Abstract
<jats:title>Summary</jats:title><jats:p>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.</jats:p>
Original language | English |
---|---|
Pages (from-to) | 1-16 |
Number of pages | 0 |
Journal | Robotica |
Volume | 0 |
Issue number | 0 |
Early online date | 8 Apr 2019 |
DOIs | |
Publication status | Published - 8 Apr 2019 |