摘要
路径规划作为移动机器人自主导航的关键技术,主要是使目标对象在规定范围内找到一条从起点到终点的无碰撞安全路径。阐述基于常规方法和强化学习方法的路径规划技术,将强化学习方法主要分为基于值和基于策略两类,对比时序差分、Q-Learning等基于值的代表方法与策略梯度、模仿学习等基于策略的代表方法,并分析其融合策略和深度强化学习方法方法的发展现状。在此基础上,总结各种强化学习方法的优缺点及适用场合,同时对基于强化学习的路径规划技术的未来发展方向进行展望。
Path planning is one of the key technologies for autonomous navigation of mobile robots.It aims at planning a collision free optimal path from the current position to the destination in real time.This paper introduces the path planning techniques that are based on Reinforcement Learning(RL)and common methods,and categorizes the methods based on RL into two types:the value-based methods and the strategy-based methods.Then the paper compares valuebased representation methods(including Timing Difference(TD),Q-Learning,etc.)and the strategy-based representation methods(including Strategy Gradient(SG)and Imitation Learning(IL),etc.),and analyzes the development status of its fusion strategy and Deep Reinforcement Learning(DRL).On this basis,the paper summarizes the advantages,disadvantages and application scenarios of the RL-based methods.Finally,the future development trends of the path planning techniques based on RL are discussed.
作者
闫皎洁
张锲石
胡希平
YAN Jiaojie;ZHANG Qieshi;HU Xiping(Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,Guangdong 518055,China;Shenzhen College of Advanced Technology,University of Chinese Academy of Sciences,Shenzhen,Guangdong 518055,China)
出处
《计算机工程》
CAS
CSCD
北大核心
2021年第10期16-25,共10页
Computer Engineering
基金
国家自然科学基金(U1913202,U1813205)
深圳科技计划基础研究项目(JSGG20191129094012321,JCYJ20180507182610734)。
关键词
路径规划
强化学习
深度强化学习
移动机器人
自主导航
path planning
Reinforcement Learning(RL)
Deep Reinforcement Learning(DRL)
mobile robot
autonomous navigation
