An AI-Assisted and Self-Powered Smart Robotic Gripper Based on Eco-EGaIn Nanocomposite for Pick-and-Place Operation.

Autor: Goh QL; Department of Mechatronics and Biomedical Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Bandar Sungai Long, Kajang 43000, Selangor, Malaysia., Chee PS; Department of Mechatronics and Biomedical Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Bandar Sungai Long, Kajang 43000, Selangor, Malaysia., Lim EH; Department of Electrical and Electronic Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Bandar Sungai Long, Kajang 43000, Selangor, Malaysia., Ng DW; Department of Mechatronics and Biomedical Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Bandar Sungai Long, Kajang 43000, Selangor, Malaysia.
Jazyk: angličtina
Zdroj: Nanomaterials (Basel, Switzerland) [Nanomaterials (Basel)] 2022 Apr 12; Vol. 12 (8). Date of Electronic Publication: 2022 Apr 12.
DOI: 10.3390/nano12081317
Abstrakt: High compliance and muscle-alike soft robotic grippers have shown promising performance in addressing the challenges in traditional rigid grippers. Nevertheless, a lack of control feedback (gasping speed and contact force) in a grasping operation can result in undetectable slipping and false positioning. In this study, a pneumatically driven and self-powered soft robotic gripper that can recognize the grabbed object is reported. We integrated pressure (P-TENG) and bend (B-TENG) triboelectric sensors into a soft robotic gripper to transduce the features of gripped objects in a pick-and-place operation. Both the P-TENG and B-TENG sensors are fabricated using a porous structure made of soft Ecoflex and Euthethic Gallium-Indium nanocomposite (Eco-EGaIn). The output voltage of this porous setup has been improved by 63%, as compared to the non-porous structure. The developed soft gripper successfully recognizes three different objects, cylinder, cuboid, and pyramid prism, with a good accuracy of 91.67% and has shown its potential to be beneficial in the assembly lines, sorting, VR/AR application, and education training.
Databáze: MEDLINE