Biomimetic Grasp Control of Robotic Hands Using Deep Learning

• DOI: 10.1109/jeeit58638.2023.10185845
• Publication Date: 2023-07-24T13:37:53Z
• Authors: Yazan M. Dweiri; Mohammad M. AlAjl...; Jawdat R. Ayoub; Alaa Y. Al-Zeer; Ali H. Hejazi
• Keywords: Biomimetics; Wired glove; Pressure Control; Intelligent Control; Robotic hand; Grippers

Gripping force modulation based on pressure feedback is an essential element for intuitive and natural-like control of powered limb prostheses. This paper aims to mimic human hand-gripping in robotic arms by processing dynamic maps with state-of-the-art artificial intelligence algorithms. A pressure-sensing glove was built integrated data acquisition learn grip behavior when holding various objects, then transfer the observed pattern a arm. The readings are processed using recurrent convolutional neural network were able predict biological gripping termination accuracy 84.5% single type object 77% mixed types. proposed system has proven be viable approach biomimetic handling intelligent arm feedback.