Research on Multi-USV Collision Avoidance Based on Priority-Driven and Expert-Guided Deep Reinforcement Learning

Deep reinforcement learning (DRL) has demonstrated considerable potential for autonomous collision avoidance in unmanned surface vessels (USVs). However, its application in complex multi-agent maritime environments is often limited by challenges such as convergence issues and high computational cost...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Lixin Xu, Zixuan Wang, Zhichao Hong, Chaoshuai Han, Jiarong Qin, Ke Yang
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2026-01-01
Colecção:	Journal of Marine Science and Engineering
Assuntos:	deep reinforcement learning collision avoidance unmanned surface vessels hybrid reciprocal velocity obstacles COLREGs
Acesso em linha:	https://www.mdpi.com/2077-1312/14/2/197
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!