Rozprawy doktorskie na temat „Intelligent cruise control”

Intelligent cruise control (ICC) has the potential to impact both roadway throughput and safety by assisting drivers in maintaining safe headways. This thesis explores this potential through comparisons of ICC to conventional cruise control (CCC) and manual driving. Accordingly, descriptions are given of both CCC and ICC systems. Furthermore, descriptions of ICC evaluation studies and car-following models are presented.

The evaluation of ICC is conducted using data collected as part of the Field Operational Test (FOT) performed in Ann Arbor, Michigan. Two levels of analysis are presented in this thesis. The first level of analysis compares the usage of ICC to CCC from a macro level. This study demonstrated that ICC was used more along similar trips. In addition, it was shown that there was no difference in usage of the ON, SET, CANCEL and RESUME buttons. ICC resulted in a higher usage of the ACCEL button and a lower usage of the COAST button compared to CCC. Furthermore, the number of brake interventions while ICC was engaged was higher than CCC. Lastly, the macro-level analysis indicated that there was no difference in the number of near encounters for ICC and CCC. The second analysis makes comparisons at a micro level. The most probable speed, acceleration and headway for each driving mode as well as the probability of using cruise control (based on speed) were determined. The probability of ICC use exceeded CCC use for every freeway speed bin and all but two high-speed arterial speed bins. Finally, a car-following behavior comparison was performed. Manual driving resulted in larger headway values for speeds less than 80 km/h. The ICC speed-headway curve was similar to the CCC speed-headway curve created from high-speed arterial data. The mean headway-speed charts, however, indicated that ICC was more similar to manual driving. Exploration into the specific differences is needed in order to determine the impact of ICC on system safety.
Master of Science

Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1999.
Includes bibliographical references (p. 95-96).
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
In recent years, automobiles have become increasingly computerized and varying degrees of intelligent control has been integrated into automotive systems. A natural extension of this trend is full intelligent and autonomous control of vehicle by onboard computer systems. This thesis presents the design, development, and construction of a low-cost, low-power vision system suitable for on-board automated vehicle systems such as intelligent cruise control. The apparatus leverages vision algorithms, simplified by a prescribed camera geometry, to compute depth maps in real-time, given the input from three imagers mounted on the vehicle. The early vision algorithms are implemented using Dr. David Martin's ADAP mixed signal array processor. The back-end algorithms are mplemented in software on PC for simplicity, but could easily be implemented in hardware in a later design. The final apparatus was able to compute depth maps at a rate of 24 frames per second, limited only by the interrupt latency of the PC executing the algorithms.
by Mark Christian Spaeth.
S.M.

The author's concept of the distance and tracking control problem for autonomous vehicles relates to the cooperative behaviour of two successive vehicles travelling in the same environment. This behaviour requires one vehicle, designated the leader to move autonomously around it's environment with other vehicles, designated followers maintaining a coincident travel path and desired longitudinal distance with respect to the leader. Distance and tracking control is beneficial in numerous applications including guiding autonomous vehicles in Intelligent Transport Systems (ITS) which increases traffic safety and the capacity of pre-existing road infrastructure. Service robotics may also benefit from the cost savings and flexibility offered by distance and tracking control which enables a number of robots to cooperate together in order to achieve a task beyond the capabilities ofjust one robot. Using a distance and tracking control scheme an intelligent leader robot may guide a number of less intelligent (and therefore less costly and less complex) followers to a work-site to perform a task. The author's approach to the distance and tracking control problem consisted of two separate solutions - an initial solution used as a starting point and learning experience and a second, more robust, fuzzy control-based solution. This thesis briefly describes the initial solution, but places a greater emphasis on the second solution. The reason for this is that the fuzzy control-based solution offers significant improvement on the initial solution and was developed based on conclusions drawn from the initial solution. Most implementations of distance and tracking control, sometimes referred to as Intelligent Cruise Control (ICC) or platooning, are limited to longitudinal distance control only. The leader tracking control is performed either implicitly by a separate lane-following control system or by human drivers. The fuzzy control-based solution offered in this thesis performs both distance and tracking control of an autonomous follower vehicle with respect to a leader vehicle in front of it. It represents a simple and cost effective solution to the requirements of autonomous vehicles operating in ITS schemes - particularly close formation platooning. The follower tracks a laser signal emitted by the leader and monitors the distance to the follower at the same time using ultrasonic ranging techniques. The follower uses the data obtained from these measuring techniques as inputs to a fuzzy controller algorithm to adjust its distance and alignment with respect to the leader. Other systems employed on road vehicles utilise video-based leader tracking, or a range of lane-following methods such as magnetometer or video-based methods. Typically these methods are disadvantaged by substantial unit and/or infrastructure costs associated with their deployment. The limitations associated with the solutions presented in this thesis arise in curved trajectories at larger longitudinal distance separations between vehicles. The effects of these limitations on road vehicles has yet to be fully quantified, however it is thought that these effects would not disadvantage its use in close formation platooning. The fuzzy control-based distance and tracking control solution features two inputs, which are the distance and alignment of the follower with respect to the leader. The fuzzy controller asserts two outputs, which are left and right wheel velocities to control the speed and trajectory of a differential drive vehicle. Each of the input and output fuzzy membership functions has seven terms based around lambda, Z-type and S-type functions. The fuzzy rule base consists of 49 rules and the fuzzy inference stage is based on the MAX/MIN method. A Centre of Maximum (CoM) def'uzzification method is used to provide the two crisp valued outputs to the vehicle motion control. The methods chosen for the fuzzy control of distance and tracking for autonomous vehicles were selected based on a compromise between their computational complexity and performance characteristics. This compromise was necessary in order to implement the chosen controller structure on pre-existing hardware test beds based on an 8-bit microcontrollers with limited memory and processing resources. Overall the fuzzy control-based solution presented in this thesis effectively solves the distance and tracking control problem. The solution was applied to differential drive hardware test-beds and was tested to verify performance. The solution was thoroughly tested in both the simulation environment and on hardware test-beds. Several issues are identified in this thesis regarding the application of the solution to other platforms and road vehicle use. The solution will be shown to be directly portable to service robotics applications and, with minor modifications, applicable to road vehicle close-formation platooning.

