Abstract
The robotic gripper, a pivotal device in robotics for accomplishing grasping tasks, has revolutionized industrial processes, elevating efficiency and productivity by ensuring secure and precise object handling. However, evolving technological demands have spurred the need for improved grasping capabilities, including precise grasping, force control, shape identification, and adaptability. To meet these challenges, recent developments in composite materials and tactile sensors have led to significant advancements in gripper technology over the past decades. Notably, the integration of an all-printed soft Triboelectric Nanogenerator (TENG) as a tactile sensor has emerged as a cutting-edge solution, offering unique capabilities to perceive physical object shapes and patterns through voltage modulation. In this research, we propose a new approach for the application of a self-powered TENG sensor embedded with a flexible gripper. Moreover, the classification of objects' shapes was conducted by using machine learning.