Human behaviour recognition with segmented inertial data

Abstract

The development and recent advancements of integrated inertial sensors has afforded substantive new possibilities for the acquisition and study of complex human motor skills and ultimately their imitation within robotic systems. This paper describes continuing work on kinetic models that are derived through unsupervised learning from a continuous stream of signals, including Euler angles and accelerations in three spatial dimensions, acquired from motions of a human arm. An intrinsic classification algorithm, MML (Minimum Message Length encoding) is used to segment the complex data, formulating a Gaussian Mixture Model of the dynamic modes it represents. Subsequent representation and analysis as FSM (Finite State Machines) has found distinguishing and consistent sequences of modes that persist across both, a variety of tasks as well as multiple candidates. An exemplary “standard” sequence for each behaviour can be abstracted from a corpus of suitable data and in turn utilised together with alignment techniques to identify behaviours of new sequences, as well as detail the homologous extent between each. The progress in contrast to previous work and future objectives are discussed.