基于博弈论的右转无信号交叉口行人行为模拟

doi:10.3901/JME.2024.10.086

机械工程学报 ›› 2024, Vol. 60 ›› Issue (10): 86-101.doi: 10.3901/JME.2024.10.086

扫码分享

基于博弈论的右转无信号交叉口行人行为模拟

李文礼^1,2, 张祎楠¹, 石晓辉¹, 王梦昕¹

1. 重庆理工大学汽车零部件先进制造技术教育部重点实验室重庆 400054;
2. 重庆长安汽车股份有限公司重庆 400020

收稿日期:2023-05-30 修回日期:2024-01-20 出版日期:2024-05-20 发布日期:2024-07-24
作者简介:李文礼(通信作者),男,1983年出生,博士,副教授,硕士研究生导师。主要研究方向为智能交通模拟、智能汽车测试理论与方法、汽车安全测试与仿真。
E-mail:liwenli@cqut.edu.cn
张祎楠,男,1999年出生。主要研究方向为行人-车辆交互机理与行为轨迹模拟。
E-mail:zhangyinan@stu.cqut.edu.cn
石晓辉,男,1963年出生,博士,教授,博士研究生导师。主要研究方向为汽车摩托车试验检测技术及装备、汽车传动系统动态模拟试验技术、虚拟试验技术。
E-mail:shixiaohui@cqut.edu.cn
王梦昕,女,1999年出生。主要研究方向为智能网联汽车与行人行为。
E-mail:51220402113@stu.cqut.edu.cn
基金资助:
重庆市自然科学基金(cstc2021jcyj-msxmX0183)、重庆市留学人员回国创业创新支持计划(CX2021070)、重庆市教委科学技术研究(KJQN202201170)和重庆市技术创新与应用发展专项重大(CSTB2022TIAD-STX0003)资助项目。

Game Theory-based Simulation of Pedestrian Behavior at Right-turn Unsignalized Intersections

LI Wenli^1,2, ZHANG Yinan¹, SHI Xiaohui¹, WANG Mengxin¹

1. Key Laboratory of Advanced Manufacturing Technology for Automobile Parts, Ministry of Education, Chongqing University of Technology, Chongqing 400054;
2. Chongqing Changan Automobile Co., Ltd., Chongqing 400020

Received:2023-05-30 Revised:2024-01-20 Online:2024-05-20 Published:2024-07-24

摘要/Abstract

摘要： 为逼真模拟行人-车辆交互的真实交通场景，融合博弈理论和数据驱动的思想，在逆强化学习和博弈论的基础上提出博弈—深度最大熵逆强化学习算法(Game-deep max entropy inverse reinforcement learning，G-DMIRL)。将行人建模为智能体，通过真实的行人-车辆交互轨迹获取不同博弈决策下的行人的奖励函数，并推断行人-车辆交互的博弈机制，利用获取的奖励函数和动作策略开发出行人行为模拟模型。仿真结果表明，开发的模型在有限状态下能够准确地模拟出不同决策下行人的行为动作，建立的行人-车辆交通场景能够为自动驾驶汽车的识别、预测与路径规划算法的开发验证提供支撑。

关键词: 逆强化学习, 强化学习, 行人-车辆交互, 博弈论, 右转交叉口

Abstract: In order to realistically simulate the real traffic scene of pedestrian-vehicle interaction, this study integrates game theory and data-driven ideas, and proposes a game-deep maximum entropy inverse reinforcement learning algorithm(G-DMIRL), modeling pedestrians as intelligent bodies, obtaining the reward functions of pedestrians under different game decisions through real pedestrian-vehicle interaction trajectories, and inferring the game mechanism of pedestrian-vehicle interaction, and developing a simulation model of pedestrian behavior by using the obtained reward functions and action strategies. The simulation results show that the developed model can accurately simulate the behavioral actions of pedestrians under different decisions in a finite state, and the established pedestrian-vehicle traffic scenario can provide support for the development and validation of recognition, prediction and path planning algorithms for self-driving cars.

