面向区域智能运输的多智能车辆协作研究
|
摘要
区域智能运输系统是智能运输系统的重要分支,为解决城市及其周边特定区域的交通问题提供了新的解决方案。该系统以全自动的智能车辆为运输工具,旨在提高运输系统的效率和安全性,是未来运输技术的新概念之一。区域智能运输系统中智能车辆的协作是保证系统运行效率和安全的根本之所在,本文研究面向区域智能运输的智能车辆协作问题,涉及智能车辆协作的体系结构设计,及协作中的决策与控制问题。
多智能车辆协作的体系结构是实现协作的基础,也是集成协作中的决策与控制的框架。在对多智能车辆协作问题进行分析的基础上,结合区域智能运输系统的结构及其运行特点,设计了基于多智能体协作模型的并行协作体系结构。该协作体系结构集成了行为协作和任务协作,能够满足区域智能运输系统中智能车辆协作的要求。依照本文所设计协作体系结构,实现了一个面向区域智能运输的多智能车协作系统。
区域智能运输系统的运行必须保证智能车辆在途行驶的安全性及整个系统的运行效率,车辆的安全性及系统的运行效率均由智能车辆的在途行为协作来保证。行为协作同时涉及智能车辆的离散状态和连续状态,为此,本文提出了基于混合动态系统模型的智能车辆行为协作方法,其中车辆智能体的状态及其行为采用混合动态系统模型描述。采用基于混合动态系统模型的行为协作方法,能完整地描述智能车辆的状态、意图及其决策方法,并综合智能车辆的基本机动模式,在保证行车安全的前提下实现直道上的所有协作行为。该方法的有效性在多智能车协作仿真平台及相关试验中得到了验证。
车队是智能车辆行为协作的主要模式,车队的控制是智能车辆行为协作必须考虑的问题。本文首先分析了典型的车辆跟随距离准则,并建立了与之对应的智能车辆跟随控制模型。分析了跟随控制条件下的车队稳定性问题,包括车队的局部稳定性和全局稳定性。以互联系统稳定性理论为基础,提出了基于车队稳定性的最优跟随时距及其确定方法。试验研究结果表明,采用基于车队稳定性的最优跟随时距,可以在尽量减少车辆间距的条件下保证车队的安全性及其稳定性。
超车是智能车辆行为协作的另一重要模式,智能车辆的超车控制必需保证相关车辆的安全性及超车的快速性;另外,智能车辆的超车同时涉及决策和控制问题。为此,本文提出了基于冲突概率预估的超车控制方法,以冲突概率为超车的安全性指标,采用模型预测控制算法跟踪安全冲突概率,将超车中涉及的决策及控制问题综合为一个跟踪控制问题,由此实现安全快速的自动超车。该超车控制方法的效能在不同配置的对比试验中得到了验证。
区域智能运输中的运输任务具有分布性、动态性及随机特性,智能车辆需要通过协作完成运输任务。为解决上述问题,本文提出了基于多智能体协作模型的任务协作方法,采用多智能体“预规划-协调-再规划”的协作方法实现运输任务的分配和行驶线路的规划。车辆智能体根据局部运输任务进行预规划,在此基础上进行协调及再规划,由此实现分布式的任务协作。对比试验研究结果表明,基于多智能体协作模型的分布式任务协作能够适应随机动态的运输环境,显著地减少乘客的平均等车时间及总旅行时间。
IV The local intelligent transportation system is an important branch of the intelligent transportation systems (ITS), which providing a new solution to the urban transportation. This system uses fully automated intelligent vehicles as transportation tools, and intends to improve the efficiency and safety of the transportation system; therefore the local intelligent transportation system has become a new concept of the future transport technology. The coordination of intelligent vehicles is critical to ensure the efficiency and safety of the local intelligent transportation system. In this thesis, the coordination problems of intelligent vehicles in the local intelligent transportation system, including the design of coordination architecture, the decision-making, and the control problems, have been studied.
The coordination architecture is not only the basis of the coordination of multiple intelligent vehicles, but also the framework for integrating control and decision-making of the coordination. By analyzing the multiple intelligent vehicle coordination problems, the parallel coordination architecture based on the multi-agent systems coordination model has been designed by considering the composition and operating characteristics of the local intelligent transportation system. This coordination architecture integrates the behavior coordination and the task coordination, and can meet the requirements of the multiple intelligent vehicle coordination in local transportation system. Refer to the above mentioned coordination architecture, a multiple intelligent vehicle coordination system for the local intelligent transportation has been realized.
The operation of the local transportation system must ensure the safety of intelligent vehicles and the en route operating efficiency of the whole system, which are ensured by the en route behavior coordination. The en route behavior coordination concerns both continuous and discrete states of the intelligent vehicles; therefore a hybrid system based behavior coordination method is proposed, in which the state and behavior of a vehicle agent are described by a hybrid system. The hybrid system model based behavior coordination method can describe the state, intention, and decision-making method of an intelligent vehicle completely, and can realize all the coordination behaviors on the straight lane by synthesizing the basic maneuvers of intelligent vehicles. The validity of the proposed behavior coordination method has been verified in both the multiple intelligent vehicle coordination simulation platform and the relative tests.
Platoon is a primary behavior coordination mode of the intelligent vehicles, the control problems must be considered for the platoon. The intelligent vehicle following control model has been established by analyzing different vehicle following distance policies. The platoon stability on the condition of following control has been analyzed. From the interconnected system stability theoretical perspective, the platoon stability based optimal following headway and the corresponding determination methods for this headway have been proposed. Test results show that the optimal following headway determined by the proposed method can ensure the safety and stability of the platoon, and can reduce the inter-vehicle distances.
Overtaking is another important mode of the intelligent vehicle coordination, safety and celerity must be ensured in this maneuver. In addition, the overtaking concerns both decision-making and control. An overtaking control method based on conflict probability estimation is proposed, which uses conflict probability as the safety indicator. This method adopts model predict control to track a safe conflict probability, and integrates decision-making and control of overtaking into a tracking control problem, then realizes automotive overtaking with safety and celerity. The performance of the proposed overtaking control method has been validated in the comparative experiments with different configurations.
