Privileged Learning for UAV Navigation Fusing Global Point Cloud Priors and Local Perception

Abstract

Fine-grained inspection by Unmanned Aerial Vehicles (UAVs) in substation environments faces stringent challenges for autonomous navigation and real-time obstacle avoidance due to dense equipment and narrow spaces. Existing pure local planners are highly prone to getting trapped in dead ends due to limited fields of view, whereas global planners incur high computational overhead and struggle to react to dynamic disturbances during execution. To address this issue, this paper proposes a UAV navigation framework based on privileged learning. During the training phase, a pre-built global point cloud map is utilized as a prior environment, and a traditional heuristic search algorithm is employed to generate an absolutely safe, collision-free reference trajectory as an expert demonstration. During the deployment phase, the student policy relies solely on spherical depth and intensity images projected from a Mid-360 LiDAR, along with real-time attitude information provided by an Inertial Measurement Unit (IMU). A two-branch lightweight network is utilized to extract local spatial geometric and dynamic features to predict the trajectory. Simulation experiments demonstrate that this method significantly improves obstacle avoidance foresight, navigation success rate, and trajectory smoothness in complex substation scenarios while maintaining extremely low onboard computational overhead.