Collective robotics search using particle system

Abstract EN

This work introduces the implementation of particle system to be simulated to work as a group of unmanned mobile robots (swarm robots).

These robots are able to locate a specified target in the predefined environment with high efficiency when driven by an optimized Particle Swarm Optimization (PSO) algorithm.

The application of the particle system to the mobile robots to search for a target in the environment is called Collective Robotics Search (CRS) problem.

The main benefit of this application is to evolve better solutions than using single robot through the collective interaction of all robots between them to achieve the searching task successfully.

Particle system has been chosen in this work to employ the mobile robots in the CRS problem due to its simplicity and easy to implement.

To measure the performance of this simulation, a simple obstacle free environment will be used to implement behaviors of the group of mobile robots when those robots are used to search for a single target.

The results of this work show that applying PSO to a CRS problem in off-line and on-line approaches are efficient in terms of minimum error and also minimum number of iterations during the evolutionary process.