Key words: inverse reinforcement learning, reinforcement learning, human-vehicle interaction, game theory, right-turn intersection

中图分类号:

U492
TP391

李文礼, 张祎楠, 石晓辉, 王梦昕. 基于博弈论的右转无信号交叉口行人行为模拟[J]. 机械工程学报, 2024, 60(10): 86-101.

LI Wenli, ZHANG Yinan, SHI Xiaohui, WANG Mengxin. Game Theory-based Simulation of Pedestrian Behavior at Right-turn Unsignalized Intersections[J]. Journal of Mechanical Engineering, 2024, 60(10): 86-101.

参考文献

[1] 彭金栓，赵刘昌，杨欢欢. 行人过街风格多参数融合识别[J]. 交通运输系统工程与信息，2022，22(5):215-222. PENG Jinshuan，ZHAO Liuchang，YANG Huanhuan. Multi-parameter fusion recognition of pedestrian crossing style[J]. Transportation System Engineering and Information，2022，22(5):215-222.
[2] WHO. Global status report on road safety 2018[EB/OL]. https://www.who.int/publications/i/item/9789241565684,2018-06-17.
[3] 中华人民共和国国家统计局. 中国统计年鉴2021[M].北京:中国统计出版社，2022. National Bureau of Statistics of China. China statistical yearbook2022[M]. Beijing:China Statistics Press，2022.
[4] 吕伟，郭伏，任增根，等. 行人与高级自动驾驶汽车的交互研究综述——基于行人视角[J]. 工业工程与管理，2022，27(6):75-85. LÜ Wei，GUO Fu，REN Zenggen，et al. A review of interaction research between pedestrians and advanced autonomous vehicles—Based on the perspective of pedestrians[J]. Industrial Engineering and Management，2022，27(6):75-85.
[5] VIZZARI G，CROCIANI L，BANDINI S. An agent-based model for plausible wayfinding in pedestrian simulation[J]. Engineering Applications of Artificial Intelligence，2020，87:103241.
[6] 邓伟文，李江坤，任秉韬，等. 面向自动驾驶的仿真场景自动生成方法综述[J]. 中国公路学报，2022，35(1):316-333. DENG Weiwen，LI Jiangkun，REN Bingtao，et al. A review of automatic generation methods for simulation scenarios for autonomous driving[J]. Journal of China Highway and Transportation Society，2022，35(1):316-333.
[7] 朱冰，张培兴，赵健，等. 基于场景的自动驾驶汽车虚拟测试研究进展[J]. 中国公路学报，2019，32(6):1-19. ZHU Bing，ZHANG Peixing，ZHAO Jian，et al. Research progress on scenario-based virtual testing of autonomous vehicles[J]. Journal of China Highway and Road Research，2019，32(6):1-19.
[8] DIAS C，IRYO-ASANO M，NISHIUCHI H，et al. Calibrating a social force based model for simulating personal mobility vehicles and pedestrian mixed traffic[J]. Simulation Modelling Practice and Theory，2018，87:395-411.
[9] NAGEL K，SCHRECKENBERG M. A cellular automaton model for freeway traffic[J]. Journal de Physique I，1992，2(12):2221-2229.
[10] HELBING D，MOLNAR P. Social force model for pedestrian dynamics[J]. Physical Review E，1995，51(5):4282.
[11] BLUE V J，ADLER J L. Cellular automata microsimulation for modeling bi-directional pedestrian walkways[J]. Transportation Research Part B:Methodological，2001，35(3):293-312.
[12] LIU Q，SUN J，TIAN Y，et al. Modeling and simulation of overtaking events by heterogeneous non-motorized vehicles on shared roadway segments[J]. Simulation Modelling Practice and Theory，2020，103:102072.
[13] ALSALEH R，SAYED T. Microscopic modeling of cyclists interactions with pedestrians in shared spaces:A Gaussian process inverse reinforcement learning approach[J]. Transportmetrica A:Transport Science，2022，18(3):828-854.
[14] BJØRNSKAU T. The zebra crossing game–using game theory to explain a discrepancy between road user behaviour and traffic rules[J]. Safety Science，2017，92:298-301.
[15] ZHU D，SZE N N. Propensities of red light running of pedestrians at the two-stage crossings with split pedestrian signal phases[J]. Accident Analysis & Prevention，2021，151:105958.
[16] AMINI R E，DHAMANIYA A，ANTONIOU C. Towards a game theoretic approach to model pedestrian road crossings[J]. Transportation Research Procedia，2021，52:692-699.
[17] HOLT C A，ROTH A E. The Nash equilibrium:A perspective[J]. Proceedings of the National Academy of Sciences，2004，101(12):3999-4002.
[18] NASH J. Two-person cooperative games[J]. Econometrica:Journal of the Econometric Society，1953:128-140.
