Robot-based autonomous crawling perception method and system inside blades

By equipping the robot with a multi-sensor array and path planning algorithm, the challenge of autonomous crawling and perception inside wind turbine blades was solved, enabling efficient and accurate obstacle recognition and defect detection, generating feasible paths, and improving detection efficiency and accuracy.

CN120973054BActive Publication Date: 2026-03-10WUHAN DITE ENERGY TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-07-21
Publication Date
2026-03-10

AI Technical Summary

Technical Problem

Existing technologies make it difficult to enable robots to autonomously crawl and perceive inside wind turbine blades, resulting in low detection efficiency and poor accuracy, and making it impossible to effectively identify internal defects.

Method used

Employing a multi-sensor array, including a binocular fisheye camera array and a ToF sensor array, the robot identifies obstacles through panoramic depth images, constructs a 3D point cloud map, generates feasible paths, and avoids obstacles in real time. Combined with an inertial measurement unit and path planning algorithms, it ensures the robot's autonomous movement within the blade.

Benefits of technology

It achieves high-precision obstacle recognition and path planning, improves the robot's detection efficiency and accuracy inside blades, can identify defects on blades, generate 3D point cloud maps with semantic labels, and enhance path planning and obstacle avoidance capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120973054B_ABST
    Figure CN120973054B_ABST
Patent Text Reader

Abstract

This invention provides a robot-based autonomous crawling and perception method and system for the interior of a blade. The method includes mounting a multi-sensor array on a robot, comprising a binocular fisheye camera array and a ToF sensor array. The robot starts from a path's starting point, acquires a panoramic depth image based on the multi-sensor array, identifies obstacles based on the panoramic depth image, constructs a 3D point cloud map based on the obstacles, avoids obstacles based on the 3D point cloud map, generates a feasible path inside the blade, and moves along the feasible path until it reaches the path's end point or the smallest impassable space. This invention ensures autonomous crawling and perception within the blade, ensuring the robot's movement and detection within the blade.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Depth detection method, depth detection device, storage medium and electronic equipment

    CN112927281A

  • Map construction method and device, electronic equipment and storage medium

    CN113284240A