robots-9

Deformable Object Manipulation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in deformable-object-manipulation-9

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find deformable-object-manipulation-9 models and implementations

Datasets

VIRDO Dataset

Subtasks

No subtasks available.

Most implemented papers

Deep Transfer Learning of Pick Points on Fabric for Robot Bed-Making

Ken Goldberg, J. Canny, Michael Laskey, Daniel Seita, Nawid Jamali, A. Tanwani, R. Berenstein, Prakash Baskaran, Soshi Iba•Tue Sep 25 2018

This work considers the task of bed-making, where a robot sequentially grasps and pulls at pick points to increase blanket coverage, and suggests that transfer-invariant robot pick points on fabric can be effectively learned.

99

Content

0

Paper Graph

Learning to Manipulate Deformable Objects without Demonstrations

P. Abbeel, Thanard Kurutach, Lerrel Pinto, Yilin Wu, Wilson Yan•Mon Oct 28 2019

This paper proposes an iterative pick-place action space that encodes the conditional relationship between picking and placing on deformable objects and obtains an order of magnitude faster learning compared to independent action-spaces on a suite of deformable object manipulation tasks with visual RGB observations.

220 0

Paper Graph

SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation

David Held, Xingyu Lin, Yufei Wang, Jake Olkin•Fri Nov 13 2020

SoftGym is presented, a set of open-source simulated benchmarks for manipulating deformable objects, with a standard OpenAI Gym API and a Python interface for creating new environments, to enable reproducible research in this important area.

254 0

Paper Graph

Sim-to-Real Reinforcement Learning for Deformable Object Manipulation

A. Davison, Stephen James, J. Matas•Tue Jun 19 2018

This work uses a combination of state-of-the-art deep reinforcement learning algorithms to solve the problem of manipulating deformable objects (specifically cloth), and evaluates the approach on three tasks --- folding a towel up to a mark, folding a face towel diagonally, and draping a piece of cloth over a hanger.

398 0

Paper Graph

PLAS: Latent Action Space for Offline Reinforcement Learning

David Held, Wenxuan Zhou, Sujay Bajracharya•Fri Nov 13 2020

This work proposes to simply learn the Policy in the Latent Action Space (PLAS) such that this requirement is naturally satisfied, and demonstrates that this method provides competitive performance consistently across various continuous control tasks and different types of datasets, outperforming existing offline reinforcement learning methods with explicit constraints.

179 0

Paper Graph

Learning Predictive Representations for Deformable Objects Using Contrastive Estimation

P. Abbeel, Lerrel Pinto, Wilson Yan, Ashwin Vangipuram•Tue Mar 10 2020

This work proposes a new learning framework that jointly optimizes both the visual representation model and the dynamics model using contrastive estimation and transfers its visual manipulation policies trained on data purely collected in simulation to a real PR2 robot through domain randomization.

203 0

Paper Graph

Recurrent Multi-view Alignment Network for Unsupervised Surface Registration

H. Bao, Junhui Hou, Juyong Zhang, Hongrui Cai, Wanquan Feng, Haofei Xu•Mon Nov 23 2020

This paper proposes to represent the non-rigid transformation with a point-wise combination of several rigid transformations, which makes the solution space well-constrained and enables the method to be solved iteratively with a recurrent framework, which greatly reduces the difficulty of learning.

48 0

Paper Graph

Learning Visible Connectivity Dynamics for Cloth Smoothing

David Held, Xingyu Lin, Yufei Wang•Thu May 20 2021

This work proposes to learn a particle-based dynamics model from a partial point cloud observation to overcome the challenges of partial observability, and shows that the method greatly outperforms previous state-of-the-art model-based and model-free reinforcement learning methods in simulation.

128 0

Paper Graph

Robot Cooking With Stir-Fry: Bimanual Non-Prehensile Manipulation of Semi-Fluid Objects

Junjia Liu, Yiting Chen, Zhipeng Dong, Shixiong Wang, S. Calinon, Miao Li, Fei Chen•Thu Mar 31 2022

This letter defines a canonical stir-fry movement, and proposes a decoupled framework for learning this deformable object manipulation from human demonstration, and develops a Graph and Transformer based model—Structured-Transformer to capture the spatio-temporal relationship between dual-arm movements.

83 0

Paper Graph

Adding a benchmark result helps the community track progress.