Reinforcement Learning with Adaptive Curriculum Dynamics Randomization for Fault-Tolerant Robot Control
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2021
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913564021751808 |
|---|---|
| author | Okamoto, Wataru Kera, Hiroshi Kawamoto, Kazuhiko |
| author_facet | Okamoto, Wataru Kera, Hiroshi Kawamoto, Kazuhiko |
| contents | This study is aimed at addressing the problem of fault tolerance of quadruped robots to actuator failure, which is critical for robots operating in remote or extreme environments. In particular, an adaptive curriculum reinforcement learning algorithm with dynamics randomization (ACDR) is established. The ACDR algorithm can adaptively train a quadruped robot in random actuator failure conditions and formulate a single robust policy for fault-tolerant robot control. It is noted that the hard2easy curriculum is more effective than the easy2hard curriculum for quadruped robot locomotion. The ACDR algorithm can be used to build a robot system that does not require additional modules for detecting actuator failures and switching policies. Experimental results show that the ACDR algorithm outperforms conventional algorithms in terms of the average reward and walking distance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2111_10005 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Reinforcement Learning with Adaptive Curriculum Dynamics Randomization for Fault-Tolerant Robot Control Okamoto, Wataru Kera, Hiroshi Kawamoto, Kazuhiko Robotics Artificial Intelligence This study is aimed at addressing the problem of fault tolerance of quadruped robots to actuator failure, which is critical for robots operating in remote or extreme environments. In particular, an adaptive curriculum reinforcement learning algorithm with dynamics randomization (ACDR) is established. The ACDR algorithm can adaptively train a quadruped robot in random actuator failure conditions and formulate a single robust policy for fault-tolerant robot control. It is noted that the hard2easy curriculum is more effective than the easy2hard curriculum for quadruped robot locomotion. The ACDR algorithm can be used to build a robot system that does not require additional modules for detecting actuator failures and switching policies. Experimental results show that the ACDR algorithm outperforms conventional algorithms in terms of the average reward and walking distance. |
| title | Reinforcement Learning with Adaptive Curriculum Dynamics Randomization for Fault-Tolerant Robot Control |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2111.10005 |