Linear Matrix Genetic Programming As A Tool For Data-driven Black-box Control-oriented Modeling In Conditions Of Limited Access To Training Data

This article discusses the development of a new evolutionary technique called Linear Matrix Genetic Programming (LMGP) for data-driven black-box control-oriented modeling. The LMGP is compared to different types of neural networks and is found to be more accurate and efficient in reproducing the behavior of a nonlinear model of an underwater vehicle. Additionally, the article highlights the use of Autonomous Mobile Robots (AMRs) equipped with an Autonomous Control System (ACS) based on artificial intelligence and machine learning algorithms for various industries.