Abstract
The paper proposes a probabilistic 3D sound source mapping system as an interface to indicate “where is the sound?”The microphone array is used for sound source localization and tracking that is based on “MUSIC” (Multiple Signal Classification) algorithm and “Multiple-Target Tracking” algorithm. The LIDAR is used to generate 3D geometric map and estimate its 6DoF location by “G-ICP SLAM” which is a state of the art ICP based SLAM (Simultaneous Localization and Mapping) method. By combing these modules, it provides sound direction in 3D global space while the robot is moving. From the time-series of tracked sound stream, the sound position is estimated by Monte Carlo Localization approach. Some experiment results using the hand-held sensor unit are shown in experiment section.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
