自主定位方法、装置、设备及计算机可读存储介质

By fusing inertial data and point cloud data, motion distortion is corrected and positioning is performed, solving the problem of low positioning accuracy on moving and rotating objects and achieving high-precision autonomous positioning.

CN115115702BActive Publication Date: 2026-07-17GUANGDONG INST OF ARTIFICIAL INTELLIGENCE & ADVANCED COMPUTING
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
GUANGDONG INST OF ARTIFICIAL INTELLIGENCE & ADVANCED COMPUTING
Filing Date
2022-05-24
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing autonomous positioning methods that do not rely on satellite signals are not robust to moving or rotating objects, resulting in low positioning accuracy.

Method used

By collecting point cloud data and inertial data of the target, the motion distortion of the point cloud data is corrected using the inertial data, and the distorted data is fused with the inertial data to construct a maximum a posteriori estimate to achieve autonomous positioning.

Benefits of technology

It improves the robustness of positioning and the accuracy of mapping the positioning target, enhances the precision of autonomous positioning, and reduces computation time and positioning delay.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115115702B_ABST
    Figure CN115115702B_ABST
Patent Text Reader

Abstract

本发明提供一种自主定位方法、装置、设备及计算机可读存储介质，所述方法包括：采集定位目标的点云数据和惯性数据，并根据所述惯性数据确定所述定位目标的预估位姿；利用所述惯性数据校正所述点云数据的运动畸变，得到去畸变数据；根据所述预估位姿融合所述去畸变数据和所述惯性数据，得到融合定位数据，并根据所述融合定位数据对所述定位目标进行定位。通过融合惯性数据和点云数据，实现对定位目标的不依赖于外界的自主定位，同时，通过校正点云数据的运动畸变，并将去畸变后的点云数据与惯性数据融合后对定位目标进行定位，提高了定位鲁棒性和定位目标的建图准确性，从而提高了自主定位的精确度。
Need to check novelty before this filing date? Find Prior Art