Iterative Machine Learning for Output Tracking
Incremental method for output tracking in control systems, but lacks empirical validation or comparison to baselines.
The paper proposes iterative machine learning for output tracking, using kernel-based methods to update both the model and input iteratively. Simulation results demonstrate the approach, but no concrete performance numbers are provided.
This article develops iterative machine learning (IML) for output tracking. The input-output data generated during iterations to develop the model used in the iterative update. The main contribution of this article to propose the use of kernel-based machine learning to iteratively update both the model and the model-inversion-based input simultaneously. Additionally, augmented inputs with persistency of excitation are proposed to promote learning of the model during the iteration process. The proposed approach is illustrated with a simulation example.