{"ID":2838788,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.17765","arxiv_id":"2511.17765","title":"LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation","abstract":"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.","short_abstract":"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 safet...","url_abs":"https://arxiv.org/abs/2511.17765","url_pdf":"https://arxiv.org/pdf/2511.17765v1","authors":"[\"Darren Chiu\",\"Zhehui Huang\",\"Ruohai Ge\",\"Gaurav S. Sukhatme\"]","published":"2025-11-21T20:29:03Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.LG\",\"cs.MA\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}