Autonomously Unweaving Multiple Cables Using Visual Feedback

2025-12-13

AI Summary

Multi-cable entanglement—characterized by interweaving, crossing, and topological coupling—poses significant challenges for autonomous manipulation. Method: This paper proposes a vision-guided, graph neural network–based approach for autonomous cable untangling. It models cable configurations as geometric-topological graphs encoding both deformation states and connectivity; introduces a novel state transition model that jointly captures bending and straightening dynamics; and designs a dual-primitive “grasp-and-place” action policy enabling end-to-end untangling in knot-free multi-cable scenarios. The framework integrates vision-driven joint geometric-topological representation, prediction-informed action cost optimization, and a closed-loop perception-planning-execution architecture. Results: Evaluated on wire and shoelace untangling tasks, the method achieves an average success rate of 84%, substantially outperforming single-cable untying methods when generalized to multi-cable settings.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Many cable management tasks involve separating out the different cables and removing tangles. Automating this task is challenging because cables are deformable and can have combinations of knots and multiple interwoven segments. Prior works have focused on untying knots in one cable, which is one subtask of cable management. However, in this paper, we focus on a different subtask called multi-cable unweaving, which refers to removing the intersections among multiple interwoven cables to separate them and facilitate further manipulation. We propose a method that utilizes visual feedback to unweave a bundle of loosely entangled cables. We formulate cable unweaving as a pick-and-place problem, where the grasp position is selected from discrete nodes in a graph-based cable state representation. Our cable state representation encodes both topological and geometric information about the cables from the visual image. To predict future cable states and identify valid actions, we present a novel state transition model that takes into account the straightening and bending of cables during manipulation. Using this state transition model, we select between two high-level action primitives and calculate predicted immediate costs to optimize the lower-level actions. We experimentally demonstrate that iterating the above perception-planning-action process enables unweaving electric cables and shoelaces with an 84% success rate on average.

Problem

• Autonomously unweaving multiple entangled cables
• Separating interwoven cables using visual feedback
• Planning actions with topological and geometric state representation

Innovation

• Visual feedback for cable unweaving
• Graph-based state representation with topology
• State transition model for action prediction