Hand-eye servo robot grasping system and method based on deep learning image segmentation technology

Abstract

The invention relates to the field of robots, in particular to a hand-eye servo robot grabbing system and method based on a depth learning and image segmentation technology. According to the difference, hardware equipment comprises a multi-shaft manipulator, a three-dimensional vision sensor, a color network camera, a single-point laser distance-measuring sensor and an embedded PC. According to the grabbing method, the off-line and on-line combined manner is adopted for the whole body, firstly, the feature extraction and hand-eye calibration based on the depth learning method are completed, then the global rough recognition positioning and local precision positioning combined method is adopted, and the target precision recognition and precision grabbing are achieved. By the adoption of the hand-eye servo robot grabbing system and method based on the depth learning and image segmentation technology, the precision recognition and precision grabbing operation of any target in a scene can be achieved, the precision is high, and the practicability is high.

Description

technical field [0001] The invention relates to the field of robots, in particular to a hand-eye servo robot grasping system and method based on deep learning image segmentation technology. Background technique [0002] Deep learning is a new field in machine learning research. Its motivation is to establish and simulate the neural network of the human brain for analysis and learning. It is an algorithm that simulates the thinking of the human brain to explain data such as images and text. [0003] With the application and development of robotics and deep learning methods, deep learning has been increasingly used in image segmentation. However, it is affected by the accuracy of stereo vision sensors and image segmentation accuracy, and due to the diversity of targets, robot vision The intelligent ability of servo grabbing is limited. Contents of the invention [0004] The purpose of the present invention is to overcome the shortcomings of the prior art, and provide a hand...

AI Technical Summary

Problems solved by technology

[0003] With the application and development of robotics and deep learning methods, deep learning has been increasingly used in image segmentation. However, it is affected by the accuracy of stereo vision sensors and image segmentation accuracy, and due to the diversity of targets, robot vision The intelligent ability of servo grabbing is limited

Images