机器人定位方法、移动机器人及存储介质
By extracting straight line segments from laser point cloud frames and matching them with reference straight line segments, and combining this with the branch and bound method to search for the pose, the problems of low accuracy and computational complexity in laser navigation in complex environments are solved, thus achieving efficient and accurate robot positioning.
CN121577036BActive Publication Date: 2026-07-17ZHEJIANG HUARAY TECH CO LTD
View PDF 2 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHEJIANG HUARAY TECH CO LTD
- Filing Date
- 2025-11-17
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing laser navigation technology has low navigation accuracy and high computational complexity in complex environments. In particular, multi-line lasers require processing a large amount of point cloud data, which leads to high performance requirements for robot platforms.
Method used
By acquiring laser point cloud frames and predicting poses, current and reference line segments are extracted, matched, and angles are calculated. The branch and bound method is used to search for poses in the laser prior map, reducing the number of candidate solutions and lowering computational complexity.
Benefits of technology
It improves the accuracy and efficiency of laser matching, reduces computational complexity, and enhances the accuracy and speed of robot positioning.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN121577036B_ABST
Abstract
本申请公开了一种机器人定位方法、移动机器人及存储介质，该机器人定位方法包括：对激光点云帧进行直线段提取得到多个当前直线段，从激光先验地图中提取处于当前预测位姿邻近范围内的直线段，得到多个参考直线段；对多个当前直线段和多个参考直线段进行匹配，得到匹配成功的直线段对；基于直线段对计算移动机器人的角度，再基于角度采用分支定界法在激光先验地图中搜索移动机器人的位置。将位姿求解进行角度和位置的区分，先充分利用激光检测到的几何信息进行角度计算，再根据分支定界法在激光先验地图中进行位姿搜索时，只需进行位置搜索即可，减少匹配过程中候选解的数量，极大降低了计算复杂度，提高激光匹配的精度和效率。
Need to check novelty before this filing date? Find Prior Art