Manifold Relevance Determination: Learning the Latent Space of Robotics
This addresses the problem of building underlying models in robotics without direct theoretical assumptions, though it appears incremental as it builds on prior MRD work.
The paper introduces Manifold Relevance Determination (MRD) as a method to learn latent space models for robotics applications like sensor fusion, SLAM, and human-robot interaction, enabling data-driven construction instead of relying on first principles.
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.