Citation

BibTex format

@article{Zhang:2022:10.1126/scirobotics.abm6010,
author = {Zhang, F and Demiris, Y},
doi = {10.1126/scirobotics.abm6010},
journal = {Science Robotics},
pages = {eabm6010--eabm6010},
title = {Learning garment manipulation policies toward robot-assisted dressing.},
url = {http://dx.doi.org/10.1126/scirobotics.abm6010},
volume = {7},
year = {2022}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - Assistive robots have the potential to support people with disabilities in a variety of activities of daily living, such as dressing. People who have completely lost their upper limb movement functionality may benefit from robot-assisted dressing, which involves complex deformable garment manipulation. Here, we report a dressing pipeline intended for these people and experimentally validate it on a medical training manikin. The pipeline is composed of the robot grasping a hospital gown hung on a rail, fully unfolding the gown, navigating around a bed, and lifting up the user's arms in sequence to finally dress the user. To automate this pipeline, we address two fundamental challenges: first, learning manipulation policies to bring the garment from an uncertain state into a configuration that facilitates robust dressing; second, transferring the deformable object manipulation policies learned in simulation to real world to leverage cost-effective data generation. We tackle the first challenge by proposing an active pre-grasp manipulation approach that learns to isolate the garment grasping area before grasping. The approach combines prehensile and nonprehensile actions and thus alleviates grasping-only behavioral uncertainties. For the second challenge, we bridge the sim-to-real gap of deformable object policy transfer by approximating the simulator to real-world garment physics. A contrastive neural network is introduced to compare pairs of real and simulated garment observations, measure their physical similarity, and account for simulator parameters inaccuracies. The proposed method enables a dual-arm robot to put back-opening hospital gowns onto a medical manikin with a success rate of more than 90%.
AU - Zhang,F
AU - Demiris,Y
DO - 10.1126/scirobotics.abm6010
EP - 6010
PY - 2022///
SN - 2470-9476
SP - 6010
TI - Learning garment manipulation policies toward robot-assisted dressing.
T2 - Science Robotics
UR - http://dx.doi.org/10.1126/scirobotics.abm6010
UR - https://www.ncbi.nlm.nih.gov/pubmed/35385294
UR - https://www.science.org/doi/10.1126/scirobotics.abm6010
UR - http://hdl.handle.net/10044/1/96313
VL - 7
ER -