Task coordination is another aspect of the intelligent vehicles’coordination in the local transportation system. The transportation tasks of the local intelligent transportation are distributed, dynamic, and random, therefore the intelligent vehicles should complete these tasks by coordination. To resolve the above problem, a task coordination method based on the multi-agent system coordination model has been proposed. This method uses the“pre-planning, negotiation, re-planning”coordination of multiple agents to complete the transportation task assigning and route planning. The vehicle agents carry out pre-plan according to the local transportation tasks, then initiate negotiation and re-plan on the basis of the pre-plan, thus the distributed task coordination can be completed. The comparative test results show that the proposed multi-agent systems coordination based distributed task coordination is able to adapt to the random and dynamic transportation conditions, and reduce both the average waiting time and the total travel time of passengers significantly.
多智能车辆协作的体系结构是实现协作的基础,也是集成协作中的决策与控制的框架。在对多智能车辆协作问题进行分析的基础上,结合区域智能运输系统的结构及其运行特点,设计了基于多智能体协作模型的并行协作体系结构。该协作体系结构集成了行为协作和任务协作,能够满足区域智能运输系统中智能车辆协作的要求。依照本文所设计协作体系结构,实现了一个面向区域智能运输的多智能车协作系统。
区域智能运输系统的运行必须保证智能车辆在途行驶的安全性及整个系统的运行效率,车辆的安全性及系统的运行效率均由智能车辆的在途行为协作来保证。行为协作同时涉及智能车辆的离散状态和连续状态,为此,本文提出了基于混合动态系统模型的智能车辆行为协作方法,其中车辆智能体的状态及其行为采用混合动态系统模型描述。采用基于混合动态系统模型的行为协作方法,能完整地描述智能车辆的状态、意图及其决策方法,并综合智能车辆的基本机动模式,在保证行车安全的前提下实现直道上的所有协作行为。该方法的有效性在多智能车协作仿真平台及相关试验中得到了验证。
车队是智能车辆行为协作的主要模式,车队的控制是智能车辆行为协作必须考虑的问题。本文首先分析了典型的车辆跟随距离准则,并建立了与之对应的智能车辆跟随控制模型。分析了跟随控制条件下的车队稳定性问题,包括车队的局部稳定性和全局稳定性。以互联系统稳定性理论为基础,提出了基于车队稳定性的最优跟随时距及其确定方法。试验研究结果表明,采用基于车队稳定性的最优跟随时距,可以在尽量减少车辆间距的条件下保证车队的安全性及其稳定性。
超车是智能车辆行为协作的另一重要模式,智能车辆的超车控制必需保证相关车辆的安全性及超车的快速性;另外,智能车辆的超车同时涉及决策和控制问题。为此,本文提出了基于冲突概率预估的超车控制方法,以冲突概率为超车的安全性指标,采用模型预测控制算法跟踪安全冲突概率,将超车中涉及的决策及控制问题综合为一个跟踪控制问题,由此实现安全快速的自动超车。该超车控制方法的效能在不同配置的对比试验中得到了验证。
区域智能运输中的运输任务具有分布性、动态性及随机特性,智能车辆需要通过协作完成运输任务。为解决上述问题,本文提出了基于多智能体协作模型的任务协作方法,采用多智能体“预规划-协调-再规划”的协作方法实现运输任务的分配和行驶线路的规划。车辆智能体根据局部运输任务进行预规划,在此基础上进行协调及再规划,由此实现分布式的任务协作。对比试验研究结果表明,基于多智能体协作模型的分布式任务协作能够适应随机动态的运输环境,显著地减少乘客的平均等车时间及总旅行时间。
IV The local intelligent transportation system is an important branch of the intelligent transportation systems (ITS), which providing a new solution to the urban transportation. This system uses fully automated intelligent vehicles as transportation tools, and intends to improve the efficiency and safety of the transportation system; therefore the local intelligent transportation system has become a new concept of the future transport technology. The coordination of intelligent vehicles is critical to ensure the efficiency and safety of the local intelligent transportation system. In this thesis, the coordination problems of intelligent vehicles in the local intelligent transportation system, including the design of coordination architecture, the decision-making, and the control problems, have been studied.
The coordination architecture is not only the basis of the coordination of multiple intelligent vehicles, but also the framework for integrating control and decision-making of the coordination. By analyzing the multiple intelligent vehicle coordination problems, the parallel coordination architecture based on the multi-agent systems coordination model has been designed by considering the composition and operating characteristics of the local intelligent transportation system. This coordination architecture integrates the behavior coordination and the task coordination, and can meet the requirements of the multiple intelligent vehicle coordination in local transportation system. Refer to the above mentioned coordination architecture, a multiple intelligent vehicle coordination system for the local intelligent transportation has been realized.
The operation of the local transportation system must ensure the safety of intelligent vehicles and the en route operating efficiency of the whole system, which are ensured by the en route behavior coordination. The en route behavior coordination concerns both continuous and discrete states of the intelligent vehicles; therefore a hybrid system based behavior coordination method is proposed, in which the state and behavior of a vehicle agent are described by a hybrid system. The hybrid system model based behavior coordination method can describe the state, intention, and decision-making method of an intelligent vehicle completely, and can realize all the coordination behaviors on the straight lane by synthesizing the basic maneuvers of intelligent vehicles. The validity of the proposed behavior coordination method has been verified in both the multiple intelligent vehicle coordination simulation platform and the relative tests.
Platoon is a primary behavior coordination mode of the intelligent vehicles, the control problems must be considered for the platoon. The intelligent vehicle following control model has been established by analyzing different vehicle following distance policies. The platoon stability on the condition of following control has been analyzed. From the interconnected system stability theoretical perspective, the platoon stability based optimal following headway and the corresponding determination methods for this headway have been proposed. Test results show that the optimal following headway determined by the proposed method can ensure the safety and stability of the platoon, and can reduce the inter-vehicle distances.
Overtaking is another important mode of the intelligent vehicle coordination, safety and celerity must be ensured in this maneuver. In addition, the overtaking concerns both decision-making and control. An overtaking control method based on conflict probability estimation is proposed, which uses conflict probability as the safety indicator. This method adopts model predict control to track a safe conflict probability, and integrates decision-making and control of overtaking into a tracking control problem, then realizes automotive overtaking with safety and celerity. The performance of the proposed overtaking control method has been validated in the comparative experiments with different configurations.
