摘 要:智能驾驶行为决策系统的构建对智能驾驶的可靠性具有重要影响。本文对国内外学者所提出的智能驾驶行为决策系统构建方法进行了分析总结,归纳总结不同方法的不足,并针对各方法的不足提出了解决方法,指出了未来的发展趋势,以对智能驾驶行为决策系统的构建提供一定的参考意义。
关键词:智能驾驶;行为决策;有限状态机;学习算法
中图分类号:TP301.6 文献标识码:A 文章编号:2096-4706(2019)24-0191-03
Research on Intelligent Vehicle Driving Behavior Decision-making Method
ZHAO Zhicheng,HUA Yiding,WANG Wenyang,CHEN Zheng
(China Automotive Technology and Research Center Co.,Ltd,Tianjin 300300,China)
Abstract:The construction of intelligent driving behavior decision system has an important influence on the reliability of intelligent driving. This paper analyzes and summarizes the construction methods of intelligent driving behavior decision-making system proposed by scholars at home and abroad,this paper sums up the shortcomings of different methods,puts forward solutions to the shortcomings of each method,and points out the future development trend,so as to provide some reference for the construction of intelligent driving behavior decision system.
Keywords:intelligent driving;behavior decision;finite state machine;learning algorithm
参考文献:
[1] 陈佳佳. 城市环境下无人驾驶车辆决策系统研究 [D]. 合肥:中国科学技术大学,2014.
[2] KATRAKAZAS C,QUDDUS M,CHEN W H,et al. Realtime motion planning methods for autonomous on-road driving:Stateof-the-art and future research directions [J]. Transportation Research Part C:Emerging Technologies,2015(60):416-442.
[3] OKUMURA B ,JAMES M R ,KANZAWA Y ,et al. Challenges in perception and decision making for intelligent automotivevehicles:a case study [J].IEEE Transactions on Intelligent Vehicles,2016,1(1):20-32.
[4] KURT A,ÖZGÜNER Ü.Hierarchical finite state machines for autonomous mobile systems [J]. Control Engineering Practice,2013,21(2):184-194.
[5] 陈雪梅,田赓,苗一松,等. 城市环境下无人驾驶车辆驾驶规则获取及决策算法 [J]. 北京理工大学学报,2017,37(5):491-496.
[6] 熊光明,李勇,王诗源. 基于有限状态机的智能车辆交叉口行为预测与控制 [J]. 北京理工大学学报,2015,35(1):34-38.
[7] 熊璐,黄少帅,王龙祥,等. 基于有限状态机的差动转向无人车整车控制策略设计 [J]. 制造业自动化,2015,37(19):146-152.
[8] 冯关明,胡大宏,吴壮文. 基于FSM 理论的模糊自适应控制汽车巡航系统仿真与设计 [J]. 机械科学与技术,2012,31(3):446-451.
[9] 冀杰,黄岩军,李云伍,等. 基于有限状态机的车辆自动驾驶行为决策分析 [J]. 汽车技术,2018(12):1-7.
[10] You Y R,Pan X L,Wang Z Y,et al. Virtual to real reinforcement learning for autonomous driving [J/OL].arXiv:1704.03952 [cs.AI](2017-04-13). https://arxiv.org/abs/1704.03952.
[11] SHALEV-SHWARTZ S,SHAMMAH S,SHASHUA A.Safe,multi-agent,reinforcement learning for autonomous driving [J/OL].arXiv:1610.03295 [cs.AI](2016-10-11). https://arxiv.org/abs/1610.03295v1.
[12] ZHENG R,LIU C,GUO Q. A decision-making method for autonomous vehicles based on simulation and reinforcement learning [C]//2013 International Conference on Machine Learning and Cybernetics.IEEE,2013.
[13] BOJARSKI M,DEL TESTA D,DWORAKOWSKI D,et al. End to end learning for self-driving cars [J/OL]. arXiv:1604.07316 [cs.CV](2016-04-25). https://arxiv.org/abs/1604.07316.
[14] OLIVER N,PENTLAND AP. Graphical models for driver behavior recognition in a SmartCar [C]// Intelligent Vehicles Symposium,2000. IV 2000. Proceedings of the IEEE. S.l.:s.n.,2000:7-12.
[15] VACEK S,GINDELE T,ZOLLNER J M,et al. Using case-based reasoning for autonomous vehicle guidance [C]//2007 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE,2007.
[16] 杜明博. 基于人类驾驶行为的无人驾驶车辆行为决策与运动规划方法研究 [D]. 合肥:中国科学技术大学,2016.
[17] 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.
[18] FURDA A,VLACIC L. Enabling Safe Autonomous Driving in Real-World City Traffic Using Multiple Criteria Decision Making [J].IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE,2011,3(1):4-17.
作者简介:赵志成(1985.09-),男,汉族,天津人,高级工程师,工学学士,研究方向:智能网联汽车。