Towards Using Reinforcement Learning for Autonomous Docking of Unmanned Surface Vehicles

Martin Holen, Else-Line Malene Ruud, Narada Dilp Warakagoda, Morten Goodwin, Paal Engelstad, Kristian Muri Knausgård

Abstract: Providing full autonomy to Unmanned Surface Vehicles (USV) is a challenging goal to achieve. Autonomous docking is a subtask that is particularly difficult. The vessel has to distinguish between obstacles and the dock, and the obstacles can be either static or moving. This paper developed a simulator using Reinforcement Learning (RL) to approach the problem.