Object edge recognition method, device and system based on vision and touch and medium

Abstract

The embodiment of the invention discloses an object edge recognition method, device and system based on vision and touch and a medium, and the method comprises the steps: obtaining the global touch information of an object through an active touch exploration algorithm, and extracting an object edge contour 1 according to the global touch information of the object; processing the three-dimensionalpoint cloud information by using a visual algorithm, and extracting object edge contour information 2, wherein the three-dimensional point cloud information is obtained by a visual sensor; and fusingthe object edge contour 1 and the object edge contour 2 by using a Bayesian model to obtain final edge features of the object. By implementing the embodiment of the invention, the visual sense and thetactile sense are fused to realize the identification of the edge features of the object, and the identified edge features of the object can be used for mechanical arm grabbing, so that the grabbingaccuracy, robustness and reliability of the mechanical arm are improved.

Description

technical field [0001] The invention relates to the technical field of robot cognition, in particular to a method, device, system and medium for object edge recognition based on vision and touch. Background technique [0002] Today, with the rapid development of robot technology, the application fields of robots are becoming wider and wider, and the market's requirements for robots are getting higher and higher, especially in the field of robotic arm grasping. At present, the grasping of manipulators mainly relies on vision to identify and grasp objects. Because of the lack of tactile feedback, it can only grasp objects with simple shapes and high hardness, but cannot grasp objects with complex geometric shapes and soft and fragile, which seriously limits the ability of manipulators and manipulators. scope of application. [0003] The fusion of vision and touch can complement each other. Vision is good at providing geometric and positional information at long distances, wh...

AI Technical Summary

Problems solved by technology

At present, the grasping of manipulators mainly relies on vision to identify and grasp objects. Because of the lack of tactile feedback, it can only grasp objects with simple shapes and high hardness, but cannot grasp objects with complex geometric shapes and soft and fragile, which seriously limits the ability of manipulators and manipulators. scope of application

Images