Recognizing people based on their footsteps using a wearable accelerometer

Collaboration of mobile robots and people generate the need for methods allowing the robot to reliable identify a person. The robust identification of the user is especially important in the context of people tracking when there are frequent occlusions. In this paper we present a novel approach for recognizing the user of a mobile robot. Our approach assumes that the user wears a mobile footstep sensor whose data are fused with footstep data extracted from leg movements of people. It relies on a recursive Bayesian estimation scheme to calculate a posterior about the potential associations between the different footstep perceptions. Our approach has been implemented and tested on real data. In simulated experiments, in which we use ground truth leg movement data recorded with a motion capture suite, and with a real robot we demonstrate the robustness of our method even when multiple people are present.