to adapt to any network configuration.This thesis suggests an alternative method for broadcasting information throughout the network, without having to use pure flooding. The method is called ICE (Information Combined and Exchanged). This method collects the available data and aggregates this to one single new message. To do this a delay is introduced between a vehicle receiving a message and retransmitting it. All messages received during this time are included in the following transmission.ICE does not limit what kind of information that could be exchanged, but examples of useful information might be warnings, points of interest, infotainment and advertisements.Based upon the behaviour of ICE a simulator was made to test the performance. The simulator made it possible to compare the performance of both ICE and pure flooding by measuring various variables. The main parameters were the size of the introduced delay and the number of vehicles in the simulation area. The combinations of the parameters and broadcast methods lead to 96 simulations from which a great amount of information could be extracted.The results showed that ICE outperformed pure flooding with regards to transmission load, interference and lost messages. At selected delays the time each vehicle is involved in the communication is also superior to pure flooding.The most significant findings are:ICE generally performs at its best with a delay of about 50 ms Any individual vehicles involvement time might be reduced by as much as 74%Depending on the number of unique messages the number of sent messages can be reduced by 77% to 86%The interference can on average be reduced by 66%Pure flooding is outperformed by ICE in almost all the situations that were tested in the simulator in this thesis. A situation with very sparsely populated networks and long delays is the exception. In this case pure flooding is faster, but might waste more resources. Implementation of dynamic delays would make ICE suitable for this scenario as well.
40
Eze, Elias Chinedum. "Achieving reliable and enhanced communication in vehicular ad hoc networks (VANETs)." Thesis, University of Bedfordshire, 2017. http://hdl.handle.net/10547/622523.
Full textAbstract:
With the envisioned age of Internet of Things (IoTs), different aspects of Intelligent Transportation System (ITS) will be linked so as to advance road transportation safety, ease congestion of road traffic, lessen air pollution, improve passenger transportation comfort and significantly reduce road accidents. In vehicular networks, regular exchange of current position, direction, speed, etc., enable mobile vehicle to foresee an imminent vehicle accident and notify the driver early enough in order to take appropriate action(s) or the vehicle on its own may take adequate preventive measures to avert the looming accident. Actualizing this concept requires use of shared media access protocol that is capable of guaranteeing reliable and timely broadcast of safety messages. This dissertation investigates the use of Network Coding (NC) techniques to enrich the content of each transmission and ensure improved high reliability of the broadcasted safety messages with less number of retransmissions. A Code Aided Retransmission-based Error Recovery (CARER) protocol is proposed. In order to avoid broadcast storm problem, a rebroadcasting vehicle selection metric η, is developed, which is used to select a vehicle that will rebroadcast the received encoded message. Although the proposed CARER protocol demonstrates an impressive performance, the level of incurred overhead is fairly high due to the use of complex rebroadcasting vehicle selection metric. To resolve this issue, a Random Network Coding (RNC) and vehicle clustering based vehicular communication scheme with low algorithmic complexity, named Reliable and Enhanced Cooperative Cross-layer MAC (RECMAC) scheme, is proposed. The use of this clustering technique enables RECMAC to subdivide the vehicular network into small manageable, coordinated clusters which further improve transmission reliability and minimise negative impact of network overhead. Similarly, a Cluster Head (CH) selection metric F(j) is designed, which is used to determine and select the most suitably qualified candidate to become the CH of a particular cluster. Finally, in order to investigate the impact of available radio spectral resource, an in-depth study of the required amount of spectrum sufficient to support high transmission reliability and minimum latency requirements of critical road safety messages in vehicular networks was carried out. The performance of the proposed schemes was clearly shown with detailed theoretical analysis and was further validated with simulation experiments.
41
Doolittle, Daniel Foster. "Automated Fish Species Classification using Artificial Neural Networks and Autonomous Underwater Vehicles." W&M ScholarWorks, 2003. https://scholarworks.wm.edu/etd/1539617813.
Full text
42
Wegener, Jan-Thierry. "Redeployment in Convoys of Fleets of Shared Vehicles." Thesis, Clermont-Ferrand 2, 2016. http://www.theses.fr/2016CLF22722/document.
