VO-Safe Reinforcement Learning for Drone Navigation

Abstract

This work is focused on reinforcement learning (RL)-based navigation for drones, whose localisation is based on visual odometry (VO). Such drones should avoid flying into areas with poor visual features, as this can lead to deteriorated localization or complete loss of tracking. To achieve this, we propose a hierarchical control scheme, which uses an RLtrained policy as the high-level controller to generate waypoints for the next control step and a low-level controller to guide the drone to reach subsequent waypoints. For the high-level policy training, unlike other RL-based navigation approaches, we incorporate awareness of VO performance into our policy by introducing pose estimation-related punishment. To aid robots in distinguishing between perception-friendly areas and unfavoured zones, we instead provide semantic scenes, as input for decision-making instead of raw images. This approach also helps minimise the sim-to-real application gap.The authors thank the China Scholarship Council (CSC) for financially supporting Feiqiang Lin in his PhD programme (201906020170).