Dumrongsak Kijdech and Supachai Vongbunyong
Yumi, convolution neural networks, YOLO, RGB-D camera, artificial intelligent
Nowadays, in many industries, robots and cameras are used together to detect certain objects and perform specific tasks. However, misdetection can be occurred due to uncertainty of lighting condition, background, and environment. Using a dual arm 7-DOF collaborative robot and RGB-D camera with YOLOv5 in pick- and-place application is proposed in this research to resolve the aforementioned problems. The images are collected and labelled in preparation of the dataset. The dataset is trained with the machine learning algorithm, YOLOv5. It became weight for real- time detection. When RGB images from the camera are sent to YOLOv5, data in regard to position x–y and colour of the bottle is extracted from the depth and the colour images. The experiments were done to assess the performance of YOLO and the grasping capability of the robot.
Important Links:
Go Back
