GeCCo -- a Generalist Contact-Conditioned Policy for Loco-Manipulation Skills on Legged Robots
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908560336617472 |
|---|---|
| author | Atanassov, Vassil Yu, Wanming Gangapurwala, Siddhant Wilson, James Havoutis, Ioannis |
| author_facet | Atanassov, Vassil Yu, Wanming Gangapurwala, Siddhant Wilson, James Havoutis, Ioannis |
| contents | Most modern approaches to quadruped locomotion focus on using Deep Reinforcement Learning (DRL) to learn policies from scratch, in an end-to-end manner. Such methods often fail to scale, as every new problem or application requires time-consuming and iterative reward definition and tuning. We present Generalist Contact-Conditioned Policy (GeCCo) -- a low-level policy trained with Deep Reinforcement Learning that is capable of tracking arbitrary contact points on a quadruped robot. The strength of our approach is that it provides a general and modular low-level controller that can be reused for a wider range of high-level tasks, without the need to re-train new controllers from scratch. We demonstrate the scalability and robustness of our method by evaluating on a wide range of locomotion and manipulation tasks in a common framework and under a single generalist policy. These include a variety of gaits, traversing complex terrains (eg. stairs and slopes) as well as previously unseen stepping-stones and narrow beams, and interacting with objects (eg. pushing buttons, tracking trajectories). Our framework acquires new behaviors more efficiently, simply by combining a task-specific high-level contact planner and the pre-trained generalist policy. A supplementary video can be found at https://youtu.be/o8Dd44MkG2E. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17582 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GeCCo -- a Generalist Contact-Conditioned Policy for Loco-Manipulation Skills on Legged Robots Atanassov, Vassil Yu, Wanming Gangapurwala, Siddhant Wilson, James Havoutis, Ioannis Robotics Most modern approaches to quadruped locomotion focus on using Deep Reinforcement Learning (DRL) to learn policies from scratch, in an end-to-end manner. Such methods often fail to scale, as every new problem or application requires time-consuming and iterative reward definition and tuning. We present Generalist Contact-Conditioned Policy (GeCCo) -- a low-level policy trained with Deep Reinforcement Learning that is capable of tracking arbitrary contact points on a quadruped robot. The strength of our approach is that it provides a general and modular low-level controller that can be reused for a wider range of high-level tasks, without the need to re-train new controllers from scratch. We demonstrate the scalability and robustness of our method by evaluating on a wide range of locomotion and manipulation tasks in a common framework and under a single generalist policy. These include a variety of gaits, traversing complex terrains (eg. stairs and slopes) as well as previously unseen stepping-stones and narrow beams, and interacting with objects (eg. pushing buttons, tracking trajectories). Our framework acquires new behaviors more efficiently, simply by combining a task-specific high-level contact planner and the pre-trained generalist policy. A supplementary video can be found at https://youtu.be/o8Dd44MkG2E. |
| title | GeCCo -- a Generalist Contact-Conditioned Policy for Loco-Manipulation Skills on Legged Robots |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.17582 |