Learning Neural Networks for Visual Servoing Using Evolutionary Methods
Nils T. Siebel, Yohannes Kassahun · 2006
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 CMA-ES 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. 1. Introduction and Related