mlsanityData to 7 Oct 2026

SGTM 2.0: Autonomously Untangling Long Cables using Interactive Perception

arXiv 2209.13706 ↗First posted 27 Sep 2022cs.RO cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Cables are commonplace in homes, hospitals, and industrial warehouses and are prone to tangling. This paper extends prior work on autonomously untangling long cables by introducing novel uncertainty quantification metrics and actions that interact with the cable to reduce perception uncertainty. We present Sliding and Grasping for Tangle Manipulation 2.0 (SGTM 2.0), a system that autonomously untangles cables approximately 3 meters in length with a bilateral robot using estimates of uncertainty at each step to inform actions. By interactively reducing uncertainty, Sliding and Grasping for Tangle Manipulation 2.0 (SGTM 2.0) reduces the number of state-resetting moves it must take, significantly speeding up run-time. Experiments suggest that SGTM 2.0 can achieve 83% untangling success on cables with 1 or 2 overhand and figure-8 knots, and 70% termination detection success across these configurations, outperforming SGTM 1.0 by 43% in untangling accuracy and 200% in full rollout speed. Supplementary material, visualizations, and videos can be found at sites.google.com/view/sgtm2.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 27 of its 43 references that are in the map. First posted on arXiv 27 Sep 2022.

Builds on

27 of 43 references.

References · 27

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2018Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulationcited by 140
  4. 2018Sim-to-Real Reinforcement Learning for Deformable Object Manipulationcited by 124
  5. 2016Revisiting Active Perceptioncited by 90
  6. 2017Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulationcited by 90
  7. 2016Interactive Perception: Leveraging Action in Perception and Perception in Actioncited by 77
  8. 2020Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networkscited by 77
  9. 2019Learning to Manipulate Deformable Objects without Demonstrationscited by 76
  10. 2020Learning Predictive Representations for Deformable Objects Using Contrastive Estimationcited by 72
  11. 2021Learning Visible Connectivity Dynamics for Cloth Smoothingcited by 61
  12. 2020Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Datacited by 51
15 more
  1. 2022SpeedFolding: Learning Efficient Bimanual Folding of Garmentscited by 51
  2. 2019Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisorcited by 44
  3. 2020VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulationcited by 40
  4. 2019Learning Robotic Manipulation through Visual Planning and Actingcited by 39
  5. 2021Planar Robot Casting with Real2Sim2Real Self-Supervised Learningcited by 38
  6. 2019Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Cluttercited by 30
  7. 2020Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experiencecited by 24
  8. 2020Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cablescited by 21
  9. 2020Untangling Dense Knots by Learning Task-Relevant Keypointscited by 21
  10. 2019Object Finding in Cluttered Scenes Using Interactive Perceptioncited by 18
  11. 2021Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policiescited by 11
  12. 2020Learning Dense Visual Correspondences in Simulation to Smooth and Fold Real Fabricscited by 10
  13. 2022Autonomously Untangling Long Cablescited by 9
  14. 2022Efficiently Learning Single-Arm Fling Motions to Smooth Garmentscited by 8
  15. 2021Disentangling Dense Multi-Cable Knotscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 1; 2026: 1.

5 papers.

  1. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  2. 2023GenDOM: Generalizable One-shot Deformable Object Manipulation with Parameter-Aware Policycited by 3
  3. 2025Implicit Neural-Representation Learning for Elastic Deformable-Object Manipulationscited by 2
  4. 2023Self-Supervised Learning for Interactive Perception of Surgical Thread for Autonomous Suture Tail-Shorteningcited by 1
  5. 2026TWISTED-RL: Hierarchical Skilled Agents for Knot-Tying without Human Demonstrationscited by 0