Biologically inspired posture recognition and posture change detection for humanoid robots

This paper presents a biologically inspired approach to posture recognition and posture change detection for a biped robot. Slow Feature Analysis, an algorithm developed by theoretical biologists for extracting slowly changing signals from signals varying on a fast time scale, is applied to the problem of recognizing the posture of biped humanoid robots over time and successively on the recognition of the change of posture. Both the recognition of basic static postures, like lying and standing, of peer robots via visual sensory information and the recognition of the same postures via internal proprioceptive sensors are considered. Given promising results in this domain we extend the application of the method onto the dynamic domain of detecting the change of posture, specifically we show the utility of the algorithm for detecting when a robot falls.