Filters








2,617 Hits in 5.6 sec

Learning Dense Visual Correspondences in Simulation to Smooth and Fold Real Fabrics [article]

Aditya Ganapathi, Priya Sundaresan, Brijen Thananjeyan, Ashwin Balakrishna, Daniel Seita, Jennifer Grannen, Minho Hwang, Ryan Hoque, Joseph E. Gonzalez, Nawid Jamali, Katsu Yamane, Soshi Iba (+1 others)
2020 arXiv   pre-print
In this paper, we learn visual correspondences for deformable fabrics across different configurations in simulation and show that this representation can be used to design policies for a variety of tasks  ...  This makes it possible to robustly imitate a broad set of multi-step fabric smoothing and folding tasks on multiple physical robotic systems.  ...  We contribute (1) a framework for learning dense visual correspondences of fabric in simulation using dense object descriptors from [6, 41] and applying them to manipulation tasks on real fabrics with  ... 
arXiv:2003.12698v2 fatcat:ftdd3zxw5vektkcrb5q7zhxi7a

VisuoSpatial Foresight for Physical Sequential Fabric Manipulation [article]

Ryan Hoque, Daniel Seita, Ashwin Balakrishna, Aditya Ganapathi, Ajay Kumar Tanwani, Nawid Jamali, Katsu Yamane, Soshi Iba, Ken Goldberg
2021 arXiv   pre-print
In this earlier work, we evaluated VSF on multi-step fabric smoothing and folding tasks against 5 baseline methods in simulation and on the da Vinci Research Kit (dVRK) surgical robot without any demonstrations  ...  We extend our earlier work on VisuoSpatial Foresight (VSF), which learns visual dynamics on domain randomized RGB images and depth maps simultaneously and completely in simulation.  ...  to Smooth and Fold Real Fabrics.  ... 
arXiv:2102.09754v2 fatcat:kyxkizg7ofg2vbsor6q6jclf3y

VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulation [article]

Ryan Hoque, Daniel Seita, Ashwin Balakrishna, Aditya Ganapathi, Ajay Kumar Tanwani, Nawid Jamali, Katsu Yamane, Soshi Iba, Ken Goldberg
2021 arXiv   pre-print
We experimentally evaluate VSF on multi-step fabric smoothing and folding tasks against 5 baseline methods in simulation and on the da Vinci Research Kit (dVRK) surgical robot without any demonstrations  ...  We introduce VisuoSpatial Foresight (VSF), which builds on prior work by learning visual dynamics on domain randomized RGB images and depth maps simultaneously and completely in simulation.  ...  the learned policy transfers to a real physical system with promising smoothing and folding results.  ... 
arXiv:2003.09044v3 fatcat:cgsbhrgtwnblhmugujvc6ckpya

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

Robert Lee, Daniel Ward, Akansel Cosgun, Vibhavari Dasagi, Peter Corke, Jurgen Leitner
2020 arXiv   pre-print
In this paper, we show that it is possible to learn fabric folding skills in only an hour of self-supervised real robot experience, without human supervision or simulation.  ...  Our approach relies on fully convolutional networks and the manipulation of visual inputs to exploit learned features, allowing us to create an expressive goal-conditioned pick and place policy that can  ...  [19] train a dense object descriptors model in simulation and showed successful transfer to two different robots in multi-step fabric smoothing and folding tasks.  ... 
arXiv:2010.03209v1 fatcat:wzajwisuizhbzla6wbohudqm7u

Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor [article]

Daniel Seita, Aditya Ganapathi, Ryan Hoque, Minho Hwang, Edward Cen, Ajay Kumar Tanwani, Ashwin Balakrishna, Brijen Thananjeyan, Jeffrey Ichnowski, Nawid Jamali, Katsu Yamane, Soshi Iba, John Canny (+1 others)
2020 arXiv   pre-print
Sequential pulling policies to flatten and smooth fabrics have applications from surgery to manufacturing to home tasks such as bed making and folding clothes.  ...  fabric smoothing policies can be learned from an algorithmic supervisor and that depth sensing is a valuable addition to color alone.  ...  Figure 1 shows examples of learned smoothing episodes in simulation and the physical robot.  ... 
arXiv:1910.04854v2 fatcat:zcibrbailjhhdephrdsn4q2v5a

