Automatic Path Generation of USV Using Reinforcement Learning for Complex Coastal Areas

International Journal of Machine Learning · 2024

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.

Read the paper · More papers on PaperTik