Autonomous fabric manipulation is a longstanding challenge in robotics, but evaluating progress is difficult due to the cost and diversity of robot hardware. Using Reach, a cloud robotics platform that enables low-latency remote execution of control policies on physical robots, we present the first systematic benchmarking of fabric manipulation algorithms on physical hardware. We develop 4 novel learning-based algorithms that model expert actions, keypoints, reward functions, and dynamic motions, and we compare these against 4 learning-free and inverse dynamics algorithms on the task of folding a crumpled T-shirt with a single robot arm. The entire lifecycle of data collection, model training, and policy evaluation is performed remotely without physical access to the robot workcell. Results suggest a new algorithm combining imitation learning with analytic methods achieves 84% of human-level performance on the folding task. See https://sites.google.com/berkeley.edu/cloudfolding for all data, code, models, and supplemental material.
@article{arxiv.2204.10297,
title = {Learning to Fold Real Garments with One Arm: A Case Study in Cloud-Based Robotics Research},
author = {Ryan Hoque and Kaushik Shivakumar and Shrey Aeron and Gabriel Deza and Aditya Ganapathi and Adrian Wong and Johnny Lee and Andy Zeng and Vincent Vanhoucke and Ken Goldberg},
journal= {arXiv preprint arXiv:2204.10297},
year = {2022}
}