Autonomous Vehicular Landings on the Deck of an Unmanned Surface Vehicle using Deep Reinforcement Learning. Issue 11 (8th April 2019)

• Record Type: Journal Article
• Authors: Polvara, Riccardo; Sharma, Sanjay; Wan, Jian; Manning, Andrew; Sutton, Robert
• Is Part Of: Robotica. Volume 37:Issue 11(2019)
• Page Start: 1867
• Page End: 1882
• Publication Date: 2019-04-08
• Subjects: Deep reinforcement learning, -- Unmanned aerial vehicle, -- Autonomous agents; Robots -- Periodicals; 629.89205
• DOI: 10.1017/S0263574719000316
• Languages: English
• ISSNs: 0263-5747

Abstract

Summary: Autonomous landing on the deck of a boat or an unmanned surface vehicle (USV) is the minimum requirement for increasing the autonomy of water monitoring missions. This paper introduces an end-to-end control technique based on deep reinforcement learning for landing an unmanned aerial vehicle on a visual marker located on the deck of a USV. The solution proposed consists of a hierarchy of Deep Q-Networks (DQNs) used as high-level navigation policies that address the two phases of the flight: the marker detection and the descending manoeuvre. Few technical improvements have been proposed to stabilize the learning process, such as the combination of vanilla and double DQNs, and a partitioned buffer replay. Simulated studies proved the robustness of the proposed algorithm against different perturbations acting on the marine vessel. The performances obtained are comparable with a state-of-the-art method based on template matching.