Investigation on the evolution of a robotic controller for autonomous vehicle navigation

This work addresses the evolution of an Artificial Neural Network (ANN) to assist in the problem of autonomous navigation of a vehicle in urban environments. We propose a system architecture based on the use of two ANNs, one is trained for image processing, in charge of road recognition and employing template matching. The other ANN is evolved to perform the navigation control. The paper focuses on the evolved ANN, which provides steering and speed control to the autonomous vehicle, corroborating with the Evolutionary Robotic research area and showing its practical viability. The proposed system was tested in several experiments, evaluating not only the impact of different evolutionary computation parameters but also the role of the transfer functions on the evolution of the ANN. Results show that slight variations in the parameters lead to huge differences on the accuracy of the evolutionary process.