融合边界信息的空间位置表征方法、存储介质及设备
By fusing boundary information into the SLAM algorithm, a group of active grid cells is generated using the direction and velocity information perceived by the mobile robot. The position cells are corrected when they reach the excitement zone of the boundary cells. This solves the problem of positioning accuracy and cumulative error of the SLAM algorithm in unknown environments and achieves higher accuracy spatial position representation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ANHUI POLYTECHNIC UNIV MECHANICAL & ELECTRICAL COLLEGE
- Filing Date
- 2023-04-07
- Publication Date
- 2026-07-17
AI Technical Summary
Existing SLAM algorithms have low localization accuracy for mobile robots in unknown environments, and long-term operation leads to large cumulative errors. Furthermore, traditional biomimetic SLAM algorithms fail to effectively utilize boundary orientation information.
A spatial position representation method integrating boundary information is proposed. This method generates a grid cell activity group by sensing direction and speed information of a mobile robot, obtains position cell response values using a competitive Hebb learning network, and corrects position cells by activating boundary cells when reaching the boundary cell excitation zone, thereby eliminating cumulative errors and establishing a boundary cell model to update the grid cell distribution pattern.
It improves the positioning accuracy of mobile robots in unknown environments, reduces cumulative errors, ensures that the distribution of grid cells conforms to physiological characteristics, and achieves more accurate spatial position representation.
Smart Images
Figure CN116592882B_ABST