The author's concept of the distance and tracking control problem for autonomous vehicles relates to the cooperative behaviour of two successive vehicles travelling in the same environment. This behaviour requires one vehicle, designated the leader to move autonomously around it's environment with other vehicles, designated followers maintaining a coincident travel path and desired longitudinal distance with respect to the leader. Distance and tracking control is beneficial in numerous applications including guiding autonomous vehicles in Intelligent Transport Systems (ITS) which increases traffic safety and the capacity of pre-existing road infrastructure. Service robotics may also benefit from the cost savings and flexibility offered by distance and tracking control which enables a number of robots to cooperate together in order to achieve a task beyond the capabilities ofjust one robot. Using a distance and tracking control scheme an intelligent leader robot may guide a number of less intelligent (and therefore less costly and less complex) followers to a work-site to perform a task. The author's approach to the distance and tracking control problem consisted of two separate solutions - an initial solution used as a starting point and learning experience and a second, more robust, fuzzy control-based solution. This thesis briefly describes the initial solution, but places a greater emphasis on the second solution. The reason for this is that the fuzzy control-based solution offers significant improvement on the initial solution and was developed based on conclusions drawn from the initial solution. Most implementations of distance and tracking control, sometimes referred to as Intelligent Cruise Control (ICC) or platooning, are limited to longitudinal distance control only. The leader tracking control is performed either implicitly by a separate lane-following control system or by human drivers. The fuzzy control-based solution offered in this thesis performs both distance and tracking control of an autonomous follower vehicle with respect to a leader vehicle in front of it. It represents a simple and cost effective solution to the requirements of autonomous vehicles operating in ITS schemes - particularly close formation platooning. The follower tracks a laser signal emitted by the leader and monitors the distance to the follower at the same time using ultrasonic ranging techniques. The follower uses the data obtained from these measuring techniques as inputs to a fuzzy controller algorithm to adjust its distance and alignment with respect to the leader. Other systems employed on road vehicles utilise video-based leader tracking, or a range of lane-following methods such as magnetometer or video-based methods. Typically these methods are disadvantaged by substantial unit and/or infrastructure costs associated with their deployment. The limitations associated with the solutions presented in this thesis arise in curved trajectories at larger longitudinal distance separations between vehicles. The effects of these limitations on road vehicles has yet to be fully quantified, however it is thought that these effects would not disadvantage its use in close formation platooning. The fuzzy control-based distance and tracking control solution features two inputs, which are the distance and alignment of the follower with respect to the leader. The fuzzy controller asserts two outputs, which are left and right wheel velocities to control the speed and trajectory of a differential drive vehicle. Each of the input and output fuzzy membership functions has seven terms based around lambda, Z-type and S-type functions. The fuzzy rule base consists of 49 rules and the fuzzy inference stage is based on the MAX/MIN method. A Centre of Maximum (CoM) def'uzzification method is used to provide the two crisp valued outputs to the vehicle motion control. The methods chosen for the fuzzy control of distance and tracking for autonomous vehicles were selected based on a compromise between their computational complexity and performance characteristics. This compromise was necessary in order to implement the chosen controller structure on pre-existing hardware test beds based on an 8-bit microcontrollers with limited memory and processing resources. Overall the fuzzy control-based solution presented in this thesis effectively solves the distance and tracking control problem. The solution was applied to differential drive hardware test-beds and was tested to verify performance. The solution was thoroughly tested in both the simulation environment and on hardware test-beds. Several issues are identified in this thesis regarding the application of the solution to other platforms and road vehicle use. The solution will be shown to be directly portable to service robotics applications and, with minor modifications, applicable to road vehicle close-formation platooning.
Thesis (Masters)
Master of Philosophy (MPhil)
School of Microelectronic Engineering
Science, Environment, Engineering and Technology
Full Text

The thesis is composed of two main parts. The first part deals with a microscopic traffic flow theory. Models describing the individual acceleration, deceleration and lane-changing behavior are formulated and the emerging collective traffic dynamics are investigated by means of numerical simulations. The models and simulation tools presented provide the methodical prerequisites for the second part of the thesis in which a novel concept of a traffic-adaptive control strategy for ACC systems is presented. The impact of such systems on the traffic dynamics can solely be investigated and assessed by traffic simulations. The focus is on future adaptive cruise control (ACC) systems and their potential applications in the context of vehicle-based intelligent transportation systems. In order to ensure that ACC systems are implemented in ways that improve rather than degrade traffic conditions, the thesis proposes an extension of ACC systems towards traffic-adaptive cruise control by means of implementing an actively jam-avoiding driving strategy. The newly developed traffic assistance system introduces a driving strategy layer which modifies the driver's individual settings of the ACC driving parameters depending on the local traffic situation. Whilst the conventional operational control layer of an ACC system calculates the response to the input sensor data in terms of accelerations and decelerations on a short time scale, the automated adaptation of the ACC driving parameters happens on a somewhat longer time scale of, typically, minutes. By changing only temporarily the comfortable parameter settings of the ACC system in specific traffic situations, the driving strategy is capable of improving the traffic flow efficiency whilst retaining the comfort for the driver. The traffic-adaptive modifications are specified relative to the driver settings in order to maintain the individual preferences. The proposed system requires an autonomous real-time detection of the five traffic states by each ACC-equipped vehicle. The formulated algorithm is based on the evaluation of the locally available data such as the vehicle's velocity time series and its geo-referenced position (GPS) in conjunction with a digital map. It is assumed that the digital map is complemented by information about stationary bottlenecks as most of the observed traffic flow breakdowns occur at these fixed locations. By means of a heuristic, the algorithm determines which of the five traffic states mentioned above applies best to the actual traffic situation. Optionally, inter-vehicle and infrastructure-to-car communication technologies can be used to further improve the accuracy of determining the respective traffic state by providing non-local information. By means of simulation, we found that the automatic traffic-adaptive driving strategy improves traffic stability and increases the effective road capacity. Depending on the fraction of ACC vehicles, the driving strategy "passing a bottleneck" effects a reduction of the bottleneck strength and therefore delays (or even prevents) the breakdown of traffic flow. Changing to the driving mode "leaving the traffic jam" increases the outflow from congestion resulting in reduced queue lengths in congested traffic and, consequently, a faster recovery to free flow conditions. The current travel time (as most important criterion for road users) and the cumulated travel time (as an indicator of the system performance) are used to evaluate the impact on the quality of service. While traffic congestion in the reference scenario was completely eliminated when simulating a proportion of 25% ACC vehicles, travel times were significantly reduced even with much lower penetration rates. Moreover, the cumulated travel times decreased consistently with the increase in the proportion of ACC vehicles
In der Arbeit wird ein neues verkehrstelematisches Konzept für ein verkehrseffizientes Fahrverhalten entwickelt und als dezentrale Strategie zur Vermeidung und Auflösung von Verkehrsstaus auf Richtungsfahrbahnen vorgestellt. Die operative Umsetzung erfolgt durch ein ACC-System, das um eine, auf Informationen über die lokale Verkehrssituation basierende, automatisierte Fahrstrategie erweitert wird. Die Herausforderung bei einem Eingriff in das individuelle Fahrverhalten besteht - unter Berücksichtigung von Sicherheits-, Akzeptanz- und rechtlichen Aspekten - im Ausgleich der Gegensätze Fahrkomfort und Verkehrseffizienz. Während sich ein komfortables Fahren durch große Abstände bei geringen Fahrzeugbeschleunigungen auszeichnet, erfordert ein verkehrsoptimierendes Verhalten kleinere Abstände und eine schnellere Anpassung an Geschwindigkeitsänderungen der umgebenden Fahrzeuge. Als allgemeiner Lösungsansatz wird eine verkehrsadaptive Fahrstrategie vorgeschlagen, die ein ACC-System mittels Anpassung der das Fahrverhalten charakterisierenden Parameter umsetzt. Die Wahl der Parameter erfolgt in Abhängigkeit von der lokalen Verkehrssituation, die auf der Basis der im Fahrzeug zur Verfügung stehenden Informationen automatisch detektiert wird. Durch die Unterscheidung verschiedener Verkehrssituationen wird ein temporärer Wechsel in ein verkehrseffizientes Fahrregime (zum Beispiel beim Herausfahren aus einem Stau) ermöglicht. Machbarkeit und Wirkungspotenzial der verkehrsadaptiven Fahrstrategie werden im Rahmen eines mikroskopischen Modellierungsansatzes simuliert und hinsichtlich der kollektiven Verkehrsdynamik, insbesondere der Stauentstehung und Stauauflösung, auf mehrspurigen Richtungsfahrbahnen bewertet. Die durchgeführte Modellbildung, insbesondere die Formulierung eines komplexen Modells des menschlichen Fahrverhaltens, ermöglicht eine detaillierte Analyse der im Verkehr relevanten kollektiven Stabilität und einer von der Stabilität abhängigen stochastischen Streckenkapazität. Ein tieferes Verständnis der Stauentstehung und -ausbildung wird durch das allgemeine Konzept der Engstelle erreicht. Dieses findet auch bei der Entwicklung der Strategie für ein stauvermeidendes Fahrverhalten Anwendung. In der Arbeit wird die stauvermeidende und stauauflösende Wirkung eines individuellen, verkehrsadaptiven Fahrverhaltens bereits für geringe Ausstattungsgrade nachgewiesen. Vor dem Hintergrund einer zu erwartenden Verbreitung von ACC-Systemen ergibt sich damit eine vielversprechende Option für die Steigerung der Verkehrsleistung durch ein teilautomatisiertes Fahren. Der entwickelte Ansatz einer verkehrsadaptiven Fahrstrategie ist unabhängig vom ACC-System. Er erweitert dessen Funktionalität im Hinblick auf zukünftige, informationsbasierte Fahrerassistenzsysteme um eine neue fahrstrategische Dimension. Die lokale Interpretation der Verkehrssituation kann neben einer verkehrsadaptiven ACC-Regelung auch der Entwicklung zukünftiger Fahrerinformationssysteme dienen

