# Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies

arXiv: https://arxiv.org/abs/2107.08942 · HTML: https://mlsanity.com/paper/2107.08942/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 44 references that are in the map.
- First posted on arXiv 29 Jun 2021.

## Builds on (most cited first, 21 of 21)

- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Residual Reinforcement Learning for Robot Control](https://mlsanity.com/paper/1812.03201/) (2018)
- [Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones](https://mlsanity.com/paper/2010.15920/) (2020)
- [Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation](https://mlsanity.com/paper/1806.08756/) (2018)
- [Sim-to-Real Reinforcement Learning for Deformable Object Manipulation](https://mlsanity.com/paper/1806.07851/) (2018)
- [SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation](https://mlsanity.com/paper/2011.07215/) (2020)
- [Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation](https://mlsanity.com/paper/1703.02018/) (2017)
- [Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks](https://mlsanity.com/paper/2012.03385/) (2020)
- [Learning Predictive Representations for Deformable Objects Using Contrastive Estimation](https://mlsanity.com/paper/2003.05436/) (2020)
- [Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data](https://mlsanity.com/paper/2003.01835/) (2020)
- [Cable Manipulation with a Tactile-Reactive Gripper](https://mlsanity.com/paper/1910.02860/) (2019)
- [Self-Supervised Learning of State Estimation for Manipulating Deformable Linear Objects](https://mlsanity.com/paper/1911.06283/) (2019)
- [Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor](https://mlsanity.com/paper/1910.04854/) (2019)
- [VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulation](https://mlsanity.com/paper/2003.09044/) (2020)
- [Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning](https://mlsanity.com/paper/2005.10872/) (2020)
- [Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experience](https://mlsanity.com/paper/2010.03209/) (2020)
- [Untangling Dense Knots by Learning Task-Relevant Keypoints](https://mlsanity.com/paper/2011.04999/) (2020)
- [Occlusion-robust Deformable Object Tracking without Physics Simulation](https://mlsanity.com/paper/2101.00733/) (2021)
- [Intermittent Visual Servoing: Efficiently Learning Policies Robust to Instrument Changes for High-precision Surgical Manipulation](https://mlsanity.com/paper/2011.06163/) (2020)
- [Learning Dense Visual Correspondences in Simulation to Smooth and Fold Real Fabrics](https://mlsanity.com/paper/2003.12698/) (2020)
- [Tethered Tool Manipulation Planning with Cable Maneuvering](https://mlsanity.com/paper/1909.10686/) (2019)

## Built on by (most cited first, 11 of 11)

- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [KITE: Keypoint-Conditioned Policies for Semantic Manipulation](https://mlsanity.com/paper/2306.16605/) (2023)
- [Autonomously Untangling Long Cables](https://mlsanity.com/paper/2207.07813/) (2022)
- [RecoveryChaining: Learning Local Recovery Policies for Robust Manipulation](https://mlsanity.com/paper/2410.13979/) (2024)
- [Efficient Recovery Learning using Model Predictive Meta-Reasoning](https://mlsanity.com/paper/2209.13605/) (2022)
- [Learning Sequential Acquisition Policies for Robot-Assisted Feeding](https://mlsanity.com/paper/2309.05197/) (2023)
- [SGTM 2.0: Autonomously Untangling Long Cables using Interactive Perception](https://mlsanity.com/paper/2209.13706/) (2022)
- [All You Need is LUV: Unsupervised Collection of Labeled Images using Invisible UV Fluorescent Indicators](https://mlsanity.com/paper/2203.04566/) (2022)
- [Knot So Simple: A Minimalistic Environment for Spatial Reasoning](https://mlsanity.com/paper/2505.18028/) (2025)
- [Learning Quasi-Static 3D Models of Markerless Deformable Linear Objects for Bimanual Robotic Manipulation](https://mlsanity.com/paper/2309.07609/) (2023)
- [Learning Sim-Grounded Policies for Bimanual Rope Manipulation from Human Teleoperation Data](https://mlsanity.com/paper/2605.16043/) (2026)

## Abstract (arXiv)

Robot manipulation for untangling 1D deformable structures such as ropes, cables, and wires is challenging due to their infinite dimensional configuration space, complex dynamics, and tendency to self-occlude. Analytical controllers often fail in the presence of dense configurations, due to the difficulty of grasping between adjacent cable segments. We present two algorithms that enhance robust cable untangling, LOKI and SPiDERMan, which operate alongside HULK, a high-level planner from prior work. LOKI uses a learned model of manipulation features to refine a coarse grasp keypoint prediction to a precise, optimized location and orientation, while SPiDERMan uses a learned model to sense task progress and apply recovery actions. We evaluate these algorithms in physical cable untangling experiments with 336 knots and over 1500 actions on real cables using the da Vinci surgical robot. We find that the combination of HULK, LOKI, and SPiDERMan is able to untangle dense overhand, figure-eight, double-overhand, square, bowline, granny, stevedore, and triple-overhand knots. The composition of these methods successfully untangles a cable from a dense initial configuration in 68.3% of 60 physical experiments and achieves 50% higher success rates than baselines from prior work. Supplementary material, code, and videos can be found at https://tinyurl.com/rssuntangling.