Manifold Relevance Determination: Learning the Latent Space of Robotics

TL;DR

This paper introduces manifold relevance determination (MRD), a data-driven method for learning latent spaces applicable to robotics tasks like sensor fusion, SLAM, and human-robot interaction, emphasizing model construction from data rather than first principles.

Contribution

The paper presents MRD as a novel approach for constructing models in robotics applications using data-driven latent space learning, expanding its potential uses.

Findings

MRD can effectively model sensor fusion and SLAM tasks.

MRD enables data-driven model construction in robotics.

MRD has been applied to improve robot grasp stability.

Abstract

In this article we present the basics of manifold relevance determination (MRD) as introduced in \cite{mrd}, and some applications where the technology might be of particular use. Section 1 acts as a short tutorial of the ideas developed in \cite{mrd}, while Section 2 presents possible applications in sensor fusion, multi-agent SLAM, and "human-appropriate" robot movement (e.g. legibility and predictability~\cite{dragan-hri-2013}). In particular, we show how MRD can be used to construct the underlying models in a data driven manner, rather than directly leveraging first principles theories (e.g., physics, psychology) as is commonly the case for sensor fusion, SLAM, and human robot interaction. We note that [Bekiroglu et al., 2016] leveraged MRD for correcting unstable robot grasps to stable robot grasps.