A Study on Robotic Arm Target Recognition and Grasping Method Based on Deep Learning

摘要

In this research, a 3D visual recognition system has been developed based on Wei deep learning algorithm using GPU. The proposed system consisted of a GPU with depth image function library, which performed image data acquisition, depth information operation, coordinate conversion, image contour search, convolutional class neural network model training, etc., and achieved object pinning by TCP/IP communication with motion control system. The obtained experimental results revealed that the recognition rate of the developed algorithm for target objects at different positions was as high as 92%. Experimental target recognition rates for different angles were relatively low, but reached 87%, and experimental accuracy rates of different luminance values also reached 89%. The errors of robot hand clamping targets also fell within 1–4[Formula: see text]mm, which were higher than experimental expectation.