Swarm-robot formation optimization based on multiobjective genetic algorithm

Authors:
Ju-Feng Xiong;Guan-Zheng Tan
Affiliations:
College of Information Science and Engineering, Central South University, Changsha and College of Physics and Information Science, Hunan Normal University, Changsha;College of Physics and Information Science, Hunan Normal University, Changsha
Venue:
CCDC'09 Proceedings of the 21st annual international conference on Chinese control and decision conference
Year:
2009

Citing 4
Cited 0

Pheromone Robotics

Autonomous Robots
Distributed, Physics-Based Control of Swarms of Vehicles

Autonomous Robots
The SWARM-BOTS project

SAB'04 Proceedings of the 2004 international conference on Swarm Robotics
The I-SWARM project: intelligent small world autonomous robots for micro-manipulation

SAB'04 Proceedings of the 2004 international conference on Swarm Robotics

Quantified Score

Hi-index	0.00

Visualization

Abstract

On improving the performance in which the swarm-robot grid formation motion are controlled in a complicated circumstance based on virtual force method, it is used the multiobjective genetic algorithm to optimize control parameters. Performance indexes include collision, break the ranks, connectivity, etc. The weight value of the indexes is determined by their importance. Optimization model is established, the multiobjective genetic algorithm based on Pareto sets is used to search the solution of the problem. Simulation results show that this algorithm is effectively capable of obtaining a set of non-dominated solution within a finite evolutionary generation, which overcomes the weakness of handiwork to set control parameters.