Deep learning‐based grasp‐detection method for a five‐fingered industrial robot hand. Issue 1 (4th December 2018)

• Record Type: Journal Article
• Authors: Chao, Ya; Chen, Xingchen; Xiao, Nanfeng
• Is Part Of: IET computer vision. Volume 13:Issue 1(2019)
• Page Start: 61
• Page End: 70
• Publication Date: 2018-12-04
• Subjects: dexterous manipulators -- robot vision -- learning (artificial intelligence) -- object detection -- industrial robots -- data gloves -- feedforward neural nets; object-detection network -- grasp objects -- robotic grasp detection -- grasp-predictor methods -- direct grasp predictor -- multimodal grasp predictor -- deep learning-based grasp-detection method -- deep learning-based object-detection method -- 6-DOF robot arm -- five-fingered industrial robot hand model -- sensor data -- 5DT data glove -- convolutional neural network -- single shot multibox detector; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2018.5002
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : To improve the accuracy of robotic grasp in some uncertain environments, a deep learning‐based object‐detection method for a five‐fingered industrial robot hand model is proposed in this study. The authors first design a five‐fingered industrial robot hand model with 21‐degrees of freedom (DOF). Based on the sensor data of a 5DT data glove, the industrial robot hand can be controlled in real time. They use the object‐detection network's faster regions convolutional neural network and single shot multibox detector to locate the grasp objects. To optimise the robotic grasp detection, two grasp‐predictor methods, direct grasp predictor and multi‐modal grasp predictor, are applied to obtain the best graspable region. In the simulation designed in this study, cooperating with a 6‐DOF robot arm, the five‐fingered industrial robot hand can detect an object accurately and grasp it steadily.