Controlled Gaussian Process Dynamical Models with Application to Robotic Cloth Manipulation

TL;DR

This paper introduces Controlled Gaussian Process Dynamical Models (CGPDM) that effectively learn and predict complex, high-dimensional cloth dynamics in robotic manipulation by embedding them into a low-dimensional latent space, improving generalization.

Contribution

The paper presents a novel CGPDM approach that combines Gaussian Processes with low-dimensional embedding for modeling nonlinear, high-dimensional cloth dynamics in robotics.

Findings

CGPDM accurately predicts cloth motion in unseen sequences.

Model generalizes well across different cloth manipulation tasks.

Effective in both simulated and real scenarios.

Abstract

Over the last years, significant advances have been made in robotic manipulation, but still, the handling of non-rigid objects, such as cloth garments, is an open problem. Physical interaction with non-rigid objects is uncertain and complex to model. Thus, extracting useful information from sample data can considerably improve modeling performance. However, the training of such models is a challenging task due to the high-dimensionality of the state representation. In this paper, we propose Controlled Gaussian Process Dynamical Model (CGPDM) for learning high-dimensional, nonlinear dynamics by embedding it in a low-dimensional manifold. A CGPDM is constituted by a low-dimensional latent space, with an associated dynamics where external control variables can act and a mapping to the observation space. The parameters of both maps are marginalized out by considering Gaussian Process (GP) priors. Hence, a CGPDM projects a high-dimensional state space into a smaller dimension latent space, in which it is feasible to learn the system dynamics from training data. The modeling capacity of CGPDM has been tested in both a simulated and a real scenario, where it proved to be capable of generalizing over a wide range of movements and confidently predicting the cloth motions obtained by previously unseen sequences of control actions.