Task coordination is another aspect of the intelligent vehicles’coordination in the local transportation system. The transportation tasks of the local intelligent transportation are distributed, dynamic, and random, therefore the intelligent vehicles should complete these tasks by coordination. To resolve the above problem, a task coordination method based on the multi-agent system coordination model has been proposed. This method uses the“pre-planning, negotiation, re-planning”coordination of multiple agents to complete the transportation task assigning and route planning. The vehicle agents carry out pre-plan according to the local transportation tasks, then initiate negotiation and re-plan on the basis of the pre-plan, thus the distributed task coordination can be completed. The comparative test results show that the proposed multi-agent systems coordination based distributed task coordination is able to adapt to the random and dynamic transportation conditions, and reduce both the average waiting time and the total travel time of passengers significantly.
引文
[1] Sussman J M. What have we learned about intelligent transportation systems?. U. S. Department of Transportation. Washington DC, 2000.
[2]黄卫,陈里德.智能运输系统概论.北京:人民交通出版社, 1999.
[3]沈国江,孙优贤.城市交通干线递阶模糊控制及其神经网络实现.系统工程理论与实践, 2004, 4: 99-105.
[4]李瑞敏,史其信.基于多智能体系统的城市交通控制与诱导集成化研究.公路交通科技, 2004, 21(5): 109-112.
[5]王亮,马寿峰,贺国光.一种交通控制与诱导递阶协调优化模型.系统工程理论与实践, 2004, 6: 126-133.
[6]黄铮,邹群,邹国平.基于Multi—Agent的高速公路集成交通控制系统.交通运输工程学报, 2005, 5(1): 116-119.
[7] Varaiya P. Smart cars on smart roads: problems of control. IEEE Transactions on Automatic Control, 1993, 38(2): 195-207.
[8]杨明.无人自动驾驶车辆研究综述与展望.哈尔滨工业大学学报, 2006, 38: 1259-1262.
[9] Shladover S E. PATH at 20 - history and major milestones. IEEE Transactions on Intelligent Transportation Systems, 2007, 8(4): 584-592.
[10] http://www.path.berkeley.edu/.
[11] Parent M, Daviet P. Automated urban vehicles: towards a dual made PRT (Persmnal Rapid Transit). Proceedings of the 1996 IEEE International Conference on Robotics 2nd Automation Minneapolis, Minnesota, April 1996.
[12] Anderson J E. A review of the state of the art of Personal Rapid Transit. Journal of Advanced Transportation, 2000, 34(1): 3-29.
[13] Parent M. Advanced urban transport: automation is on the way. Intelligent Systems, 2007, 22(2): 9-11.
[14] Parent M, Fortelle A de La. Cybercars: past, present and future of the technology. Dans ITS World Congress, 2005: 6-9.
[15] Kopits E, Cropper M. Traffic fatalities and economic growth. Research Report of the World Bank, (3035), April, 2003.
[16] Parker L E. Current research in multirobot systems. Artificial Life Robotics, 2003, 7: 1-5.
[17] Tsugawa S. An introduction to Demo 2000: the cooperative driving scenario. Intelligent Transportation Systems, 2000, 15(4): 78-79.
[18] Sousa J B, Girard A R, Hedrick J K. Elemental maneuvers and coordination structures for unmanned air vehicles. 43rd IEEE Conference on Decision and Control. December, Atlantis, Paradise Island, Bahamas. 2004: 608-613.
[19]喻俊志,王硕,谭民.多仿生机器鱼控制与协调.机器人技术与应用, 2003, 3: 27-35.
[20]梁建宏,王田苗,魏洪兴,等.水下仿生机器鱼的研究进展IIV-多仿生机器鱼协调控制研究.机器人, 2002, 24(5): 413-417.
[21]喻俊志,陈尔奎,王硕,等.一种多仿生机器鱼协作系统的设计与初步实现.系统仿真学报. 2002, 14(10): 1316-1320.
[22]党宏社,韩崇昭,段战胜.智能车辆系统发展及其关键技术概述.公路交通科技,2002, 19(6): 127-130.
[23]王荣本,李兵,施树明,等.世界智能车研究概述.公路交通科技, 2001, 18(5): 93-97.
[24]王荣本,李兵,李斌.世界智能车辆近况综述.汽车工程,2001, 123(5): 289-295.
[25] Vahidi A, Eskandarian A. Research advances in intelligent collision avoidance and adaptive cruise control. IEEE Transactions on Intelligent Transportation Systems, 2003, 4(3): 143-153.
[26] Hatipoglu C, ?zgünerü, Redmill K A. Automated lane change controller design. IEEE Transactions on Intelligent Transportation Systems, 2003, 4: 13-22.
[27] Guldner J, Utkin V I, Ackermann J. A sliding mode control approach to automatic car steering. Proceedings of American Control Conference, Baltimore, MD, June, 1994: 1969-1973.
[28] You S S, Jeong S K. Controller design and analysis for automatic steering of passenger cars. Mechatronics, 2002, 12: 427 - 446.
[29]王荣本,张荣辉,金立生,等.区域交通智能车辆导航控制技术.农业机械学报, 2007, 38(7): 39-42.
[30]谭满春,徐建闽,许伦辉,等.车辆换道控制策略及其灵敏度分析.系统工程学报, 2005, 21(2): 206-210.
[31] Peter H. Modelling lane changing and merging in microscopic traffic simulation. Transportation Research Part C, 2002, 10(5-6): 351–371.
[32]周俊,姬长英.智能车辆横向控制研究.机器人, 2003, 25(1): 26-30.
[33]高振海.汽车方向预瞄式自适应PD控制算法.机械工程学报, 2004, 40(5): 101-105.
[34]王荣本,张荣辉,游峰,等.智能车辆弧线跟踪控制算法.吉林大学学报, 2006, 36(5): 731-735.
[35]吴超仲,严新平.自动公路系统横向控制研究.交通与计算机, 2001, 19(99): 23-25.
[36]ünyelioglu K A, Hatipoglu C, ?zgünerü. Design and stability analysis of a Lane following controller. IEEE Transactions on Control Systems Technology, 1997, 5(1): 127-134.
