考虑社会性行为的自动驾驶运动规划研究综述

doi:10.3901/JME.2024.10.112

摘要/Abstract

摘要： 目前自动驾驶技术正处于从园区内示范运营向开放场景的大规模市场应用过渡的关键阶段。自动驾驶车辆若想应用于人们的日常生活，必将与人类驾驶的车辆在道路上长期共存，这势必会产生大量的交互场景，而如何恰当地与人类驾驶的车辆进行交互，则成为提升驾乘人员体验感及其对自动驾驶接受度的关键。人类的交互基于其社会属性，自动驾驶也应如此。但目前尚未有相关领域的完善综述。鉴于此，梳理其来龙去脉与最新进展。依次探讨传统方法所面临的驾驶困境、驾驶员社会性行为机理的相关研究和考虑社会属性的运动规划方法的最新进展与应用案例。在此基础上，总结现有方法的不足并对未来的研究方向进行展望。分析表明，结合社会学等领域的理论工具，分析驾驶员在复杂交通流中的社会性行为机理，并基于此构建符合大众预期的驾驶行为自动化决策体系，是未来自动驾驶社会性运动规划的主要研究方向。此外，进一步建立健全自动驾驶社会性行为的评价体系，同样对智能汽车的社会性人性化设计具有重要意义。

关键词: 自动驾驶, 社会属性, 运动规划, 交互行为, 混合交通流

Abstract: At present, autonomous driving technology is at a critical stage of transition from demonstration operations in parks to large-scale market applications in open scenarios. If self-driving vehicles are to be used in people's daily lives, they are bound to coexist with human-driven vehicles on the road for a long time, which inevitably generates a large number of interaction scenarios, and how to properly interact with human-driven vehicles becomes the key to improving the driver's experience and their acceptance of autonomous driving. Human interaction is based on its social attributes, and so should autonomous vehicles. However, there is no comprehensive review in this area. In light of this, the ins and outs and recent developments are reviewed. The driving dilemma faced by traditional methods, the research on the mechanism of driver social behaviour, and the recent progress and application cases of motion planning methods considering social attributes are discussed in turn. On this basis, the shortcomings of the existing methods are summarized and future research directions are prospected. The analysis shows that combining theoretical tools from sociology and other fields, analysing drivers’ social behavioural mechanisms in complex traffic flows, and constructing an automated decision-making system for driving behaviour that meets public expectations based on this is the main research direction for future social motion planning for autonomous driving. In addition, further establis0hing a sound evaluation system for the social behaviour of autonomous driving is equally important for the social humanization design of intelligent vehicles.

Key words: autonomous vehicles, social compliance, motion planning, interaction behaviour, new mixed traffic flow

中图分类号:

U46
TP399

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.

GAO Zhenhai, YU Tong, SUN Tianjun. Review on Autonomous Vehicle Motion Planning Methods Considering Social Behavior[J]. Journal of Mechanical Engineering, 2024, 60(10): 112-128.

