Feasibility-Guided Planning over Multi-Specialized Locomotion Policies
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917257594011648 |
|---|---|
| author | Luo, Ying-Sheng Wang, Lu-Ching Mandala, Hanjaya Chou, Yu-Lun Christmann, Guilherme Chen, Yu-Chung Chan, Yung-Shun Lee, Chun-Yi Chen, Wei-Chao |
| author_facet | Luo, Ying-Sheng Wang, Lu-Ching Mandala, Hanjaya Chou, Yu-Lun Christmann, Guilherme Chen, Yu-Chung Chan, Yung-Shun Lee, Chun-Yi Chen, Wei-Chao |
| contents | Planning over unstructured terrain presents a significant challenge in the field of legged robotics. Although recent works in reinforcement learning have yielded various locomotion strategies, planning over multiple experts remains a complex issue. Existing approaches encounter several constraints: traditional planners are unable to integrate skill-specific policies, whereas hierarchical learning frameworks often lose interpretability and require retraining whenever new policies are added. In this paper, we propose a feasibility-guided planning framework that successfully incorporates multiple terrain-specific policies. Each policy is paired with a Feasibility-Net, which learned to predict feasibility tensors based on the local elevation maps and task vectors. This integration allows classical planning algorithms to derive optimal paths. Through both simulated and real-world experiments, we demonstrate that our method efficiently generates reliable plans across diverse and challenging terrains, while consistently aligning with the capabilities of the underlying policies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07932 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Feasibility-Guided Planning over Multi-Specialized Locomotion Policies Luo, Ying-Sheng Wang, Lu-Ching Mandala, Hanjaya Chou, Yu-Lun Christmann, Guilherme Chen, Yu-Chung Chan, Yung-Shun Lee, Chun-Yi Chen, Wei-Chao Robotics Planning over unstructured terrain presents a significant challenge in the field of legged robotics. Although recent works in reinforcement learning have yielded various locomotion strategies, planning over multiple experts remains a complex issue. Existing approaches encounter several constraints: traditional planners are unable to integrate skill-specific policies, whereas hierarchical learning frameworks often lose interpretability and require retraining whenever new policies are added. In this paper, we propose a feasibility-guided planning framework that successfully incorporates multiple terrain-specific policies. Each policy is paired with a Feasibility-Net, which learned to predict feasibility tensors based on the local elevation maps and task vectors. This integration allows classical planning algorithms to derive optimal paths. Through both simulated and real-world experiments, we demonstrate that our method efficiently generates reliable plans across diverse and challenging terrains, while consistently aligning with the capabilities of the underlying policies. |
| title | Feasibility-Guided Planning over Multi-Specialized Locomotion Policies |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.07932 |