Computational approaches to motor learning by imitation

TLDR

Movement imitation requires a complex set of mechanisms that map observed teacher movements onto one's own motor system, encompassing recognition, pose estimation, tracking, correspondence, coordinate transformation, redundancy resolution, representation, and modularization—each an active research problem, making a complete imitation system a daunting undertaking. This paper examines imitation purely from a computational perspective to untangle its complexity. The authors review statistical and mathematical approaches for motor imitation, assuming perceptual features are pre‑identified, and formalize motor control via control policies and performance criteria to generate taxonomies. These taxonomies clarify existing imitation approaches and outline future research directions.

Abstract

Movement imitation requires a complex set of mechanisms that map an observed movement of a teacher onto one's own movement apparatus. Relevant problems include movement recognition, pose estimation, pose tracking, body correspondence, coordinate transformation from external to egocentric space, matching of observed against previously learned movement, resolution of redundant degrees-of-freedom that are unconstrained by the observation, suitable movement representations for imitation, modularization of motor control, etc. All of these topics by themselves are active research problems in computational and neurobiological sciences, such that their combination into a complete imitation system remains a daunting undertaking-indeed, one could argue that we need to understand the complete perception-action loop. As a strategy to untangle the complexity of imitation, this paper will examine imitation purely from a computational point of view, i.e. we will review statistical and mathematical approaches that have been suggested for tackling parts of the imitation problem, and discuss their merits, disadvantages and underlying principles. Given the focus on action recognition of other contributions in this special issue, this paper will primarily emphasize the motor side of imitation, assuming that a perceptual system has already identified important features of a demonstrated movement and created their corresponding spatial information. Based on the formalization of motor control in terms of control policies and their associated performance criteria, useful taxonomies of imitation learning can be generated that clarify different approaches and future research directions.