Distance-Controllable Long Jump of Quadruped Robot Based on Parameter Optimization Using Deep Reinforcement Learning
Quadruped robots interact with the ground with discrete foot points during locomotion, which makes them gain an advantage in obstacle crossing compared with the wheeled and tracked robots. Quadruped robots can jump from current position to one position a certain distance ahead to negotiate the obsta...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10246264/ |
| _version_ | 1797685350703824896 |
|---|---|
| author | Qingyu Liu Duo Xu Bing Yuan Zian Mou Min Wang |
| author_facet | Qingyu Liu Duo Xu Bing Yuan Zian Mou Min Wang |
| author_sort | Qingyu Liu |
| collection | DOAJ |
| description | Quadruped robots interact with the ground with discrete foot points during locomotion, which makes them gain an advantage in obstacle crossing compared with the wheeled and tracked robots. Quadruped robots can jump from current position to one position a certain distance ahead to negotiate the obstacles between them, for example. However, current quadruped control strategies usually assume that the landing area is large enough, and thus jumping distance control of quadruped robots had not yet been studied sufficiently. This paper proposes a method for controlling the distance of quadruped robot jumps based on deep reinforcement learning (DRL). In the method, kinematic parameters in the control module are optimized to achieve the quadruped jumping tasks. Based on the understanding of the kinematics and dynamics of quadruped robot jumping, an initial jumping is realized by controlling the robot foot moving along a carefully designed parameterized trajectory. This initial trajectory is then used to train a set of jumping parameters using a deep reinforcement learning (DRL) algorithm. Through thousands of jumping trials in the Gazebo simulation environment, the optimal parameters were acquired. Our proposed method allows for accurate jumping within the 0.5 m to 0.8 m range. Additionally, the controller has been successfully implemented on a real quadruped robot. |
| first_indexed | 2024-03-12T00:42:54Z |
| format | Article |
| id | doaj.art-253277740ef643c88250223880cf8a43 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T00:42:54Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-253277740ef643c88250223880cf8a432023-09-14T23:01:17ZengIEEEIEEE Access2169-35362023-01-0111985669857710.1109/ACCESS.2023.331363710246264Distance-Controllable Long Jump of Quadruped Robot Based on Parameter Optimization Using Deep Reinforcement LearningQingyu Liu0https://orcid.org/0009-0002-9657-3948Duo Xu1https://orcid.org/0009-0004-9730-9094Bing Yuan2https://orcid.org/0000-0002-4695-856XZian Mou3https://orcid.org/0009-0006-8542-6423Min Wang4https://orcid.org/0000-0003-1756-1405Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan, ChinaHubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, ChinaPrecision Manufacturing Institute, Wuhan University of Science and Technology, Wuhan, ChinaPrecision Manufacturing Institute, Wuhan University of Science and Technology, Wuhan, ChinaSchool of Mechatronic Engineering and Automation, Shanghai University, Shanghai, ChinaQuadruped robots interact with the ground with discrete foot points during locomotion, which makes them gain an advantage in obstacle crossing compared with the wheeled and tracked robots. Quadruped robots can jump from current position to one position a certain distance ahead to negotiate the obstacles between them, for example. However, current quadruped control strategies usually assume that the landing area is large enough, and thus jumping distance control of quadruped robots had not yet been studied sufficiently. This paper proposes a method for controlling the distance of quadruped robot jumps based on deep reinforcement learning (DRL). In the method, kinematic parameters in the control module are optimized to achieve the quadruped jumping tasks. Based on the understanding of the kinematics and dynamics of quadruped robot jumping, an initial jumping is realized by controlling the robot foot moving along a carefully designed parameterized trajectory. This initial trajectory is then used to train a set of jumping parameters using a deep reinforcement learning (DRL) algorithm. Through thousands of jumping trials in the Gazebo simulation environment, the optimal parameters were acquired. Our proposed method allows for accurate jumping within the 0.5 m to 0.8 m range. Additionally, the controller has been successfully implemented on a real quadruped robot.https://ieeexplore.ieee.org/document/10246264/Quadruped robotstrajectory planningdeep reinforcement learningjumping control |
| spellingShingle | Qingyu Liu Duo Xu Bing Yuan Zian Mou Min Wang Distance-Controllable Long Jump of Quadruped Robot Based on Parameter Optimization Using Deep Reinforcement Learning IEEE Access Quadruped robots trajectory planning deep reinforcement learning jumping control |
| title | Distance-Controllable Long Jump of Quadruped Robot Based on Parameter Optimization Using Deep Reinforcement Learning |
| title_full | Distance-Controllable Long Jump of Quadruped Robot Based on Parameter Optimization Using Deep Reinforcement Learning |
| title_fullStr | Distance-Controllable Long Jump of Quadruped Robot Based on Parameter Optimization Using Deep Reinforcement Learning |
| title_full_unstemmed | Distance-Controllable Long Jump of Quadruped Robot Based on Parameter Optimization Using Deep Reinforcement Learning |
| title_short | Distance-Controllable Long Jump of Quadruped Robot Based on Parameter Optimization Using Deep Reinforcement Learning |
| title_sort | distance controllable long jump of quadruped robot based on parameter optimization using deep reinforcement learning |
| topic | Quadruped robots trajectory planning deep reinforcement learning jumping control |
| url | https://ieeexplore.ieee.org/document/10246264/ |
| work_keys_str_mv | AT qingyuliu distancecontrollablelongjumpofquadrupedrobotbasedonparameteroptimizationusingdeepreinforcementlearning AT duoxu distancecontrollablelongjumpofquadrupedrobotbasedonparameteroptimizationusingdeepreinforcementlearning AT bingyuan distancecontrollablelongjumpofquadrupedrobotbasedonparameteroptimizationusingdeepreinforcementlearning AT zianmou distancecontrollablelongjumpofquadrupedrobotbasedonparameteroptimizationusingdeepreinforcementlearning AT minwang distancecontrollablelongjumpofquadrupedrobotbasedonparameteroptimizationusingdeepreinforcementlearning |