The article presents TacFR-Gripper, a Fin Ray-based robotic gripper with tactile skin for handling diverse objects. It can grasp objects of various shapes and stiffness levels. The gripper uses Force Sensitive Resistor sensors to provide tactile skin, allowing the robot to perceive contact information during manipulation. The design also includes a Graph Neural Network-based tactile perception approach for reliable grasping. The gripper’s performance was evaluated through physical experiments, showing it can handle complex-shaped objects with a high success rate and perform dexterous in-hand manipulation.
Publication date: 20 Nov 2023
Project Page: https://sites.google.com/view/tacfr-gripper/homepage
Paper: https://arxiv.org/pdf/2311.10611
