An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms
Aiming at the poor robustness and adaptability of traditional control methods for different situations, the deep deterministic policy gradient (DDPG) algorithm is improved by designing a hybrid function that includes different rewards superimposed on each other. In addition, the experience replay me...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Neuroinformatics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fninf.2023.1096053/full |
| _version_ | 1797945477714411520 |
|---|---|
| author | Ruyi Dong Junjie Du Yanan Liu Ali Asghar Heidari Huiling Chen |
| author_facet | Ruyi Dong Junjie Du Yanan Liu Ali Asghar Heidari Huiling Chen |
| author_sort | Ruyi Dong |
| collection | DOAJ |
| description | Aiming at the poor robustness and adaptability of traditional control methods for different situations, the deep deterministic policy gradient (DDPG) algorithm is improved by designing a hybrid function that includes different rewards superimposed on each other. In addition, the experience replay mechanism of DDPG is also improved by combining priority sampling and uniform sampling to accelerate the DDPG’s convergence. Finally, it is verified in the simulation environment that the improved DDPG algorithm can achieve accurate control of the robot arm motion. The experimental results show that the improved DDPG algorithm can converge in a shorter time, and the average success rate in the robotic arm end-reaching task is as high as 91.27%. Compared with the original DDPG algorithm, it has more robust environmental adaptability. |
| first_indexed | 2024-04-10T20:55:44Z |
| format | Article |
| id | doaj.art-8afc2f2df1304ce6b4a4974962d6b632 |
| institution | Directory Open Access Journal |
| issn | 1662-5196 |
| language | English |
| last_indexed | 2024-04-10T20:55:44Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroinformatics |
| spelling | doaj.art-8afc2f2df1304ce6b4a4974962d6b6322023-01-23T04:56:52ZengFrontiers Media S.A.Frontiers in Neuroinformatics1662-51962023-01-011710.3389/fninf.2023.10960531096053An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic armsRuyi Dong0Junjie Du1Yanan Liu2Ali Asghar Heidari3Huiling Chen4College of Information and Control Engineering, Jilin Institute of Chemical Technology, Jilin, ChinaCollege of Information and Control Engineering, Jilin Institute of Chemical Technology, Jilin, ChinaCollege of Information and Control Engineering, Jilin Institute of Chemical Technology, Jilin, ChinaSchool of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, IranCollege of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, ChinaAiming at the poor robustness and adaptability of traditional control methods for different situations, the deep deterministic policy gradient (DDPG) algorithm is improved by designing a hybrid function that includes different rewards superimposed on each other. In addition, the experience replay mechanism of DDPG is also improved by combining priority sampling and uniform sampling to accelerate the DDPG’s convergence. Finally, it is verified in the simulation environment that the improved DDPG algorithm can achieve accurate control of the robot arm motion. The experimental results show that the improved DDPG algorithm can converge in a shorter time, and the average success rate in the robotic arm end-reaching task is as high as 91.27%. Compared with the original DDPG algorithm, it has more robust environmental adaptability.https://www.frontiersin.org/articles/10.3389/fninf.2023.1096053/fullrobotic armintelligent controlreward functionexperience replay mechanismdeep deterministic policy gradient algorithmartificial intelligence |
| spellingShingle | Ruyi Dong Junjie Du Yanan Liu Ali Asghar Heidari Huiling Chen An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms Frontiers in Neuroinformatics robotic arm intelligent control reward function experience replay mechanism deep deterministic policy gradient algorithm artificial intelligence |
| title | An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms |
| title_full | An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms |
| title_fullStr | An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms |
| title_full_unstemmed | An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms |
| title_short | An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms |
| title_sort | enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms |
| topic | robotic arm intelligent control reward function experience replay mechanism deep deterministic policy gradient algorithm artificial intelligence |
| url | https://www.frontiersin.org/articles/10.3389/fninf.2023.1096053/full |
| work_keys_str_mv | AT ruyidong anenhanceddeepdeterministicpolicygradientalgorithmforintelligentcontrolofroboticarms AT junjiedu anenhanceddeepdeterministicpolicygradientalgorithmforintelligentcontrolofroboticarms AT yananliu anenhanceddeepdeterministicpolicygradientalgorithmforintelligentcontrolofroboticarms AT aliasgharheidari anenhanceddeepdeterministicpolicygradientalgorithmforintelligentcontrolofroboticarms AT huilingchen anenhanceddeepdeterministicpolicygradientalgorithmforintelligentcontrolofroboticarms AT ruyidong enhanceddeepdeterministicpolicygradientalgorithmforintelligentcontrolofroboticarms AT junjiedu enhanceddeepdeterministicpolicygradientalgorithmforintelligentcontrolofroboticarms AT yananliu enhanceddeepdeterministicpolicygradientalgorithmforintelligentcontrolofroboticarms AT aliasgharheidari enhanceddeepdeterministicpolicygradientalgorithmforintelligentcontrolofroboticarms AT huilingchen enhanceddeepdeterministicpolicygradientalgorithmforintelligentcontrolofroboticarms |