Search Results for author: Priya Sundaresan

Found 8 papers, 0 papers with code

DiffCloud: Real-to-Sim from Point Clouds with Differentiable Simulation and Rendering of Deformable Objects

no code implementations7 Apr 2022 Priya Sundaresan, Rika Antonova, Jeannette Bohg

However, for highly deformable objects it is challenging to align the output of a simulator with the behavior of real objects.

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

no code implementations29 Jun 2021 Priya Sundaresan, Jennifer Grannen, Brijen Thananjeyan, Ashwin Balakrishna, Jeffrey Ichnowski, Ellen Novoseller, Minho Hwang, Michael Laskey, Joseph E. Gonzalez, Ken Goldberg

We present two algorithms that enhance robust cable untangling, LOKI and SPiDERMan, which operate alongside HULK, a high-level planner from prior work.

Untangling Dense Knots by Learning Task-Relevant Keypoints

no code implementations10 Nov 2020 Jennifer Grannen, Priya Sundaresan, Brijen Thananjeyan, Jeffrey Ichnowski, Ashwin Balakrishna, Minho Hwang, Vainavi Viswanath, Michael Laskey, Joseph E. Gonzalez, Ken Goldberg

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.

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

no code implementations3 Mar 2020 Priya Sundaresan, Jennifer Grannen, Brijen Thananjeyan, Ashwin Balakrishna, Michael Laskey, Kevin Stone, Joseph E. Gonzalez, Ken Goldberg

We address these challenges using interpretable deep visual representations for rope, extending recent work on dense object descriptors for robot manipulation.

Visual Reasoning

Cannot find the paper you are looking for? You can Submit a new open access paper.