Initialization of latent space coordinates via random linear projections for learning robotic sensory-motor sequences

ABSTRACT: Robot kinematic data, despite being high-dimensional, is highly correlated, especially when considering motions grouped in certain primitives. These almost linear correlations within primitives allow us to interpret motions as points drawn close to a union of low-dimensional affine subspaces in the space of all motions. Motivated by results of embedding theory, in particular, generalizations of the Whitney embedding theorem, we show that random linear projection of motor sequences into low-dimensional space loses very little information about the structure of kinematic data. Projected points offer good initial estimates for values of latent variables in a generative model of robot sensory-motor behavior primitives. We conducted a series of experiments in which we trained a Recurrent Neural

SUBMITTER:  

PROVIDER: S-EPMC9515618 | biostudies-literature | 2022 Jan

REPOSITORIES: biostudies-literature