深度强化学习智能驾驶汽车增广决策模型  

Deep reinforcement learning augmented decision-making model for intelligent driving vehicles

作　　者：田彦涛[1] 季言实 唱寰 谢波 TIAN Yan-tao;JI Yan-shi;CHANG Huan;XIE Bo(College of Communication Engineering,Jilin University,Changchun 130022,China)

机构地区：[1]吉林大学通信工程学院,长春130022

出　　处：《吉林大学学报（工学版）》2023年第3期682-692,共11页Journal of Jilin University:Engineering and Technology Edition

基　　金：国家自然科学基金联合基金项目(U19A2069)。

摘　　要：针对状态机决策模型不能有效处理冰雪环境下丰富的上下文信息和不确定因素影响等问题,构建了一种基于深度Q网络算法(DQN)的深度强化学习智能体。使用运动规划器对该智能体进行增广,将基于规则的决策规划模块和深度强化学习模型整合在一起,建立了DQN-planner模型,从而提高了强化学习智能体的收敛速度和驾驶能力。最后,基于CARLA模拟仿真平台对DQN模型和DQN-planner模型在低附着系数冰雪路面上的驾驶能力进行了对比实验,分别就训练过程和验证结果进行了分析。A deep reinforcement learning agent based on Deep Q-Network(DQN) algorithm was constructed to solve the problem that the state machine decision model cannot effectively deal with the rich context information and the influence of uncertain factors in the snow and ice environment.The motion planner was used to augment the agent,and the rule-based decision planning module and the deep reinforcement learning model were integrated together to build the DQN-planner model,so as to improve the convergence speed and driving ability of the reinforcement learning agent.Finally,the driving ability of DQN model and DQN-planner on ice and snow road with low adhesion coefficient is compared based on CARLA simulation platform,and the training process and verification results are analyzed respectively.

关 键 词：车辆工程 深度强化学习 智能驾驶 冰雪路面 决策规划 

分 类 号：U495[交通运输工程—交通运输规划与管理]