参考文献

[1] PADEN B，CAP M，YONG S Z，et al. A survey of motion planning and control techniques for self-driving urban vehicles[J]. IEEE Transactions on Intelligent Vehicles，2016，1(1):33-55.
[2] GAO Z，YU T，SUN T，et al. Data filtering method for intelligent vehicle shared autonomy based on a dynamic time warping algorithm[J]. Sensors，2022，22(23):9436.
[3] SALLET J. On the evolutionary roots of human social cognition[J]. Neurosci Biobehav Rev，2022，137:104632.
[4] 赫伯特・金迪斯，萨缪・鲍尔斯. 人类的趋社会性及其研究:一个超越经济学的经济分析[M]. 上海:上海人民出版社，2006. HERBERT G，SAMUEL B. Human sociality and its study:An economic analysis beyond economics[M]. Shanghai:Shanghai People's Publishing House，2006.
[5] 周业安. 人的社会性与偏好的微观结构[J]. 学术月刊，2017，49(6):59-73. ZHOU Yean. The microstructure of human sociality and preference[J]. Academic Monthly，2017，49(6):59-73.
[6] KAHNEMAN D，TVERSKY A. Prospect theory-analysis of decision under risk[J]. Econometrica，1979，47(2):263-291.
[7] EFRATI A. Waymo's big ambitions slowed by tech trouble[J]. The Information，2018，8:1-7.
[8] TOGHI B，VALIENTE R，SADIGH D，et al. Social coordination and altruism in autonomous driving[J]. IEEE Transactions on Intelligent Transportation Systems，2022，23(12):24791-24804.
[9] FERRER G，GARRELL A，SANFELIU A. Robot companion:A social-force based approach with human awareness-navigation in crowded environments[C]//2013 IEEE/RSJ International Conference on Intelligent Robots and Systems，2013:1688-1694.
[10] KRETZSCHMAR H，SPIES M，SPRUNK C，et al. Socially compliant mobile robot navigation via inverse reinforcement learning[J]. The International Journal of Robotics Research，2016，35(11):1289-1307.
[11] VEMULA A，MUELLING K，OH J. Social attention:Modeling attention in human crowds[C]//2018 IEEE International Conference on Robotics and Automation (ICRA)，2018:4601-4607.
[12] LI C，TRINH T，WANG L，et al. Efficient game-theoretic planning with prediction heuristic for socially-compliant autonomous driving[J]. IEEE Robotics and Automation Letters，2022，7(4):10248-10255.
[13] SCHWARTING W，PIERSON A，ALONSO-MORA J，et al. Social behavior for autonomous vehicles[J]. Proc Natl Acad Sci USA，2019，116(50):24972-24978.
[14] WANG L，SUN L，TOMIZUKA M，et al. Socially-compatible behavior design of autonomous vehicles with verification on real human data[J]. IEEE Robotics and Automation Letters，2021，6(2):3421-3428.
[15] 耿新力. 城区不确定环境下无人驾驶车辆行为决策方法研究[D]. 合肥:中国科学技术大学，2017. GENG Xinli. Research on behavior decision-making approaches for autonomous vehicle in urban uncertainly environments[D]. Heifei:University of Science and Technology of China，2017.
[16] BUEHLER M，IAGNEMMA K，SINGH S. The DARPA urban challenge:Autonomous vehicles in city traffic[M]. Berlin:Springer，2009.
[17] XIN J，WANG C，ZHANG Z，et al. China future challenge:Beyond the intelligent vehicle[J]. IEEE Intell. Transp. Syst. Soc. Newslett，2014，16(2):8-10.
[18] KAVRAKI L E，SVESTKA P，LATOMBE J C，et al. Probabilistic roadmaps for path planning in high-dimensional configuration spaces[J]. IEEE Transactions on Robotics and Automation，1996，12(4):566-580.
[19] LAVALLE S M，KUFFNER J J. Randomized kinodynamic planning[J].International Journal of Robotics Research，2001，20(5):378-400.
[20] URMSON C，SIMMONS R. Approaches for heuristically biasing RRT growth[C]//IROS 2003:Proceedings of The 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems，2003:1178-1183.
[21] SHKOLNIK A，WALTER M，TEDRAKE R，et al. Reachability-guided sampling for planning under differential constraints[C]//ICRA:2009 IEEE International Conference on Robotics and Automation， 2009:4387-4393.
[22] PENG C， LAVALLE S M. Reducing metric sensitivity in randomized trajectory design[C]//Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the Next Millennium，2001:43-48.
[23] KARAMAN S. Sampling-based algorithms for optimal path planning problems[D]. Cambridge:Massachusetts Institute of Technology，2012.
[24] KARAMAN S，FRAZZOLI E. Incremental sampling-based algorithms for optimal motion planning[C]//International Conference on Robotics Science and Systems，RSS，2011:267-274.
