Deep Reinforcement Learning-based Trajectory Planning for Manipulator Obstacle Avoidance
A deep reinforcement learning (DRL)-based motion planning method is proposed to improve long planning elapse and lengthy path of the traditional planning algorithms for robotic manipulator movement in obstacle avoidance. Firstly, based on the mathematical model of the manipulator and the motion envi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Transmission
2023-12-01
|
| Series: | Jixie chuandong |
| Subjects: | |
| Online Access: | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2023.12.006 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841546970088341504 |
|---|---|
| author | Cao Yi Guo Yinhui Li Lei Zhu Baiyu Zhao Zhihua |
| author_facet | Cao Yi Guo Yinhui Li Lei Zhu Baiyu Zhao Zhihua |
| author_sort | Cao Yi |
| collection | DOAJ |
| description | A deep reinforcement learning (DRL)-based motion planning method is proposed to improve long planning elapse and lengthy path of the traditional planning algorithms for robotic manipulator movement in obstacle avoidance. Firstly, based on the mathematical model of the manipulator and the motion environment, the DOBOT robot and the operating environment are built in PyBullet, and the parameters such as the reward function, the action and the state variables required for DRL are set. Secondly, the deep deterministic policy gradient (DDPG) algorithm is applied for the characteristics of static obstacle avoidance, and motion simulation experiments are conducted. The simulation results show that the proposed DDPG algorithm has a certain degree of improvements in planning elapse and path length compared with the rapid-exploring random tree (RRT) algorithm and the improved RRT algorithm. Finally, the effectiveness of the DDPG algorithm in obstacle avoidance operations is tested using the DOBOT robot in a laboratory environment with multiple obstacles. |
| format | Article |
| id | doaj-art-05a37baed57949dca57c4127b3a77bf0 |
| institution | Kabale University |
| issn | 1004-2539 |
| language | zho |
| publishDate | 2023-12-01 |
| publisher | Editorial Office of Journal of Mechanical Transmission |
| record_format | Article |
| series | Jixie chuandong |
| spelling | doaj-art-05a37baed57949dca57c4127b3a77bf02025-01-10T14:59:37ZzhoEditorial Office of Journal of Mechanical TransmissionJixie chuandong1004-25392023-12-0147404646660574Deep Reinforcement Learning-based Trajectory Planning for Manipulator Obstacle AvoidanceCao YiGuo YinhuiLi LeiZhu BaiyuZhao ZhihuaA deep reinforcement learning (DRL)-based motion planning method is proposed to improve long planning elapse and lengthy path of the traditional planning algorithms for robotic manipulator movement in obstacle avoidance. Firstly, based on the mathematical model of the manipulator and the motion environment, the DOBOT robot and the operating environment are built in PyBullet, and the parameters such as the reward function, the action and the state variables required for DRL are set. Secondly, the deep deterministic policy gradient (DDPG) algorithm is applied for the characteristics of static obstacle avoidance, and motion simulation experiments are conducted. The simulation results show that the proposed DDPG algorithm has a certain degree of improvements in planning elapse and path length compared with the rapid-exploring random tree (RRT) algorithm and the improved RRT algorithm. Finally, the effectiveness of the DDPG algorithm in obstacle avoidance operations is tested using the DOBOT robot in a laboratory environment with multiple obstacles.http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2023.12.006ManipulatorDeep reinforcement learningObstacle avoidance path planningDeep deterministic policy gradient algorithm |
| spellingShingle | Cao Yi Guo Yinhui Li Lei Zhu Baiyu Zhao Zhihua Deep Reinforcement Learning-based Trajectory Planning for Manipulator Obstacle Avoidance Jixie chuandong Manipulator Deep reinforcement learning Obstacle avoidance path planning Deep deterministic policy gradient algorithm |
| title | Deep Reinforcement Learning-based Trajectory Planning for Manipulator Obstacle Avoidance |
| title_full | Deep Reinforcement Learning-based Trajectory Planning for Manipulator Obstacle Avoidance |
| title_fullStr | Deep Reinforcement Learning-based Trajectory Planning for Manipulator Obstacle Avoidance |
| title_full_unstemmed | Deep Reinforcement Learning-based Trajectory Planning for Manipulator Obstacle Avoidance |
| title_short | Deep Reinforcement Learning-based Trajectory Planning for Manipulator Obstacle Avoidance |
| title_sort | deep reinforcement learning based trajectory planning for manipulator obstacle avoidance |
| topic | Manipulator Deep reinforcement learning Obstacle avoidance path planning Deep deterministic policy gradient algorithm |
| url | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2023.12.006 |
| work_keys_str_mv | AT caoyi deepreinforcementlearningbasedtrajectoryplanningformanipulatorobstacleavoidance AT guoyinhui deepreinforcementlearningbasedtrajectoryplanningformanipulatorobstacleavoidance AT lilei deepreinforcementlearningbasedtrajectoryplanningformanipulatorobstacleavoidance AT zhubaiyu deepreinforcementlearningbasedtrajectoryplanningformanipulatorobstacleavoidance AT zhaozhihua deepreinforcementlearningbasedtrajectoryplanningformanipulatorobstacleavoidance |