[37] Hall′e S, Laumonier J, Chaib B. A decentralized approach to collaborative driving coordination. 7th international IEEE conference on intelligent transportation systems (ITSC), Washington DC, 2004: 453-458.
[38] Liang C Y, Peng H. String stability analysis of adaptive cruise controlled vehicles. The Japan Society of Mechanical Engineers, 2000, 43(3): 671-677.
[39] Yanakiev D, Kanellakopoulos I. A simplified framework for string stability analysis in AHS. The 13th IFAC World Congress, San Francisco, CA, 1996: 177-182.
[40] Rogge J, Aeyels D. Decentralized control of vehicle platoons with interconnection possessing ring topology. Proceedings of the 44th IEEE Conference on Decision and Control, and the European Control Conference 2005. Seville, Spain, December, 2005: 1491-1496.
[41] Seiler P, Pant A, Hedrick K. Disturbance propagation in vehicle strings. IEEE Transactions on Automatic Control, 2004, 49(10): 1835-1841.
[42] Naranjo J E, González C, Reviejo J, et al. Adaptive fuzzy control for inter-vehicle gap keeping. IEEE Transactions on Intelligent Transportation Systems, 2003, 4(3): 132-142.
[43] Liang C. Y, Peng H. String stability analysis of adaptive cruise controlled vehicles. The Japan Society of Mechanical Engineers, 2000, 43(3): 671-677.
[44]施绍有,高峰,杜发荣,等.起停车辆巡航系统的建模与仿真.中国公路学报, 2007, 20(3): 115-120.
[45] Shamir T. How should an autonomous vehicle overtake a slower moving vehicle: design and analysis of an optimal trajectory. IEEE Transactions on. Automatic Control, 2004, 49: 607–610.
[46] Ichoua S, Gendreau M, Potvin J Y. Vehicle dispatching with time-dependent travel times. European Journal of Operational Research, 2003, 144: 379-396.
[47] Ganesharajaha T, Hallb N G, Sriskandarajahc C. Design and operational issues in AGV-served manufacturing systems. Annals of Operations Research, 1998, 76(1): 109-154.
[48] Heijden M, Ebben M, Gademann N, et al. Scheduling vehicles in automated transportation systems algorithms and case study*. OR Spectrum, 2002, 24: 31-58.
[49] Potvin J Y, Xu Y, Benyahiac I. Vehicle routing and scheduling with dynamic travel times. Computers & Operations Research, 2006, 33:1129-1137.
[50] Eisenstein D D, Iyer A V. Garbage collection in Chicago - a dynamic scheduling model. Management Science, 1997, 43(7): 922-933.
[51] Hoff E B, Sarker B R. An overview of path design and dispatching methods for automated guided vehicles. Integrated Manufacturing Systems, 1998, 9(5): 296-307.
[52] Gademann A J, Velde S L. Positioning automated guided vehicles in a loop layout. European Journal of Operational Research, 2000, 127: 565-573.
[53] Lee J H, Lee B H, Choi M H. A routing table approach for minimum time traffic control of multiple AGV systems. IEEE Transactions on Systems Man and Cybernetics, 1998, 28(3): 347-358.
[54] Ho Y C. A dynamic-zone strategy for vehicle-collision prevention and load balancing in an AGV system with a single-loop guide path. Computers in Industry, 2000, 42: 159-176.
[55] Heijden M, Ebben M, Gademann N, et al. Scheduling vehicles in automated transportation systems Algorithms and case study. OR Spectrum, 2002, 24: 31-58.
[56] Wong K I, Wong S C, Yang H, et al. Modeling urban taxi services with multiple user classes and vehicle modes. Transportation Research Part B: Methodological, 2008, 42(10): 985-1007.
[57] Tsang C W, Ho T K. Conflict resolution through negotiation in a railway open access market: a multi-agent system approach. Transportation Research Part B: Methodological, 2006, 29(3): 157-182.
[58]宋伟刚,张宏霞,佟玲.有时间窗约束非满载车辆调度问题的遗传算法.系统仿真学报, 2005, 17(11): 2593-2597.
[59]李军,郭耀煌.物流配送车辆优化调度理论与方法,中国物资出版社,2001.
[60]齐二石,田青,宋宁华.物流系统规划设计方法综述,天津大学学报, 2003, 5(3): 225-228.
[61] Powell W B, Ioannis K. Shipment routing algorithms with tree constraints. Transportation Science, 1992, 26(3): 230-245.
[62] Powell W B. Optimization models and algorithms: An emerging technology for the motor carrier industry. IEEE Transactions on Vehicular Technology, 1991, 40(1): 68-80.
[63] Farvolden J M, Powell W B, Lustig I J. Primal partitioning solution for the arc-chain formulation of a multicommodity network flow problem. Operations Research, 1993, 41(4): 669-693.
[64] Weerdt M. Transport planning and scheduling. Computers and Chemical Engineering, 1999, 24(9): 2259-2276.
[65] Weerdt M, Mors A, Witteveen C. Multi-agent planning: an introduction to planning and coordination. Handouts of the European Agent Summer School, 2006: 1-32.
[66] Witteveen C, Weerdt M. Multi-agent planning for non-cooperative agents. Proceedings of the AAAI Spring Symposium on Distributed Plan and Schedule Management, 2006: 169-170.
[67] Valk J, Witteveen C, Zutt J. Task allocation policies for logistic problems. Proceedings of the First Seminar ''Joint TNO TRAIL Transport Research T3'' (TRAIL'01), Delft, March 2001.
[68] Mes M, Heijden M, Harten A. Comparison of agent-based scheduling to look-ahead heuristics for real-time transportation problems. European Journal of Operational Research, 2007, 181(1): 59-75.
[69] Valk J, Witteveen C, Zutt J. Approximation results for multi-agent planning systems. Proceedingsof the fourth Pacific Rim International Workshop on Multi-Agents (PRIMA'01), Taipei, Taiwan, 2001.
[70] Zutt J. Cooperative transport planning. Master’s Thesis, January 16, 2001.
[71] Moree B J, Tonino A B H, Witteveen C. Cooperation by iterated plan revision. Proceedings of Fourth International Conference on Boston Multi-Agent Systems, MA, USA, 2000: 191-198.
