Research on Self-Recovery Control Algorithm of Quadruped Robot Fall Based on Reinforcement Learning
When a quadruped robot is climbing stairs, due to unexpected factors, such as the size of the differing from the international standard or the stairs being wet and slippery, it may suddenly fall down. Therefore, solving the self-recovery problem of the quadruped robot after falling is of great signi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Actuators |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-0825/12/3/110 |
| _version_ | 1797614175702220800 |
|---|---|
| author | Guichen Zhang Hongwei Liu Zihao Qin Georgy V. Moiseev Jianwen Huo |
| author_facet | Guichen Zhang Hongwei Liu Zihao Qin Georgy V. Moiseev Jianwen Huo |
| author_sort | Guichen Zhang |
| collection | DOAJ |
| description | When a quadruped robot is climbing stairs, due to unexpected factors, such as the size of the differing from the international standard or the stairs being wet and slippery, it may suddenly fall down. Therefore, solving the self-recovery problem of the quadruped robot after falling is of great significance in practical engineering. This is inspired by the self-recovery of crustaceans when they fall; the swinging of their legs will produce a resonance effect of a specific body shape, and then the shell will swing under the action of external force, and self-recovery will be achieved by moving the center of gravity. Based on the bionic mechanism, the kinematics model of a one-leg swing and the self-recovery motion model of a falling quadruped robot are established in this paper. According to the established mathematical model, the algorithm training environment is constructed, and a control strategy based on the reinforcement learning algorithm is proposed as a controller to be applied to the fall self-recovery of quadruped robots. The simulation results show that the quadruped robot only takes 2.25 s to achieve self-recovery through DDPG on flat terrain. In addition, we compare the proposed algorithm with PID and LQR algorithms, and the simulation experiments verify the superiority of the proposed algorithm. |
| first_indexed | 2024-03-11T07:06:05Z |
| format | Article |
| id | doaj.art-ee896ecddb744e86b8b9ec3183dae18b |
| institution | Directory Open Access Journal |
| issn | 2076-0825 |
| language | English |
| last_indexed | 2024-03-11T07:06:05Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Actuators |
| spelling | doaj.art-ee896ecddb744e86b8b9ec3183dae18b2023-11-17T08:56:48ZengMDPI AGActuators2076-08252023-03-0112311010.3390/act12030110Research on Self-Recovery Control Algorithm of Quadruped Robot Fall Based on Reinforcement LearningGuichen Zhang0Hongwei Liu1Zihao Qin2Georgy V. Moiseev3Jianwen Huo4Robot Technology Used for Special Environment Key Laboratory of Sichuan Province, Southwest University of Science and Technology, Mianyang 621010, ChinaRobot Technology Used for Special Environment Key Laboratory of Sichuan Province, Southwest University of Science and Technology, Mianyang 621010, ChinaChina Academy of Space Technology (Xi’an), Xi’an 710000, ChinaDepartment of Big Data Analysis and Machine Learning, Financial University under the Government of Russia Federation, 125993 Moscow, RussiaRobot Technology Used for Special Environment Key Laboratory of Sichuan Province, Southwest University of Science and Technology, Mianyang 621010, ChinaWhen a quadruped robot is climbing stairs, due to unexpected factors, such as the size of the differing from the international standard or the stairs being wet and slippery, it may suddenly fall down. Therefore, solving the self-recovery problem of the quadruped robot after falling is of great significance in practical engineering. This is inspired by the self-recovery of crustaceans when they fall; the swinging of their legs will produce a resonance effect of a specific body shape, and then the shell will swing under the action of external force, and self-recovery will be achieved by moving the center of gravity. Based on the bionic mechanism, the kinematics model of a one-leg swing and the self-recovery motion model of a falling quadruped robot are established in this paper. According to the established mathematical model, the algorithm training environment is constructed, and a control strategy based on the reinforcement learning algorithm is proposed as a controller to be applied to the fall self-recovery of quadruped robots. The simulation results show that the quadruped robot only takes 2.25 s to achieve self-recovery through DDPG on flat terrain. In addition, we compare the proposed algorithm with PID and LQR algorithms, and the simulation experiments verify the superiority of the proposed algorithm.https://www.mdpi.com/2076-0825/12/3/110quadruped robotself-recovery from fallsmotion modelreinforcement learning |
| spellingShingle | Guichen Zhang Hongwei Liu Zihao Qin Georgy V. Moiseev Jianwen Huo Research on Self-Recovery Control Algorithm of Quadruped Robot Fall Based on Reinforcement Learning Actuators quadruped robot self-recovery from falls motion model reinforcement learning |
| title | Research on Self-Recovery Control Algorithm of Quadruped Robot Fall Based on Reinforcement Learning |
| title_full | Research on Self-Recovery Control Algorithm of Quadruped Robot Fall Based on Reinforcement Learning |
| title_fullStr | Research on Self-Recovery Control Algorithm of Quadruped Robot Fall Based on Reinforcement Learning |
| title_full_unstemmed | Research on Self-Recovery Control Algorithm of Quadruped Robot Fall Based on Reinforcement Learning |
| title_short | Research on Self-Recovery Control Algorithm of Quadruped Robot Fall Based on Reinforcement Learning |
| title_sort | research on self recovery control algorithm of quadruped robot fall based on reinforcement learning |
| topic | quadruped robot self-recovery from falls motion model reinforcement learning |
| url | https://www.mdpi.com/2076-0825/12/3/110 |
| work_keys_str_mv | AT guichenzhang researchonselfrecoverycontrolalgorithmofquadrupedrobotfallbasedonreinforcementlearning AT hongweiliu researchonselfrecoverycontrolalgorithmofquadrupedrobotfallbasedonreinforcementlearning AT zihaoqin researchonselfrecoverycontrolalgorithmofquadrupedrobotfallbasedonreinforcementlearning AT georgyvmoiseev researchonselfrecoverycontrolalgorithmofquadrupedrobotfallbasedonreinforcementlearning AT jianwenhuo researchonselfrecoverycontrolalgorithmofquadrupedrobotfallbasedonreinforcementlearning |