[25] KARAMAN S，FRAZZOLI E. Sampling-based algorithms for optimal motion planning[J]. International Journal of Robotics Research，2011，30(7):846-894.
[26] DIJKSTRA E W. A note on two problems in connexion with graphs[J]. Numerische Mathematik，1959，1(1):269-271.
[27] HART P E，NILSSON N J，RAPHAEL B. A formal basis for the heuristic determination of minimum cost paths[J]. IEEE Transactions on Systems Science and Cybernetics，1968，4(2):100-107.
[28] STENTZ A. Optimal and efficient path planning for partially-known environments[C]//Proceedings of the 1994 IEEE International Conference on Robotics and Automation，1994:3310-3317.
[29] LIKHACHEV M，GORDON G J，THRUN S. ARA*:Anytime A* with provable bounds on sub-optimality[J]. Advances in Neural Information Processing Systems，2003，16:1-8.
[30] AINE S，SWAMINATHAN S，NARAYANAN V，et al. Multi-Heuristic A*[J]. International Journal of Robotics Research，2016，35(1-3):224-243.
[31] 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，2020，69(1):55-66.
[32] LU H，ZONG Q，LAI S，et al. Real-time perception-limited motion planning using sampling-based mpc[J]. IEEE Transactions on Industrial Electronics，2022，69(12):13182-13191.
[33] ZIWEI Z，LING Z，YINONG L，et al. Structured road-oriented motion planning and tracking framework for active collision avoidance of autonomous vehicles[J]. Science China(Technological Sciences)，2021，64(11):2427-2440.
[34] WANG H，HUANG Y，KHAJEPOUR A，et al. Crash mitigation in motion planning for autonomous vehicles[J]. IEEE Transactions on Intelligent Transportation Systems，2019，20(9):3313-3323.
[35] 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.
[36] VON S H. Market structure and equilibrium[M]. Berlin:Springer Science & Business Media，2010.
[37] YU H，TSENG H E，LANGARI R. A human-like game theory-based controller for automatic lane changing[J]. Transportation Research Part C:Emerging Technologies，2018，88:140-158.
[38] LI N，OYLER D W，ZHANG M X，et al. Game theoretic modeling of driver and vehicle interactions for verification and validation of autonomous vehicle control systems[J]. IEEE Transactions on Control Systems Technology，2018，26(5):1782-1797.
[39] LIU K，LI N，TSENG H E，et al. Interaction-aware trajectory prediction and planning for autonomous vehicles in forced merge scenarios[J]. IEEE Transactions on Intelligent Transportation Systems，2022，24(1):474-488.
[40] LENZ D，KESSLER T，KNOLL A，et al. Tactical cooperative planning for autonomous highway driving using monte-carlo tree search[C]//2016 IEEE Intelligent Vehicles Symposium(IV)，2016:447-453.
[41] SMIRNOV N，LIU Y，VALIDI A，et al. A game theory-based approach for modeling autonomous vehicle behavior in congested，urban lane-changing scenarios[J]. Sensors，2021，21(4):1523.
[42] LIAO X，ZHAO X，WANG Z，et al. Game theory-based ramp merging for mixed traffic with unity-sumo co-simulation[J]. IEEE Transactions on Systems Man Cybernetics-systems，2022，52(9):5746-5757.
[43] HANG P，LV C，XING Y，et al. Human-like decision making for autonomous driving:A noncooperative game theoretic approach[J]. IEEE Transactions on Intelligent Transportation Systems，2021，22(4):2076-2087.
[44] HUBMANN C，BECKER M，ALTHOFF D，et al. Decision making for autonomous driving considering interaction and uncertain prediction of surrounding vehicles[C]//2017 28th IEEE Intelligent Vehicles Symposium，2017:1671-1678.
[45] KURNIAWATI H，HSU D，LEE W S. Sarsop:Efficient point-based POMDP planning by approximating optimally reachable belief spaces[C]//Robotics:Science and Systems，2008.
[46] HOERGER M，KURNIAWATI H. An on-line POMDP solver for continuous observation spaces[C]//2021 IEEE International Conference On Robotics And Automation，2021:7643-7649.
[47] SUNBERG Z，KOCHENDERFER M J. Improving automated driving through pomdp planning with human internal states[J]. IEEE Transactions on Intelligent Transportation Systems，2022，23(11):20073-20083.
[48] SHALEV-SHWARTZ S，SHAMMAH S，SHASHUA A. Safe，multi-agent，reinforcement learning for autonomous driving[EB/OL]. [2023-11-23]. https://arxiv.org/pdf/1610.03295.pdf.
