Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2401.12389 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929219630530560 |
|---|---|
| author | Li, Yinghui Wu, Jinze Liu, Xin Guo, Weizhong Xue, Yufei |
| author_facet | Li, Yinghui Wu, Jinze Liu, Xin Guo, Weizhong Xue, Yufei |
| contents | Multi-legged robots offer enhanced stability in complex terrains, yet autonomously learning natural and robust motions in such environments remains challenging. Drawing inspiration from animals' progressive learning patterns, from simple to complex tasks, we introduce a universal two-stage learning framework with two-step reward setting based on self-acquired experience, which efficiently enables legged robots to incrementally learn natural and robust movements. In the first stage, robots learn through gait-related rewards to track velocity on flat terrain, acquiring natural, robust movements and generating effective motion experience data. In the second stage, mirroring animal learning from existing experiences, robots learn to navigate challenging terrains with natural and robust movements using adversarial imitation learning. To demonstrate our method's efficacy, we trained both quadruped robots and a hexapod robot, and the policy were successfully transferred to a physical quadruped robot GO1, which exhibited natural gait patterns and remarkable robustness in various terrains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_12389 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Experience-Learning Inspired Two-Step Reward Method for Efficient Legged Locomotion Learning Towards Natural and Robust Gaits Li, Yinghui Wu, Jinze Liu, Xin Guo, Weizhong Xue, Yufei Robotics Multi-legged robots offer enhanced stability in complex terrains, yet autonomously learning natural and robust motions in such environments remains challenging. Drawing inspiration from animals' progressive learning patterns, from simple to complex tasks, we introduce a universal two-stage learning framework with two-step reward setting based on self-acquired experience, which efficiently enables legged robots to incrementally learn natural and robust movements. In the first stage, robots learn through gait-related rewards to track velocity on flat terrain, acquiring natural, robust movements and generating effective motion experience data. In the second stage, mirroring animal learning from existing experiences, robots learn to navigate challenging terrains with natural and robust movements using adversarial imitation learning. To demonstrate our method's efficacy, we trained both quadruped robots and a hexapod robot, and the policy were successfully transferred to a physical quadruped robot GO1, which exhibited natural gait patterns and remarkable robustness in various terrains. |
| title | Experience-Learning Inspired Two-Step Reward Method for Efficient Legged Locomotion Learning Towards Natural and Robust Gaits |
| topic | Robotics |
| url | https://arxiv.org/abs/2401.12389 |