基于无人艇路径规划方法的海上救援技术研究OA
Maritime Rescue Technology Reserch Based on Unmanned Boat Path Planning Method
为了提高海上救援的效率和安全性,根据无人艇的性能优化动作空间,采用Q-Learning算法学习适应复杂多变的环境,选择模拟退火算法保证全局最优解的搜索.结果表明:在较小规模海上环境中,该方法的平均路径长度比传统的模拟退火算法短了 10.02％,平均耗时减少了 1.41％,且没有出现急转角.
In order to improve the efficiency and safety of maritime rescue,this study optimizes the action space based on the performance of unmanned boats,adopts Q-Learning algorithm to learn and adapt to complex and changing environments,and selects simulated annealing algorithm to ensure the search for the global optimal solution.The results show that the average path length of the adopted method in small-scale offshore environments is 10.02％shorter than traditional simulated annealing algorithms,and the average time is reduced by 1.41％,without sharp corners.
毛君赫;李峰;马裕清;胡家庆
中国人民解放军海军军医大学卫生勤务学系,上海 200433中国人民解放军海军军医大学卫生勤务学系,上海 200433中国人民解放军海军军医大学海军医学系,上海 200433中国人民解放军海军军医大学卫生勤务学系,上海 200433
医药卫生
路径规划USVQ-Learning模拟退火算法海上救援
path planningUSVQ-Learningsimulated annealing algorithmsea rescue
《机械制造与自动化》 2026 (2)
126-130,5
评论