The thesis is composed of two main parts. The first part deals with a microscopic traffic flow theory. Models describing the individual acceleration, deceleration and lane-changing behavior are formulated and the emerging collective traffic dynamics are investigated by means of numerical simulations. The models and simulation tools presented provide the methodical prerequisites for the second part of the thesis in which a novel concept of a traffic-adaptive control strategy for ACC systems is presented. The impact of such systems on the traffic dynamics can solely be investigated and assessed by traffic simulations. The focus is on future adaptive cruise control (ACC) systems and their potential applications in the context of vehicle-based intelligent transportation systems. In order to ensure that ACC systems are implemented in ways that improve rather than degrade traffic conditions, the thesis proposes an extension of ACC systems towards traffic-adaptive cruise control by means of implementing an actively jam-avoiding driving strategy. The newly developed traffic assistance system introduces a driving strategy layer which modifies the driver's individual settings of the ACC driving parameters depending on the local traffic situation. Whilst the conventional operational control layer of an ACC system calculates the response to the input sensor data in terms of accelerations and decelerations on a short time scale, the automated adaptation of the ACC driving parameters happens on a somewhat longer time scale of, typically, minutes. By changing only temporarily the comfortable parameter settings of the ACC system in specific traffic situations, the driving strategy is capable of improving the traffic flow efficiency whilst retaining the comfort for the driver. The traffic-adaptive modifications are specified relative to the driver settings in order to maintain the individual preferences. The proposed system requires an autonomous real-time detection of the five traffic states by each ACC-equipped vehicle. The formulated algorithm is based on the evaluation of the locally available data such as the vehicle's velocity time series and its geo-referenced position (GPS) in conjunction with a digital map. It is assumed that the digital map is complemented by information about stationary bottlenecks as most of the observed traffic flow breakdowns occur at these fixed locations. By means of a heuristic, the algorithm determines which of the five traffic states mentioned above applies best to the actual traffic situation. Optionally, inter-vehicle and infrastructure-to-car communication technologies can be used to further improve the accuracy of determining the respective traffic state by providing non-local information. By means of simulation, we found that the automatic traffic-adaptive driving strategy improves traffic stability and increases the effective road capacity. Depending on the fraction of ACC vehicles, the driving strategy "passing a bottleneck" effects a reduction of the bottleneck strength and therefore delays (or even prevents) the breakdown of traffic flow. Changing to the driving mode "leaving the traffic jam" increases the outflow from congestion resulting in reduced queue lengths in congested traffic and, consequently, a faster recovery to free flow conditions. The current travel time (as most important criterion for road users) and the cumulated travel time (as an indicator of the system performance) are used to evaluate the impact on the quality of service. While traffic congestion in the reference scenario was completely eliminated when simulating a proportion of 25% ACC vehicles, travel times were significantly reduced even with much lower penetration rates. Moreover, the cumulated travel times decreased consistently with the increase in the proportion of ACC vehicles.
In der Arbeit wird ein neues verkehrstelematisches Konzept für ein verkehrseffizientes Fahrverhalten entwickelt und als dezentrale Strategie zur Vermeidung und Auflösung von Verkehrsstaus auf Richtungsfahrbahnen vorgestellt. Die operative Umsetzung erfolgt durch ein ACC-System, das um eine, auf Informationen über die lokale Verkehrssituation basierende, automatisierte Fahrstrategie erweitert wird. Die Herausforderung bei einem Eingriff in das individuelle Fahrverhalten besteht - unter Berücksichtigung von Sicherheits-, Akzeptanz- und rechtlichen Aspekten - im Ausgleich der Gegensätze Fahrkomfort und Verkehrseffizienz. Während sich ein komfortables Fahren durch große Abstände bei geringen Fahrzeugbeschleunigungen auszeichnet, erfordert ein verkehrsoptimierendes Verhalten kleinere Abstände und eine schnellere Anpassung an Geschwindigkeitsänderungen der umgebenden Fahrzeuge. Als allgemeiner Lösungsansatz wird eine verkehrsadaptive Fahrstrategie vorgeschlagen, die ein ACC-System mittels Anpassung der das Fahrverhalten charakterisierenden Parameter umsetzt. Die Wahl der Parameter erfolgt in Abhängigkeit von der lokalen Verkehrssituation, die auf der Basis der im Fahrzeug zur Verfügung stehenden Informationen automatisch detektiert wird. Durch die Unterscheidung verschiedener Verkehrssituationen wird ein temporärer Wechsel in ein verkehrseffizientes Fahrregime (zum Beispiel beim Herausfahren aus einem Stau) ermöglicht. Machbarkeit und Wirkungspotenzial der verkehrsadaptiven Fahrstrategie werden im Rahmen eines mikroskopischen Modellierungsansatzes simuliert und hinsichtlich der kollektiven Verkehrsdynamik, insbesondere der Stauentstehung und Stauauflösung, auf mehrspurigen Richtungsfahrbahnen bewertet. Die durchgeführte Modellbildung, insbesondere die Formulierung eines komplexen Modells des menschlichen Fahrverhaltens, ermöglicht eine detaillierte Analyse der im Verkehr relevanten kollektiven Stabilität und einer von der Stabilität abhängigen stochastischen Streckenkapazität. Ein tieferes Verständnis der Stauentstehung und -ausbildung wird durch das allgemeine Konzept der Engstelle erreicht. Dieses findet auch bei der Entwicklung der Strategie für ein stauvermeidendes Fahrverhalten Anwendung. In der Arbeit wird die stauvermeidende und stauauflösende Wirkung eines individuellen, verkehrsadaptiven Fahrverhaltens bereits für geringe Ausstattungsgrade nachgewiesen. Vor dem Hintergrund einer zu erwartenden Verbreitung von ACC-Systemen ergibt sich damit eine vielversprechende Option für die Steigerung der Verkehrsleistung durch ein teilautomatisiertes Fahren. Der entwickelte Ansatz einer verkehrsadaptiven Fahrstrategie ist unabhängig vom ACC-System. Er erweitert dessen Funktionalität im Hinblick auf zukünftige, informationsbasierte Fahrerassistenzsysteme um eine neue fahrstrategische Dimension. Die lokale Interpretation der Verkehrssituation kann neben einer verkehrsadaptiven ACC-Regelung auch der Entwicklung zukünftiger Fahrerinformationssysteme dienen.

