一种AUV能量优化路径规划方法及装置

By combining the bidirectional RRT* algorithm and the artificial potential field method in AUV path planning, and using flow field information to optimize sampling probability and node position, the blindness and energy consumption problems of AUV path planning in complex marine environments are solved, and more efficient path generation is achieved.

CN121916906BActive Publication Date: 2026-07-17INST OF ACOUSTICS CHINESE ACAD OF SCI

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
INST OF ACOUSTICS CHINESE ACAD OF SCI
Filing Date
2026-01-12
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing AUV path planning algorithms suffer from problems such as high search blindness, high energy consumption, and slow convergence speed in complex marine environments. In particular, they fail to effectively utilize flow field information for energy-saving route planning in dynamic flow fields.

Method used

A bidirectional RRT* algorithm combined with an artificial potential field method is adopted to correct the sampling probability distribution through flow field information, introduce an adaptive flow field optimization mechanism, optimize node positions, and comprehensively consider path length and energy consumption to achieve path planning.

Benefits of technology

It improves the computational and energy efficiency of path planning, generates shorter, lower-energy routes, and adapts to dynamic flow field changes in complex marine environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121916906B_ABST
    Figure CN121916906B_ABST
Patent Text Reader

Abstract

一种AUV能量优化路径规划方法,包括:初始化三维规划环境,构建起点为根节点的第一随机树和终点为根节点的第二随机树;获取三维规划环境的流场信息,若未知则通过传感器实时感知,若已知则调用预存流场模型;基于流场信息计算采样概率分布,通过流场与目标一致性、距离权重和目标偏置策略修正采样概率;第一随机树和第二随机树进行交替扩展,在扩展过程中引入人工势场对节点位置进行流场自适应优化;对新生成节点与其父节点之间的路径段进行碰撞检测,若安全则加入随机树并进行重联优化;第一随机树和第二随机树连接成功时提取全局路径,输出能量优化路径。本方法能够充分利用顺流节能机制,使AUV规划路径长度更短、计算效率更高。
Need to check novelty before this filing date? Find Prior Art