Unmanned Ground Vehicle Selection with Artificial Neural Networks

Abstract

In this study, a selection program is intended to be developed to determine the purpose for which unmanned ground vehicles for military use will be employed. Based on the operating principles of the unmanned ground vehicle, the basic mechanical systems have been identified. Subsequently, a design catalog containing these basic mechanical systems has been created. The desired features of the unmanned ground vehicle to be used in the field were asked of the customer, and the most suitable unmanned ground vehicle was determined using an artificial neural networks algorithm based on the responses received. In the artificial neural network model, a feedforward neural network architecture was used. SGD was utilized in the network training function to minimize the model’s loss function. The activation functions tanh and softmax were used, and the model has four hidden layers. Results were obtained for the metrics of accuracy, precision, recall, and F1-score. The model’s accuracy rate was found to be 99.6%