Autonomous Sorting with 6 DOF Robotic Arm using Machine Vision

Numerous industrial and logistical applications frequently use robotic automation. Robots must be able to autonomously classify objects in congested surroundings to increase operational effectiveness and minimize human involvement. The use of robotic arms for autonomous sorting tasks has gained significant attention due to its potential to enhance efficiency and productivity in various industries. This robotic system is based on the Niryo-ned robotic arm, combined with an overhead USB webcam. For the object detection purpose YOLO v7 (You Only Look Once version 7) and Faster RCNN (Region based Convolutional Neural Networks) were trained. For that custom dataset was used. Dataset consists of different colored cubes. After training YOLO v7 has given better accuracy 98.4% as compared to faster RCNN 94.1%. As a result, YOLO v7 was chosen as the preferred model for autonomously sorting objects using the Niryo Ned robot. Further by adding novel features to the existing model autonomous sorting has successfully completed by niryo ned robot.