Multi-Sound-Source Localization Using Machine Learning for Small Autonomous Unmanned Vehicles with a Self-Rotating Bi-Microphone Array

While vision-based localization techniques have been widely studied for small autonomous unmanned vehicles (SAUVs), sound-source capabilities not fully enabled SAUVs. This paper presents two novel approaches SAUVs to perform three-dimensional (3D) multi-sound-sources (MSSL) using only the inter-channel time difference (ICTD) signal generated by a self-rotating bi-microphone array. The proposed are based on machine learning viz., Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Random Sample Consensus (RANSAC) algorithms, respectively, whose performances were tested compared in both simulations experiments. results show that capable correctly identifying number sound sources along their 3D orientations reverberant environment.