基于侧扫声纳的自主水下机器人海底管线跟踪方法及装置

By combining side-scan sonar and Kalman filter, the forward-looking distance and heading of the underwater robot are dynamically adjusted, solving the problems of detecting discontinuities and controlling oscillations in autonomous tracking of subsea pipelines, and achieving high-precision and stable tracking in complex sea conditions.

CN122172201BActive Publication Date: 2026-07-17SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
Filing Date
2026-05-09
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing technologies for autonomous tracking of subsea pipelines suffer from discontinuous and uncertain detection results, and are prone to oscillations during the control process, lacking forward-looking prediction, resulting in insufficient tracking reliability under complex sea conditions.

Method used

An autonomous underwater robot based on side-scan sonar is used to track subsea pipelines. A Kalman filter is used for state estimation, and combined with trajectory quality assessment and adaptive line-of-sight guidance law, the forward-looking distance and heading are dynamically adjusted to generate a smooth target tracking trajectory.

Benefits of technology

It improves the accuracy and stability of submarine pipeline tracking, suppresses the effects of environmental interference and noise, and ensures stable tracking under complex sea conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122172201B_ABST
    Figure CN122172201B_ABST
Patent Text Reader

Abstract

本发明提供一种基于侧扫声纳的自主水下机器人海底管线跟踪方法及装置,涉及水下管线跟踪技术领域,所述方法包括:在控制水下机器人在管线调查区域内进行梳状搜索期间,利用侧扫声纳持续获取海底声学图像;基于海底声学图像检测管线点迹,并基于管线点迹确定管线的初始轨迹;利用卡尔曼滤波器基于所述初始轨迹进行所述管线的状态估计;以状态估计结果为基础,采用轨迹质量评估方法确定初始轨迹的空间长度、置信度及连续性,生成轨迹评分;响应于轨迹评分满足预设要求,确定所述初始轨迹为水下机器人的目标跟踪轨迹;基于所述目标跟踪轨迹动态调整所述水下机器人的前视距离及航向。
Need to check novelty before this filing date? Find Prior Art