Target object dynamic adaptation method applied to sorting by conveyor belt

Abstract

The invention discloses a target object dynamic adaptation method applied to sorting by a conveyor belt. The method at least comprises the following steps that S1, a machine vision unit is arranged ina sorting control system, and image information of target objects on the conveyor belt is acquired in real time; S2, the image information is put into a neural network to be matched with a pre-trained identification model, and the category and position information of the target objects in real time are identified; and S3, a machine arm is controlled according to the type and position informationof the target objects so as to enable the machine arm to self-adaptively adjust a motion plan according to the actual state of the target objects. Compared with the prior art, machine vision and machine arm control are combined, and a deep neural network training model is adopted in advance, so that the mechanical arm can be controlled according to the image information obtained by machine visionto enable the mechanical arm to self-adaptively adjust the travel track according to the actual situation of the target objects, the sorting of the target objects is sorted, and dynamic embedding andself-adaption of a target object model is achieved.

Description

technical field [0001] The invention relates to the technical field of industrial automation, in particular to a dynamic adaptation method for a target object applied to conveyor belt sorting. Background technique [0002] In recent years, robot arms have been widely used in industry, but the robot arms used in industry basically operate according to pre-programmed programs, with a high degree of customization, such as repetitive tasks such as handling, painting, and electric welding. However, there are fixed timing requirements for the use of the robotic arm. If there is a deviation from the fixed trajectory or a change in product category during the process, the robotic arm control system will still execute the action according to the original program and cannot make adaptive changes. [0003] Therefore, aiming at the defects of the prior art, it is really necessary to propose a technical solution to solve the technical problems existing in the prior art. Contents of the...

AI Technical Summary

Problems solved by technology

However, the use of these robotic arms has fixed timing requirements. If there is a deviation from the fixed trajectory or a change in product category during the process, the robotic arm control system will still perform actions according to the original program and cannot make adaptive changes.

Images