FabricFlowNet: Bimanual Cloth Manipulation with a Flow-based Policy [article]

Thomas Weng, Sujay Bajracharya, Yufei Wang, Khush Agrawal, David Held
2022 arXiv   pre-print
Our insight is that optical flow, a technique normally used for motion estimation in video, can also provide an effective representation for corresponding cloth poses across observation and goal images  ...  We also present real-world experiments on a bimanual system, demonstrating effective sim-to-real transfer.  ...  Acknowledgments This work was supported by the National Science Foundation (NSF) Smart and Autonomous Systems Program (IIS-1849154), a NSF CAREER Award (IIS-2046491), LG Electronics, and a NSF Graduate  ... 
arXiv:2111.05623v3 fatcat:z73tl2t3mzgozfiifmfanwzy64

All You Need is LUV: Unsupervised Collection of Labeled Images using Invisible UV Fluorescent Indicators [article]

Brijen Thananjeyan, Justin Kerr, Huang Huang, Joseph E. Gonzalez, Ken Goldberg
2022 arXiv   pre-print
The networks trained on these labels are used to smooth and fold crumpled towels with 83 respect to human labels on a surgical needle pose estimation task.  ...  Current approaches often rely on human labelers, which can be expensive, or simulation data, which can visually or physically differ from real data.  ...  ACKNOWLEDGMENTS This research was performed at the AUTOLAB at UC Berkeley in affiliation with the Berkeley AI Research (BAIR) Lab, the CITRIS "People and Robots" (CPAR) Initiative, the Real-Time Intelligent  ... 
arXiv:2203.04566v2 fatcat:qy2mvcv7bbgt7ph22t7lp34p5u

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

Daniel Seita, Pete Florence, Jonathan Tompson, Erwin Coumans, Vikas Sindhwani, Ken Goldberg, Andy Zeng
2021 arXiv   pre-print
Rearranging and manipulating deformable objects such as cables, fabrics, and bags is a long-standing challenge in robotic manipulation.  ...  In this work, we develop a suite of simulated benchmarks with 1D, 2D, and 3D deformable structures, including tasks that involve image-based goal-conditioning and multi-step deformable manipulation.  ...  For example, IL is used with human [54] and scripted [53] demonstrators for fabric smoothing, while RL is applied for smoothing and folding in [44] , [29] , [63] .  ... 
arXiv:2012.03385v3 fatcat:ern2rrdeznbdpcnwm7u2r5vqai

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

Daniel Seita, Nawid Jamali, Michael Laskey, Ajay Kumar Tanwani, Ron Berenstein, Prakash Baskaran, Soshi Iba, John Canny, Ken Goldberg
2019 arXiv   pre-print
A fundamental challenge in manipulating fabric for clothes folding and textiles manufacturing is computing "pick points" to effectively modify the state of an uncertain manifold.  ...  We present a supervised deep transfer learning approach to locate pick points using depth images for invariance to color and texture.  ...  Recently, pick points for fabric manipulation have been learned via reinforcement learning in simulation and then conducting sim-to-real transfer. Thananjeyan et al.  ... 
arXiv:1809.09810v3 fatcat:umvv6asdwbaevj3dgx5ew42bbi

Research on Multi-Precision Fabric Modeling Method Based on Machine Learning

Yanxia. Jin, Zhixu. Chen, Ye. Lu, Jing. Yang, Yabian. Liu, Zhiru. Shi, Sikandar Ali
2022 Scientific Programming  
In order to solve the shortcomings of complex calculation and time consumption of fabric physical simulation methods, many single-precision fabric simulation technologies based on machine learning methods  ...  Finally, the subgraph convolutional neural network and super-resolution network are trained to model the multi-precision fabric, and we compared the two different multi-precision fabric machine learning  ...  Because the physical simulation produces too many detail folds, it affects the visual quality to some extent.  ... 
doi:10.1155/2022/4339095 fatcat:3gm7hhkjzzcpxgr36vwoolly3i

GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion [article]

Cheng Chi, Shuran Song
2021 arXiv   pre-print
By mapping the observed partial surface to the canonical space and completing it in this space, the output representation describes the garment's full configuration using a complete 3D mesh with the per-vertex  ...  However, garments are also commonly subject to extreme cases of self-occlusion, especially when folded or crumpled, making it challenging to perceive their full 3D surface.  ...  Acknowledgement The authors would like to thank Eric Cousineau, Benjamin Burchfiel Naveen Kuppuswamy, and other researchers in Toyota Research Institute for their helpful feedback and fruitful discussions.We  ... 
arXiv:2104.05177v2 fatcat:62ntns5pkbbfpe2brrkog3dcre

DextAIRity: Deformable Manipulation Can be a Breeze [article]

Zhenjia Xu, Cheng Chi, Benjamin Burchfiel, Eric Cousineau, Siyuan Feng, Shuran Song
2022 arXiv   pre-print
In contrast to conventional contact-based quasi-static manipulations, DextAIRity allows the system to apply dense forces on out-of-contact surfaces, expands the system's reach range, and provides safe  ...  By using a closed-loop formulation for blowing, the system continuously adjusts its blowing direction based on visual feedback in a way that is robust to the highly stochastic dynamics.  ...  ACKNOWLEDGEMENT We would like to thank Huy Ha, Dale McConachie, Naveen Kuppuswamy for their helpful feedback and fruitful discussions.  ... 
arXiv:2203.01197v3 fatcat:omqssvegcfa75bqlk7ws4afivq

Learning a Shared Shape Space for Multimodal Garment Design [article]

Tuanfeng Y. Wang and Duygu Ceylan and Jovan Popovic and Niloy J. Mitra
2018 arXiv   pre-print
Instead, we present a data-driven approach wherein the user directly indicates desired fold patterns simply by sketching while our system estimates corresponding garment and body shape parameters at interactive  ...  Traditional workflow involves a trial-and-error procedure wherein a mannequin is draped to judge the resultant folds and the sewing pattern iteratively adjusted until the desired look is achieved.  ...  Our learned shared latent space is compact and smooth, as shown in Figure13.  ... 
arXiv:1806.11335v2 fatcat:dzjya3hu2nfvbph5ok7j6gik4y

Fusing Convolutional Neural Network Features with Hand-Crafted Features for Objective Fabric Smoothness Appearance Assessment

Jingan Wang, Kangjun Shi, Lei Wang, Zhengxin Li, Fengxin Sun, Ruru Pan, Weidong Gao
2020 IEEE Access  
In the textile and apparel industry, it remains a challenging task to evaluate the fabric smoothness appearance objectively.  ...  In existing studies, with computer vision technology, researchers use the hand-crafted image features and deep convolutional neural network (CNN) based image features to describe the fabric smoothness  ...  And the four varieties of fabric correspond to the four fabrics introduced in table 1, which have different fabric structures.  ... 
doi:10.1109/access.2020.3001354 fatcat:6jvj3togljchjnfc2r2slhr45e

Mobile devices' GPUs in cloth dynamics simulation

Marcin Wawrzonowski, Dominik Szajerman, Marcin Daszuta, Piotr Napieralski
2017 Proceedings of the 2017 Federated Conference on Computer Science and Information Systems  
The realistic simulation of cloths is nowadays a key to produce good-quality, authentic graphical visualizations of various cloth, such as characters garment elements, flags or curtains.  ...  The solution to this matter was to use GPU (Graphic Processing Unit) and perform all calculations on this device.  ...  Both methods of cloth simulation generate the desired visual effect, ie realistic folds and wrinkles of the fabric and its characteristic positioning on the object.  ... 
doi:10.15439/2017f191 dblp:conf/fedcsis/WawrzonowskiSDN17 fatcat:t4akb3fnpncjpbx27wpisjbmqu
« Previous Showing results 1 — 15 out of 2,617 results