Title: YOLO-based gripping method for industrial robots

Authors: Wei Gao

Addresses: Hunan College of Information, Changsha, Hunan, China

Abstract: With the current development of industrial intelligence in society, new challenges have been created for traditional industrial robots, and grasping is a significant capability of robots. The problem of robot grasping has been a famous research problem at home and abroad. Machine vision has developed very rapidly in recent years, and combining machine vision, deep learning and robotics has become a mainstream trend in the development of industrial robots. In this paper, two target detection models are optimised, and the Faster R-CNN target detection model is optimised to adjust the network structure, the scale size of anchors, the target classification and the position regression structure. The YOLO-v2 target detection model is optimised, and the Darknet-19 feature extraction network structure and the loss function are adjusted. The experimental results demonstrate that the target detection network learns useful image features, and the grasping system can complete the autonomous grasping task.

Keywords: convolutional neural network; target detection; automatic grasping.

DOI: 10.1504/IJCAT.2024.144660

International Journal of Computer Applications in Technology, 2024 Vol.75 No.1, pp.48 - 57

Received: 10 Apr 2023
Accepted: 31 Jul 2023
Published online: 26 Feb 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article