Diffusion-based learning of contact plans for agile locomotion
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_ | 1866908415218941952 |
|---|---|
| author | Dhédin, Victor Ravi, Adithya Kumar Chinnakkonda Jordana, Armand Zhu, Huaijiang Meduri, Avadesh Righetti, Ludovic Schölkopf, Bernhard Khadiv, Majid |
| author_facet | Dhédin, Victor Ravi, Adithya Kumar Chinnakkonda Jordana, Armand Zhu, Huaijiang Meduri, Avadesh Righetti, Ludovic Schölkopf, Bernhard Khadiv, Majid |
| contents | Legged robots have become capable of performing highly dynamic maneuvers in the past few years. However, agile locomotion in highly constrained environments such as stepping stones is still a challenge. In this paper, we propose a combination of model-based control, search, and learning to design efficient control policies for agile locomotion on stepping stones. In our framework, we use nonlinear model predictive control (NMPC) to generate whole-body motions for a given contact plan. To efficiently search for an optimal contact plan, we propose to use Monte Carlo tree search (MCTS). While the combination of MCTS and NMPC can quickly find a feasible plan for a given environment (a few seconds), it is not yet suitable to be used as a reactive policy. Hence, we generate a dataset for optimal goal-conditioned policy for a given scene and learn it through supervised learning. In particular, we leverage the power of diffusion models in handling multi-modality in the dataset. We test our proposed framework on a scenario where our quadruped robot Solo12 successfully jumps to different goals in a highly constrained environment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_03639 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diffusion-based learning of contact plans for agile locomotion Dhédin, Victor Ravi, Adithya Kumar Chinnakkonda Jordana, Armand Zhu, Huaijiang Meduri, Avadesh Righetti, Ludovic Schölkopf, Bernhard Khadiv, Majid Robotics Legged robots have become capable of performing highly dynamic maneuvers in the past few years. However, agile locomotion in highly constrained environments such as stepping stones is still a challenge. In this paper, we propose a combination of model-based control, search, and learning to design efficient control policies for agile locomotion on stepping stones. In our framework, we use nonlinear model predictive control (NMPC) to generate whole-body motions for a given contact plan. To efficiently search for an optimal contact plan, we propose to use Monte Carlo tree search (MCTS). While the combination of MCTS and NMPC can quickly find a feasible plan for a given environment (a few seconds), it is not yet suitable to be used as a reactive policy. Hence, we generate a dataset for optimal goal-conditioned policy for a given scene and learn it through supervised learning. In particular, we leverage the power of diffusion models in handling multi-modality in the dataset. We test our proposed framework on a scenario where our quadruped robot Solo12 successfully jumps to different goals in a highly constrained environment. |
| title | Diffusion-based learning of contact plans for agile locomotion |
| topic | Robotics |
| url | https://arxiv.org/abs/2403.03639 |