Flexible robot vision recognition and positioning system based on depth learning

Abstract

The present invention discloses a flexible robot vision recognition and positioning system based on the depth learning. The system is implemented in the following steps: obtaining an image of a part, carrying out binarization processing on the image of the part to extract an outer contour of the image of the part; finding out a circumscribed rectangle of the outer contour edge in the lateral direction, determining to-be-recognized areas, and normalizing the areas to a standard image; gradually rotating the standard image at an equal angle, finding out a rotation angle alpha when the standard image is rotated to a minimum area of the circumscribed rectangle of the outer contour edge in the lateral direction; using a depth learning network to extract the outer contour edge when the rotation angle is alpha, and recognizing the part and the pose of the part; and according to the rotation angle alpha and the pose, calculating the actual pose of the to-be-recognized part before rotating, and transmitting the pose data to a flexible robot, so that the flexible robot can pick up the to-be-recognized part. According to the system disclosed by the present invention, contour shape features contained in the part image data are automatically extracted layer by layer by using the depth learning network, so that accuracy and adaptability of part recognition and positioning can be greatly improved under the complicated conditions.

Description

technical field [0001] The invention relates to the technical field of visual recognition and positioning in the robot industry, in particular to a flexible robot visual recognition and positioning system based on deep learning. Background technique [0002] In the automatic assembly, handling and sorting of parts by flexible industrial robots, how to accurately identify and locate randomly placed and mixed mechanical parts on the transmission device is a very important and very difficult task. Whether the characteristics of the parts are correctly selected , Whether it is effectively described or not has a significant or even decisive impact on the final recognition and positioning of the soft robot. Under complex conditions such as mixed parts, random placement, viewing angle changes, image scaling, distortion, lighting changes, background interference, etc., the recognition and positioning accuracy of existing flexible robots is not high. The main reason is that the featu...

AI Technical Summary

Problems solved by technology

However, in the face of mixed parts, random placement, viewing angle changes, lighting changes, background interference, and even image scaling or distortion, these methods cannot perform good part target recognition.

Moreover, there are big problems in the validity and adaptability of the above-mentioned artificial features, which require heuristic methods, very professional knowledge, largely rely on personal experience, and may be limited by specific conditions, and the adaptability is often poor

The poor validity and adaptability of artificial features of parts is one of the main reasons for the low accuracy of identification and positioning of existing flexible robots

Images