地图更新方法、电子设备以及存储介质
By dividing and comparing the first and second point cloud maps, and updating the point cloud map using the current policy network, the problem of low accuracy of point cloud maps caused by dynamic obstacles is solved, and higher precision point cloud map updates are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHEJIANG HUARAY TECH CO LTD
- Filing Date
- 2025-10-30
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, the point cloud maps constructed by robots are frequently updated in dynamic obstacle environments, resulting in low accuracy of the updated point cloud maps.
By acquiring the first point cloud map and the second point cloud map, they are divided into multiple initial map blocks according to a preset partitioning rule. After determining the target map block, the comparison result of the first point cloud data and the second point cloud data in the target map block is input into the current policy network to obtain the current prediction result. The target map block is updated in response to the prediction result, and the first point cloud map is updated using the second point cloud data.
It improves the accuracy of point cloud map updates, ensuring that the updated point cloud map more accurately reflects environmental changes.
Smart Images
Figure CN121453027B_ABST