Disentangling Dense Multi-Cable Knots

Vainavi Viswanath*, Jennifer Grannen*, Priya Sundaresan*, Brijen Thananjeyan, Ashwin Balakrishna, Ellen Novoseller, Jeffrey Ichnowski, Michael Laskey, Joseph E. Gonzalez, Ken Goldberg

*equal contribution

Paper: [Link]

Abstract

Keywords: Deformable Manipulation, Computer Vision

Disentangling two or more cables requires many steps to remove crossings between and within cables. We formalize the problem of disentangling multiple cables and present an algorithm, Iterative Reduction Of Non-planar Multiple cAble kNots (IRON-MAN), that outputs robot actions to remove crossings from multi-cable knotted structures. We instantiate this algorithm with a learned perception system inspired by prior work in single-cable untying, which given an image input, can disentangle two-cable twists, three-cable braids, and knots of two or three cables, such as overhand, square, carrick bend, sheet bend, crown, and fisherman’s knots. IRON-MAN keeps track of task-relevant keypoints corresponding to target cable endpoints and crossings and iteratively disentangles the cables by identifying and undoing crossings that are critical to knot structure. Using a da Vinci surgical robot, we experimentally evaluate the effectiveness of IRON-MAN on untangling multi-cable knots of types that appear in the training data, as well as generalizing to novel classes of multi-cable knots. Results suggest that IRON-MAN is effective in disentangling knots involving up to three cables with 80.5% success and generalizing to knot types that are not present during training, with cables of both distinct or identical colors.

IROS 2021 Video Submission

IROS_2021_final_compressed.mp4

IRON-MAN: An Algorithm for Disentangling Multi-cable Knots

We define an algorithmic supervisor IRON-MAN (Iterative Reduction of Non-planar Multiple cAble kNots) for the task of disentangling multi-cable knots. IRON-Man extends prior work by using a graph representation of a knot configuration to perform multi-cable disentangling actions. IRON-MAN employs five primitives — (1) Reidemeister (straightening) moves, (2) Node Deletion (undo) moves, (3) Cable Extraction moves, (4) Re-posing (center the cable in the workspace) moves, and (5) wedge-recovery moves (freeing grippers stuck to the cable). We disentangle densely knotted cables by sequentially undoing the right-most under-crossing in the scene and extracting cables from the scene as they become disentangled, performing re-posing and wedge-recovery actions when required. We introduce the distinction on trivial and non-trivial crossings. Trivial crossings are not integral to the knot structure and can be undone with reidemeister moves while non-trivial crossings are integral to the knot structure and require node deletion moves.