Untangling Dense Knots by Learning Task-Relevant Keypoints

• URL: http://arxiv.org/abs/2011.04999v1
• Date: Tue, 10 Nov 2020 09:29:01 GMT
• Title: Untangling Dense Knots by Learning Task-Relevant Keypoints
• Abstract summary: Untangling ropes, wires, and cables is a challenging task for robots due to the high-dimensional configuration space, visual homogeneity, self-occlusions, and complex dynamics. We instantiate this into an algorithm, HULK: Hierarchical Untangling from Learned Keypoints, which combines learning-based perception with a geometric planner into a policy. We find that HULK is able to untangle cables with dense figure-eight and overhand knots and generalize to varied textures and appearances.
• Score: 36.553233699648175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Untangling ropes, wires, and cables is a challenging task for robots due to the high-dimensional configuration space, visual homogeneity, self-occlusions, and complex dynamics. We consider dense (tight) knots that lack space between self-intersections and present an iterative approach that uses learned geometric structure in configurations. We instantiate this into an algorithm, HULK: Hierarchical Untangling from Learned Keypoints, which combines learning-based perception with a geometric planner into a policy that guides a bilateral robot to untangle knots. To evaluate the policy, we perform experiments both in a novel simulation environment modelling cables with varied knot types and textures and in a physical system using the da Vinci surgical robot. We find that HULK is able to untangle cables with dense figure-eight and overhand knots and generalize to varied textures and appearances. We compare two variants of HULK to three baselines and observe that HULK achieves 43.3% higher success rates on a physical system compared to the next best baseline. HULK successfully untangles a cable from a dense initial configuration containing up to two overhand and figure-eight knots in 97.9% of 378 simulation experiments with an average of 12.1 actions per trial. In physical experiments, HULK achieves 61.7% untangling success, averaging 8.48 actions per trial. Supplementary material, code, and videos can be found at https://tinyurl.com/y3a88ycu.

Related papers

• Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation [67.16145181790522]
  This paper tackles spatial perception and manipulation challenges in Vision-Language-Action (VLA) models.<n>We propose a Geometry-Guided Gated Transformer (G3T) that aligns multi-view features under 3D geometric guidance.<n>To improve action learning efficiency, we introduce Action Manifold Learning (AML), which directly predicts actions on the valid action manifold.
  arXiv  Detail & Related papers  (2026-05-12T09:21:29Z)
• ShapeGrasp: Simultaneous Visuo-Haptic Shape Completion and Grasping for Improved Robot Manipulation [3.415147604573136]
  The proposed method is an iterative grasp-and-complete pipeline that couples implicit surface visuo-haptic shape completion with physics-based grasp planning.<n>From a single RGB-D view, ShapeGrasp infers a complete shape, generates candidate grasps via rigid-body simulation, and executes the best feasible grasp.<n>We evaluate ShapeGrasp in the real world using two different robots and grippers.
  arXiv  Detail & Related papers  (2026-05-04T08:49:52Z)
• Learning Deformable Object Manipulation Using Task-Level Iterative Learning Control [0.0]
  We introduce a Task-Level Iterative Learning Control method for dynamic manipulation of deformable objects.<n>We demonstrate this method on a non-planar rope manipulation task called the flying knot.
  arXiv  Detail & Related papers  (2026-02-24T19:13:25Z)
• A Stable Whitening Optimizer for Efficient Neural Network Training [99.7641280234926]
  Building on the Shampoo family of algorithms, we identify and alleviate three key issues, resulting in the proposed SPlus method.<n>First, we find that naive Shampoo is prone to divergence when matrix-inverses are cached for long periods.<n>Second, we adapt a shape-aware scaling to enable learning rate transfer across network width.<n>Third, we find that high learning rates result in large parameter noise, and propose a simple iterate-averaging scheme which unblocks faster learning.
  arXiv  Detail & Related papers  (2025-06-08T18:43:31Z)
• Offline Imitation Learning Through Graph Search and Retrieval [57.57306578140857]
  Imitation learning is a powerful machine learning algorithm for a robot to acquire manipulation skills. We propose GSR, a simple yet effective algorithm that learns from suboptimal demonstrations through Graph Search and Retrieval. GSR can achieve a 10% to 30% higher success rate and over 30% higher proficiency compared to baselines.
  arXiv  Detail & Related papers  (2024-07-22T06:12:21Z)
• Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning [58.69297999175239]
  In robot learning, the observation space is crucial due to the distinct characteristics of different modalities. In this study, we explore the influence of various observation spaces on robot learning, focusing on three predominant modalities: RGB, RGB-D, and point cloud.
  arXiv  Detail & Related papers  (2024-02-04T14:18:45Z)
• Autonomously Untangling Long Cables [79.09016120505088]
  Cables are ubiquitous in many settings, but are prone to self-occlusions and knots. In this paper, we focus on autonomously untangling cables up to 3 meters in length using a bilateral robot. We develop new motion primitives to efficiently untangle long cables and novel jaws specialized for this task.
  arXiv  Detail & Related papers  (2022-07-16T02:35:09Z)
• Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation [79.60988242843437]
  We propose a novel approach that achieves self-supervised and magnification-flexible point clouds upsampling simultaneously. Experimental results demonstrate that our self-supervised learning based scheme achieves competitive or even better performance than supervised learning based state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-18T07:18:25Z)
• Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies [28.75186178614213]
  We present two algorithms that enhance robust cable untangling, LOKI and SPiDERMan. 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.
  arXiv  Detail & Related papers  (2021-06-29T04:13:14Z)
• Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations [20.155920256334706]
  We show that 3D reconstruction and grasp learning are two intimately connected tasks. We propose to utilize the synergies between grasp affordance and 3D reconstruction through multi-task learning of a shared representation. Our method outperforms baselines by over 10% in terms of grasp success rate.
  arXiv  Detail & Related papers  (2021-04-04T05:46:37Z)
• TSGCNet: Discriminative Geometric Feature Learning with Two-Stream GraphConvolutional Network for 3D Dental Model Segmentation [141.2690520327948]
  We propose a two-stream graph convolutional network (TSGCNet) to learn multi-view information from different geometric attributes. We evaluate our proposed TSGCNet on a real-patient dataset of dental models acquired by 3D intraoral scanners.
  arXiv  Detail & Related papers  (2020-12-26T08:02:56Z)
• Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cables [31.103646278125318]
  High-speed robot arm motions can manipulate cables to vault over obstacles, knock objects from pedestals, and weave between obstacles. We propose a self-supervised learning framework that enables a UR5 robot to perform these three tasks.
  arXiv  Detail & Related papers  (2020-11-10T00:19:50Z)
• SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognition [0.0]
  We propose a metric learning approach to reduce the action recognition problem to a nearest neighbor search in embedding space. We encode signals into images and extract features using a deep residual CNN. The resulting encoder transforms features into an embedding space in which closer distances encode similar actions while higher distances encode different actions.
  arXiv  Detail & Related papers  (2020-04-23T11:28:27Z)
• Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data [32.936908766549344]
  We present an approach that learns point-pair correspondences between initial and goal rope configurations. In 50 trials of a knot-tying task with the ABB YuMi Robot, the system achieves a 66% knot-tying success rate from previously unseen configurations.
  arXiv  Detail & Related papers  (2020-03-03T23:43:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.