Learning-based Feedback Controller for Deformable Object Manipulation

TL;DR

This paper introduces a learning-based feedback control framework for deformable object manipulation that uses visual features and Gaussian Process Regression to achieve accurate and robust servo-control.

Contribution

It proposes a novel framework combining online GPR-based and offline imitation learning for deformable object control, adaptable to various objects and goals.

Findings

Fast and accurate manipulation with GPR-based online learning

Robust control against small perturbations

Effective servo-control demonstrated on multiple tasks

Abstract

In this paper, we present a general learning-based framework to automatically visual-servo control the position and shape of a deformable object with unknown deformation parameters. The servo-control is accomplished by learning a feedback controller that determines the robotic end-effector's movement according to the deformable object's current status. This status encodes the object's deformation behavior by using a set of observed visual features, which are either manually designed or automatically extracted from the robot's sensor stream. A feedback control policy is then optimized to push the object toward a desired featured status efficiently. The feedback policy can be learned either online or offline. Our online policy learning is based on the Gaussian Process Regression (GPR), which can achieve fast and accurate manipulation and is robust to small perturbations. An offline imitation learning framework is also proposed to achieve a control policy that is robust to large perturbations in the human-robot interaction. We validate the performance of our controller on a set of deformable object manipulation tasks and demonstrate that our method can achieve effective and accurate servo-control for general deformable objects with a wide variety of goal settings.