LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chiu, Darren, Huang, Zhehui, Ge, Ruohai, Sukhatme, Gaurav S.
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