[72] Zidi S, Maouche S, Hammadi S. Real-time route planning of the public transportation system. Proceedings of the IEEE Intelligent Transportation Systems Conference, Toronto, Canada, September, 2006: 17-20
[73]刘云忠,宣慧玉.车辆路径问题的模型及算法研究综述,管理工程学报, 2005, 19(1): 124-130.
[74]陈辉,刘春草.物流配送管理中的路径优化问题研究,西安电子科技大学学报, 2006, 16(5): 16-20.
[75] Pankratz G. Dynamic vehicle routing by means of a genetic algorithm. International Journal of Physical Distribution & Logistics Management, 2005, 35(5): 362-383.
[76] Larsen A. The dynamic vehicle routing problem. IMM, DTU Bookbinder Hans Meyer, 2000.
[77] Haghania A, Jungb S. A dynamic vehicle routing problem with time-dependent travel times. Computers & Operations Research, 2005, 32: 2959-2968.
[78] Guo Y H, Xie B L. Overview of stochastic vehicle routing problems. Journal of Southwest Jiao Tong University, 2002, 10(2): 113-121.
[79] Fleischmann B. Dynamic vehicle routing based on online traffic information. Transportation Science, 2004, 38(4): 420-433.
[80]谢秉磊,郭耀煌,郭强.动态车辆路径问题:现状与展望.系统工程理论方法应用, 2002, 11(2): 116-120.
[81] Garcia A, Kulesza U, Lucena C. Aspectizing multi-agent systems: from architecture to implementation. Lecture Notes in Computer Science, 2005, 3390: 121-143.
[82] Pynadath D V, Tambe M. Multiagent teamwork: analyzing the optimality and complexity of key theories and models. AAMAS’02, Bologna, Italy, July, 2002: 6-11.
[83] Kraus S, Ilan B. Negotiation and cooperation in multi-agent environments. Artificial Intelligence, 1997, 94(1-2): 79-97.
[84]李海刚,吴启迪.多Agent系统研究综述.同济大学学报, 2003, 31(6): 728-732.
[85]刘大有,杨鲲,陈建宁. Agent研究现状与发展趋势.软件学报, 2000, 11(3): 315-321.
[86]李常洪,李敏强,寇纪淞.多Agent合作结构研究.管理科学学报, 2003, 6(5): 6-11.
[87]王飞跃,汤淑明.人工交通系统的基本思想与框架体系.复杂系统与复杂性科学, 2004, 1(2): 52-59.
[88]王飞跃,戴汝为,汤淑明,等.城市综合交通、物流、生态问题的基础研究方法.交通运输系统工程与信息, 2004, 4(3): 37-46.
[89]陈淼发,毛岚.城市交通信号灯模糊线控制及其仿真.系统仿真学报, 2000, 12(6): 668-670.
[90]刘智勇,吴今培,李秀平.城市交通大系统递阶模糊神经网络控制.信息与控制, 1997, 26(6): 441-448.
[91]沈国江,孙优贤.城市交通干线递阶模糊控制及其神经网络实现.系统工程理论与实践, 2004, 4: 99-105.
[92] Luo J, Hubaux J P. A survey of inter-vehicle communication. EPFL, Lausanne, Switzerland,Technical Report,2004.
[93] Issues T S. Recent trends in vehicle safety communication systems. IATSS research, 2005, 29(1): 7-15.
[94] Reichardt D, Miglietta M, Moretti L, et al. CarTALK 2000: safe and comfortable driving based upon inter-vehicle-communication. Proceedings of Intelligent Vehicle Symposium. Versailles, France, 2002: 545-550.
[95] Bana S V. Coordinating automated vehicles via communication. California PATH Research Report, 2001.
[96] Sun M T, Feng W C, Lai T H, et al. GPS-Based message broadcasting for inter-vehicle communication. Proceedings of International Conference on Parallel Processing, Toronto, Canada, 2000: 279-286.
[100] Malone T W, Crowston K. The interdisciplinary study of coordination. ACM Computing Surveys,1994, 26(1): 87-119.
[101] Girard A R, Sousa J B, Hedrick J K. A selection of recent advances in networked multi-vehicle systems. Journal of Systems and Control Engineering, 2005, 219(1): 1-14.
[102] Lyons D M, Hendriks A J. Planning for reactive robot behavior. Proceedings of the 1992 International Conference on Robotica and Automation. Nice, France, 1992: 2675-2680.
[103] Jennings N R. Towards a cooperation knowledge level for collaborative problem solving. Proceedings of the 10th European Conference on Artificial Intelligence. Vienna, Austria: John Wiley and Sons, 1992: 224–228.
[104] Bana S V. Coordinating automated vehicles via communication. Doctoral Dissertation, University of California, Berkeley, CA, USA, 2000.
[105] Luck M. A manifesto for agent technology: towards next generation computing. Autonomous Agents and Multi-Agent Systems, 2004, 9: 203–252.
[106] Jennings N R, Sycara K, Wooldridge M. A roadmap of agent research and development. Autonomous Agents and Multi-Agent Systems, 1998. 1: 7-38.
[107] Lerner A Y. Fundamentals of Cybernetics. Chapman and Hall, 1980.
[108] Hegeman G, Brookhuis K, Hoogendoorn S. Opportunities of advanced driver assistance systems towards overtaking. European Journal of Transport and Infrastructure Research, 2005, 5(4): 281~296.
[109]佟春生.系统工程的理论与方法概论.北京:国防工业出版社, 2005.
[110] Hegeman G, Horst R, Brookhuis K A., et al. Functioning and acceptance of overtaking assistant design tested in driving simulator experiment. Transportation Research Record, 2007, 2018: 45-52.
[111] Horowitz R, Varaiya P. Control design of an automated highway system. Proceedings of IEEE, July, 2000, 88(7): 913-925.
[112] Kato S, Tsugawa S, Tokuda K, et al. Vehicle control algorithms for cooperative driving with automated vehicles and intervehicle communications. IEEE Transactions on Intelligent Transportation Systems, 2002, 3(3): 155-161.
[113] Blosseville J M. Driver assistance systems, a long way to AHS. Proceedings of IEEE Intelligent Vehicular Symposium, Tokyo, Japan, June, 2006: 237.
