An optimal sound detection for robots in an unknown environment

Abstract

Robot technology has been rapidly developed more & more robots such as humanoid robots work with humans. The objective of this project is to develop a system for an autonomous mobile robot for searching and tracking sound source based target using sound sensors. Finding objects or events by following a sound source direction is an intuitive response for human and animal when they cannot see the target. Lego nxt sound sensor can detect the frequency of sound but is unable to detect the direction from where the sound is originating. PSO algorithm has been implemented for the optimization of the exact sound source. PSO (particle swarm optimization) is a stochastic population based computational method that optimizes the problem in each iteration, trying to improve the particle solutions and to get better quality of the particles each time. Objective function has been applied to detect the frequency and then the source continuously updates its position on the basis of frequency being detected. So that maximum frequency sound can be detected in minimum possible time and in exact location. Simulation work has been carried out by implementing the PSO algorithm in MATLAB to see how exactly the sound sources are detecting the frequency and at what particular frequency the source is exactly detecting the sound. Results have been computed by changing the number of iterations to see the exact location where the sound source is finding the frequency. Thus the main objective of this paper is to compute that the source is detecting the optimized maximum frequency sound by updating its gbest values continuously in every iteration and finally reaching the best possible value.