Mixtures of controlled Gaussian processes for dynamical modeling of deformable objects

Conference Article


Learning for Dynamics & Control Conference (L4DC)





Doc link


Download the digital copy of the doc pdf document


Control and manipulation of objects is a highly relevant topic in Robotics research. Although significant advances have been made over the manipulation of rigid bodies, the manipulation of non-rigid objects is still challenging and an open problem. Due to the uncertainty of the outcome when applying physical actions to non-rigid objects, using prior knowledge on objects’ dynamics can greatly improve the control performance. However, fitting such models is a challenging task for materials such as clothing, where the state is represented by points in a mesh, resulting in very large dimensionality that makes models difficult to learn, process and predict based on measured data. In this paper, we expand previous work on Controlled Gaussian Process Dynamical Models (CGPDM), a method that uses a non-linear projection of the state space onto a much smaller dimensional latent space, and learns the object dynamics in the latent space. We take advantage of the variability in training data by employing Mixture of Experts (MoE), and we devise theory and experimental validations that demonstrate significant improvements in training and prediction times, plus robustness and error stability when predicting deformable objects exposed to disparate movement ranges.


learning (artificial intelligence), robots.

Author keywords

Gaussian Processes, Learning from Demonstration, Dimensionality Reduction, Mixture of Gaussian Experts, Data-driven Dynamic Model Learning

Scientific reference

C. Xu, A. Colomé, L. Sentis and C. Torras. Mixtures of controlled Gaussian processes for dynamical modeling of deformable objects, 2022 Learning for Dynamics & Control Conference, 2022, Stanford, CA, USA, pp. 415-426.