VO-Safe Reinforcement Learning for Drone Navigation
Feiqiang Lin,Changyun Wei,Raphael Grech,Ze Ji,Feiqiang Lin,Changyun Wei,Raphael Grech,Ze Ji
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 RL-trained policy as the high-level controller ...
