LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914167195172864 |
|---|---|
| author | Chiu, Darren Huang, Zhehui Ge, Ruohai Sukhatme, Gaurav S. |
| author_facet | Chiu, Darren Huang, Zhehui Ge, Ruohai Sukhatme, Gaurav S. |
| contents | Nano-UAV teams offer great agility yet face severe navigation challenges due to constrained onboard sensing, communication, and computation. Existing approaches rely on high-resolution vision or compute-intensive planners, rendering them infeasible for these platforms. We introduce LEARN, a lightweight, two-stage safety-guided reinforcement learning (RL) framework for multi-UAV navigation in cluttered spaces. Our system combines low-resolution Time-of-Flight (ToF) sensors and a simple motion planner with a compact, attention-based RL policy. In simulation, LEARN outperforms two state-of-the-art planners by $10\%$ while using substantially fewer resources. We demonstrate LEARN's viability on six Crazyflie quadrotors, achieving fully onboard flight in diverse indoor and outdoor environments at speeds up to $2.0 m/s$ and traversing $0.2 m$ gaps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_17765 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation Chiu, Darren Huang, Zhehui Ge, Ruohai Sukhatme, Gaurav S. Robotics Machine Learning Multiagent Systems Nano-UAV teams offer great agility yet face severe navigation challenges due to constrained onboard sensing, communication, and computation. Existing approaches rely on high-resolution vision or compute-intensive planners, rendering them infeasible for these platforms. We introduce LEARN, a lightweight, two-stage safety-guided reinforcement learning (RL) framework for multi-UAV navigation in cluttered spaces. Our system combines low-resolution Time-of-Flight (ToF) sensors and a simple motion planner with a compact, attention-based RL policy. In simulation, LEARN outperforms two state-of-the-art planners by $10\%$ while using substantially fewer resources. We demonstrate LEARN's viability on six Crazyflie quadrotors, achieving fully onboard flight in diverse indoor and outdoor environments at speeds up to $2.0 m/s$ and traversing $0.2 m$ gaps. |
| title | LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation |
| topic | Robotics Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2511.17765 |