Localization of Simultaneous Moving Sound Sources for Mobile Robot Using a Frequency-Domain Steered Beamformer Approach

TL;DR

This paper presents a real-time, robust method for mobile robots to localize multiple moving sound sources in 3D space using an 8-microphone array and frequency-domain steered beamforming, enhancing environmental awareness.

Contribution

The paper introduces a novel frequency-domain steered beamformer combined with probabilistic post-processing for accurate 3D sound source localization on mobile robots.

Findings

Localizes multiple moving sources within 5 meters

Achieves a response time of 200 milliseconds

Operates in real-time in dynamic environments

Abstract

Mobile robots in real-life settings would benefit from being able to localize sound sources. Such a capability can nicely complement vision to help localize a person or an interesting event in the environment, and also to provide enhanced processing for other capabilities such as speech recognition. In this paper we present a robust sound source localization method in three-dimensional space using an array of 8 microphones. The method is based on a frequency-domain implementation of a steered beamformer along with a probabilistic post-processor. Results show that a mobile robot can localize in real time multiple moving sources of different types over a range of 5 meters with a response time of 200 ms.