Cette thèse est consacrée à l'analyse de performance de Régulateurs de Vitesse Adaptatifs Coopératifs(CACC) pour un train de véhicules intelligents afin de réduire la congestion du trafic et améliorer la sécurité routière.Premièrement, la politique d'espacement, à Intervalles Constants de Temps (CTH) est introduite. Basé sur cette politique d'espacement, un nouveau système décentralisé de Deux-Véhicules-Devant CACC (TVACACC) est proposé, dans lequel l'accélération souhaitée de deux véhicules précédents est prise en compte. Ensuite, la stabilité de la chaîne du système proposé est analysée théoriquement. Il est démontré que grâce à l'aide de la communication multiple entre véhicules, une meilleure stabilité de la chaîne est obtenue par rapport au système conventionnel. Un train de véhicules dans le scénario Stop-and-Go est simulé avec une communication parfaite puis dégradée. Le système proposé donne un comportement stable de la chaîne, correspondant à l'analyse théorique.Deuxièmement, une technique de dégradation pour CACC est présentée comme stratégie alternative lorsque la communication sans fil est partiellement ou complètement perdue. La stratégie proposée, appelée DTVACACC, utilise le filtre de Kalman pour estimer l'accélération actuelle du véhicule précédent qui remplace l'accélération souhaitée. Il est démontré que la performance pour le DTVACACC, peut être maintenue à un niveau beaucoup plus élevé.Enfin, une approche d’Apprentissage par Renforcement (RL) pour système CACC est proposée. L' algorithme politique- gradient est introduit pour réaliser le contrôle longitudinal . Ensuite, la simulation a montré que cette nouvelle approche de RL est efficace pour CACC
This PhD thesis is dedicated to the performance analysis of Cooperative Adaptive Cruise Control (CACC) system for intelligent vehicle platoon with the main aims of alleviating traffic congestion and improving traffic safety. At first, the Constant Time Headway (CTH) spacing policy for vehicle platoon is introduced. Based on this spacing policy, a novel decentralized Two-Vehicle-Ahead CACC (TVACACC) system is proposed, in which the desired acceleration of two front vehicles is taken into account. Then the string stability of the proposed system is theoretically analyzed. It is shown that by using the multiple wireless communication among vehicles, a better string stability is obtained compared to the conventional system. Vehicle platoon in Stop-and-Go scenario is simulated with both normal and degraded communication.Secondly, a graceful degradation technique for CACC was presented, as an alternative fallback strategy when wireless communication is lost or badly degraded. The proposed strategy, which is referred to DTVACACC, uses Kalman filter to estimate the preceding vehicle’s current acceleration as a replacement of the desired acceleration. It is shown that the performance is maintained at a much higher level.Finally, a Reinforcement Learning (RL) approach of CACC system is proposed. The policy-gradient algorithm is introduced to achieve the longitudinal control. Then simulation has shown that this new RL approach results in efficient performance for CACC

Cette thèse est consacrée au domaine interdisciplinaire des Systèmes de Transport Intelligents et des technologies de Réalité Virtuelle. Elle se concentre sur l'amélioration des stratégies de commande des véhicules intelligents en tenant compte des impacts de l'environnement naturel ainsi que sur l'analyse de performance, la visualisation et la vérification de la validité des algorithmes de commande sur la plateforme de véhicules intelligents réalité virtuelle (IVVR).La plateforme IVVR comprend trois sous-systèmes : un sous-système de commande de véhicules intelligents, un sous-système de visualisation et un sous-système virtuel sans fil. Le synthétique environnement naturel a été modélisé et simulé pour la simulation et l'analyse de performance des stratégies de commande sous conditions environnementales complexes. Ensuite, les expérimentations concernant le trafic équipé du régulateur de vitesses adaptatives (ou coopérative) sont exécutés et ils montrent que les systèmes existants ont échoué à maintenir une espace inter-véhiculaire de sécurité lorsque les conditions d'environnement naturel sont défavorables. Dans ce cas, nous proposons un nouvel algorithme de commande appelé NECACC pour le contrôle longitudinal du véhicule en maintenant une espace inter-véhiculaire de sécurité et garantissant une capacité de circulation optimisée même dans des conditions environnementales complexes. Cet algorithme est ensuite simulé, vérifié et validé sur la plateforme IVVR. Enfin, les démonstrations de trafic virtuel effectuant des manœuvres communes de circulation contrôlés par les systèmes de commande intégrés proposées sont présentées sous diverse conditions environnementales

