Design of Automatic Sorting and Transportation System for Fruits and Vegetables Based on Dobot Magician Robotic Arm

Abstract

Aiming at the problems of low automation level and efficiency in agricultural production of sorting and transportation facilities, an automatic sorting and transportation system for fruits and vegetables is designed based on the Dobot Magician robotic arm. The technique combines software with hardware and consists of four parts: a robotic arm, PC, industrial camera, and conveyor belt. The PC receives the information about the conveyor belt, writes the Python script to control the industrial camera to collect images of fruits and vegetables, and loads the YOLOv5s target detection model to identify the target for fruits and vegetables. According to the recognition results and the transformation relationship of the coordinate system, the system can precisely control the robotic arm to complete the sorting of fruits and vegetables and realize the high-efficiency automatic sorting and transportation for the whole process. The system separates the model loading process from YOLOv5s target detection, improves the JUMP movement mode, optimizes the movement path, avoids collisions during movement, and reduces the time spent on target detection and robotic arm movement. After testing, the accuracy rate of fruit and vegetable identification can reach 95%, and the accuracy rate of robotic arm grasping is about 90%.