机器人定位方法、移动机器人及存储介质
By acquiring texture images and odometry data from a mobile robot, and matching keyframes and texture feature points from a priori texture map, the problem of low robot localization accuracy was solved, achieving higher accuracy and robust pose estimation.
CN121521110BActive Publication Date: 2026-07-17ZHEJIANG HUARAY TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHEJIANG HUARAY TECH CO LTD
- Filing Date
- 2025-10-20
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing robot positioning technologies are not very accurate in complex environments, and are either costly or susceptible to interference, making them difficult to apply effectively in scenarios requiring high precision.
Method used
By acquiring texture images and odometry data of the mobile robot, matching is performed using keyframes and texture feature points in the prior texture map, the initial pose is calculated by combining odometry data, and the final pose is optimized by matching texture feature points to improve positioning accuracy.
Benefits of technology
It improves the accuracy and robustness of robot localization, ensures smoother pose estimation, and reduces dependence on the environment and sensitivity to disturbances.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN121521110B_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：基于里程计数据和前一时刻位姿计算当前时刻的位姿得到初始位姿，从先验纹理地图中查找关键帧位姿与初始位姿之间的距离满足预设距离条件的关键帧，得到关联关键帧；将关联关键帧对应的纹理特征点类型作为目标类型，从当前纹理图像中提取目标类型的纹理特征点；对关联关键帧与当前纹理图像之间的纹理特征点进行匹配得到匹配点对，基于匹配点对计算得到当前时刻最终的位姿。可以通过关联关键帧对应的纹理特征点类型确定当前纹理图像需要提取的纹理特征点的类型，从而保证能提取有效的纹理信息来提高定位精度，使得位姿估计更加平滑、鲁棒，精度更高。
Need to check novelty before this filing date? Find Prior Art