Learning Deformable Object Manipulation from Expert Demonstrations
This addresses the problem of robotic manipulation of deformable objects for robotics and automation, presenting an incremental advancement in Learning from Demonstration methods.
The paper tackles deformable object manipulation tasks, such as rope and cloth manipulation, by introducing a Learning from Demonstration method called DMfD, which achieves performance improvements of up to 12.9% for state-based tasks and up to 33.44% for image-based tasks over baselines, with minimal real-world performance loss (~6%).
We present a novel Learning from Demonstration (LfD) method, Deformable Manipulation from Demonstrations (DMfD), to solve deformable manipulation tasks using states or images as inputs, given expert demonstrations. Our method uses demonstrations in three different ways, and balances the trade-off between exploring the environment online and using guidance from experts to explore high dimensional spaces effectively. We test DMfD on a set of representative manipulation tasks for a 1-dimensional rope and a 2-dimensional cloth from the SoftGym suite of tasks, each with state and image observations. Our method exceeds baseline performance by up to 12.9% for state-based tasks and up to 33.44% on image-based tasks, with comparable or better robustness to randomness. Additionally, we create two challenging environments for folding a 2D cloth using image-based observations, and set a performance benchmark for them. We deploy DMfD on a real robot with a minimal loss in normalized performance during real-world execution compared to simulation (~6%). Source code is on github.com/uscresl/dmfd