基于2D视觉的AGV机械手定位方法、装置、终端及存储介质
By using 2D vision-based camera calibration and hand-eye calibration methods, the problem of insufficient positioning accuracy of AGV robotic arms was solved, achieving high-precision positioning, reducing costs, and improving the applicability and stability of the system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DAXIANG IND TECH(SUZHOU) CO LTD
- Filing Date
- 2025-08-27
- Publication Date
- 2026-07-17
AI Technical Summary
Existing monocular vision-based AGV robot positioning systems suffer from insufficient positioning accuracy when faced with factors such as the manufacturing precision of the AGV chassis and uneven ground. Furthermore, the use of 3D cameras is costly and has poor applicability, making it difficult to meet the requirements for high-precision and low-cost positioning.
By adopting a 2D vision-based method, multiple sets of calibration images under different robot poses are acquired to perform camera calibration and hand-eye calibration. The final positioning position is calculated by combining the teaching results, avoiding the use of high-cost 3D cameras, reducing procurement and maintenance costs, and improving positioning accuracy and stability.
It achieves high-precision positioning of AGV robots, reduces procurement and maintenance costs, reduces debugging time and effort, and improves applicability, measurement accuracy and stability in complex environments.
Smart Images
Figure CN120985657B_ABST