REASAN: Learning Reactive Safe Navigation for Legged Robots
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911311234859008 |
|---|---|
| author | Yuan, Qihao Cao, Ziyu Cao, Ming Li, Kailai |
| author_facet | Yuan, Qihao Cao, Ziyu Cao, Ming Li, Kailai |
| contents | We present a novel modularized end-to-end framework for legged reactive navigation in complex dynamic environments using a single light detection and ranging (LiDAR) sensor. The system comprises four simulation-trained modules: three reinforcement-learning (RL) policies for locomotion, safety shielding, and navigation, and a transformer-based exteroceptive estimator that processes raw point-cloud inputs. This modular decomposition of complex legged motor-control tasks enables lightweight neural networks with simple architectures, trained using standard RL practices with targeted reward shaping and curriculum design, without reliance on heuristics or sophisticated policy-switching mechanisms. We conduct comprehensive ablations to validate our design choices and demonstrate improved robustness compared to existing approaches in challenging navigation tasks. The resulting reactive safe navigation (REASAN) system achieves fully onboard and real-time reactive navigation across both single- and multi-robot settings in complex environments. We release our training and deployment code at https://github.com/ASIG-X/REASAN. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09537 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | REASAN: Learning Reactive Safe Navigation for Legged Robots Yuan, Qihao Cao, Ziyu Cao, Ming Li, Kailai Robotics We present a novel modularized end-to-end framework for legged reactive navigation in complex dynamic environments using a single light detection and ranging (LiDAR) sensor. The system comprises four simulation-trained modules: three reinforcement-learning (RL) policies for locomotion, safety shielding, and navigation, and a transformer-based exteroceptive estimator that processes raw point-cloud inputs. This modular decomposition of complex legged motor-control tasks enables lightweight neural networks with simple architectures, trained using standard RL practices with targeted reward shaping and curriculum design, without reliance on heuristics or sophisticated policy-switching mechanisms. We conduct comprehensive ablations to validate our design choices and demonstrate improved robustness compared to existing approaches in challenging navigation tasks. The resulting reactive safe navigation (REASAN) system achieves fully onboard and real-time reactive navigation across both single- and multi-robot settings in complex environments. We release our training and deployment code at https://github.com/ASIG-X/REASAN. |
| title | REASAN: Learning Reactive Safe Navigation for Legged Robots |
| topic | Robotics |
| url | https://arxiv.org/abs/2512.09537 |