Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911102673092608 |
|---|---|
| author | Bohlinger, Nico Kinzel, Jonathan Palenicek, Daniel Antczak, Lukasz Peters, Jan |
| author_facet | Bohlinger, Nico Kinzel, Jonathan Palenicek, Daniel Antczak, Lukasz Peters, Jan |
| contents | On-robot Reinforcement Learning is a promising approach to train embodiment-aware policies for legged robots. However, the computational constraints of real-time learning on robots pose a significant challenge. We present a framework for efficiently learning quadruped locomotion in just 8 minutes of raw real-time training utilizing the sample efficiency and minimal computational overhead of the new off-policy algorithm CrossQ. We investigate two control architectures: Predicting joint target positions for agile, high-speed locomotion and Central Pattern Generators for stable, natural gaits. While prior work focused on learning simple forward gaits, our framework extends on-robot learning to omnidirectional locomotion. We demonstrate the robustness of our approach in different indoor and outdoor environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08375 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion Bohlinger, Nico Kinzel, Jonathan Palenicek, Daniel Antczak, Lukasz Peters, Jan Robotics Machine Learning On-robot Reinforcement Learning is a promising approach to train embodiment-aware policies for legged robots. However, the computational constraints of real-time learning on robots pose a significant challenge. We present a framework for efficiently learning quadruped locomotion in just 8 minutes of raw real-time training utilizing the sample efficiency and minimal computational overhead of the new off-policy algorithm CrossQ. We investigate two control architectures: Predicting joint target positions for agile, high-speed locomotion and Central Pattern Generators for stable, natural gaits. While prior work focused on learning simple forward gaits, our framework extends on-robot learning to omnidirectional locomotion. We demonstrate the robustness of our approach in different indoor and outdoor environments. |
| title | Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2503.08375 |