Learning Skateboarding for Humanoid Robots through Massively Parallel Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913498548666368 |
|---|---|
| author | Thibault, William Rajendran, Vidyasagar Melek, William Mombaur, Katja |
| author_facet | Thibault, William Rajendran, Vidyasagar Melek, William Mombaur, Katja |
| contents | Learning-based methods have proven useful at generating complex motions for robots, including humanoids. Reinforcement learning (RL) has been used to learn locomotion policies, some of which leverage a periodic reward formulation. This work extends the periodic reward formulation of locomotion to skateboarding for the REEM-C robot. Brax/MJX is used to implement the RL problem to achieve fast training. Initial results in simulation are presented with hardware experiments in progress. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07846 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Skateboarding for Humanoid Robots through Massively Parallel Reinforcement Learning Thibault, William Rajendran, Vidyasagar Melek, William Mombaur, Katja Robotics Learning-based methods have proven useful at generating complex motions for robots, including humanoids. Reinforcement learning (RL) has been used to learn locomotion policies, some of which leverage a periodic reward formulation. This work extends the periodic reward formulation of locomotion to skateboarding for the REEM-C robot. Brax/MJX is used to implement the RL problem to achieve fast training. Initial results in simulation are presented with hardware experiments in progress. |
| title | Learning Skateboarding for Humanoid Robots through Massively Parallel Reinforcement Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2409.07846 |