In-Hand Following of Deformable Linear Objects Using Dexterous Fingers with Tactile Sensing

TL;DR

This paper presents a novel method for in-hand following of deformable linear objects using a dexterous robotic hand with tactile sensing, inspired by human manipulation skills, achieving robustness and generalizability beyond traditional grippers.

Contribution

The work introduces a tactile-sensing dexterous hand framework for in-hand DLO following, surpassing parallel grippers in robustness and adaptability.

Findings

Significantly better performance than parallel grippers.

High robustness and generalizability demonstrated in experiments.

Effective in real-world scenarios with complex DLO manipulation.

Abstract

Most research on deformable linear object (DLO) manipulation assumes rigid grasping. However, beyond rigid grasping and re-grasping, in-hand following is also an essential skill that humans use to dexterously manipulate DLOs, which requires continuously changing the grasp point by in-hand sliding while holding the DLO to prevent it from falling. Achieving such a skill is very challenging for robots without using specially designed but not versatile end-effectors. Previous works have attempted using generic parallel grippers, but their robustness is unsatisfactory owing to the conflict between following and holding, which is hard to balance with a one-degree-of-freedom gripper. In this work, inspired by how humans use fingers to follow DLOs, we explore the usage of a generic dexterous hand with tactile sensing to imitate human skills and achieve robust in-hand DLO following. To enable the hardware system to function in the real world, we develop a framework that includes Cartesian-space arm-hand control, tactile-based in-hand 3-D DLO pose estimation, and task-specific motion design. Experimental results demonstrate the significant superiority of our method over using parallel grippers, as well as its great robustness, generalizability, and efficiency.