SEA-Nav: Efficient Policy Learning for Safe and Agile Quadruped Navigation in Cluttered Environments
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915850330570752 |
|---|---|
| author | Chen, Shiyi Yang, Mingye Mao, Haiyan Zhang, Jiaqi Liu, Haiyi He, Shuheng Zhang, Debing Qiu, Zihao Zhang, Chun |
| author_facet | Chen, Shiyi Yang, Mingye Mao, Haiyan Zhang, Jiaqi Liu, Haiyi He, Shuheng Zhang, Debing Qiu, Zihao Zhang, Chun |
| contents | Efficiently training quadruped robot navigation in densely cluttered environments remains a significant challenge. Existing methods are either limited by a lack of safety and agility in simple obstacle distributions or suffer from slow locomotion in complex environments, often requiring excessively long training phases. To this end, we propose SEA-Nav (Safe, Efficient, and Agile Navigation), a reinforcement learning framework for quadruped navigation. Within diverse and dense obstacle environments, a differentiable control barrier function (CBF)-based shield constraints the navigation policy to output safe velocity commands. An adaptive collision replay mechanism and hazardous exploration rewards are introduced to increase the probability of learning from critical experiences, guiding efficient exploration and exploitation. Finally, kinematic action constraints are incorporated to ensure safe velocity commands, facilitating successful physical deployment. To the best of our knowledge, this is the first approach that achieves highly challenging quadruped navigation in the real world with minute-level training time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09460 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SEA-Nav: Efficient Policy Learning for Safe and Agile Quadruped Navigation in Cluttered Environments Chen, Shiyi Yang, Mingye Mao, Haiyan Zhang, Jiaqi Liu, Haiyi He, Shuheng Zhang, Debing Qiu, Zihao Zhang, Chun Robotics Efficiently training quadruped robot navigation in densely cluttered environments remains a significant challenge. Existing methods are either limited by a lack of safety and agility in simple obstacle distributions or suffer from slow locomotion in complex environments, often requiring excessively long training phases. To this end, we propose SEA-Nav (Safe, Efficient, and Agile Navigation), a reinforcement learning framework for quadruped navigation. Within diverse and dense obstacle environments, a differentiable control barrier function (CBF)-based shield constraints the navigation policy to output safe velocity commands. An adaptive collision replay mechanism and hazardous exploration rewards are introduced to increase the probability of learning from critical experiences, guiding efficient exploration and exploitation. Finally, kinematic action constraints are incorporated to ensure safe velocity commands, facilitating successful physical deployment. To the best of our knowledge, this is the first approach that achieves highly challenging quadruped navigation in the real world with minute-level training time. |
| title | SEA-Nav: Efficient Policy Learning for Safe and Agile Quadruped Navigation in Cluttered Environments |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.09460 |