[19] NASH J. Non-cooperative games[M]. London:Edward Elgar Publishing，1996.
[20] BAŞAR T，OLSDER G J. Dynamic noncooperative game theory[M]. New York:Society for Industrial and Applied Mathematics，1998.
[21] NOWAK M A，MAY R M. Evolutionary games and spatial chaos[J]. Nature，1992，359(6398):826-829.
[22] WU W J，CHEN R C，JIA H，et al. Game theory modeling for vehicle–pedestrian interactions and simulation based on cellular automata[J]. International Journal of Modern Physics C，2019，30(4):1950025.
[23] YANG C，WANG J，DONG J. Capacity model of exclusive right-turn lane at signalized intersection considering pedestrian-vehicle interaction[J]. Journal of Advanced Transportation，2020，2020:1-19.
[24] ZHANG R，WEI Z，GU H，et al. Behavior evolution of multi-group in the process of pedestrian crossing based on evolutionary game theory[J]. Sustainability，2021，13(4):2009.
[25] RAHMATI Y，TALEBPOUR A，MITTAL A，et al. Game theory-based framework for modeling human–vehicle interactions on the road[J]. Transportation Research Record，2020，2674(9):701-713.
[26] ZHANG Y，CHAI Z，LYKOTRAFITIS G. Deep reinforcement learning with a particle dynamics environment applied to emergency evacuation of a room with obstacles[J]. Physica A:Statistical Mechanics and Its Applications，2021，571:125845.
[27] MOHAMMED H，SAYED T，BIGAZZI A. Microscopic modeling of cyclists on off-street paths:A stochastic imitation learning approach[J]. Transportmetrica A:Transport Science，2022，18(3):345-366.
[28] GETTMAN D，HEAD L. Surrogate safety measures from traffic simulation models[J]. Transportation Research Record，2003，1840(1):104-115.
[29] SHUMIN F，YULONG P E I. Analysis of vehicle delay on road sections on the condition of pedestrian crossing[J]. Journal of Transportation Systems Engineering and Information Technology，2007，7(3):73-77.
[30] ALMODFER R，XIONG S，FANG Z，et al. Quantitative analysis of lane-based pedestrian-vehicle conflict at a non-signalized marked crosswalk[J]. Transportation Research Part F:Traffic Psychology and Behaviour，2016，42:468-478.
[31] GUO Y，SAYED T，ZHENG L. A hierarchical bayesian peak over threshold approach for conflict-based before-after safety evaluation of leading pedestrian intervals[J]. Accident Analysis & Prevention，2020，147:105772.
[32] ZHANG Y，FRICKER J D. Incorporating conflict risks in pedestrian-motorist interactions:A game theoretical approach[J]. Accident Analysis & Prevention，2021，159:106254.
[33] CHANDLER R E，HERMAN R，MONTROLL E W. Traffic dynamics:Studies in car following[J]. Operations Research，1958，6(2):165-184.
[34] GAZIS D C，HERMAN R，ROTHERY R W. Nonlinear follow-the-leader models of traffic flow[J]. Operations Research，1961，9(4):545-567.
[35] HUSSEIN M，SAYED T. A bi-directional agent-based pedestrian microscopic model[J]. Transportmetrica A:Transport Science，2017，13(4):326-355.
[36] WANG W L，LO S M，LIU S B，et al. Microscopic modeling of pedestrian movement behavior:Interacting with visual attractors in the environment[J]. Transportation Research Part C:Emerging Technologies，2014，44:21-33.
[37] TEKNOMO K. Application of microscopic pedestrian simulation model[J]. Transportation Research Part F:Traffic Psychology and Behaviour，2006，9(1):15-27.
[38] NASERNEJAD P，SAYED T，ALSALEH R. Modeling pedestrian behavior in pedestrian-vehicle near misses:A continuous Gaussian process inverse reinforcement learning (GP-IRL) approach[J]. Accident Analysis & Prevention，2021，161:106355.
[39] SUTTON R S，BARTO A G. Reinforcement learning:An introduction[M]. Cambridge:MIT Press，2018.
[40] ZIEBART B D，MAAS A L，BAGNELL J A，et al. Maximum entropy inverse reinforcement learning[C]//AAAI，2008，8:1433-1438.
[41] WULFMEIER M，ONDRUSKA P，POSNER I. Maximum entropy deep inverse reinforcement learning[J]. arXiv Preprint arXiv:1507.04888，2015.

