面向无信号灯十字路口场景的自动驾驶安全决策方法研究

doi:10.3901/JME.2024.10.147

机械工程学报 ›› 2024, Vol. 60 ›› Issue (10): 147-159.doi: 10.3901/JME.2024.10.147

扫码分享

面向无信号灯十字路口场景的自动驾驶安全决策方法研究

杨凯, 唐小林, 钟桂川, 王明, 李国法, 胡晓松

重庆大学机械与运载工程学院重庆 400044

收稿日期:2023-06-20 修回日期:2024-01-15 出版日期:2024-05-20 发布日期:2024-07-24
作者简介:杨凯,男,1995年出生,博士研究生。主要研究方向为自动驾驶安全决策与控制。
E-mail:kaiyang0401@cqu.edu.cn
唐小林(通信作者),男,1984年出生,博士,教授,博士研究生导师。主要研究方向为智能网联新能源汽车决策规划与节能控制。
E-mail:tangxl0923@cqu.edu.cn
基金资助:
国家自然科学基金(52222215，52072051)和重庆市自然科学基金(CSTB2023NSCQ-JQX0003)资助项目。

Research on Safe Decision-making for Autonomous Driving at Unsignalized Intersections

YANG Kai, TANG Xiaolin, ZHONG Guichuan, WANG Ming, LI Guofa, HU Xiaosong

College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044

Received:2023-06-20 Revised:2024-01-15 Online:2024-05-20 Published:2024-07-24

摘要/Abstract

摘要： 针对环境遮挡与交通参与者行为随机导致的驾驶风险，提出一种面向无信号灯十字路口场景的安全决策方法。首先，建立一种基于值分布式强化学习-全参数化分位数网络(Fully parameterized quantile network，FPQN)的基础决策策略。其次，融合FPQN建模的累积回报分布与条件风险价值函数(Conditional value at risk，CVaR)，进而构建具有驾驶风险意识的安全决策策略。再次，引入集成学习理论(Ensemble)，建立基于集成FPQN的决策不确定性估计框架EFPQN，能够实时量化决策风险。同时，为应对决策不确定性较高带来的驾驶风险，设计基于模型预测控制的备选策略以提升安全性。最后，采用SUMO仿真平台搭建无信号灯十字路口场景，对提出的安全决策方法进行验证。试验结果表明，与基准方法相比，所提出的方法能够有效降低遮挡与交通参与者行为随机导致的驾驶风险。

关键词: 无信号灯十字路口, 环境遮挡, 偶然不确定性, 未知场景, 认知不确定性

Abstract: Proposes a safe decision-making method for unsignalized intersections, focusing on driving risks caused by environmental occlusion and the random behaviors of traffic participants. Firstly, a fundamental decision-making policy is established based on the value-distributional reinforcement learning-fully parameterized quantile network(FPQN). Secondly, the cumulative reward distribution modeled by FPQN and conditional value at risk(CVaR) are integrated to construct a driving risk-aware decision-making policy. Thirdly, the ensemble learning theory is introduced to establish the decision-making uncertainty estimation framework based on ensemble FPQN(EFPQN), which can quantify decision risks in real-time. Meanwhile, to handle the driving risk induced by high decision-making uncertainty, a model predictive control-based backup strategy is designed. Finally, the proposed safe decision-making method is validated using the SUMO simulation platform in an unsignalized intersection scenario. Experimental results show that the proposed method effectively reduces driving risks caused by environmental occlusion and random behaviors of traffic participants compared with baseline methods.

Key words: unsignalized intersections, environmental occlusion, aleatoric uncertainty, unknown scenario, epistemic uncertainty

中图分类号:

U461

杨凯, 唐小林, 钟桂川, 王明, 李国法, 胡晓松. 面向无信号灯十字路口场景的自动驾驶安全决策方法研究[J]. 机械工程学报, 2024, 60(10): 147-159.

YANG Kai, TANG Xiaolin, ZHONG Guichuan, WANG Ming, LI Guofa, HU Xiaosong. Research on Safe Decision-making for Autonomous Driving at Unsignalized Intersections[J]. Journal of Mechanical Engineering, 2024, 60(10): 147-159.