[49] BAHERI A，NAGESHRAO S，TSENG H E，et al. Deep reinforcement learning with enhanced safety for autonomous highway driving[C]//IEEE Intelligent Vehicles Symposium，Proceedings，2020:1550-1555.
[50] LI H，LI N，KOLMANOVSKY I，et al. Energy-efficient autonomous vehicle control using reinforcement learning and interactive traffic simulations[C]//Proceedings of the American Control Conference，2020:3029-3034.
[51] SAXENA D M，BAE S，NAKHAEI A，et al. Driving in dense traffic with model-free reinforcement learning[C]//Proceedings-IEEE International Conference on Robotics and Automation，2020:5385-5392.
[52] LI G，LI S，LI S，et al. Deep reinforcement learning enabled decision-making for autonomous driving at intersections[J]. Automotive Innovation，2020，3(4):374-385.
[53] LENZ D，DIEHL F，LE M T，et al. Deep neural networks for markovian interactive scene prediction in highway scenarios[C]//2017 28th IEEE Intelligent Vehicles Symposium，2017:685-692.
[54] ZIEBART B D，MAAS A，BAGNELL J A，et al. Maximum entropy inverse reinforcement learning[C]//Proceedings of the National Conference on Artificial Intelligence，2008:1433-1438.
[55] KUDERER M，GULATI S，BURGARD W，et al. Learning driving styles for autonomous vehicles from demonstration[C]//2015 IEEE International Conference on Robotics And Automation，2015:2641-2646.
[56] PFEIFFER M，SCHWESINGER U，SOMMER H，et al. Predicting actions to act predictably:Cooperative partial motion planning with maximum entropy models[C]//2016 IEEE/RSJ International Conference on Intelligent Robots and Systems，2016:2096-2101.
[57] JOSEP H，ALOI S，SCHUMPETER J，et al. The general theory of employment，interest and money[J]. Journal of the American Statistical Association，1936，31:1-9.
[58] MORGENSTERN O，VON NEUMANN J. Theory of games and economic behavior[M]. Princeton:Princeton University Press，1953.
[59] BALLIET D P，PARKS C，JOIREMAN J J. Social value orientation and cooperation in social dilemmas:A meta-analysis[J]. Group Processes & Intergroup Relations，2009，12(4):533-547.
[60] MCCLINTOCK C G，ALLISON S T. Social value orientation and helping behavior[J]. Journal of Applied Social Psychology，1989，19(4):353-362.
[61] VAN L P A M. The pursuit of joint outcomes and equality in outcomes:An integrative model of social value orientation[J]. Journal of Personality and Social Psychology，1999，77(2):337-349.
[62] AU W T，KWONG J Y. Measurements and effects of social-value orientation in social dilemmas:A review[J]. APA PsycNet，2004:71-98.
[63] TVERSKY A，KAHNEMAN D. Availability:A heuristic for judging frequency and probability[J]. Cognitive Psychology，1973，5(2):207-232.
[64] TVERSKY A，KAHNEMAN D. Judgment under uncertainty:Heuristics and biases[J]. Science，1974，185(4157):1124-1131.
[65] RABIN M. Incorporating fairness into game theory and economics[J]. The American Economic Review，1993: 1281-1302.
[66] COOPER D J，KAGEL J H. Other-regarding preferences[J]. The Handbook of Experimental Economics，2016，2:217.
[67] CAMERER C F. Progress in behavioral game theory[J]. Journal of Economic Perspectives，1997，11(4):167-188.
[68] 王云，张畇彬. 社会偏好理论:争议与未来发展[J]. 学术月刊，2021，53(6):72-86. WANG Yun，ZHANG Yunbin. Social preference theory:Controversy and future development[J]. Academic Monthly，2021，53(6):72-86.
[69] GARY C，MATTHEW R. Understanding social preferences with simple tests[J]. Quarterly Journal of Economics，2002，117(3):817-869.
[70] KOCHER M G，POULSEN O，ZIZZO D J. Social preferences，accountability，and wage bargaining[J]. Social Choice and Welfare，2017，48(3):659-678.
[71] ZAIDEL D M. A modeling perspective on the culture of driving[J]. Accident Analysis & Prevention，1992，24(6):585-597.
[72] ABERG L，LARSEN L，GLAD A，et al. Observed vehicle speed and drivers' perceived speed of others[J]. Applied Psychology:An International Review，1997，46(3):287-302.
[73] HAGLUND M，ÅBERG L. Speed choice in relation to speed limit and influences from other drivers[J]. Transportation Research Part F:Traffic Psychology and Behaviour，2000，3(1):39-51.
