Application of fuzzy NARX to human gait modelling and identification

A new modelling and classification approach for human gait is proposed. Body movements are obtained using a sensor suit recording inertial signals that are subsequently modelled on a humanoid frame with 23 degrees of freedom (DOF). Measured signals include position, velocity, acceleration, orientation, angular velocity and angular acceleration. The identification and modelling method segments the stream of non–linear movement data on the basis of the features extracted from the sensor signals. A model is then created for the movement of every individual. This model is used as a dynamic finger print for that specific individual. In the future stages of the work, the proposed approach will be further developed to include identification of various gestures and emotional manners as well as the identity of an individual. Furthermore, the feasibility of generating the identified behaviours in a humanoid robot will be explored. The approach is described and the characteristics of the algorithm are presented. The results obtained so far are reported and conclusions are drawn.