[114] Paielli R A, Erzberger H. Conflict probability estimation for free flight. Journal of Guidacne, Control, Dynamics, May/June, 1997, 20(3): 588-596.
[115] Patera R P. Space vehicle conflict-avoidance analysis. Journal of Guidacne, Control, Dynamics, March/April, 2007, 30(2): 492-498.
[116] Qin S J, Badgwell T A. A survey of industrial model predictive control technology. Control Engineer Practice, November, 2003, 11: 733–764.
[2]黄卫,陈里德.智能运输系统概论.北京:人民交通出版社, 1999.
[3]沈国江,孙优贤.城市交通干线递阶模糊控制及其神经网络实现.系统工程理论与实践, 2004, 4: 99-105.
[4]李瑞敏,史其信.基于多智能体系统的城市交通控制与诱导集成化研究.公路交通科技, 2004, 21(5): 109-112.
[5]王亮,马寿峰,贺国光.一种交通控制与诱导递阶协调优化模型.系统工程理论与实践, 2004, 6: 126-133.
[6]黄铮,邹群,邹国平.基于Multi—Agent的高速公路集成交通控制系统.交通运输工程学报, 2005, 5(1): 116-119.
[7] Varaiya P. Smart cars on smart roads: problems of control. IEEE Transactions on Automatic Control, 1993, 38(2): 195-207.
[8]杨明.无人自动驾驶车辆研究综述与展望.哈尔滨工业大学学报, 2006, 38: 1259-1262.
[9] Shladover S E. PATH at 20 - history and major milestones. IEEE Transactions on Intelligent Transportation Systems, 2007, 8(4): 584-592.
[10] http://www.path.berkeley.edu/.
[11] Parent M, Daviet P. Automated urban vehicles: towards a dual made PRT (Persmnal Rapid Transit). Proceedings of the 1996 IEEE International Conference on Robotics 2nd Automation Minneapolis, Minnesota, April 1996.
[12] Anderson J E. A review of the state of the art of Personal Rapid Transit. Journal of Advanced Transportation, 2000, 34(1): 3-29.
[13] Parent M. Advanced urban transport: automation is on the way. Intelligent Systems, 2007, 22(2): 9-11.
[14] Parent M, Fortelle A de La. Cybercars: past, present and future of the technology. Dans ITS World Congress, 2005: 6-9.
[15] Kopits E, Cropper M. Traffic fatalities and economic growth. Research Report of the World Bank, (3035), April, 2003.
[16] Parker L E. Current research in multirobot systems. Artificial Life Robotics, 2003, 7: 1-5.
[17] Tsugawa S. An introduction to Demo 2000: the cooperative driving scenario. Intelligent Transportation Systems, 2000, 15(4): 78-79.
[18] Sousa J B, Girard A R, Hedrick J K. Elemental maneuvers and coordination structures for unmanned air vehicles. 43rd IEEE Conference on Decision and Control. December, Atlantis, Paradise Island, Bahamas. 2004: 608-613.
[19]喻俊志,王硕,谭民.多仿生机器鱼控制与协调.机器人技术与应用, 2003, 3: 27-35.
[20]梁建宏,王田苗,魏洪兴,等.水下仿生机器鱼的研究进展IIV-多仿生机器鱼协调控制研究.机器人, 2002, 24(5): 413-417.
[21]喻俊志,陈尔奎,王硕,等.一种多仿生机器鱼协作系统的设计与初步实现.系统仿真学报. 2002, 14(10): 1316-1320.
[22]党宏社,韩崇昭,段战胜.智能车辆系统发展及其关键技术概述.公路交通科技,2002, 19(6): 127-130.
[23]王荣本,李兵,施树明,等.世界智能车研究概述.公路交通科技, 2001, 18(5): 93-97.
[24]王荣本,李兵,李斌.世界智能车辆近况综述.汽车工程,2001, 123(5): 289-295.
[25] Vahidi A, Eskandarian A. Research advances in intelligent collision avoidance and adaptive cruise control. IEEE Transactions on Intelligent Transportation Systems, 2003, 4(3): 143-153.
[26] Hatipoglu C, ?zgünerü, Redmill K A. Automated lane change controller design. IEEE Transactions on Intelligent Transportation Systems, 2003, 4: 13-22.
[27] Guldner J, Utkin V I, Ackermann J. A sliding mode control approach to automatic car steering. Proceedings of American Control Conference, Baltimore, MD, June, 1994: 1969-1973.
[28] You S S, Jeong S K. Controller design and analysis for automatic steering of passenger cars. Mechatronics, 2002, 12: 427 - 446.
[29]王荣本,张荣辉,金立生,等.区域交通智能车辆导航控制技术.农业机械学报, 2007, 38(7): 39-42.
[30]谭满春,徐建闽,许伦辉,等.车辆换道控制策略及其灵敏度分析.系统工程学报, 2005, 21(2): 206-210.
[31] Peter H. Modelling lane changing and merging in microscopic traffic simulation. Transportation Research Part C, 2002, 10(5-6): 351–371.
[32]周俊,姬长英.智能车辆横向控制研究.机器人, 2003, 25(1): 26-30.
[33]高振海.汽车方向预瞄式自适应PD控制算法.机械工程学报, 2004, 40(5): 101-105.
[34]王荣本,张荣辉,游峰,等.智能车辆弧线跟踪控制算法.吉林大学学报, 2006, 36(5): 731-735.
[35]吴超仲,严新平.自动公路系统横向控制研究.交通与计算机, 2001, 19(99): 23-25.
[36]ünyelioglu K A, Hatipoglu C, ?zgünerü. Design and stability analysis of a Lane following controller. IEEE Transactions on Control Systems Technology, 1997, 5(1): 127-134.
[37] Hall′e S, Laumonier J, Chaib B. A decentralized approach to collaborative driving coordination. 7th international IEEE conference on intelligent transportation systems (ITSC), Washington DC, 2004: 453-458.
[38] Liang C Y, Peng H. String stability analysis of adaptive cruise controlled vehicles. The Japan Society of Mechanical Engineers, 2000, 43(3): 671-677.
[39] Yanakiev D, Kanellakopoulos I. A simplified framework for string stability analysis in AHS. The 13th IFAC World Congress, San Francisco, CA, 1996: 177-182.