Full textAbstract:
L’autopartage est une manière moderne de louer une voiture. C'est un système attractif pour les clients qui utilisent une voiture occasionnellement. Dans un système d’autopartage, une flotte de véhicules est répartie sur une aire urbaine. Les client peuvent prendre ou rendre une voiture à n'importe quel moment et à n'importe quelle station, à condition qu’il y ait une voiture de libre à la station de départ et qu’il y a une place de parking libre à la station de destination. Pour s'en assurer, les clients peuvent réserver une voiture en avance. Pour qu’un tel système fonctionne de manière satisfaisante, il faut que le nombre de véhicules et le nombre de places libres dans les stations s'équilibrent. Cela conduit à un problème d'équilibre d'occupation des stations, appelé problème de relocalisation : un opérateur doit surveiller l'occupation des stations et décider quand et de quelle manière les voiture doivent être deplacées d’une station « trop pleine » à une station « insuffisamment pleine ». Nous considérons un système d’autopartage innovant, où les voitures sont partiellement autonomes. Cela permet de constituer des convois de véhicules que dirige un véhicule spécial, de sorte qu'un convoi est mis en mouvement par un seul conducteur. Cette configuration est similaire au système mis en place pour les vélos en libre-service, où un camion peut déplacer plusieurs vélos simultanément pendant le processus de la relocalisation. Dans le cadre de cette thèse, nous développons les aspects dynamiques et statiques du problème de relocalisation. Le « problème de relocalisation dynamique » décrit la situation où les voitures sont déplacées pendant les heures de travail afin de satisfaire les besoins des clients. L’opérateur doit prendre des décisions « dynamiques », en fonction de la situation. Dans le cadre du « problème de relocalisation statique », nous supposons qu’il n'y a aucune interaction (ou très peu) entre les clients et le système. Cette situation se produit lorsque le système est préparé pour le lendemain (ex : processus de la relocalisation effectué pendant la nuit). Nous modélisons le problème de relocalisation dans le cadre d’un système de tâches métriques. Ensuite, nous analysons les deux problèmes et nous donnons des stratégies pour les résoudre. Enfin, nous effectuons quelques expériences de calcul pour examiner l’applicabilité des algorithmes présentés en pratiqueCarsharing is a modern way of car rental, attractive to customers who make only occasional use of a car on demand. In a carsharing system, a fleet of cars is distributed at specified stations in an urban area, customers can take a car at any time and station and return it at any time and station, provided that there is a car available at the start station and a free place at the destination station. To ensure the latter, customers have to book their demands in advance. For operating such a system in a satisfactory way, the stations have to keep a good ratio between the total number of places and the number of cars in each station, in order to serve as many requests as possible. This leads to the problem of balancing the load of the stations, called Relocation Problem: an operator has to monitor the load and to decide when and how to move cars from “overfull” stations to “underfull” ones. We consider an innovative carsharing system, where the cars are partly autonomous, which allows to build wireless convoys of cars leaded by a special vehicle, such that the whole convoy is moved by only one driver. This setting is similar to bikesharing, where trucks can simultaneously move several bikes during the relocation process. In this thesis, we address the dynamic and static aspects of the Relocation Problem. The “Dynamic Relocation Problem” describes the situation when cars can be moved between stations during the working hours in order to satisfy the needs of the customers. Hereby, the operator has to make decisions dynamically according to the current situation. In the “Static Relocation Problem” we assume that there is no (or only little) interaction by customers with the system. This situation occurs when the carsharing system is prepared for the next day, i.e., the relocation process is performed during the night. We model the Relocation Problem in the framework of a metric task system. Afterwards, we theoretically analyze both problems and give strategies to solve them. Finally, we perform some computational experiments to examine the applicability of the presented algorithms in practice
43
Puttige, Vishwas Ramadas Engineering & Information Technology Australian Defence Force Academy UNSW. "Neural network based adaptive control for autonomous flight of fixed wing unmanned aerial vehicles." Awarded by:University of New South Wales - Australian Defence Force Academy. Engineering & Information Technology, 2009. http://handle.unsw.edu.au/1959.4/43736.
Full textAbstract:
This thesis presents the development of small, inexpensive unmanned aerial vehicles (UAVs) to achieve autonomous fight. Fixed wing hobby model planes are modified and instrumented to form experimental platforms. Different sensors employed to collect the flight data are discussed along with their calibrations. The time constant and delay for the servo-actuators for the platform are estimated. Two different data collection and processing units based on micro-controller and PC104 architectures are developed and discussed. These units are also used to program the identification and control algorithms. Flight control of fixed wing UAVs is a challenging task due to the coupled, time-varying, nonlinear dynamic behaviour. One of the possible alternatives for the flight control system is to use the intelligent adaptive control techniques that provide online learning capability to cope with varying dynamics and disturbances. Neural network based indirect adaptive control strategy is applied for the current work. The two main components of the adaptive control technique are the identification block and the control block. Identification provides a mathematical model for the controller to adapt to varying dynamics. Neural network based identification provides a black-box identification technique wherein a suitable network provides prediction capability based upon the past inputs and outputs. Auto-regressive neural networks are employed for this to ensure good retention capabilities for the model that uses the past outputs and inputs along with the present inputs. Online and offline identification of UAV platforms are discussed based upon the flight data. Suitable modifications to the Levenberg-Marquardt training algorithm for online training are proposed. The effect of varying the different network parameters on the performance of the network are numerically tested out. A new performance index is proposed that is shown to improve the accuracy of prediction and also reduces the training time for these networks. The identification algorithms are validated both numerically and flight tested. A hardware-in-loop simulation system has been developed to test the identification and control algorithms before flight testing to identify the problems in real time implementation on the UAVs. This is developed to keep the validation process simple and a graphical user interface is provided to visualise the UAV flight during simulations. A dual neural network controller is proposed as the adaptive controller based upon the identification models. This has two neural networks collated together. One of the neural networks is trained online to adapt to changes in the dynamics. Two feedback loops are provided as part of the overall structure that is seen to improve the accuracy. Proofs for stability analysis in the form of convergence of the identifier and controller networks based on Lyapunov's technique are presented. In this analysis suitable bounds on the rate of learning for the networks are imposed. Numerical results are presented to validate the adaptive controller for single-input single-output as well as multi-input multi-output subsystems of the UAV. Real time validation results and various flight test results confirm the feasibility of the proposed adaptive technique as a reliable tool to achieve autonomous flight. The comparison of the proposed technique with a baseline gain scheduled controller both in numerical simulations as well as test flights bring out the salient adaptive feature of the proposed technique to the time-varying, nonlinear dynamics of the UAV platforms under different flying conditions.
