An Adaptive Robotic Gripper with L-Shape Fingers for Peg-in-Hole Tasks

Abstract

This paper develops an adaptive gripper for peg-in-hole tasks. Conventional grippers require complicated compliant mechanisms or complicated control strategy and force sensing to successfully insert pegs into holes. Different from them, this paper proposes a simple gripper with an L-shape finger as a low-cost peg-in-hole solution. The basic idea is to divide a peg-in-hole process into a preparation phase and an execution phase, and eliminate uncertainty step-by-step by pushing using the L-shape finger in the preparation phase. The robustness of the gripper for peg-in-hole tasks is examined by repeated executions for different pegs in the International Robotic Exhibition 2017 (IREX) in Tokyo. The experimental section presents details of the executions, and qualitatively shows the high performance of the proposed gripper.