Autonomously Untangling Long Cables

TL;DR

This paper presents a robotic system that autonomously untangles long cables using specialized perception, motion primitives, and an iterative algorithm, achieving moderate success rates on various knot configurations.

Contribution

It introduces a novel algorithm, SGTM, combining perception and motion primitives for autonomous cable untangling with a bilateral robot.

Findings

67% success on simple knots

50% success on complex knots

Effective for cables up to 3 meters long

Abstract

Cables are ubiquitous in many settings and it is often useful to untangle them. However, cables are prone to self-occlusions and knots, making them difficult to perceive and manipulate. The challenge increases with cable length: long cables require more complex slack management to facilitate observability and reachability. In this paper, we focus on autonomously untangling cables up to 3 meters in length using a bilateral robot. We develop RGBD perception and motion primitives to efficiently untangle long cables and novel gripper jaws specialized for this task. We present Sliding and Grasping for Tangle Manipulation (SGTM), an algorithm that composes these primitives to iteratively untangle cables with success rates of 67% on isolated overhand and figure-eight knots and 50% on more complex configurations. Supplementary material, visualizations, and videos can be found at https://sites.google.com/view/rss-2022-untangling/home.