Manuscript received May 30, 2023; revised June 15 date, 2023; accepted June 25, 2023; published April 15, 2024
Abstract—In order to derive local search path points for unmanned surface vehicles in complex coastal areas, the operator has to take the points manually. To solve this problem, we propose an algorithm for automatic generation of local search path points that combines reinforcement learning and the existing shortest path planning algorithm. The demonstration results of the algorithm show a reduction in travelling distance of about 34% and a reduction in redundant visit of 66%. It is expected that this developed algorithm can be more effectively used to automatically generate search path points for complex coastal areas in the future.
Keywords—reconnaissance, reinforcement learning, A* Algorithm, path planning, automation, simulation
Cite: Sejin Kim, Mingyu Shin, Hyojun Ahn, Sunoh Byun, Eunseo Baek, and Yongjin Kwon, "Automatic Path Generation of USV Using Reinforcement Learning for Complex Coastal Areas," International Journal of Machine Learning vol. 14, no. 2, pp. 38-42, 2024.
Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).