Design of Genetic Algorithms for the Simulation-Based Training of Artificial Neural Networks in the Context of Automated Vehicle Guidance

Abstract

This paper describes the design of a Genetic Algorithm (GA) for intelligent control systems with Artificial Neural Networks (ANNs) in the context of autonomous driving in a model-based and verification-oriented process. First, a summary of the state of the art is given on the use of ANNs and GAs in control engineering. This is followed by an explanation of the design methodology used in this paper. Then the concept of a universal GA for the (simulation-based) training of any common ANNs is presented. Afterwards the design of the GA is explained in detail. Special aspects of parameterization and algorithms are also discussed. Finally, the presented method is validated by an example of a model-based design of a driving function based on an ANN for automated lateral guidance.