Localization of moving microphone arrays from moving sound sources for robot audition

Abstract

Acoustic Simultaneous Localization and Mapping (a-SLAM) jointly localizes the trajectory of a microphone array installed on a moving platform, whilst estimating the acoustic map of surrounding sound sources, such as human speakers. Whilst traditional approaches for SLAM in the vision and optical research literature rely on the assumption that the surrounding map features are static, in the acoustic case the positions of talkers are usually time-varying due to head rotations and body movements. This paper demonstrates that tracking of moving sources can be incorporated in a-SLAM by modelling the acoustic map as a Random Finite Set (RFS) of multiple sources and explicitly imposing models of the source dynamics. The proposed approach is verified and its performance evaluated for realistic simulated data.