LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation
This addresses navigation challenges for nano-UAV teams in resource-constrained environments, representing a strong specific gain but incremental over existing RL and planning methods.
The paper tackles the problem of multi-UAV navigation in cluttered spaces under severe resource constraints by introducing LEARN, a lightweight reinforcement learning framework that outperforms state-of-the-art planners by 10% in simulation and achieves fully onboard flight on six quadrotors at speeds up to 2.0 m/s.
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.