Evolutionary Decision-Making and Planning for Autonomous Driving Based on Safe and Rational Exploration and Exploitation

作     者：Kang Yuan Yanjun Huang Shuo Yang Zewei Zhou Yulei Wang Dongpu Cao Hong Chen Kang Yuan;Yanjun Huang;Shuo Yang;Zewei Zhou;Yulei Wang;Dongpu Cao;Hong Chen

作者机构：College of Electronic and Information EngineeringTongji UniversityShanghai 201804China Shanghai Institute of Intelligent Science and TechnologyTongji UniversityShanghai 201210China School of Automotive StudiesTongji UniversityShanghai 201804China School of Vehicle and MobilityTsinghua UniversityBeijing 100084China 

出 版 物：《Engineering》 (工程（英文）)

年 卷 期：2024年第33卷第2期

页      面：108-120页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the financial support of the National Key Research and Development Program of China(2020AAA0108100) the Shanghai Municipal Science and Technology Major Project(2021SHZDZX0100) the Shanghai Gaofeng and Gaoyuan Project for University Academic Program Development for funding。 

主　　题：Autonomous driving Decision-making Motion planning Deep reinforcement learning Model predictive control 

摘      要：Decision-making and motion planning are extremely important in autonomous driving to ensure safe driving in a real-world environment.This study proposes an online evolutionary decision-making and motion planning framework for autonomous driving based on a hybrid data-and model-driven method.First,a data-driven decision-making module based on deep reinforcement learning(DRL)is developed to pursue a rational driving performance as much as possible.Then,model predictive control(MPC)is employed to execute both longitudinal and lateral motion planning tasks.Multiple constraints are defined according to the vehicle’s physical limit to meet the driving task requirements.Finally,two principles of safety and rationality for the self-evolution of autonomous driving are proposed.A motion envelope is established and embedded into a rational exploration and exploitation scheme,which filters out unreasonable experiences by masking unsafe actions so as to collect high-quality training data for the DRL agent.Experiments with a high-fidelity vehicle model and MATLAB/Simulink co-simulation environment are conducted,and the results show that the proposed online-evolution framework is able to generate safer,more rational,and more efficient driving action in a real-world environment.