Explainable Machine Learning Control -- robust control and stability analysis
This work addresses the need for interpretable control systems in fields like robotics or automation, though it appears incremental as it builds on prior genetic programming methods.
The authors tackled the problem of making machine learning control interpretable by using symbolic regression to derive optimal control laws for dynamical systems, demonstrating that explainable models offer significant advantages over less interpretable neural networks.
Recently, the term explainable AI became known as an approach to produce models from artificial intelligence which allow interpretation. Since a long time, there are models of symbolic regression in use that are perfectly explainable and mathematically tractable: in this contribution we demonstrate how to use symbolic regression methods to infer the optimal control of a dynamical system given one or several optimization criteria, or cost functions. In previous publications, network control was achieved by automatized machine learning control using genetic programming. Here, we focus on the subsequent analysis of the analytical expressions which result from the machine learning. In particular, we use AUTO to analyze the stability properties of the controlled oscillator system which served as our model. As a result, we show that there is a considerable advantage of explainable models over less accessible neural networks.