考虑交互博弈的无信号交叉路口自动驾驶车辆决策规划研究

doi:10.3901/JME.2023.14.202

机械工程学报 ›› 2023, Vol. 59 ›› Issue (14): 202-212.doi: 10.3901/JME.2023.14.202

扫码分享

考虑交互博弈的无信号交叉路口自动驾驶车辆决策规划研究

徐灿^1,2, 赵万忠², 李琳², 张瑞军², 王春燕², 陈锋³

1. 合肥工业大学汽车与交通工程学院合肥 230009;
2. 南京航空航天大学能源与动力学院南京 210016;
3. 浙江万安科技股份有限公司诸暨 311835

收稿日期:2022-07-09 修回日期:2022-11-05 出版日期:2023-07-20 发布日期:2023-08-16
通讯作者: 赵万忠(通信作者),男,1982年出生,博士,教授,博士研究生导师。主要研究方向为车辆系统动力学,智能车安全与控制。E-mail:zhaowanzhong@126.com
作者简介:徐灿,男,1994年出生,讲师。主要研究方向为智能车决策控制。E-mail:xucan2011@126.com
基金资助:
国家自然科学基金资助项目(52072175，51775007)。

Interactive Decision-making and Planning for Autonomous Driving Vehicles in Unsignalized Intersection

XU Can^1,2, ZHAO Wanzhong², LI Lin², ZHANG Ruijun², WANG Chunyan², CHEN Feng³

1. School of Automotive and Transportation Engineering, Hefei University of Technology, Hefei 230009;
2. College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016;
3. Zhejiang VIE Science & Technology Company limited., Zhuji 311835

Received:2022-07-09 Revised:2022-11-05 Online:2023-07-20 Published:2023-08-16

摘要/Abstract

摘要： 为了解决无信号交叉路口自动驾驶车辆决策保守，与周围车辆交互性差的问题，提出一种考虑交互博弈的无信号交叉路口自动驾驶车辆决策规划算法。该方法分为以下几步，首先基于运动学模型及道路约束对自车和周围车辆进行初步的运动预测，并建立两车的交互动作空间，得到车辆可能的行驶域。其次，建立一个新颖的危险度评估方法，能评估两车在任意位置、任意姿态、任意速度下的碰撞危险度，用于各交互动作状态行为值的求解。进一步基于斯塔克伯格主从博弈求出两车的均衡动作策略，该策略即为当前交通环境下考虑交互得到的最优动作。最后，通过Prescan/Simulink构建交叉路口场景进行联合仿真，来验证该算法的合理性。结果表明所提出的考虑交互博弈的算法在保证安全性的基础上，能相对于基于决策树和无交互的方法分别提高7.3%和12.4%的效率，并能在多车复杂工况下与周围车辆进行灵活交互。

关键词: 自动驾驶, 决策规划, 交互博弈, 危险度评估, 无信号路口

Abstract: In order to solve the driving conservatism and the poor interaction of autonomous vehicles in unsignalized intersection, an interactive decision-making and planning algorithm is proposed. It can be divided into the following steps. Firstly, the motion of surrounding vehicles is tentatively predicted by the kinematic model-based method with road constraints. Based on this, the interactive action space of ego vehicle and the surrounding vehicle is built to cover the feasible driving range. Then, a novel threat assessment function is formulated that can evaluate the colliding risk of vehicles under any position, posture, and velocity. It is used for the solution of the state-action value. Furthermore, the Stackelberg Game is utilized to obtain the equilibrium action of ego vehicle and the interactive vehicle, which is the optimal action with considering the interaction in current traffic. Finally, the proposed algorithm is validated by the constructed intersection scenario in Prescan/Simulink. The results reveal that the proposed interactive algorithm can improve the efficiency by 7.3% and 12.4% compared to the decision-tree and the no-interaction method respectively while ensuring safety. Besides, it can also realize agile interaction in multi-vehicle complex interaction.

Key words: autonomous driving, decision-making and planning, interaction, threat assessment, unsignalized intersection

中图分类号:

U471

徐灿, 赵万忠, 李琳, 张瑞军, 王春燕, 陈锋. 考虑交互博弈的无信号交叉路口自动驾驶车辆决策规划研究[J]. 机械工程学报, 2023, 59(14): 202-212.