[74] FLEITER J J，LENNON A，WATSON B. How do other people influence your driving speed? Exploring the “who” and the “how” of social influences on speeding from a qualitative perspective[J]. Transportation Research Part F:Traffic Psychology and Behaviour，2010，13(1):49-62.
[75] HELBING D，MOLNAR P. Social force model for pedestrian dynamics[J]. Physical Review E，1995，51(5):4282.
[76] SONG D，THARMARASA R，ZHOU G，et al. Multi-vehicle tracking using microscopic traffic models[J]. IEEE Transactions on Intelligent Transportation Systems，2019，20(1):149-161.
[77] MOHAMMADI S，KAMRANI M，KHATTAK A J，et al. Social influence on driver decisions using modeling and gossip algorithms[C/CD]//Transportation Research Board 98th Annual Meeting，2019.
[78] PILECKA M. Combined reformulation of bilevel programming problems[J]. Schedae Informaticae，2012， 21:65-79.
[79] LI Y，CHEN Y，WANG F. The impact of traffic environmental vision pressure on driver behaviour[J]. Journal of Advanced Transportation，2018，2018:4941605.
[80] RATSAMEE P，MAE Y，OHARA K，et al. Human-robot collision avoidance using a modified social force model with body pose and face orientation[J]. International Journal of Humanoid Robotics，2013，10(1):1350008.
[81] FERRER G，SANFELIU A. Proactive kinodynamic planning using the extended social force model and human motion prediction in urban environments[C/CD]//2014 IEEE/RSJ International Conference on Intelligent Robots and Systems，2014.
[82] LUBER M，SPINELLO L，SILVA J，et al. Socially-aware robot navigation:A learning approach[C]//2012 IEEE/RSJ International Conference on Intelligent Robots and Systems，2012:902-907.
[83] KUDERER M，KRETZSCHMAR H，SPRUNK C，et al. Feature-based prediction of trajectories for socially compliant navigation[C]//Robotics:Science and Systems，2012，8:193-200.
[84] SUN L，ZHAN W，TOMIZUKA M，et al. Courteous autonomous cars[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems，2018:663-670.
[85] KULLBACK S，LEIBLER R A. On information and sufficiency[J]. The Annals of Mathematical Statistics，1951，22(1):79-86.
[86] LI H H，MA W J. Confidence reports in decision-making with multiple alternatives violate the Bayesian confidence hypothesis[J]. Nature Communications，2020，11(1):1-11.
[87] SUN L，ZHAN W，CHAN C Y，et al. Behavior planning of autonomous cars with social perception[C]//2019 IEEE Intelligent Vehicles Symposium. IEEE，2019:207-213.
[88] SADIGH D，SASTRY S，SESHIA S A，et al. Planning for autonomous cars that leverage effects on human actions[C]//Robotics:Science & Systems，2016.
[89] SADIGH D，SASTRY S S，SESHIA S A，et al. Information gathering actions over human internal state[C]//2016 IEEE/RSJ International Conference on Intelligent Robots and Systems，2016:66-73.
[90] GALVAN M，REPISO E，SANFELIU A. Robot navigation to approach people using-spline path planning and extended social force model[C]//Iberian Robotics Conference，2019:15-27.
[91] FERNANDO T，DENMAN S，SRIDHARAN S，et al. Soft+ hardwired attention:An lstm framework for human trajectory prediction and abnormal event detection[J]. Neural Networks，2018，108:466-478.
[92] SHARMA S，KIROS R，SALAKHUTDINOV R. Action recognition using visual attention[C]//Neural Information Processing Systems (NIPS) Time Series Workshop，2015.
[93] ALAHI A，GOEL K，RAMANATHAN V，et al. Social LSTM:Human trajectory prediction in crowded spaces[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)，2016:961-971.
[94] GUPTA A，JOHNSON J，FEI-FEI L，et al. Social GAN: Socially acceptable trajectories with generative adversarial networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018:2255-2264.
[95] QUEHL J，HU H，TAS O S，et al. How good is my prediction? Finding a similarity measure for trajectory prediction evaluation[C]//IEEE International Conference on Intelligent Transportation Systems，2017:1-6.
[96] ALT H， GODAU M. Computing the fréchet distance between two polygonal curves[J]. International Journal of Computational Geometry & Applications，1995，5(1):75-91.
[97] SHALEV-SHWARTZ S，SHAMMAH S，SHASHUA A. On a formal model of safe and scalable self-driving cars[EB/OL]. [2018-10-27]. https://arxiv.org/abs/1708.06374.