Robot operation task fine perception and positioning method based on visual-tactile hybrid modeling
By combining vision and touch, the problems of small measurement range of tactile sensors and large positioning error of visual sensors are solved, realizing high-precision perception and positioning of robot operation tasks, and improving positioning accuracy and modeling efficiency.
CN118418119BActive Publication Date: 2026-06-23NORTHWESTERN POLYTECHNICAL UNIV
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NORTHWESTERN POLYTECHNICAL UNIV
- Filing Date
- 2024-04-26
- Publication Date
- 2026-06-23
Smart Images
Figure CN118418119B_ABST
Abstract
The application relates to the technical field of robot task perception, in particular to a robot operation task fine perception and positioning method based on visual-tactile hybrid modeling, which comprises the following steps: acquiring a task target image of a robot; dividing the task target image into multiple single tactile sweeping areas; acquiring an optimized target single tactile sweeping area and acquiring an rgb image about visual-tactile; extracting an edge contour in the rgb image, and sequentially performing contour splicing and completion to obtain a target edge contour; and acquiring a final contour area of the task target. The method of combining visual modeling with tactile modeling is adopted to realize higher-precision positioning of the task target.
Need to check novelty before this filing date? Find Prior Art