10 Hits in 5.1 sec

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
We present a supervised deep transfer learning approach to locate pick points using depth images for invariance to color and texture.  ...  Average coverage results of 92% for 193 beds suggest that transfer-invariant robot pick points on fabric can be effectively learned.  ...  The contributions of this paper include: (1) a deep transfer learning approach to selecting pick points that generalizes across robots and blankets, and (2) a formalization of robot bed-making based on  ... 
arXiv:1809.09810v3 fatcat:umvv6asdwbaevj3dgx5ew42bbi

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.  ...  Manipulating deformable objects, such as fabric, is a long standing problem in robotics, with state estimation and control posing a significant challenge for traditional methods.  ...  They showed that using RGB as input transferred better than using only depth images. Our work utilizes only RGB images. Ganapathi et al.  ... 
arXiv:2010.03209v1 fatcat:wzajwisuizhbzla6wbohudqm7u

Modeling, learning, perception, and control methods for deformable object manipulation

Hang Yin, Anastasia Varava, Danica Kragic
2021 Science Robotics  
of deformable objects.  ...  Perceiving and handling deformable objects is an integral part of everyday life for humans.  ...  A recent work (75) demonstrates bed making by integrating deep transfer learning and grasping.  ... 
doi:10.1126/scirobotics.abd8803 pmid:34043538 fatcat:3q54vpiprrcsnpffmbduj3fjrm

kPAM: KeyPoint Affordances for Category-Level Robotic Manipulation [article]

Lucas Manuelli, Wei Gao, Peter Florence, Russ Tedrake
2019 arXiv   pre-print
We would like robots to achieve purposeful manipulation by placing any instance from a category of objects into a desired set of goal states.  ...  Hence we propose a novel formulation of category-level manipulation that uses semantic 3D keypoints as the object representation.  ...  Robot bed-making: Deep transfer learn- ing using depth sensing of deformable fabric. arXiv preprint arXiv:1809.09810, 2018. 25. Xiao Sun, Bin Xiao, Fangyin Wei, Shuang Liang, and Yichen Wei.  ... 
arXiv:1903.06684v2 fatcat:gaghpp3ukjg7xad3u35yplur24

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
Results suggest that training visual dynamics models using longer, corner-based actions can improve the efficiency of fabric folding by 76% and enable a physical sequential fabric folding task that VSF  ...  A key finding was that depth sensing significantly improves performance: RGBD data yields an 80% improvement in fabric folding success rate in simulation over pure RGB data.  ...  Seita D, Jamali N, Laskey M, Berenstein R, Tanwani AK, Baskaran P, Iba S, Canny J, Goldberg K (2019) Deep Transfer Learning of Pick Points on Fabric for Robot Bed-Making.  ... 
arXiv:2102.09754v2 fatcat:kyxkizg7ofg2vbsor6q6jclf3y

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
Due to the complexity of fabric states and dynamics, we apply deep imitation learning to learn policies that, given color (RGB), depth (D), or combined color-depth (RGBD) images of a rectangular fabric  ...  fabric smoothing policies can be learned from an algorithmic supervisor and that depth sensing is a valuable addition to color alone.  ...  [51] trained an image-based policy for fabric smoothing in simulation using deep reinforcement learning, and then applied domain randomization to transfer it to a physical PR2 robot.  ... 
arXiv:1910.04854v2 fatcat:zcibrbailjhhdephrdsn4q2v5a

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  ...  Given a single demonstration of a new task from an initial fabric configuration, the learned correspondences can be used to compute geometrically equivalent actions in a new fabric configuration.  ...  INTRODUCTION Robot fabric manipulation has applications in folding laundry [4, 17, 25, 46] , bed making [37] , surgery [8, 38, 42, 43] , and manufacturing [27, 45] .  ... 
arXiv:2003.12698v2 fatcat:ftdd3zxw5vektkcrb5q7zhxi7a

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
Robotic fabric manipulation has applications in home robotics, textiles, senior care and surgery.  ...  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.  ...  Fabric manipulation in particular has applications ranging from senior care [18] , sewing [47] , ironing [30] , bed-making [50] and laundry folding [35, 29, 66, 51] to manufacturing upholstery  ... 
arXiv:2003.09044v3 fatcat:cgsbhrgtwnblhmugujvc6ckpya

Bodies Uncovered: Learning to Manipulate Real Blankets Around People via Physics Simulations [article]

Kavya Puthuveetil, Charles C. Kemp, Zackory Erickson
2022 arXiv   pre-print
We compare two approaches for optimizing policies which provide a robot with grasp and release points that uncover a target part of the body: 1) reinforcement learning and 2) self-supervised learning with  ...  We trained and conducted evaluations of these policies in physics simulation environments that consist of a deformable cloth mesh covering a simulated human lying supine on a bed.  ...  Seita et al [8] , has introduced a method for autonomous bed-making that leverages depth images to find and pull the corners of a blanket to corresponding corners of a bed.  ... 
arXiv:2109.04930v2 fatcat:xvgwj6a5c5gqxkem36tmne7si4


Kit, Ard, Cy Li, Donald Freibert, Joan Il, F Dwell, Cathy Davidson, Davidson, I Oliver, Glkn Christopher Wiseman, Ron Charach, M Lane (+39 others)
The general horrors of mealtimes in the hospital, of bed-making and working in the operating room, are presented in both novels and so are specific episodes : a bungled taking of blood from one of the  ...  She fabricates a past that bears little relation to her own and labels the picture of her fat self "Aunt Dierdre."  ...  of metaphor derives from a fear of subjectivity.  ...