{"title":"Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground","authors":"W. Peng, Xiaoqiang Li, Chunxiao Song, S. Zhai","doi":"10.1155/2020/7167243","DOIUrl":null,"url":null,"abstract":"The existing dynamic path planning algorithm cannot properly solve the problem of the path planning of wheeled robot on the slope ground with dynamic moving obstacles. To solve the problem of slow convergence rate in the training phase of DDQN, the dynamic path planning algorithm based on Tree-Double Deep Q Network (TDDQN) is proposed. The algorithm discards detected incomplete and over-detected paths by optimizing the tree structure, and combines the DDQN method with the tree structure method. Firstly, DDQN algorithm is used to select the best action in the current state after performing fewer actions, so as to obtain the candidate path that meets the conditions. And then, according to the obtained state, the above process is repeatedly executed to form multiple paths of the tree structure. Finally, the non-maximum suppression method is used to select the best path from the plurality of eligible candidate paths. ROS simulation and experiment verify that the wheeled robot can reach the target effectively on the slope ground with moving obstacles. The results show that compared with DDQN algorithm, TDDQN has the advantages of fast convergence and low loss function.","PeriodicalId":51834,"journal":{"name":"Journal of Robotics","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1155/2020/7167243","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Robotics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1155/2020/7167243","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ROBOTICS","Score":null,"Total":0}
引用次数: 6
Abstract
The existing dynamic path planning algorithm cannot properly solve the problem of the path planning of wheeled robot on the slope ground with dynamic moving obstacles. To solve the problem of slow convergence rate in the training phase of DDQN, the dynamic path planning algorithm based on Tree-Double Deep Q Network (TDDQN) is proposed. The algorithm discards detected incomplete and over-detected paths by optimizing the tree structure, and combines the DDQN method with the tree structure method. Firstly, DDQN algorithm is used to select the best action in the current state after performing fewer actions, so as to obtain the candidate path that meets the conditions. And then, according to the obtained state, the above process is repeatedly executed to form multiple paths of the tree structure. Finally, the non-maximum suppression method is used to select the best path from the plurality of eligible candidate paths. ROS simulation and experiment verify that the wheeled robot can reach the target effectively on the slope ground with moving obstacles. The results show that compared with DDQN algorithm, TDDQN has the advantages of fast convergence and low loss function.
期刊介绍:
Journal of Robotics publishes papers on all aspects automated mechanical devices, from their design and fabrication, to their testing and practical implementation. The journal welcomes submissions from the associated fields of materials science, electrical and computer engineering, and machine learning and artificial intelligence, that contribute towards advances in the technology and understanding of robotic systems.