Controlled Gaussian Process Dynamical Models with Application to Robotic Cloth Manipulation
This work addresses the challenge of uncertain and complex physical interactions with non-rigid objects like cloth in robotics, offering a method to improve modeling performance through data-driven learning, though it appears incremental as it builds on existing Gaussian Process Dynamical Models by incorporating control variables.
The paper tackles the problem of modeling high-dimensional, nonlinear dynamics in robotic cloth manipulation by proposing Controlled Gaussian Process Dynamical Models (CGPDM), which embed the dynamics into a low-dimensional manifold using Gaussian Process priors, and it demonstrates the model's ability to generalize and predict cloth motions in simulated and real scenarios.
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.