The demand for road freight transport continues to grow with the growing economy, resulting in increased fossil fuel consumption and emissions. At the same time, the fossil fuel use needs to decrease substantially to counteract the ongoing global warming. One way to reduce fuel consumption is to utilize emerging intelligent transport system (ITS) technologies and introduce heavy-duty vehicle (HDV) platooning, i.e. HDVs driving with small inter-vehicle gaps enabled by the use of sensors and controllers. It is of importance for transport authorities and industries to investigate the effects of introducing HDV platooning. Previous studies have investigated the potential benefits, but the effects in real traffic, both for the platoons and for the surrounding vehicles, have barely been explored. To further utilize ITS and optimize the platoons, information about the traffic situation ahead can be used to optimize the vehicle trajectories for the platoons. Paper I presents a dynamic programming-based optimal speed control including information of the traffic situation ahead. The optimal control is applied to HDV platoons in a deceleration case and the potential fuel consumption reduction is evaluated by a microscopic traffic simulation study with HDV platoons driving in real traffic conditions. The effects for the surrounding traffic are also analysed. Paper II and Paper III present a simulation platform to assess the effects of HDV platooning in real traffic conditions. Through simulation studies, the potential fuel consumption reduction by adopting HDV platooning on a real highway stretch is evaluated, and the effects for the other vehicles in the network are investigated.
Efterfrågan på godstransporter på väg fortsätter att öka i takt med den växande ekonomin, vilket resulterar i ökad förbrukning av fossila bränslen och ökade utsläpp. Samtidigt behöver användandet av fossila bränslen minska för att motverka den pågående globala uppvärmningen. Ett sätt för att minska bränsleförbrukningen är att utnyttja den teknik kring intelligenta transportsystem som är under utveckling och introducera lastbilskonvojer, det vill säga lastbilar som använder sensorer och regulatorer för att kunna köra med korta avstånd mellan sig. För transportföretag och -myndigheter är det viktigt att undersöka effekterna av att införa lastbilskonvojkörning. Tidigare studier har undersökt de möjliga fördelarna, men effekterna vid körning i trafik, både för konvojerna och för omgivande fordon, är outforskade. För att ytterligare utnyttja intelligenta transportsystem och optimera konvojerna kan information om trafiksituationen längre fram på vägen användas för att optimera konvojernas körning. Artikel I presenterar en optimal hastighetsregulator baserad på dynamisk programmering och som inkluderar information om trafiksituationen längre fram. Den optimala regulatorn appliceras på lastbilskonvojer under ett inbromsningsscenario och den potentiella minskningen i bränsleförbrukning utvärderas genom en mikroskopisk trafiksimuleringsstudie där lastbilskonvojerna kör i verkliga trafikförhållanden. Effekterna för omgivande fordon är också analyserade.Artikel II och artikel III presenterar en simuleringsplattform för att utvärdera effekterna av lastbilskonvojkörning i verkliga trafikförhållanden. Genom simuleringsstudier analyseras den potentiella bränsleförbrukningsminskningen då lastbilskonvojer körs på en verklig motorvägssträcka och effekterna för de övriga fordonen på vägen undersöks.

QC 20180516

Over the past decades, congestion and emission problems has increased remarkablywhich escalates the demands on vehicles. The advancements withinthe eld of information and communication systems gives the opportunity todeal with the aforementioned problems. The concept of platooning shows tobe an attractive way of reducing both congestion and emissions by having ashort inter-vehicle spacing. The ndings in studies show that fuel reductionpotentials of 5-20 % are viable as a result of the lowered air drag by drivingin platoon. This thesis investigates the state of the art within the areaof intelligent transport systems (ITS) along with advanced driver assistancesystems (ADAS). Furthermore, the prosecuted work results in a proposedcontrol design for a longitudinal control in a platoon of vehicles. The platoonconsists of two homogeneous radio controlled vehicles (RCV) which aremodelled by taking advantage of system identication methods. The identi-ed plant models are implemented into a Simulink model where the controlsystem is developed. Moreover, the developed control system is implementedinto a real-time demonstrator for experimental evaluation. The results showsthat the modelled dynamics corresponds reasonably well with the real dynamicsof the system. The developed control system proves to work well andagree with the expectations of its performance obtained from simulations.The performance of the proposed controller has been evaluated by means ofsimulations and real experiments. The resulting control system consists ofPID controllers for both speed and spacing control.
Under de senaste decennierna har mangden trakstockningar och problemmed utslapp okat - darmed aven kraven pa vara fordon. Samtidigt skaparframstegen inom informations- och kommunikationssystem mojligheter foratt hantera ovannamnda problem. Kolonnkorning, eller platooning har visatsig vara en eektiv metod for att minska saval trakstockningar som utslappsom en foljd av kortare avstand mellan fordon. Resultat fran studier visarhur en branslereduktion runt 5-20 % ar mojlig till foljd av det sankta luftmotstandet vid kolonnkorning. Avhandlingen undersoker teknikens standpunktinom intelligenta transportsystem (ITS) tillsammans med avancerade drivhjalpsystem(ADAS). Vidare resulterar arbetet i ett forslag till regleringsdesignfor en longitudinell kontroll i en kolonn av fordon. Kolonnen bestar av tvahomogena radiostyrda fordon (RCV) som modelleras genom att utnyttjametoder for systemidentiering. De identierade systemmodellerna implementerasi en Simulink-modell dar styrsystemet utvecklas. Dessutom implementerasdet utvecklade styrsystemet i en realtids-demonstration for experimentellutvardering. Resultaten visar att den modellerade dynamikenstammer bra overens med systemets verkliga dynamik. Det utvecklade styrsystemetvisar sig fungera bra och overensstammer med forvantningarna pa dessprestanda som erhallits genom simuleringar. Den foreslagna regulatorns prestandahar utvarderats med hjalp av simuleringar och verkliga experiment.Det resulterande styrsystemet bestar av PID regulatorer for bade hastighetsochavstandskontroll.

