Learning to Fold Real Garments with One Arm: A Case Study in Cloud-Based Robotics Research
This addresses the problem of evaluating robotic fabric manipulation in a cost-effective way for robotics researchers, though it is incremental as it builds on existing methods.
The paper tackled the challenge of autonomous fabric manipulation by benchmarking fabric folding algorithms on physical hardware using a cloud robotics platform, finding that a novel algorithm combining imitation learning with analytic methods achieved 84% of human-level performance in folding a crumpled T-shirt with one arm.
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.