Dispersedly stacked material pickup apparatus and method

Abstract

The present invention discloses a dispersedly stacked material pickup apparatus and method. The apparatus comprises a robot, a host computer, and a light measuring system; the light measuring system comprises a projection device, a left camera and a right camera that are respectively located on the left and right sides of the projection device; the projection device sequentially projects a Gray code image in the material pickup scene; the left camera and the right camera respectively collect the Gray code images in the material pickup scene and transmit the Gray code images to the host computer; according to the Gray code images collected by the left camera and the right camera, the host computer reconstructs the point cloud of the target object, carries out identification and locating on the target object in the material pickup scene to obtain the three-dimensional stacking location and the three-dimensional posture of the target object, formulates the pickup strategy, plans the pickup path of the robotic arm of the robot, and transmits the pickup path to the robot; and the robot performs a pickup operation according to the pickup path. According to the apparatus and method disclosed by the present invention, the problem that the robot path is difficult to plan due to the arbitrary posture of the dispersedly stacked material can be effectively solved.

Description

technical field [0001] The invention belongs to the field of robot application, and in particular relates to a device and method for picking up materials for random stacking. Background technique [0002] Vision-guided robot grasping technology is more and more widely used in industry, and the application scenarios are also increasingly rich. With the development of technology, robots will gradually replace humans to complete some simple, repetitive, and low-intelligence tasks. [0003] At present, the application of vision-guided robot grasping mainly focuses on the picking of target objects on a fixed plane based on 2D visual detection. The 2D visual detection method can provide limited part position information, and usually can only limit the parts to a fixed measurement depth. for detection, which obviously limits the scope of application of the robot. [0004] With the development and iteration of depth image acquisition equipment, it is no longer difficult and expensi...

AI Technical Summary

Problems solved by technology

However, since the processing object of 3D objects is a large amount of point cloud data, which has one more dimension of information than 2D images, the processing efficiency is much slower than that of 2D images, and there is no more efficient 3D object recognition algorithm yet.

In addition, due to the randomness of scattered materials, it is difficult to plan the picking path of the robot

Due to the above reasons, there are very few applications of robots picking up scattered materials in industry.

Images