Deformable Elasto-Plastic Object Shaping using an Elastic Hand and Model-Based Reinforcement Learning

TL;DR

This paper introduces a novel elastic end-effector and model-based reinforcement learning to shape deformable elasto-plastic objects like dough, achieving efficient and adaptable manipulation with fewer actions and improved performance through stiffness estimation.

Contribution

It presents a new elastic hand and reinforcement learning framework for deformable object shaping, with a learned transition model from limited exploration and stiffness-based model initialization.

Findings

Achieved dough rolling with 60% fewer actions than heuristic methods.

Estimated stiffness improves model initialization and robot performance by ~40%.

Successfully generalized to different dough hydration levels.

Abstract

Deformable solid objects such as clay or dough are prevalent in industrial and home environments. However, robotic manipulation of such objects has largely remained unexplored in literature due to the high complexity involved in representing and modeling their deformation. This work addresses the problem of shaping elasto-plastic dough by proposing to use a novel elastic end-effector to roll dough in a reinforcement learning framework. The transition model for the end-effector-to-dough interactions is learned from one hour of robot exploration, and doughs of different hydration levels are rolled out into varying lengths. Experimental results are encouraging, with the proposed framework accomplishing the task of rolling out dough into a specified length with 60% fewer actions than a heuristic method. Furthermore, we show that estimating stiffness using the soft end-effector can be used to effectively initialize models, improving robot performance by approximately 40% over incorrect model initialization.