[40] Rogge J, Aeyels D. Decentralized control of vehicle platoons with interconnection possessing ring topology. Proceedings of the 44th IEEE Conference on Decision and Control, and the European Control Conference 2005. Seville, Spain, December, 2005: 1491-1496.
[41] Seiler P, Pant A, Hedrick K. Disturbance propagation in vehicle strings. IEEE Transactions on Automatic Control, 2004, 49(10): 1835-1841.
[42] Naranjo J E, González C, Reviejo J, et al. Adaptive fuzzy control for inter-vehicle gap keeping. IEEE Transactions on Intelligent Transportation Systems, 2003, 4(3): 132-142.
[43] Liang C. Y, Peng H. String stability analysis of adaptive cruise controlled vehicles. The Japan Society of Mechanical Engineers, 2000, 43(3): 671-677.
[44]施绍有,高峰,杜发荣,等.起停车辆巡航系统的建模与仿真.中国公路学报, 2007, 20(3): 115-120.
[45] Shamir T. How should an autonomous vehicle overtake a slower moving vehicle: design and analysis of an optimal trajectory. IEEE Transactions on. Automatic Control, 2004, 49: 607–610.
[46] Ichoua S, Gendreau M, Potvin J Y. Vehicle dispatching with time-dependent travel times. European Journal of Operational Research, 2003, 144: 379-396.
[47] Ganesharajaha T, Hallb N G, Sriskandarajahc C. Design and operational issues in AGV-served manufacturing systems. Annals of Operations Research, 1998, 76(1): 109-154.
[48] Heijden M, Ebben M, Gademann N, et al. Scheduling vehicles in automated transportation systems algorithms and case study*. OR Spectrum, 2002, 24: 31-58.
[49] Potvin J Y, Xu Y, Benyahiac I. Vehicle routing and scheduling with dynamic travel times. Computers & Operations Research, 2006, 33:1129-1137.
[50] Eisenstein D D, Iyer A V. Garbage collection in Chicago - a dynamic scheduling model. Management Science, 1997, 43(7): 922-933.
[51] Hoff E B, Sarker B R. An overview of path design and dispatching methods for automated guided vehicles. Integrated Manufacturing Systems, 1998, 9(5): 296-307.
[52] Gademann A J, Velde S L. Positioning automated guided vehicles in a loop layout. European Journal of Operational Research, 2000, 127: 565-573.
[53] Lee J H, Lee B H, Choi M H. A routing table approach for minimum time traffic control of multiple AGV systems. IEEE Transactions on Systems Man and Cybernetics, 1998, 28(3): 347-358.
[54] Ho Y C. A dynamic-zone strategy for vehicle-collision prevention and load balancing in an AGV system with a single-loop guide path. Computers in Industry, 2000, 42: 159-176.
[55] Heijden M, Ebben M, Gademann N, et al. Scheduling vehicles in automated transportation systems Algorithms and case study. OR Spectrum, 2002, 24: 31-58.
[56] Wong K I, Wong S C, Yang H, et al. Modeling urban taxi services with multiple user classes and vehicle modes. Transportation Research Part B: Methodological, 2008, 42(10): 985-1007.
[57] Tsang C W, Ho T K. Conflict resolution through negotiation in a railway open access market: a multi-agent system approach. Transportation Research Part B: Methodological, 2006, 29(3): 157-182.
[58]宋伟刚,张宏霞,佟玲.有时间窗约束非满载车辆调度问题的遗传算法.系统仿真学报, 2005, 17(11): 2593-2597.
[59]李军,郭耀煌.物流配送车辆优化调度理论与方法,中国物资出版社,2001.
[60]齐二石,田青,宋宁华.物流系统规划设计方法综述,天津大学学报, 2003, 5(3): 225-228.
[61] Powell W B, Ioannis K. Shipment routing algorithms with tree constraints. Transportation Science, 1992, 26(3): 230-245.
[62] Powell W B. Optimization models and algorithms: An emerging technology for the motor carrier industry. IEEE Transactions on Vehicular Technology, 1991, 40(1): 68-80.
[63] Farvolden J M, Powell W B, Lustig I J. Primal partitioning solution for the arc-chain formulation of a multicommodity network flow problem. Operations Research, 1993, 41(4): 669-693.
[64] Weerdt M. Transport planning and scheduling. Computers and Chemical Engineering, 1999, 24(9): 2259-2276.
[65] Weerdt M, Mors A, Witteveen C. Multi-agent planning: an introduction to planning and coordination. Handouts of the European Agent Summer School, 2006: 1-32.
[66] Witteveen C, Weerdt M. Multi-agent planning for non-cooperative agents. Proceedings of the AAAI Spring Symposium on Distributed Plan and Schedule Management, 2006: 169-170.
[67] Valk J, Witteveen C, Zutt J. Task allocation policies for logistic problems. Proceedings of the First Seminar ''Joint TNO TRAIL Transport Research T3'' (TRAIL'01), Delft, March 2001.
[68] Mes M, Heijden M, Harten A. Comparison of agent-based scheduling to look-ahead heuristics for real-time transportation problems. European Journal of Operational Research, 2007, 181(1): 59-75.
[69] Valk J, Witteveen C, Zutt J. Approximation results for multi-agent planning systems. Proceedingsof the fourth Pacific Rim International Workshop on Multi-Agents (PRIMA'01), Taipei, Taiwan, 2001.
[70] Zutt J. Cooperative transport planning. Master’s Thesis, January 16, 2001.
[71] Moree B J, Tonino A B H, Witteveen C. Cooperation by iterated plan revision. Proceedings of Fourth International Conference on Boston Multi-Agent Systems, MA, USA, 2000: 191-198.
[72] Zidi S, Maouche S, Hammadi S. Real-time route planning of the public transportation system. Proceedings of the IEEE Intelligent Transportation Systems Conference, Toronto, Canada, September, 2006: 17-20
[73]刘云忠,宣慧玉.车辆路径问题的模型及算法研究综述,管理工程学报, 2005, 19(1): 124-130.
[74]陈辉,刘春草.物流配送管理中的路径优化问题研究,西安电子科技大学学报, 2006, 16(5): 16-20.