基于博弈论的右转无信号交叉口行人行为模拟

Game Theory-based Simulation of Pedestrian Behavior at Right-turn Unsignalized Intersections

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]	王无印, 黄子钊, 庄子龙, 方怀瑾, 秦威. 基于深度强化学习的自动化码头堆场场桥调度方法[J]. 机械工程学报, 2024, 60(6): 44-57.
[2]	赵阔, 王皂琦, 潘臻信, 潘扬华, 张中飞, 屈挺. 大数据驱动的快消品终端拜访“云-边”联动决策与优化[J]. 机械工程学报, 2024, 60(6): 58-68.
[3]	唐小林, 杨剑英, 杨凯, 李文博. 面向无信号灯十字路口的自动驾驶多车协同控制方法研究[J]. 机械工程学报, 2024, 60(20): 217-228.
[4]	郭景华, 李文昌, 王班, 王靖瑶. 基于深度强化学习的网联混合动力汽车队列控制[J]. 机械工程学报, 2024, 60(2): 262-271.
[5]	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.
[6]	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.
[7]	崔宇朋, 余杨, 韦明秀, 李振眠, 余建星. 改进博弈论四重组合赋权法下的开口甲板多目标拓扑优化设计[J]. 机械工程学报, 2023, 59(9): 263-273.
[8]	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.
[9]	郭洪飞, 陆鑫宇, 任亚平, 张超勇, 李建庆. 基于强化学习的群体进化算法求解双边多目标同步并行拆解线平衡问题[J]. 机械工程学报, 2023, 59(7): 355-366.
[10]	郑湃, 李成熙, 殷悦, 张荣, 鲍劲松, 王柏村, 谢海波, 王力翚. 增强现实辅助的互认知人机安全交互系统[J]. 机械工程学报, 2023, 59(6): 173-184.
[11]	娄山河, 冯毅雄, 郑浩, 胡炳涛, 洪兆溪, 谭建荣. 模拟人脑工作机制的机械产品概念设计行为原理启发求解方法[J]. 机械工程学报, 2023, 59(24): 344-358.
[12]	马丽莹, 魏云冰. 基于DDPG算法的发电企业报价策略研究[J]. 电气工程学报, 2023, 18(2): 192-200.
[13]	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.
[14]	钟沛成, 骆德渊, 庞明君. 基于深度强化学习的四足机器人跟随策略研究及系统实现[J]. 机械工程学报, 2023, 59(13): 79-88.
[15]	顾文斌, 李育鑫, 刘斯麒, 苑明海, 裴凤雀. 数据驱动的智慧车间实时调度方法研究[J]. 机械工程学报, 2023, 59(12): 47-61.