Car-following strategy of intelligent connected vehicle using extended disturbance observer adjusted by reinforcement learning  

作　　者：Ruidong Yan Penghui Li Hongbo Gao Jin Huang Chengbo Wang 

机构地区：[1]School of Traffic and Transportation,The Beijing Jiaotong University,Beijing,China [2]Department of Automation,School of Information Science and Technology,University of Science and Technology of China,Hefei,China [3]School of Vehicle and Mobility,The Tsinghua University,Beijing,China [4]Liverpool Logistics,Offshore and Marine Research Institute(LOOM),Liverpool John Moores University,Liverpool,UK

出　　处：《CAAI Transactions on Intelligence Technology》2024年第2期365-373,共9页智能技术学报（英文）

基　　金：State Key Laboratory of Automotive Safety and Energy,Grant/Award Number:KFY2208;National Natural Science Foundation of China,Grant/Award Numbers:U2013601,U20A20225;Key Research and Development Plan of Anhui Province,Grant/Award Number:202004a05020058;the Natural Science Foundation of Hefei,China(Grant No.2021032)。

摘　　要：Disturbance observer-based control method has achieved good results in the carfollowing scenario of intelligent and connected vehicle(ICV).However,the gain of conventional extended disturbance observer(EDO)-based control method is usually set manually rather than adjusted adaptively according to real time traffic conditions,thus declining the car-following performance.To solve this problem,a car-following strategy of ICV using EDO adjusted by reinforcement learning is proposed.Different from the conventional method,the gain of proposed strategy can be adjusted by reinforcement learning to improve its estimation accuracy.Since the“equivalent disturbance”can be compensated by EDO to a great extent,the disturbance rejection ability of the carfollowing method will be improved significantly.Both Lyapunov approach and numerical simulations are carried out to verify the effectiveness of the proposed method.

关 键 词：adaptive system autonomous vehicle intelligent control 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]