[75] Pankratz G. Dynamic vehicle routing by means of a genetic algorithm. International Journal of Physical Distribution & Logistics Management, 2005, 35(5): 362-383.
[76] Larsen A. The dynamic vehicle routing problem. IMM, DTU Bookbinder Hans Meyer, 2000.
[77] Haghania A, Jungb S. A dynamic vehicle routing problem with time-dependent travel times. Computers & Operations Research, 2005, 32: 2959-2968.
[78] Guo Y H, Xie B L. Overview of stochastic vehicle routing problems. Journal of Southwest Jiao Tong University, 2002, 10(2): 113-121.
[79] Fleischmann B. Dynamic vehicle routing based on online traffic information. Transportation Science, 2004, 38(4): 420-433.
[80]谢秉磊,郭耀煌,郭强.动态车辆路径问题:现状与展望.系统工程理论方法应用, 2002, 11(2): 116-120.
[81] Garcia A, Kulesza U, Lucena C. Aspectizing multi-agent systems: from architecture to implementation. Lecture Notes in Computer Science, 2005, 3390: 121-143.
[82] Pynadath D V, Tambe M. Multiagent teamwork: analyzing the optimality and complexity of key theories and models. AAMAS’02, Bologna, Italy, July, 2002: 6-11.
[83] Kraus S, Ilan B. Negotiation and cooperation in multi-agent environments. Artificial Intelligence, 1997, 94(1-2): 79-97.
[84]李海刚,吴启迪.多Agent系统研究综述.同济大学学报, 2003, 31(6): 728-732.
[85]刘大有,杨鲲,陈建宁. Agent研究现状与发展趋势.软件学报, 2000, 11(3): 315-321.
[86]李常洪,李敏强,寇纪淞.多Agent合作结构研究.管理科学学报, 2003, 6(5): 6-11.
[87]王飞跃,汤淑明.人工交通系统的基本思想与框架体系.复杂系统与复杂性科学, 2004, 1(2): 52-59.
[88]王飞跃,戴汝为,汤淑明,等.城市综合交通、物流、生态问题的基础研究方法.交通运输系统工程与信息, 2004, 4(3): 37-46.
[89]陈淼发,毛岚.城市交通信号灯模糊线控制及其仿真.系统仿真学报, 2000, 12(6): 668-670.
[90]刘智勇,吴今培,李秀平.城市交通大系统递阶模糊神经网络控制.信息与控制, 1997, 26(6): 441-448.
[91]沈国江,孙优贤.城市交通干线递阶模糊控制及其神经网络实现.系统工程理论与实践, 2004, 4: 99-105.
[92] Luo J, Hubaux J P. A survey of inter-vehicle communication. EPFL, Lausanne, Switzerland,Technical Report,2004.
[93] Issues T S. Recent trends in vehicle safety communication systems. IATSS research, 2005, 29(1): 7-15.
[94] Reichardt D, Miglietta M, Moretti L, et al. CarTALK 2000: safe and comfortable driving based upon inter-vehicle-communication. Proceedings of Intelligent Vehicle Symposium. Versailles, France, 2002: 545-550.
[95] Bana S V. Coordinating automated vehicles via communication. California PATH Research Report, 2001.
[96] Sun M T, Feng W C, Lai T H, et al. GPS-Based message broadcasting for inter-vehicle communication. Proceedings of International Conference on Parallel Processing, Toronto, Canada, 2000: 279-286.
[100] Malone T W, Crowston K. The interdisciplinary study of coordination. ACM Computing Surveys,1994, 26(1): 87-119.
[101] Girard A R, Sousa J B, Hedrick J K. A selection of recent advances in networked multi-vehicle systems. Journal of Systems and Control Engineering, 2005, 219(1): 1-14.
[102] Lyons D M, Hendriks A J. Planning for reactive robot behavior. Proceedings of the 1992 International Conference on Robotica and Automation. Nice, France, 1992: 2675-2680.
[103] Jennings N R. Towards a cooperation knowledge level for collaborative problem solving. Proceedings of the 10th European Conference on Artificial Intelligence. Vienna, Austria: John Wiley and Sons, 1992: 224–228.
[104] Bana S V. Coordinating automated vehicles via communication. Doctoral Dissertation, University of California, Berkeley, CA, USA, 2000.
[105] Luck M. A manifesto for agent technology: towards next generation computing. Autonomous Agents and Multi-Agent Systems, 2004, 9: 203–252.
[106] Jennings N R, Sycara K, Wooldridge M. A roadmap of agent research and development. Autonomous Agents and Multi-Agent Systems, 1998. 1: 7-38.
[107] Lerner A Y. Fundamentals of Cybernetics. Chapman and Hall, 1980.
[108] Hegeman G, Brookhuis K, Hoogendoorn S. Opportunities of advanced driver assistance systems towards overtaking. European Journal of Transport and Infrastructure Research, 2005, 5(4): 281~296.
[109]佟春生.系统工程的理论与方法概论.北京:国防工业出版社, 2005.
[110] Hegeman G, Horst R, Brookhuis K A., et al. Functioning and acceptance of overtaking assistant design tested in driving simulator experiment. Transportation Research Record, 2007, 2018: 45-52.
[111] Horowitz R, Varaiya P. Control design of an automated highway system. Proceedings of IEEE, July, 2000, 88(7): 913-925.
[112] Kato S, Tsugawa S, Tokuda K, et al. Vehicle control algorithms for cooperative driving with automated vehicles and intervehicle communications. IEEE Transactions on Intelligent Transportation Systems, 2002, 3(3): 155-161.
[113] Blosseville J M. Driver assistance systems, a long way to AHS. Proceedings of IEEE Intelligent Vehicular Symposium, Tokyo, Japan, June, 2006: 237.
[114] Paielli R A, Erzberger H. Conflict probability estimation for free flight. Journal of Guidacne, Control, Dynamics, May/June, 1997, 20(3): 588-596.
[115] Patera R P. Space vehicle conflict-avoidance analysis. Journal of Guidacne, Control, Dynamics, March/April, 2007, 30(2): 492-498.
[116] Qin S J, Badgwell T A. A survey of industrial model predictive control technology. Control Engineer Practice, November, 2003, 11: 733–764.