L'augmentation dans les dernières décennies du nombre de véhicules présents sur les routes ne s'est pas passée sans son lot d'impacts négatifs sur la société. Même s'ils ont joué un rôle important dans le développement économique des régions urbaines à travers le monde, les véhicules sont aussi responsables d'impacts négatifs sur les entreprises, car l'inefficacité du ot de traffic cause chaque jour d'importantes pertes en productivité. De plus, la sécurité des passagers est toujours problématique car les accidents de voiture sont encore aujourd'hui parmi les premières causes de blessures et de morts accidentelles dans les pays industrialisés. Ces dernières années, les aspects environnementaux ont aussi pris de plus en plus de place dans l'esprit des consommateurs, qui demandent désormais des véhicules efficaces au niveau énergétique et minimisant leurs impacts sur l'environnement. évidemment, les gouvernements de pays industrialisés ainsi que les manufacturiers de véhicules sont conscients de ces problèmes et tentent de développer des technologies capables de les résoudre. Parmi les travaux de recherche en ce sens, le domaine des Systèmes de Transport Intelligents (STI) a récemment reçu beaucoup d'attention. Ces systèmes proposent d'intégrer des systèmes électroniques avancés dans le développement de solutions intelligentes conçues pour résoudre les problèmes liés au transport automobile cités plus haut. Ce mémoire se penche donc sur un sous-domaine des STI qui étudie la résolution de ces problèmes gr^ace au développement de véhicules intelligents. Plus particulièrement, ce mémoire propose d'utiliser une approche relativement nouvelle de conception de tels systèmes, basée sur l'apprentissage machine. Ce mémoire va donc montrer comment les techniques d'apprentissage par renforcement peuvent être utilisées afin d'obtenir des contrôleurs capables d'effectuer le suivi automatisés de véhicules. Même si ces efforts de développement en sont encore à une étape préliminaire, ce mémoire illustre bien le potentiel de telles approches pour le développement futur de véhicules plus \intelligents".
The impressive growth, in the past decades, of the number of vehicles on the road has not come without its share of negative impacts on society. Even though vehicles play an active role in the economical development of urban regions around the world, they unfortunately also have negative effects on businesses as the poor efficiency of the traffic ow results in important losses in productivity each day. Moreover, numerous concerns have been raised in relation to the safety of passengers, as automotive transportation is still among the first causes of accidental casualties in developed countries. In recent years, environmental issues have also been taking more and more place in the mind of customers, that now demand energy-efficient vehicles that limit the impacts on the environment. Of course, both the governments of industrialized countries and the vehicle manufacturers have been aware of these problems, and have been trying to develop technologies in order to solve these issues. Among these research efforts, the field of Intelligent Transportation Systems (ITS) has been gathering much interest as of late, as it is considered an efficient approach to tackle these problems. ITS propose to integrate advanced electronic systems in the development of intelligent solutions designed to address the current issues of automotive transportation. This thesis focuses on a sub-field ITS since it studies the resolution of these problems through the development of Intelligent Vehicle (IV) systems. In particular, this thesis proposes a relatively novel approach for the design of such systems, based on modern machine learning. More specifically, it shows how reinforcement learning techniques can be used in order to obtain an autonomous vehicle controller for longitudinal vehiclefollowing behavior. Even if these efforts are still at a preliminary stage, this thesis illustrates the potential of using these approaches for future development of \intelligent" vehicles.
Inscrit au Tableau d'honneur de la Faculté des études supérieures

Future vehicles are expected to be equipped with wireless communication technology, that enables them to be “connected” to each others and road infrastructures. Complementing current autonomous vehicles and automated driving systems, the wireless communication allows the vehicles to interact, cooperate, and be aware of its surroundings beyond their own sensors’ range. Such sys- tems are often referred to as Cooperative Intelligent Transport Systems (C-ITS), which aims to provide extra safety, efficiency, and sustainability to transporta- tion systems. Several C-ITS applications are under development and will require thorough testing and evaluation before their deployment in the real-world. C- ITS depend on several sub-systems, which increase their complexity, and makes them difficult to evaluate. Simulations are often used to evaluate many different automotive applications, including C-ITS. Although they have been used extensively, simulation tools dedicated to determine all aspects of C-ITS are rare, especially human factors aspects, which are often ignored. The majority of the simulation tools for C-ITS rely heavily on different combinations of network and traffic simulators. The human factors issues have been covered in only a few C-ITS simulation tools, that involve a driving simulator. Therefore, in this thesis, a C-ITS simulation framework that combines driving, network, and traffic simulators is presented. The simulation framework is able to evaluate C-ITS applications from three perspectives; a) human driver; b) wireless communication; and c) traffic systems. Cooperative Adaptive Cruise Control (CACC) and its applications are chosen as the first set of C-ITS functions to be evaluated. Example scenarios from CACC and platoon merging applications are presented, and used as test cases for the simulation framework, as well as to elaborate potential usages of it. Moreover, approaches, results, and challenges from composing the simulation framework are presented and discussed. The results shows the usefulness of the proposed simulation framework.

Cette thèse est consacrée à étudier les applications potentielles de véhicules autonomes et communications V2X pour construire les systèmes de transport intelligents. Premièrement, le comportement de caravane dans un environnement de véhicule connecté est étudié. Un algorithme de commande de caravane est conçu pour obtenir l'espacement sécuritaire ainsi que la conformité de la vitesse et de l'accélération. Deuxièmement, à plus grande échelle, les caravanes autour d'une intersection sont considérées. Le débit pendant une période de signal de trafic peut être amélioré en tirant profit de la capacité redondante de la route. Dans diverses contraintes, les véhicules peuvent choisir d'accélérer et rejoindre la caravane précédente ou à décélérer de déroger à l'actuel. Troisièmement, une intersection sans signalisation en VANET est considérée. Dans des conditions de faible trafic, les véhicules peuvent réguler leur vitesse avant d'arriver à l'intersection en fonction du temps d'occupation de la zone de conflit (TOZC) stocké au niveau du gestionnaire, afin qu'ils puissent traverser l'intersection sans collision ni arrêt. Le délai peut être réduit en conséquence. Enfin, un algorithme de gestion d'intersection autonome universelle, qui peut fonctionner même avec le trafic lourd, est développé. Le véhicule cherche à sécuriser les fenêtres entrant dans le TOZC. Ensuite, sur la base des fenêtres trouvées et le mouvement du véhicule qui précède, les trajectoires des véhicules peuvent être planifiées en utilisant une méthode de programmation dynamique segmentée. Tous les algorithmes conçus sont testés et vérifiés avec succès par des simulations dans scénarios différents
This thesis is devoted to study the potential applications of autonomous vehicles and V2X communications to construct the intelligent transportation systems. Firstly, the behavior of platoon in connected vehicle environment is studied. A platoon control algorithm is designed to obtain safe spacing as well as accordance of velocity and acceleration for vehicles in the same lane. Secondly, in larger scale, the platoons around an intersection are considered. The throughput in a traffic signal period can be improved by taking advantage of the redundant road capacity. Within diverse constraints, vehicles can choose to accelerate to join in the preceding platoon or to decelerate to depart from the current one. Thirdly, an unsignalized intersection in VANET is considered. In light traffic conditions, vehicles can regulate their velocities before arriving at the intersection according to the conflict zone occupancy time (CZOT) stored at the manager, so that they could get through the intersection without collision or stop. The delay can be reduced accordingly. Finally, an universal autonomous intersection management algorithm, which can work even with heavy traffic, is developed. The vehicle searches for safe entering windows in the CZOT. Then based on the found windows and the motion of preceding vehicle, the trajectories of vehicles can be planned using a segmented dynamic programming method. All the designed algorithms are successfully tested and verified by simulations in various scenarios

