基于模型的高斯过程演示学习

Oct, 2019

Learning from demonstration with model-based Gaussian process

Noémie Jaquier, David Ginsbourger, Sylvain Calinon

TL;DR本文提出了一种基于高斯混合回归的新型多输出高斯过程（MOGP）方法，利用MOGP 的协方差将从演示中检索的变异性捕获起来，使机器人能够精确跟踪经过点，同时在高变异地区保持的柔顺性。

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 →