Learning from demonstration with model-based Gaussian process

TL;DR

This paper introduces a novel multi-output Gaussian process framework based on Gaussian mixture regression for learning from demonstrations, enabling robots to adapt trajectories based on demonstration variability and task uncertainty.

Contribution

It presents a new MOGP approach that encodes demonstration variability in the covariance, allowing adaptive and compliant robot behavior during task execution.

Findings

Effective modulation of trajectories towards new points.

Precise tracking of via-points in demonstrations.

Validated in real-robot experiments.

Abstract

In learning from demonstrations, it is often desirable to adapt the behavior of the robot as a function of the variability retrieved from human demonstrations and the (un)certainty encoded in different parts of the task. In this paper, we propose a novel multi-output Gaussian process (MOGP) based on Gaussian mixture regression (GMR). The proposed approach encapsulates the variability retrieved from the demonstrations in the covariance of the MOGP. Leveraging the generative nature of GP models, our approach can efficiently modulate trajectories towards new start-, via- or end-points defined by the task. Our framework allows the robot to precisely track via-points while being compliant in regions of high variability. We illustrate the proposed approach in simulated examples and validate it in a real-robot experiment.