Robotic arm reinforcement learning control method based on autonomous visual perception
The traditional robotic arm control methods are often based on artificially preset fixed trajectories to control them to complete specific tasks, which rely on accurate environmental models, and the control process lacks the ability of self-adaptability. Aiming at the above problems, we proposed an...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
EDP Sciences
2021-10-01
|
| Series: | Xibei Gongye Daxue Xuebao |
| Subjects: | |
| Online Access: | https://www.jnwpu.org/articles/jnwpu/full_html/2021/05/jnwpu2021395p1057/jnwpu2021395p1057.html |
| _version_ | 1797669118890999808 |
|---|---|
| author | HU Chunyang WANG Heng SHI Haobin |
| author_facet | HU Chunyang WANG Heng SHI Haobin |
| author_sort | HU Chunyang |
| collection | DOAJ |
| description | The traditional robotic arm control methods are often based on artificially preset fixed trajectories to control them to complete specific tasks, which rely on accurate environmental models, and the control process lacks the ability of self-adaptability. Aiming at the above problems, we proposed an end-to-end robotic arm intelligent control method based on the combination of machine vision and reinforcement learning. The visual perception uses the YOLO algorithm, and the strategy control module uses the DDPG reinforcement learning algorithm, which enables the robotic arm to learn autonomous control strategies in a complex environment. Otherwise, we used imitation learning and hindsight experience replay algorithm during the training process, which accelerated the learning process of the robotic arm. The experimental results show that the algorithm can converge in a shorter time, and it has excellent performance in autonomously perceiving the target position and overall strategy control in the simulation environment. |
| first_indexed | 2024-03-11T20:39:18Z |
| format | Article |
| id | doaj.art-631cdbbdc474423989410cbf89c9d587 |
| institution | Directory Open Access Journal |
| issn | 1000-2758 2609-7125 |
| language | zho |
| last_indexed | 2024-03-11T20:39:18Z |
| publishDate | 2021-10-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | Xibei Gongye Daxue Xuebao |
| spelling | doaj.art-631cdbbdc474423989410cbf89c9d5872023-10-02T03:49:33ZzhoEDP SciencesXibei Gongye Daxue Xuebao1000-27582609-71252021-10-013951057106310.1051/jnwpu/20213951057jnwpu2021395p1057Robotic arm reinforcement learning control method based on autonomous visual perceptionHU Chunyang0WANG Heng1SHI Haobin2School of Computer, Hubei University of Arts and ScienceSchool of Computer, Northwestern Polytechnical UniversitySchool of Computer, Northwestern Polytechnical UniversityThe traditional robotic arm control methods are often based on artificially preset fixed trajectories to control them to complete specific tasks, which rely on accurate environmental models, and the control process lacks the ability of self-adaptability. Aiming at the above problems, we proposed an end-to-end robotic arm intelligent control method based on the combination of machine vision and reinforcement learning. The visual perception uses the YOLO algorithm, and the strategy control module uses the DDPG reinforcement learning algorithm, which enables the robotic arm to learn autonomous control strategies in a complex environment. Otherwise, we used imitation learning and hindsight experience replay algorithm during the training process, which accelerated the learning process of the robotic arm. The experimental results show that the algorithm can converge in a shorter time, and it has excellent performance in autonomously perceiving the target position and overall strategy control in the simulation environment.https://www.jnwpu.org/articles/jnwpu/full_html/2021/05/jnwpu2021395p1057/jnwpu2021395p1057.htmlmachine visionreinforcement learningimitation learningsystem simulationintelligent control |
| spellingShingle | HU Chunyang WANG Heng SHI Haobin Robotic arm reinforcement learning control method based on autonomous visual perception Xibei Gongye Daxue Xuebao machine vision reinforcement learning imitation learning system simulation intelligent control |
| title | Robotic arm reinforcement learning control method based on autonomous visual perception |
| title_full | Robotic arm reinforcement learning control method based on autonomous visual perception |
| title_fullStr | Robotic arm reinforcement learning control method based on autonomous visual perception |
| title_full_unstemmed | Robotic arm reinforcement learning control method based on autonomous visual perception |
| title_short | Robotic arm reinforcement learning control method based on autonomous visual perception |
| title_sort | robotic arm reinforcement learning control method based on autonomous visual perception |
| topic | machine vision reinforcement learning imitation learning system simulation intelligent control |
| url | https://www.jnwpu.org/articles/jnwpu/full_html/2021/05/jnwpu2021395p1057/jnwpu2021395p1057.html |
| work_keys_str_mv | AT huchunyang roboticarmreinforcementlearningcontrolmethodbasedonautonomousvisualperception AT wangheng roboticarmreinforcementlearningcontrolmethodbasedonautonomousvisualperception AT shihaobin roboticarmreinforcementlearningcontrolmethodbasedonautonomousvisualperception |