44
Augustsson, Louise. "Study and Analysis of Convolutional Neural Networks for Pedestrian Detection in Autonomous Vehicles." Thesis, Uppsala universitet, Avdelningen för visuell information och interaktion, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-353608.
Full textAbstract:
The automotive industry is heading towards more automation. This puts high demands on many systems like Pedestrian Detection Systems. Such systems need to operate in real time with high accuracy and in embedded systems with limited power, memory resources and compute power. This in turn puts high demands on model size and model design. Lately Convolutional Neural Networks (ConvNets) have dominated the field of object detection and therefore it is reasonable to believe that they are suited for pedestrian detection as well. Therefore, this thesis investigates how ConvNets have been used for pedestrian detection and how such solutions can be implemented in embedded systems on FPGAs (Field Programmable Gate Arrays). The conclusions drawn are that ConvNets indeed perform well on pedestrian detection in terms of accuracy but to a cost of large model sizes and heavy computations. This thesis also comes up with a design proposal of a ConvNet for pedestrian detection with the implementation in an embedded system in mind. The proposed network performs well on pedestrian classification and the performance looks promising for detection as well, but further development is required.
45
Dabboussi, Abdallah. "Dependability approaches for mobile environment : Application on connected autonomous vehicles." Thesis, Bourgogne Franche-Comté, 2019. http://www.theses.fr/2019UBFCA029.
Full textAbstract:
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
46
Ekinci, Murat. "Computer vision applied to the navigation of an autonomous road vehicle in complex road networks." Thesis, University of Bristol, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.361132.
Full text
47
Kaygisiz, Huseyin Burak. "Intelligent Methods For Dynamic Analysis And Navigation Of Autonomous Land Vehicles." Phd thesis, METU, 2004. http://etd.lib.metu.edu.tr/upload/2/12605112/index.pdf.
Full textAbstract:
Autonomous land vehicles (ALVs) have received considerable attention after their introduction into military and commercial applications. ALVs still stand as a challenging research topic. One of the main problems arising in ALV operations is the navigation accuracy while the other is the dynamic effects of road irregularities which may prevent the vehicle and its cargo to function properly. In this thesis, we propose intelligent solutions to these two basic problems of ALV. First, an intelligent method is proposed to enhance the performance of a coupled global positioning/inertial navigation system (GPS/INS) for land navigation applications during the GPS signal loss. Our method is based on using an artificial neural network (ANN) to intelligently aid the GPS/INS coupled navigation system in the absence of GPS signals. The proposed enhanced GPS/INS is used in the dynamic environment of a tour of an autonomous van and we provide the results here. GPS/INS+ANN system performance is thus demonstrated with the land trials. Secondly, our work focuses on the identification and enlargement of the stability region of the ALV. In this thesis, the domain of attraction of the ALV is found to be patched by chaotic and regular regions with chaotic boundaries which are extracted using novel technique of cell mapping equipped with measures of fractal dimension and rough sets. All image cells in the cellular state space, with their individual fractal dimension are classified as being members of lower approximation (surely stable), upper approximation (possibly stable) or boundary region using rough set theory. The obtained rough set with fractal dimension as its attribute is used to model the uncertainty of the regular regions. This uncertainty is then smoothed by a reinforcement learning algorithm in order to enlarge regular regions that are used for chassis control, critical in ALV in preventing vibration damages that can harm the payload. Hence, we will make ALV work in the largest safe area in dynamical sense and prevent the vehicle and its cargo.
48
Mostafa, Ahmad A. "Packet Delivery Delay and Throughput Optimization for Vehicular Networks." University of Cincinnati / OhioLINK, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1367924037.
Full text
49
Marsilio, Alan M. "Use of Hopfield networks for system identification and failure detection in autonomous underwater vehicles." Thesis, Monterey, California. Naval Postgraduate School, 1991. http://hdl.handle.net/10945/28628.
Full text
50
Livianu, Mathew Joseph. "Human-in-the-loop neural network control of a planetary rover on harsh terrain." Thesis, Atlanta, Ga. : Georgia Institute of Technology, 2008. http://hdl.handle.net/1853/26576.
Full textAbstract:
Thesis (M. S.)--Electrical and Computer Engineering, Georgia Institute of Technology, 2009.Committee Chair: Dr. Ayanna Howard; Committee Member: Dr. Patricio Vela; Committee Member: Dr. Yoria Wardi. Part of the SMARTech Electronic Thesis and Dissertation Collection.