Hybrid Intelligent Systems, International Conference on (2006)
Auckland, New Zealand
Dec. 13, 2006 to Dec. 15, 2006
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/HIS.2006.41
Yohannes Kassahun , University of Bremen, Germany
Nils T Siebel , University of Kiel, Germany
In this article we introduce a method to learn neural networks that solve a visual servoing task. Our method, called EANT, Evolutionary Acquisition of Neural Topologies, starts from a minimal network structure and gradually develops it further using evolutionary reinforcement learning. We have improved EANT by combining it with an optimisation technique called CMA-ES, Covariance Matrix Adaptation Evolution Strategy. Results from experiments with a 3 DOF visual servoing task show that the new CMAES based EANT develops very good networks for visual servoing. Their performance is significantly better than those developed by the original EANT and traditional visual servoing approaches.
Yohannes Kassahun, Nils T Siebel, "Learning Neural Networks for Visual Servoing Using Evolutionary Methods", Hybrid Intelligent Systems, International Conference on, vol. 00, no. , pp. 6, 2006, doi:10.1109/HIS.2006.41