Untangling Dense Knots by Learning Task-Relevant Keypoints

by   Jennifer Grannen, et al.

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 experiments with an average of 12.1 actions per trial. In physical experiments, HULK achieves 61.7 Supplementary material, code, and videos can be found at https://tinyurl.com/y3a88ycu.



page 2

page 4

page 6

page 16

page 17

page 18


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

Robot manipulation for untangling 1D deformable structures such as ropes...

Learning to Smooth and Fold Real Fabric Using Dense Object Descriptors Trained on Synthetic Color Images

Robotic fabric manipulation is challenging due to the infinite dimension...

Disentangling Dense Multi-Cable Knots

Disentangling two or more cables requires many steps to remove crossings...

Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data

Robotic manipulation of deformable 1D objects such as ropes, cables, and...

Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision

Commercial and industrial deployments of robot fleets often fall back on...

DinerDash Gym: A Benchmark for Policy Learning in High-Dimensional Action Space

It has been arduous to assess the progress of a policy learning algorith...

Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space

Learning causal relationships in high-dimensional data (images, videos) ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.