车辆清洗方法、装置、设备、存储介质及程序产品
By extracting feature data from the vehicle's 3D model and performing segmentation and region growing processes, the problems of fragmentation and classification errors in cleaning complex curved surfaces of modern automobiles were solved, achieving efficient and accurate vehicle cleaning results.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 上海云骥智行智能科技有限公司
- Filing Date
- 2026-04-23
- Publication Date
- 2026-07-17
AI Technical Summary
When dealing with the complex transition surfaces of modern automobiles, existing technologies are prone to fragmentation and classification errors in the segmentation of the 3D model of the vehicle body, which leads to failure in the path planning of the robotic arm and affects cleaning efficiency and quality.
By acquiring a 3D model of the vehicle, extracting feature data, segmenting based on preset direction categories and normal vectors, and combining region growing processing and preset mapping relationships, continuous target segmentation results are generated to ensure the continuity of path planning.
It improves the efficiency and accuracy of vehicle washing, avoids fragmentation problems caused by local normal vector anomalies, and meets the path planning requirements of car wash robots.
Smart Images
Figure CN122090067B_ABST