Navigation for autonomous vehicles via fast-stable and smooth reinforcement learning  

作　　者：ZHANG RuiXian YANG JiaNan LIANG Ye LU ShengAo DONG YiFei YANG BaoQing ZHANG LiXian 

机构地区：[1]School of Astronautics,Harbin Institute of Technology,Harbin 150001,China

出　　处：《Science China(Technological Sciences)》2024年第2期423-434,共12页中国科学（技术科学英文版）

基　　金：supported by the National Natural Science Foundation of China(Grant Nos.62225305 and 12072088);the Fundamental Research Funds for the Central Universities,China(Grant Nos.HIT.OCEF.2022047,HIT.BRET.2022004 and HIT.DZIJ.2023049);the Grant JCKY2022603C016,State Key Laboratory of Robotics and System(HIT);the Heilongjiang Touyan Team。

摘　　要：This paper investigates the navigation problem of autonomous vehicles based on reinforcement learning(RL)with both stability and smoothness guarantees.By introducing a data-based Lyapunov function,the stability criterion in mean cost is obtained,where the Lyapunov function has a property of fast descending.Then,an off-policy RL algorithm is proposed to train safe policies,in which a more strict constraint is exerted in the framework of model-free RL to ensure the fast convergence of policy generation,in contrast with the existing RL merely with stability guarantee.In addition,by simultaneously introducing constraints on action increments and action distribution variations,the difference between the adjacent actions is effectively alleviated to ensure the smoothness of the obtained policy,instead of only seeking the similarity of the distributions of adjacent actions as commonly done in the past literature.A navigation task of a ground differentially driven mobile vehicle in simulations is adopted to demonstrate the superiority of the proposed algorithm on the fast stability and smoothness.

关 键 词：autonomous vehicles NAVIGATION reinforcement learning SMOOTHNESS stability 

分 类 号：U463.67[机械工程—车辆工程]