Vehicular ad hoc networks (VANETs) are a hot topic in the intelligent transport system (ITS) area. The introduction of wireless communications between vehicles will enable many useful applications to enhance road traffic safety as well to increase efficiency. The standardization of IEEE 802.11p, being an amendment to IEEE 802.11 intended for VANETS, faces many challenges. In Europe a 30 MHz spectrum at 5.9 GHz have been dedicated for ITS and this spectrum has to be used to its full potential. For this reason this thesis compares a 20 MHz wide frequency channel with a 10 MHz wide through measurements using 802.11p hardware. The measurements were conducted on a highway with relative speeds of up to 240 km/h. The results from these initial measurements show that a 20 MHz channel does not perform worse than a 10 MHz channel despite the high relative speeds and large metal signs scattering the signals. What enabled this thesis to do the measurements was Halmstad University‟s participation in the Grand Cooperative Driving Challenge (GCDC) 2011. In GCDC nine teams mostly from Europe competed in having the vehicle that had the best behaviour in a platoon of vehicles using cooperative adaptive cruise control (CACC), the CACC algorithm controlled the vehicles‟ acceleration and breaking autonomously based on in-vehicle sensors and communicated messages between the vehicles in the platoon using 802.11p. This thesis implemented the communication part of Halmstad University‟s vehicle. The challenge was held in Helmond, Holland, May 14-15, 2011. Halmstad University‟s team finished in second place.
CoAct

The vehicles of tomorrow will be more sophisticated, intelligent and safe than the vehicles of today. The future is leaning towards fully autonomous vehicles. This degree project provides a data driven solution for a speed adaptation system that can be used to compute a vehicle speed for curves, suitable for the underlying driving style of the driver, road properties and weather conditions. A speed adaptation system for curves aims to compute a vehicle speed suitable for curves that can be used in Advanced Driver Assistance Systems (ADAS) or in Autonomous Driving (AD) applications. This degree project was carried out at Volvo Car Corporation. Literature in the field of speed adaptation systems and factors affecting the vehicle speed in curves was reviewed. Naturalistic driving data was both collected by driving and extracted from Volvo's data base and further processed. A novel speed adaptation system for curves was invented, implemented and evaluated. This speed adaptation system is able to compute a vehicle speed suitable for the underlying driving style of the driver, road properties and weather conditions. Two different artificial neural networks and two mathematical models were used to compute the desired vehicle speed in curves. These methods were compared and evaluated.
Morgondagens fordon kommer att vara mer sofistikerade, intelligenta och säkra än dagens fordon. Framtiden lutar mot fullständigt autonoma fordon. Detta examensarbete tillhandahåller en datadriven lösning för ett hastighetsanpassningssystem som kan beräkna ett fordons hastighet i kurvor som är lämpligt för förarens körstil, vägens egenskaper och rådande väder. Ett hastighetsanpassningssystem för kurvor har som mål att beräkna en fordonshastighet för kurvor som kan användas i Advanced Driver Assistance Systems (ADAS) eller Autonomous Driving (AD) applikationer. Detta examensarbete utfördes på Volvo Car Corporation. Litteratur kring hastighetsanpassningssystem samt faktorer som påverkar ett fordons hastighet i kurvor studerades. Naturalistisk bilkörningsdata samlades genom att köra bil samt extraherades från Volvos databas och bearbetades. Ett nytt hastighetsanpassningssystem uppfanns, implementerades samt utvärderades. Hastighetsanpassningssystemet visade sig vara kapabelt till att beräkna en lämplig fordonshastighet för förarens körstil under rådande väderförhållanden och vägens egenskaper. Två olika artificiella neuronnätverk samt två matematiska modeller användes för att beräkna fordonets hastighet. Dessa metoder jämfördes och utvärderades.

碩士
國立臺北科技大學
車輛工程系碩士班
91
Car following system is one part of the intelligent cruise control ( ICC ) system. The system can keep a safe distance between a preceding vehicle and a following one. It includes technologies of advanced safety vehicle ( ASV ) and collision warning or avoidance system. By means of these technologies and capabilities, an integrated intelligent transportation system ( ITS ) is developed. This research is to develop a car-following system using computer vision. The system build by a personal computer (PentiumⅢ 1GHz), which is equipped with a CCD camera (SONY B/W XC-ST50) and an image acquisition card (NI-IMAQ PCI-1409). The relative speed and distance between two cars could be obtained from the images of preceding vehicle by a CCD camera. The system applies fuzzy logic for controlling the speed of following vehicle in order to achieve longitudinal tracking control. This system also analyzes these images to get lateral displacement of the preceding vehicle. From the displacement, we are capable to judge the preceding vehicle whether steering or not, and regulate steering of the following vehicle. As a result, it could also track the preceding vehicle in lateral direction. In this research, the vehicle cruise control system is composed of three system modules including vision module, speed control module and steering control module. As for the vision system, we utilize a CCD camera with NI-IMAQ image acquisition card to capture the images of the preceding vehicle. Techniques of pattern matching and cross correlation are applied in image processing to track and recognize the images of the preceding vehicle. These images are analyzed to get relative distance, relative speed and lateral displacement, and then input those data to speed and steering control system, the modeling results were simulated by a computer with LabVIEW and Matlab/Simulink. These calculated displacements and speed are then used as feedback inputs to control the speed and steering of the following vehicle. Simulation results of speed and steering control using LabVIEW and Matlab/Simulink are also presented.

碩士
國立交通大學
電機與控制工程系所
94
Adaptive Cruise Control (ACC) System is an important part of the Advanced Vehicle Control and Safety System (AVCSS) in Intelligent Transportation Systems (ITS) such as drivers’ burden lightening, driver assisting and safety driving. The target of this thesis is to develop an autonomy control system of a high-speed longitudinal motion control. In this thesis, we first introduce modes, end and a basic theory of the designed adaptive cruise control system. In according with it, we design a hierarchical controller. After the driver starts the system, we can cruise at the pre-selected speed autonomously when there is no vehicle in front of us or select a driving mode according to the driver’s need when there is a vehicle in front of us. Through tests of the experimental vehicle, we reach our control goal according to road tests and implement it on an FPGA platform. In general, cruise control systems are realized on car computers. In this thesis, though it is more complex to develop with an FPGA we used. But we verify it that control rules on car computer can be implemented with an FPGA. Have represented a safe driving mode and it is not only smaller but also cheaper than a car computer. It is suitable for an automobile-used controller.

