Open access
Sep 2026
PR-Nav: Potential-Shaped Reinforcement Learning with Physics-Modulated Manifolds for Agile Autonomous Navigation
High-speed autonomous navigation of micro aerial vehicles (MAVs) is essential for inspection tasks in restricted spaces (e.g., dense industrial facilities or narrow corridors), where reliable spatial perception and stable flight control are required. However, existing deep reinforcement learning-based navigation method...
Ge-Dan Qin, Tian-Long Wang, Heng Zhong et al.
· Electronics · 0 citations