VO-safe reinforcement learning for drone navigation

Lin, Feiqiang, Wei, Changyun, Grech, Raphael and Ji, Ze ORCID: https://orcid.org/0000-0002-8968-9902 2024. VO-safe reinforcement learning for drone navigation. Presented at: IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan, 13-17 May 2024. Proceedings of International Conference on Robotics and Automation (ICRA). IEEE, pp. 279-285. 10.1109/ICRA57147.2024.10611487

PDF - Accepted Post-Print Version Download (5MB)

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 RL-trained 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.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Engineering
Publisher:	IEEE
ISBN:	9798350384581
Date of First Compliant Deposit:	5 March 2024
Last Modified:	21 Aug 2024 14:20
URI:	https://orca.cardiff.ac.uk/id/eprint/166897

Actions (repository staff only)

Edit Item