SGTM 2.0: Autonomously Untangling Long Cables using Interactive Perception

@article{Shivakumar2022SGTM2A,
  title={SGTM 2.0: Autonomously Untangling Long Cables using Interactive Perception},
  author={Kaushik Shivakumar and Vainavi Viswanath and Anrui Gu and Yahav Avigal and Justin Kerr and Jeffrey Ichnowski and Richard Cheng and Thomas Kollar and Ken Goldberg},
  journal={ArXiv},
  year={2022},
  volume={abs/2209.13706}
}
—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… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 37 REFERENCES

Autonomously Untangling Long Cables

—Cables are ubiquitous in many settings, but are prone to self-occlusions and knots, making them difficult to perceive and manipulate. The challenge often increases with cable length: long cables

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

The combination of HULK, LOKI, and SPiDERMan is able to untangle dense overhand, figure-eight, double-overhand, square, bowline, granny, stevedore, and triple-over hand knots.

SpeedFolding: Learning Efficient Bimanual Folding of Garments

SpeedFolding is developed, a reliable and efficient bimanual system, which given user-defined instructions as folding lines, manipulates an initially crumpled garment to (1) a smoothed and (2) a folded configuration.

Untangling Dense Knots by Learning Task-Relevant Keypoints

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 isInstantiated into an algorithm that is able to untangled cables with dense figure-eight and overhand knots and generalize to varied textures and appearances.

Real2Sim2Real: Self-Supervised Learning of Physical Single-Step Dynamic Actions for Planar Robot Casting

To efficiently learn a PRC policy for a given cable, Real2Sim2Real is proposed, a self-supervised framework that automatically collects physical trajectory examples to tune parameters of a dynamics simulator using Differential Evolution, generates many simulated examples, and then learns a policy using a weighted combination of simulated and physical data.

Disentangling Dense Multi-Cable Knots

The problem of disentangling multiple cables is formalized and an algorithm, Iterative Reduction Of Non-planar Multiple cAble kNots (IRON-MAN), is presented that outputs robot actions to remove crossings from multi-cable knotted structures.

Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks

This work proposes embedding goal- conditioning into Transporter Networks, a recently proposed model architecture for learning robotic manipulation that rearranges deep features to infer displacements that can represent pick and place actions, and demonstrates that goal-conditioned Transporter networks enable agents to manipulate deformable structures into flexibly specified configurations without test-time visual anchors for target locations.

Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experience

This paper shows that it is possible to learn fabric folding skills in only an hour of self-supervised real robot experience, without human supervision or simulation, and creates an expressive goal-conditioned pick and place policy that can be trained efficiently with real world robot data only.

Efficiently Learning Single-Arm Fling Motions to Smooth Garments

A coarse-to-fine learning method that uses a multi-armed bandit (MAB) framework to efficiently train a single 6-DOF robot arm that learns fling trajectories to achieve high garment coverage and proposes novel training and execution-time stopping criteria based on out-come uncertainty.

Superhuman performance of surgical tasks by robots using iterative learning from human-guided demonstrations

An apprenticeship learning approach that has potential to allow robotic surgical assistants to autonomously execute specific trajectories with superhuman performance in terms of speed and smoothness is proposed.