# Learning from demonstration with model-based Gaussian process

arXiv: https://arxiv.org/abs/1910.05005 · HTML: https://mlsanity.com/paper/1910.05005/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Robot learning from demonstration, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 3 of its 16 references that are in the map.
- First posted on arXiv 11 Oct 2019.

## Placed in

- Offline RL and imitation learning from data / [Robot learning from demonstration](https://mlsanity.com/offlinerl/robot-learning-from-demonstration/)

## Builds on (most cited first, 3 of 3)

- [Kernelized Movement Primitives](https://mlsanity.com/paper/1708.08638/) (2017)
- [Probabilistic Learning of Torque Controllers from Kinematic and Force Constraints](https://mlsanity.com/paper/1712.07249/) (2017)
- [Small Variance Asymptotics for Non-Parametric Online Robot Learning](https://mlsanity.com/paper/1610.02468/) (2016)

## Built on by (most cited first, 6 of 6)

- [Interactive Imitation Learning of Bimanual Movement Primitives](https://mlsanity.com/paper/2210.16220/) (2022)
- [Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies](https://mlsanity.com/paper/2305.10411/) (2023)
- [Gaussian-Process-based Robot Learning from Demonstration](https://mlsanity.com/paper/2002.09979/) (2020)
- [Interactive incremental learning of generalizable skills with local trajectory modulation](https://mlsanity.com/paper/2409.05655/) (2024)
- [Deep Movement Primitives: toward Breast Cancer Examination Robot](https://mlsanity.com/paper/2202.09265/) (2022)
- [The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning](https://mlsanity.com/paper/2505.03296/) (2025)

## Abstract (arXiv)

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.