Multi-Robot Box-Pushing Using VIKOR Induced Particle Swarm optimization

The paper proposes a unique strategy to formulate the popular multi-robot box-pushing problem in the multi-objective optimization setting. The problem is solved by a novel hybrid particle swarm optimization variant, which we have named as the VIKOR-PSO. This method implements local path planning scheme, and generates an optimal trajectory that minimizes the time and energy requirement of the robots by optimizing the translational and rotational traversal parameters, online through VIKOR-PSO. In contrary to traditional evolutionary algorithms, the proposed approach allows fast convergence of solutions on the Pareto Front, thus making it ideal for solving real-world multi-objective optimization problems, opening a new direction to successful multi-agent coordination.

[1]  Amit Konar,et al.  Rotation and translation selective Pareto optimal solution to the box-pushing problem by mobile robots using NSGA-II , 2009, 2009 IEEE Congress on Evolutionary Computation.

[2]  Pratyusha Rakshit,et al.  Uncertainty Management in Differential Evolution Induced Multiobjective Optimization in Presence of Measurement Noise , 2014, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[3]  Marco Laumanns,et al.  SPEA2: Improving the strength pareto evolutionary algorithm , 2001 .

[4]  Gwo-Hshiung Tzeng,et al.  Extended VIKOR method in comparison with outranking methods , 2007, Eur. J. Oper. Res..

[5]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[6]  Heinz Wörn,et al.  Human–Robot Cooperation Using Multi-Agent-Systems , 2001, J. Intell. Robotic Syst..

[7]  Joaquim Salvi,et al.  A multi-agent architecture with cooperative fuzzy control for a mobile robot , 2007, Robotics Auton. Syst..

[8]  Peter J. Fleming,et al.  An Overview of Evolutionary Algorithms in Multiobjective Optimization , 1995, Evolutionary Computation.

[9]  Serafim Opricovic,et al.  Fuzzy VIKOR with an application to water resources planning , 2011, Expert Syst. Appl..

[10]  Carlos A. Coello Coello,et al.  Handling multiple objectives with particle swarm optimization , 2004, IEEE Transactions on Evolutionary Computation.

[11]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.