Automatic Evolutionary Design of Control Systems for Underwater Vehicles

The development of an automatic evolutionary design environment based on genetic algorithms for obtaining artificial neural network based control system structures for underwater vehicles is presented. The design procedure is carried out by means of evolutionary techniques from a set of specifications using as a fitness evaluator an ad-hoc hydrodynamic simulator which includes the estimation of added mass and added inertia coefficients. The model´s equations of motion employed were obtained by theoretical formulation combined with some empirical correlations. The resulting design environment was used to obtain the neural network based controllers for submarine vehicles. Results of the simulations obtained using this technique, of the application of the automatic design procedure and of the operation of the controllers thus obtained are presented.