XU Can, ZHAO Wanzhong, LI Lin, ZHANG Ruijun, WANG Chunyan, CHEN Feng. Interactive Decision-making and Planning for Autonomous Driving Vehicles in Unsignalized Intersection[J]. Journal of Mechanical Engineering, 2023, 59(14): 202-212.

参考文献

[1] Shirazi M,Morris B. Looking at Intersections:A survey of intersection monitoring,behavior and safety analysis of recent studies[J]. IEEE Transactions on Intelligent Transportation Systems,2017,18(1):4-24.
[2] CHOI E H. Crash factors in intersection-related crashes:An on-scene perspective[R]. Washing D.C,USA:National Highway Traffic Safety Administration,2010.
[3] GULER S,MENENDEZ M,MEIER L. Using connected vehicle technology to improve the efficiency of intersections[J]. Transportation Research Part C:Emerging Technologies,2014,46:121-131.
[4] LI S,SHU K,CHEN C,et al. Planning and decision-making for connected autonomous vehicles at road intersections:A review[J]. Chinese Journal of Mechanical Engineering,2021,34:133.
[5] FABIANI F,GRAMMATICO S. Multi-vehicle automated driving as a generalized mixed-integer potential game[J]. IEEE Transactions on Intelligent Transportation Systems,2020,21(3):1064-1073.
[6] LI Li,WEN D,YAO D. A survey of traffic control with vehicular communications[J]. IEEE Transactions on Intelligent Transportation Systems,2014,15(1):425-432.
[7] YE H,LI G,JUANG B. Deep reinforcement learning based resource allocation for V2V communications[J]. IEEE Transactions on Vehicular Technology,2019,68(4):3163-3173.
[8] NOH S. Decision-making framework for autonomous driving at road intersections:Safeguarding against collision,overly conservative behavior,and violation vehicles[J]. IEEE Transactions on Industrial Electronics,2019,66(4):3275-3286.
[9] MIN K,KIM D,PARK J. RNN-based path prediction of obstacles vehicles with deep ensemble[J]. IEEE Transactions on Vehicular Technology,2019,68(10):10252-10256.
[10] XIN L,WANG P,CHAN C,et al. Intention-aware long horizon trajectory prediction of surrounding vehicles using fual LSTM networks[C]//IEEE Conf. Intell. Transp. Syst. Proceedings,ITSC,2018:1441-1446.
[11] HOU L,XIN L,LI S,et al. Interactive trajectory prediction of surrounding road users for autonomous driving using structural-LSTM network[J]. IEEE Transactions on Intelligent Transportation Systems,2020,21(11):4615-4625.
[12] SCHUBERT R,RICHTER E,WANIELIK G. Comparison and evaluation of advanced motion models for vehicle tracking[C]//Proc. 11th Int. Conf. Inf. Fusion,2008:730-735.
[13] LI N,OYLER D,ZHANG M,et al. Game theoretic modeling of driver and vehicle interactions for verification and validation of autonomous vehicle control systems[J]. IEEE Transactions on Control System Technology,2018,26(5):1782-1797.
[14] BAHRAM M,LAWITZKY A,FRIEDRICHS J,et al. A game-theoretic approach to replanning-aware interactive scene prediction and planning[J]. IEEE Transactions on Vehicular Technology,2016,65(6):3981-3992.
[15] XU C,ZHAO W,LI L,et al. A nash Q-learning based motion decision algorithm with considering interaction to traffic participants[J]. IEEE Transactions on Vehicular Technology,2020,69(11):12621-12634.
[16] HILLENBRAND J,SPIEKER A,KROSCHEL K. A multilevel collision mitigation approach-its situation assessment,decision making,and performance tradeoffs[J]. IEEE Transactions on Intelligent Transportation Systems,2006,7(4):528-540.
[17] CAMPOS G,RUNARSSON A,GRANUM F,et al. Collision avoidance at intersections:A probabilistic threat-assessment and decision-making system for safety interventions[C]//IEEE Int. Onf. Intell. Transp. Syst. ITSC,2014:649-654.
[18] WANG J,WU J,LI Y. The driving safety field based on driver-vehicle-road interactions[J]. IEEE Transactions on Intelligent Transportation Systems,2015,16(4):2203-2214.
[19] 刘梓林,黎予生,郑玲. 基于非结构化环境点云稀疏表示的无人驾驶汽车局部路径规划方法[J]. 机械工程学报,2020,56(2):163-172. LIU Zilin,LI Yusheng,ZHENG Ling. Local path planning for autonomous vehicles based on sparse representation of point cloud in unstructured environments[J]. Journal of Mechanical Engineering,2020,56(2):163-172.
[20] 马小陆,梅宏. 基于改进势场蚁群算法的移动机器人全局路径规划[J]. 机械工程学报,2021,57(1):19-27. MA Xiaolu,MEI Hong. Mobile robot global path planning based on improved ant colony system algorithm with potential field[J]. Journal of Mechanical Engineering,2021,57(1):19-27.
[21] 张三川,明珠. 基于主动安全的改进人工势场局部路径规划研究[J]. 郑州大学学报(工学版),2021,42(5):32-36. ZHANG Sanchuan,MING Zhu. Research on improved local path planning of artificial potential field based on active safety[J]. Journal of Zhengzhou Univerisity (Engineering Science),2021,42(5):32-36.
[22] MALIN F,NORROS I,INNAMAA S. Accident risk of road and weather conditions on different road types[J]. Accident Analysis and Prevention,2019,122(1):181-188.

