Analysis of sound source localization and tracking for the @home service robot in multiple distances

Abstract

Robots have been used in several areas, and in many of them it is common to see an interaction between a human and the robot. Human-Robot Interaction (HRI) became a crucial part on the process of understanding and creating machines, which will communicate using voice as the main factor. Speech is used as an input and an output of the communication between machines and humans, in the way that commands and answers are performed using this method. There are several Sound Source Localization and Tracking (SSLT) methods that may be used in an ambiance and many systems can be used to complete this task. To succeed in the usage of this knowledge source, establishing an appropriate system, which allows doing the calculus and implementation in a service robot, is necessary and, using the past work of the author, it was concluded. The main objective of this paper is to introduce some of the available methods for SSLT in the literature, and present results of the implementation and implantation of methods for a Domestic Service Robot, with the objective of having a more natural interaction with humans, allowing to interact the human facing front, instead of facing any direction.