Object capture based underwater robot obstacle avoidance system

CN121069969BActive Publication Date: 2026-07-10YITUO ELECTRIC CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
YITUO ELECTRIC CO LTD
Filing Date
2025-07-17
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Underwater robots struggle to accurately identify obstacles in complex environments, especially in dynamic environments where the accuracy of identifying fast-moving obstacles is insufficient. Furthermore, traditional vision algorithms struggle to process large amounts of image data in real time, resulting in low obstacle avoidance efficiency.

Method used

Multimodal environmental data is acquired by combining a short-exposure dynamic imaging module and a multi-beam forward-looking sonar with a polarization imaging module. Optical distortion is corrected by constructing a water scattering model using the Mueller matrix, and motion state is corrected by combining an inertial measurement unit and a Doppler current profiler. A dynamic risk field is constructed to generate obstacle avoidance strategies.

Benefits of technology

It improves the underwater robot's accuracy in identifying obstacles and its efficiency in obstacle avoidance, enhances its maneuverability and safety in complex environments, reduces the risk of collisions, and improves the continuity and reliability of underwater operations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121069969B_ABST
    Figure CN121069969B_ABST
Patent Text Reader

Abstract

The application provides an underwater robot obstacle avoidance system based on object capture. The method comprises the following steps: collecting spatial vision information of a target area where an underwater robot is located in real time; acquiring multi-modal environment data of the target area where the underwater robot is located; constructing a water body scattering model for correcting optical distortion in the spatial vision information by using Mueller matrix for polarization light data in the multi-modal environment data; acquiring real-time motion state of the underwater robot by using an inertial measurement unit; acquiring water flow disturbance data of the underwater robot, and correcting position drift in the real-time motion state caused by water flow disturbance by using a water flow model and the real-time collected water flow disturbance data; constructing a dynamic risk field corresponding to the target area based on the spatial vision information, the corrected real-time motion state and sonar ranging data in the multi-modal environment data; and generating an obstacle avoidance strategy of the underwater robot in a future preset period based on the dynamic risk field, so as to realize dynamic avoidance of obstacles.
Need to check novelty before this filing date? Find Prior Art