考虑交互博弈的无信号交叉路口自动驾驶车辆决策规划研究

Interactive Decision-making and Planning for Autonomous Driving Vehicles in Unsignalized Intersection

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	褚端峰, 刘鸿祥, 高博麟, 王金湘, 殷国栋. 车辆队列预测巡航控制研究综述[J]. 机械工程学报, 2024, 60(18): 218-246.
[2]	隗寒冰, 吴化腾, 徐进. 考虑驾驶员NMS特征的自动驾驶汽车人机共驾鲁棒横向控制[J]. 机械工程学报, 2024, 60(16): 280-290.
[3]	戢杨杰, 张馨雨, 杨紫茹, 周上航, 黄岩军, 曹建永, 熊璐, 余卓平. 多智能网联汽车轨迹规划：现状与展望[J]. 机械工程学报, 2024, 60(10): 129-146.
[4]	高镇海, 于桐, 孙天骏. 考虑社会性行为的自动驾驶运动规划研究综述[J]. 机械工程学报, 2024, 60(10): 112-128.
[5]	梁凯冲, 赵治国, 颜丹姝, 赵坤. 基于动态运动基元的车辆高速公路换道轨迹规划[J]. 机械工程学报, 2024, 60(10): 192-206.
[6]	周洪龙, 裴晓飞, 刘一平, 赵柯帆. 面向动态不确定场景的自动驾驶车辆时空耦合分层轨迹规划研究[J]. 机械工程学报, 2024, 60(10): 222-234.
[7]	曾迪, 郑玲, 李以农, 杨显通. 自动驾驶奖励函数贝叶斯逆强化学习方法[J]. 机械工程学报, 2024, 60(10): 245-260.
[8]	聂士达, 刘辉, 廖志昊, 谢雨佳, 项昌乐, 韩立金, 林思豪. 考虑复杂地形的越野环境无人车辆路径规划研究[J]. 机械工程学报, 2024, 60(10): 261-272.
[9]	杨硕, 李时珍, 赵中原, 黄小鹏, 黄岩军. 基于时序差分学习模型预测控制的一体化自动驾驶换道策略[J]. 机械工程学报, 2024, 60(10): 329-338.
[10]	张志勇, 黄大洋, 黄彩霞, 胡林, 杜荣华. TD3算法改进与自动驾驶汽车并道策略学习[J]. 机械工程学报, 2023, 59(8): 224-234.
[11]	王聪, 胡文, 李文博, 邢阳, 陈宏昌, 曹东璞. 社会认知自动驾驶[J]. 机械工程学报, 2023, 59(20): 304-324.
[12]	黄晶, 陈紫琳, 杨梦婷, 彭晓燕. 自适应自动驾驶等级的驾驶人状态监测模型研究[J]. 机械工程学报, 2023, 59(2): 187-198.
[13]	高镇海, 于桐, 孙天骏, 唐明弘, 高菲, 赵睿. 面向纵向自动驾驶的仿人驱动控制网络模型[J]. 机械工程学报, 2023, 59(18): 251-262.
[14]	林歆悠, 叶卓明, 周斌豪. 基于DQN强化学习的自动驾驶转向控制策略[J]. 机械工程学报, 2023, 59(16): 315-324.
[15]	胡文, 邓泽健, 张邦基, 曹东璞, 杨彦鼎, 曹恺, 李深. 密集交通场景下无人驾驶重卡换道决策规划方法[J]. 机械工程学报, 2023, 59(12): 332-342.