GCTD3: Modeling of Bipedal Locomotion by Combination of TD3 Algorithms and Graph Convolutional Network
In recent years, there has been a lot of research using reinforcement learning algorithms to train 2-legged robots to move, but there are still many challenges. The authors propose the GCTD3 method, which takes the idea of using Graph Convolutional Networks to represent the kinematic link features o...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/6/2948 |
| _version_ | 1797447157168472064 |
|---|---|
| author | Khoi Phan Bui Giang Nguyen Truong Dat Nguyen Ngoc |
| author_facet | Khoi Phan Bui Giang Nguyen Truong Dat Nguyen Ngoc |
| author_sort | Khoi Phan Bui |
| collection | DOAJ |
| description | In recent years, there has been a lot of research using reinforcement learning algorithms to train 2-legged robots to move, but there are still many challenges. The authors propose the GCTD3 method, which takes the idea of using Graph Convolutional Networks to represent the kinematic link features of the robot, and combines this with the Twin-Delayed Deep Deterministic Policy Gradient algorithm to train the robot to move. Graph Convolutional Networks are very effective in graph-structured problems such as the connection of the joints of the human-like robots. The GCTD3 method shows better results on the motion trajectories of the bipedal robot joints compared with other reinforcement learning algorithms such as Twin-Delayed Deep Deterministic Policy Gradient, Deep Deterministic Policy Gradient and Soft Actor Critic. This research is implemented on a 2-legged robot model with six independent joint coordinates through the Robot Operating System and Gazebo simulator. |
| first_indexed | 2024-03-09T13:50:46Z |
| format | Article |
| id | doaj.art-29fedace0b094131a343c7c6524cf8c9 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T13:50:46Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-29fedace0b094131a343c7c6524cf8c92023-11-30T20:49:22ZengMDPI AGApplied Sciences2076-34172022-03-01126294810.3390/app12062948GCTD3: Modeling of Bipedal Locomotion by Combination of TD3 Algorithms and Graph Convolutional NetworkKhoi Phan Bui0Giang Nguyen Truong1Dat Nguyen Ngoc2School of Mechanical Engineering, Hanoi University of Science and Technology, Hanoi 100000, VietnamSchool of Mechanical Engineering, Hanoi University of Science and Technology, Hanoi 100000, VietnamDepartment of Computer, Control and Management Engineering, Sapienza University of Rome, 00185 Roma, ItalyIn recent years, there has been a lot of research using reinforcement learning algorithms to train 2-legged robots to move, but there are still many challenges. The authors propose the GCTD3 method, which takes the idea of using Graph Convolutional Networks to represent the kinematic link features of the robot, and combines this with the Twin-Delayed Deep Deterministic Policy Gradient algorithm to train the robot to move. Graph Convolutional Networks are very effective in graph-structured problems such as the connection of the joints of the human-like robots. The GCTD3 method shows better results on the motion trajectories of the bipedal robot joints compared with other reinforcement learning algorithms such as Twin-Delayed Deep Deterministic Policy Gradient, Deep Deterministic Policy Gradient and Soft Actor Critic. This research is implemented on a 2-legged robot model with six independent joint coordinates through the Robot Operating System and Gazebo simulator.https://www.mdpi.com/2076-3417/12/6/2948GCTD3GCNTD3ROSreward functionbipedal robot |
| spellingShingle | Khoi Phan Bui Giang Nguyen Truong Dat Nguyen Ngoc GCTD3: Modeling of Bipedal Locomotion by Combination of TD3 Algorithms and Graph Convolutional Network Applied Sciences GCTD3 GCN TD3 ROS reward function bipedal robot |
| title | GCTD3: Modeling of Bipedal Locomotion by Combination of TD3 Algorithms and Graph Convolutional Network |
| title_full | GCTD3: Modeling of Bipedal Locomotion by Combination of TD3 Algorithms and Graph Convolutional Network |
| title_fullStr | GCTD3: Modeling of Bipedal Locomotion by Combination of TD3 Algorithms and Graph Convolutional Network |
| title_full_unstemmed | GCTD3: Modeling of Bipedal Locomotion by Combination of TD3 Algorithms and Graph Convolutional Network |
| title_short | GCTD3: Modeling of Bipedal Locomotion by Combination of TD3 Algorithms and Graph Convolutional Network |
| title_sort | gctd3 modeling of bipedal locomotion by combination of td3 algorithms and graph convolutional network |
| topic | GCTD3 GCN TD3 ROS reward function bipedal robot |
| url | https://www.mdpi.com/2076-3417/12/6/2948 |
| work_keys_str_mv | AT khoiphanbui gctd3modelingofbipedallocomotionbycombinationoftd3algorithmsandgraphconvolutionalnetwork AT giangnguyentruong gctd3modelingofbipedallocomotionbycombinationoftd3algorithmsandgraphconvolutionalnetwork AT datnguyenngoc gctd3modelingofbipedallocomotionbycombinationoftd3algorithmsandgraphconvolutionalnetwork |