Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground
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-Doubl...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Journal of Robotics |
| Online Access: | http://dx.doi.org/10.1155/2020/7167243 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850105295975481344 |
|---|---|
| author | Peng Wang Xiaoqiang Li Chunxiao Song Shipeng Zhai |
| author_facet | Peng Wang Xiaoqiang Li Chunxiao Song Shipeng Zhai |
| author_sort | Peng Wang |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-3c83d056331f46f1a2652cb400faba81 |
| institution | OA Journals |
| issn | 1687-9600 1687-9619 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Robotics |
| spelling | doaj-art-3c83d056331f46f1a2652cb400faba812025-08-20T02:39:08ZengWileyJournal of Robotics1687-96001687-96192020-01-01202010.1155/2020/71672437167243Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope GroundPeng Wang0Xiaoqiang Li1Chunxiao Song2Shipeng Zhai3School of Mechanical and Power Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Mechanical and Power Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Mechanical and Power Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Mechanical and Power Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaThe 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.http://dx.doi.org/10.1155/2020/7167243 |
| spellingShingle | Peng Wang Xiaoqiang Li Chunxiao Song Shipeng Zhai Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground Journal of Robotics |
| title | Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground |
| title_full | Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground |
| title_fullStr | Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground |
| title_full_unstemmed | Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground |
| title_short | Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground |
| title_sort | research on dynamic path planning of wheeled robot based on deep reinforcement learning on the slope ground |
| url | http://dx.doi.org/10.1155/2020/7167243 |
| work_keys_str_mv | AT pengwang researchondynamicpathplanningofwheeledrobotbasedondeepreinforcementlearningontheslopeground AT xiaoqiangli researchondynamicpathplanningofwheeledrobotbasedondeepreinforcementlearningontheslopeground AT chunxiaosong researchondynamicpathplanningofwheeledrobotbasedondeepreinforcementlearningontheslopeground AT shipengzhai researchondynamicpathplanningofwheeledrobotbasedondeepreinforcementlearningontheslopeground |