Abstract
In this paper, a novel path planning scheme based on improved Deep Q-Network (DQN) algorithm for Unmanned Surface Vehicle (USV) docking in complex port environment is proposed. First, the port map is pre-processed for edge expansion, and the level of expansion is set according to the complexity of the port environment and the strength of wind. Next, with the view of solving the problem of slow convergence speed and instability of traditional DQN algorithm, an improved Double DQN (DDQN) algorithm with prioritized experience replay and hyperparameter adaptive control is proposed. In order to strike a balance between exploration and exploitation, a dynamic ε scheme is devised to reduce network stabilization time. Finally, the B-spline technique is used to smoothly interpolate the obtained path coordinate points to obtain a viable USV path for port docking. Simulation results demonstrate the effectiveness and efficiency of the proposed scheme.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
