Workpiece grabbing and shifting intervention method and system

Abstract

The invention discloses a workpiece grabbing and shifting intervention method and system. The method comprises the steps that S1, image information of workpieces in a stacking scene is obtained; S2, the workpieces are recognized according to the image information, the number of candidate workpieces capable of being grabbed in the stacking scene is obtained; S3, if the number of the candidate workpieces is smaller than or equal to a set value, a shifting intervention strategy is triggered to shift the stacked workpieces; and S4, the steps S2 and S3 are repeated till the number of the candidate workpieces is larger than or equal to the set value plus 1, and then workpiece grabbing operation is carried out. According to the workpiece grabbing and shifting intervention method and system, shifting path planning is achieved through a grid method, the recognition and grabbing actions are coordinated and optimized, and a systematized solution is provided for the application scene of workpiece stacking recognition and grabbing in the direction of effectively shifting and improving the grabbing efficiency.

Description

technical field [0001] The invention belongs to the technical field of robot grasping, and in particular relates to a method and system for workpiece grasping and toggle intervention. Background technique [0002] Robotic grasping technology based on 2D / 3D vision has been widely used in simple scenarios such as logistics express delivery, warehouse handling, and palletizing. Vision-guided robots enhance the perception of complex environments. In industrial capture scenarios, two-dimensional images can provide dense and rich texture information. After image processing and recognition, the position (two-dimensional coordinates) of the captured workpiece can be obtained, but depth information cannot be obtained. Three-dimensional images can provide distance information in the captured scene. The two types of data have good complementarity, and the fusion of the data of the two modalities can provide a more comprehensive perception of the workpiece grasping scene. In recent ye...

AI Technical Summary

Problems solved by technology

The common disadvantage of these types of methods is that they are all based on the processing strategy after object recognition

However, in scenes where there are mutual occlusions, there are relatively few objects that can be identified, so the above five types of toggle strategies are not suitable for scenes where small artifacts are stacked and occluded.

Images