参考文献

[1] 李克强，戴一凡，李升波，等. 智能网联汽车(ICV)技术的发展现状及趋势[J]. 汽车安全与节能学报，2017，8(1):1-14. LI Keqiang，DAI Yifan，LI Shengbo，et al. State-of-the-artand technical trends of intelligent and connected vehicles[J]. Journal of Automotive Safety and Energy，2017，8(1):1-14.
[2] BOARD N T S. Collision between vehicle controlled by developmental automated driving system and pedestrian[EB/OL]. [2023-04-14]. https://www.ntsb.gov/investigations/AccidentReports/Reports/HAR1903.pdf.
[3] HO S S. Complementary and competitive framing of driverless cars:Framing effects，attitude volatility，or attitude resistance?[J]. International Journal of Public Opinion Research，2021，33(3):512-531.
[4] BRITO B，AGARWAL A，ALONSO-MORA J. Learning interaction-aware guidance for trajectory optimization in dense traffic scenarios[J]. IEEE Transactions on Intelligent Transportation Systems，2022，22(10):18808-18821.
[5] SCHWARTING W，ALONSO-MORA J，RUS D. Planning and decision-making for autonomous vehicles[J]. Annual Review of Control，Robotics，and Autonomous Systems，2018，1:187-210.
[6] ZHANG M，LI N，GIRARD A，et al. A finite state machine based automated driving controller and its stochastic optimization[C]//Dynamic Systems and Control Conference. Tysons，Virginia，USA:ASME，2017:V002T07A002.
[7] BUEHLER M，IAGNEMMA K，SINGH S. The DARPA urban challenge:Autonomous vehicles city traffic[M]. Berlin:Springer，2009.
[8] 阳鑫，唐小林，杨凯，等. 极限工况下无人驾驶车辆运动规划策略研究[J]. 机械工程学报，2022，58(22):349-359. YANG Xin，TANG Xiaolin，YANG Kai，et al. Research on the motion planning strategy for autonomous vehicles in extreme conditions[J]. Journal of Mechanical Engineering，2022，58(22):349-359.
[9] QIAN X，NAVARRO I，DE LA FORTELLE A，et al. Motion planning for urban autonomous driving using Bézier curves and MPC[C]//2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). Rio de Janeiro，Brazil:IEEE，2016:826-833.
[10] HUANG Y，WANG H，KHAJEPOUR A，et al. A novel local motion planning framework for autonomous vehicles based on resistance network and model predictive control[J]. IEEE Transactions on Vehicular Technology，2019，69(1):55-66.
[11] ZHANG C，STEINHAUSER F，HINZ G，et al. Traffic mirror-aware POMDP behavior planning for autonomous urban driving[C]//2022 IEEE Intelligent Vehicles Symposium (IV). Aachen:IEEE，2022:323-330.
[12] QIAO Z，MUELLING K，DOLAN J，et al. Pomdp and hierarchical options mdp with continuous actions for autonomous driving at intersections[C]//2018 21st International Conference on Intelligent Transportation Systems (ITSC). Maui，HI:IEEE，2018:2377-2382.
[13] BAI H，HSU D，LEE W S. Integrated perception and planning in the continuous space:A POMDP approach[J]. The International Journal of Robotics Research，2014，33(9):1288-1302.
[14] BRECHTEL S，GINDELE T，DILLMANN R. Probabilistic decision-making under uncertainty for autonomous driving using continuous POMDPs[C]//17th International IEEE Conference on Intelligent Transportation Systems (ITSC). Qingdao:IEEE，2014:392-399.
[15] ZHU Z，ZHAO H. A survey of deep RL and IL for autonomous driving policy learning[J]. IEEE Transactions on Intelligent Transportation Systems，2021，23(9):14043-14065.
[16] ISELE D，RAHIMI R，COSGUN A，et al. Navigating occluded intersections with autonomous vehicles using deep reinforcement learning[C]//2018 IEEE International Conference on Robotics and Automation (ICRA). Brisbane，QLD，Australia:IEEE，2018:2034-2039.
[17] TRAM T，JANSSON A，GRÖNBERG R，et al. Learning negotiating behavior between cars in intersections using deep Q-learning[C]//2018 21st International Conference on Intelligent Transportation Systems (ITSC). Maui，HI:IEEE，2018:3169-3174.
[18] TREIBER M，HENNECKE A，HELBING D. Congested traffic states in empirical observations and microscopic simulations[J]. Physical Review E，2000，62(2):1805.
[19] DABNEY W，OSTROVSKI G，SILVER D，et al. Implicit quantile networks for distributional reinforcement learning[C]//35th International Conference on Machine Learning (ICML). Stockholm:ACM，2018:1096-1105.
[20] YANG D，ZHAO L，LIN Z，et al. Fully parameterized quantile function for distributional reinforcement learning[J]. Advances in Neural Information Processing Systems，2019，32:6193-6202.
[21] VON NEUMANN J，MORGENSTERN O. Theory of games and economic behavior[M]. Princeton:Princefon Princeton University Press, 2007.
[22] CHAPMAN M P，BONALLI R，SMITH K M，et al. Risk-sensitive safety analysis using conditional value-at-risk[J]. IEEE Transactions on Automatic Control，2021，67(12):6521-6536.
[23] BERNHARD J，POLLOK S，KNOLL A. Addressing inherent uncertainty:Risk-sensitive behavior generation for automated driving using distributional reinforcement learning[C]//2019 IEEE Intelligent Vehicles Symposium (IV). Paris:IEEE，2019:2148-2155.
[24] HOEL C J，WOLFF K，LAINE L. Tactical decision-making in autonomous driving by reinforcement learning with uncertainty estimation[C]//2020 IEEE Intelligent Vehicles Symposium (IV). Las Vegas:IEEE，2020:1563-1569.
[25] HOEL C J，WOLFF K，LAINE L. Ensemble quantile networks:Uncertainty-aware reinforcement learning with applications in autonomous driving[J]. IEEE Transactions on Intelligent Transportation Systems，2023，24(6):6030-6041.
[26] ZANELLI A，DOMAHIDI A，JEREZ J，et al. FORCES NLP:An efficient implementation of interior-point methods for multistage nonlinear nonconvex programs[J]. International Journal of Control，2020，93(1):13-29.

面向无信号灯十字路口场景的自动驾驶安全决策方法研究

Research on Safe Decision-making for Autonomous Driving at 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 3

编辑推荐

Metrics

本文评价

[1]	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.
[2]	韦新鹏, 姚中洋, 宝文礼, 张哲, 姜潮. 一种基于主动学习克里金模型的证据理论可靠性分析方法[J]. 机械工程学报, 2024, 60(2): 356-368.
[3]	夏侯唐凡, 刘宇, 张皓冬, 张成林. 考虑认知不确定性的多状态系统Birnbaum重要度分析方法[J]. 机械工程学报, 2018, 54(8): 223-232.