期刊文献+

基于深度强化学习的车辆跟驰控制 被引量:24

A Car-following Control Algorithm Based on Deep Reinforcement Learning
原文传递
导出
摘要 针对自适应巡航控制系统在控制主车跟驰行驶中受前车运动状态的不确定性影响问题,在分析车辆运动特点的基础上.提出一种能够考虑前车运动随机性的跟驰控制策略。搭建驾驶人实车驾驶数据采集平台,招募驾驶人进行实车跟驰道路试验.建立驾驶人真实驾驶数据库。假设车辆未来时刻的加速度决策主要受前方目标车辆运动影响.建立基于双前车跟驰结构的主车纵向控制架构。将驾驶数据库中的驾驶数据分别视作前车和前前车运动变化历程,利用高斯过程算法建立了前车纵向加速度变化随机过程模型.实现对前方目标车运动状态分布的概率性建模。将车辆跟驰问题构建为一定奖励函数下的马尔可夫决策过程,引入深度强化学习研究主车跟驰控制问题。利用近端策略优化算法建立车辆跟驰控制策略.通过与前车运动随机过程模型进行交互式迭代学习,得到具有运动不确定性跟驰环境下的主车纵向控制策略,实现对车辆纵向控制的最优决策。最后基于真实驾驶数据,对控制策略进行测试。研究结果表明:该策略建立了车辆纵向控制与主车和双前车状态之间的映射关系,在迭代学习过程中对前车运动的随机性进行考虑,跟驰控制中不需要对前车运动进行额外的概率预测,能够以较低的计算量实现主车稳定跟随前车行驶。 Longitudinal acceleration decisions in a car-following control mode are directly determined by the state of the preceding vehicle.A driver's uncertainty makes car-following control difficult because of the complexity in state prediction of the target vehicle.To address the problem in which the performance of adaptive cruise control may deteriorate without consideration of the uncertainty of the preceding vehicle,a car-following control strategy based on deep reinforcement learning was proposed.To study the characteristics of human drivers,a drivingdata-acquisition platform was established,and substantial amounts of human-driving data were collected.Based on the assumption that longitudinal control decisions are mainly affected by the preceding vehicle,a two-predecessor following structure was established.The vehicles in the driving dataset were taken as target vehicles 1^# and 2^# of the car-following control.Based on the real-world driving dataset,a stochastic process model was established to describe the characteristics of preceding vehicle 1^# based on Gaussian process algorithm.Then car-following control was established as a Markov decision process.A car-following control method based on deep reinforcement learning was obtained through iterative learning with the stochastic process model using proximal policy optimization.Finally,the algorithm was verified based on the driving dataset.The results demonstrate that the mapping between longitudinal acceleration decisions and the states of the host and preceding vehicles can be obtained through iterative learning with consideration of the uncertainty of the target vehicle.
作者 朱冰 蒋渊德 赵健 陈虹 邓伟文 ZHU Bing;JIANG Yuan-de;ZHAO Jian;CHEN Hong;DENG Wei-wen(State Key Laboratory of Automotive Simulation and Control,Jilin University,Changchun 130025,Jilin,China;School of Transportation Science and Engineering. Beihang University,Beijing 100083,China)
出处 《中国公路学报》 EI CAS CSCD 北大核心 2019年第6期53-60,共8页 China Journal of Highway and Transport
基金 国家重点研发计划项目(2016YFB0100904) 国家自然科学基金项目(51775235) 吉林省科技发展计划重点科技研发项目(20180201056GX) 吉林省发改委科技研发项目(2019C036-6)
关键词 汽车工程 跟驰控制 深度强化学习 自适应巡航控制 运动不确定 高斯过程 automotive engineering car-following control deep reinforcement learning adaptive cruise control driver's uncertainty Gaussian process
  • 相关文献

参考文献5

二级参考文献32

  • 1王殿海,陶鹏飞,金盛,马东方.跟驰模型参数标定及验证方法[J].吉林大学学报(工学版),2011,41(S1):59-65. 被引量:28
  • 2高锋,王建强,侯德藻,李克强,连小珉.基于高速开关阀的电控汽车辅助制动系统[J].清华大学学报(自然科学版),2004,44(11):1532-1535. 被引量:15
  • 3YI K, KWON Y D. Vehicle-to vehicle Distance and Speed Control Using an Eleetronie-vacuum Booster [J]. JSAE Review, 2001,22(4) :403-412.
  • 4LEE C, YI K. Modeling and Control of an Electronic vacuum Booster for Vehicle Cruise Control. Journal of Mechanical Science and Technology, 2002, 16 (10):1314 1319.
  • 5MACIUCA D B, CHRISTIAN G J, KARL J H. Automatic Braking Control for IVHS[J]. JSAE Paper, 1995,16(2):219-224.
  • 6SUBRAMANIAN S C, DARBH A S, RAJ AGOPAL K R. Modeling the Pneumatic Subsystem of an S-cam Air Brake System[J]. Journal of Dynamic Systems, Measurement and Control, 2004,126 (1) : 36-46.
  • 7TAI M. Advanced Vehicle Control of Heavy Vehicles for Automated Highway Systems[D]. Berkeley: University of California, 2001.
  • 8FRITZ A,SCHIEHLEN W. Nonlinear ACC in Simulation and Measurement[J]. Vehicle System Dynamics: International Journal of Vehicle Mechanics and Mobility, 2001,36(2/3): 159-177.
  • 9YI K, MOON I, KWON Y D. A Vehicle to-vehicle Distance Control Algorithm for Stop-and-go Cruise Control[C]//IEEE. Proceeding of the 2001 Intelligent Transportation Systems Conference. Oakland.. IEEE, 2001:25-29.
  • 10WU W,CHOU Y S. Output Tracking Control of Un certain Nonlinear Systems with an Input Time Delay [J]. IEE Proceedings--Control Theory and Appliea tions, 1996,143(4) : 309-318.

共引文献86

同被引文献209

引证文献24

二级引证文献107

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部