碩士
國立交通大學
電機與控制工程系所
95
Adaptive Cruise Control (ACC) nowadays is a well-developed technology in the field of the Advanced Vehicle Control and Safety System (AVCSS) in Intelligent Transportation Systems (ITS). However, one limitation of conventional ACC systems is that they do not manage speeds under 40 km/h and, as a result, are not useful in traffic jams or urban driving situation. Therefore, the target of this thesis is to design an intelligent ACC system of a full-speed-range longitudinal motion control. In this thesis, we present the integration design and implementation of an intelligent full-speed-range ACC (IF-ACC) system. The proposed system has a hierarchical structure composed and consists of a supervisory control and a regulation control. The main feature of this thesis is that there is adaptation to a user-preset speed and, if necessary, speed reduction to keep a safe distance from the vehicle in the same lane, whatever the speed. The extreme case is the stop and go operation in which the lead car stops and the vehicle embedded this system must also do so. As the cost, performance and design complexity taken into account, the current trend is that digital signal processors (DSP) are widely applied on Automotive Electronics industry. Therefore, instead of car computer, the IF-ACC system is implemented on a DSP　as an embedded controller. Among on-road experimental tests, we verify our control rules on car computer can be implemented on a DSP, and the system validness is exhibited.

碩士
國立交通大學
電機與控制工程系所
93
Adaptive Cruise Control (ACC) System is an important part of the Advanced Vehicle Control and Safety System (AVCSS) in Intelligent Transportation Systems (ITS). In this thesis, we design an ACC controller for following a leading vehicle to achieve the desired safety distance, or cruising at the pre-selected speed when there is no vehicle in front of us. We design an intelligent cruise controller with fuzzy theory. The advantage of using fuzzy theory is that it doesn’t require the complete knowledge of nonlinear vehicle dynamics, and it can be applied to vehicle regardless of its nonlinear or unobservable dynamics. We separate the controller into two parts. The first part is used to determine which mode the controller should take according to relative distance. Besides the controller can switch between car following and cruise control automatically. The second part is when there is a vehicle in front of us the controller should accelerate or decelerate to keep the safety distance according to relative speed and relative distance or when there are no cars in the same lane the controller can accelerate or decelerate to hold a desired speed according to the target speed and real- time speed. In the thesis we try to implement the intelligent cruise controller with FPGA (without car computer). Although it is more complex to realize, it is not only smaller but also cheaper. Hence it is appropriate to be used in vehicles and to be promoted. Through this thesis we will prove that the intelligent cruise controller, which is built on FPGA, will provide a safe and comfortable driving assistance system for drivers.

碩士
國立臺灣大學
電子工程學研究所
98
In this thesis, future vision-based intelligent cruise control system is targeted. A knowledge-based intelligent vehicle tracking system is proposed to satisfy the demands of safety and energy-saving purposes. In the trend of future intelligent vehicle, safety and energy efficiency are two critical developing goals. Intelligent cruise control, which satisfies both safety and energy efficiency purposes, is an important vehicle application for that. The developing trend also shows, with the enhancement of video analysis technologies, computer vision will play an important role in the future cruise system. Therefore, this thesis explores and researches on a vision-based vehicle cruise. A vehicle recognition and tracking system is discussed and developed by three aspects of performance, cost, and system specification. First the impact of video specification on vehicle cruise control is discussed. By the energy consumption simulation for driving cycles, we can noticed that in automatic cruising condition, the detection accuracy of relative velocities of surrounding vehicles directly affects the energy efficiency. However, the velocity detection accuracy is influenced by the video specification. Considering the vehicle safety and energy efficiency issues, we expect that the proposed system can support up to super high resolution (4096x2160), and 10-frame-per-second computing throughput can be reached under that resolution. The system of vehicle recognition and tracking is explored as follows in this thesis. In the system, the module of vehicle recognition is responsible to recognize vehicle positions in image and output them to the vehicle tracking modulefor tracking and range detection. Though learning-based recognition algorithms perform high recognition rate and reliability, there are limitations on the abilities of object positioning, object size determination and false alarm rate minimization. Facing to these error conditions, several common object tracking algorithms are discussed. It can be found that current related algorithms are incapable of solving the problem of error position initialization and cannot be practically applied in vision-based cruise system. Therefore, a knowledge-based intelligent vehicle tracking algorithm is proposed. The algorithm is developed with the existed knowledge of vehicle characteristics, and it possesses two main functionalities, position auto-adjustment and false alarm reduction. As experimental results show, the proposed knowledge-based algorithm performs better ability of range detection, and it also effectively reduces the system false alarm rate. Moreover, due to the resistance against the departure error of initial position, a recognitionand- tracking parallel processing scheme can be applied instead of the sequential processing, which reduces a large amount of system memory cost. One of the essential factors is the required system throughput under the targeted high image resolution. In the last part, the execution timing performance of proposed tracking algorithm is analyzed. A hardware-oriented algorithm optimization methodology and its corresponding hardware architecture are proposed for acceleration. During hardware design, different optimization techniques are applies to the architecture. The system after hardware acceleration reaches the processing speed of 81.4 frames per second under 1280x960 image resolution, and it can support up to 4096x2160 image resolution with 11 frames per second processing speed, which fits the specification of cruise control system. The hardware is finally implemented with UMC 90nm Logic Low-K SP-RVT Process technology. The total chip size is 2.2x2.2mm2 with 12.8Kbits on-chip memory. Operating frequency is 100MHz and the minimum and maximum powers are 23.45mW and 648.75mW, respectively. Maximum five targets can be tracked simultaneously.

碩士
國立臺灣大學
機械工程學研究所
105
An eco-driving system for the plug-in hybrid electric vehicle (PHEV) to improve the energy economy is presented. This research proposes an eco-cruise controller (eco-CC), it is able to adjust cruising speed by receiving and analyzing terrain information and then furthermore to reduce the consumption of energy. The nonlinear model predictive control technique (NMPC) is used to optimally control vehicle speed and the instantaneous power minimization (IPM) strategy is adopted to deal with the torque distribution of multi-motor system. The research also takes the safety and comfort into consideration. The eco-CC deals with the design of an adaptive cruise control system considering the safety as well as comfort aspects of corner road. At last, this research has been proven with real motors response, these simulations demonstrate that eco-CC improves the total energy cost about 5~10%.