Implementasi Algoritma PSO Pada Multi Mobile Robot Dalam Penentuan Posisi Target Terdekat

Abstract

 Swarm Intelligence is an artificial intelligence developed by adapting the social behavior of a group of animal. In the migratory birds community, it is known that the behavior of the birds during the flight forms a 'V' formation that plays a role in optimizing the bird's energy saving. The basic principle of a swarm intelligence is the existence of collective, decentralized and self-organizing behavior. This is the basis for the development of behavioral algorithms flocking birds called Particle Swarm Optimization (PSO).

In this research used three mobile robot as object to implement PSO algorithm. Three pieces of this robot is homogeneous, which is similar hardware and software. A group of these robots will complete the joint mission of defining the robot with the closest distance to the target TPr (robot handler). There are three TPr targets that have to be executed by the robot handler according to their position with the target point to be completed. The test is done by taking odometry data every 250 milisekon and data frame robot communication.

At the end of this research, the result of modeling system result of PSO algorithm implementation on mobile robot group to determine the robot closest to the target. The robot system that meets the principles of PSO, namely the process of data sharing and learning process.