arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.09181cs.CVcs.LGcs.RO
收藏

基于深度强化学习的端到端视觉自适应巡航控制(ACC)

End-to-End Vision-Based Adaptive Cruise Control (ACC) Using Deep Reinforcement Learning

Center for Environmental Research and Technology(环境研究与技术中心)

Zhensong Wei, Yu Jiang, Xishun Liao, Xuewei Qi, Ziran Wang, Guoyuan Wu, Peng Hao, Matthew Barth

摘要:

提出了一种深度强化学习方法--双深度Q网络,用于设计端到端的基于视觉的自适应巡航控制(ACC)系统。在Unity中建立了一个高速公路场景的仿真环境,Unity是一个游戏引擎,它提供了车辆的物理模型和用于训练和测试的特征数据。在强化学习模型中,针对内燃机(ICE)汽车和电动汽车(EV),设计了与跟车距离和油门/制动力相关的奖励函数,以实现自适应巡航控制。对不同车型的间隙统计和总能耗进行了评估,以探索奖励函数与动力系统特性之间的关系。与传统的基于雷达的ACC系统或人在回路仿真相比,所提出的基于视觉的ACC系统可以根据预设的奖励函数生成更好的间隙调节轨迹或更平滑的速度轨迹。该系统能很好地适应前车不同的速度轨迹,并能实时运行。

英文摘要:

This paper presented a deep reinforcement learning method named Double Deep Q-networks to design an end-to-end vision-based adaptive cruise control (ACC) system. A simulation environment of a highway scene was set up in Unity, which is a game engine that provided both physical models of vehicles and feature data for training and testing. Well-designed reward functions associated with the following distance and throttle/brake force were implemented in the reinforcement learning model for both internal combustion engine (ICE) vehicles and electric vehicles (EV) to perform adaptive cruise control. The gap statistics and total energy consumption are evaluated for different vehicle types to explore the relationship between reward functions and powertrain characteristics. Compared with the traditional radar-based ACC systems or human-in-the-loop simulation, the proposed vision-based ACC system can generate either a better gap regulated trajectory or a smoother speed trajectory depending on the preset reward function. The proposed system can be well adaptive to different speed trajectories of the preceding vehicle and operated in real-time.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