Experience repository based Particle Swarm Optimization for evolutionary robotics

In this paper, experience repository based Particle Swarm Optimization (ERPSO) is proposed for effectively applying Particle Swarm Optimization (PSO) to evolutionary robotics application. The ERPSO uses a concept experience repository to store previous position and fitness of particles to accelerate convergence speed of PSO. We applied the ERPSO to find parameter of gait of a quadruped robot that produces fast gait and ERPSO showed best performance among original PSO and PSO variants. ERPSO has fast convergence property which reduces the evaluation of fitness of parameters in a real environment.

[1]  S. S. Yang,et al.  Real-time model based sensor fault tolerant control system on a chip , 2009, 2009 ICCAS-SICE.

[2]  Masahiro Fujita,et al.  Autonomous evolution of dynamic gaits with two quadruped robots , 2005, IEEE Transactions on Robotics.

[3]  山田 祐,et al.  Open Dynamics Engine を用いたスノーボードロボットシミュレータの開発 , 2007 .

[4]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[5]  Lehrstuhl für Elektrische,et al.  Gaussian swarm: a novel particle swarm optimization algorithm , 2004, IEEE Conference on Cybernetics and Intelligent Systems, 2004..

[6]  Inman Harvey,et al.  Evolutionary robotics: the Sussex approach , 1997, Robotics Auton. Syst..

[7]  Sobhi Baniardalani,et al.  A novel analytical framework for qualitative Model-Based Fault Diagnosis , 2010, IEEE ICCA 2010.

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

[9]  Dave Cliff,et al.  Challenges in evolving controllers for physical robots , 1996, Robotics Auton. Syst..

[10]  Joanne H. Walker,et al.  Evolving Controllers for Real Robots: A Survey of the Literature , 2003, Adapt. Behav..

[11]  Dario Floreano,et al.  Active Vision and Receptive Field Development in Evolutionary Robots , 2005, Evolutionary Computation.