On Recurrent Neural Networks for learning-based control: recent results and ideas for future developments

Abstract

This paper aims to discuss and analyze the potentialities of Recurrent Neural Networks (RNN) in control design applications. The main families of RNN are considered, namely Neural Nonlinear AutoRegressive eXogenous, (NNARX), Echo State Networks (ESN), Long Short Term Memory (LSTM), and Gated Recurrent Units (GRU). The goal is twofold. Firstly, to survey recent results concerning the training of RNN that enjoy Input-to-State Stability (ISS) and Incremental Input-to-State Stability ($\delta$ISS) guarantees. Secondly, to discuss the issues that still hinder the widespread use of RNN for control, namely their robustness, verifiability, and interpretability. The former properties are related to the so-called generalization capabilities of the networks, i.e. their consistency with the underlying real plants, even in presence of unseen or perturbed input trajectories. The latter is instead related to the possibility of providing a clear formal connection between the RNN model and the plant. In this context, we illustrate how ISS and $\delta$ISS represent a significant step towards the robustness and verifiability of the RNN models, while the requirement of interpretability paves the way to the use of physics-based networks. The design of model predictive controllers with RNN as plant's model is also briefly discussed. Lastly, some of the main topics of the paper are illustrated on a simulated chemical system.

Copyright 2022. This manuscript version is made available under the CC-BY-NC-ND 4.0 license. This manuscript has been published at Elsevier Journal of Process Control. Published article available at DOI https://doi.org/10.1016/j.jprocont.2022.04.011

References in corpus (7)

• On the difficulty of training Recurrent Neural Networks
• Performance-oriented model learning for data-driven MPC design
• On the stability properties of Gated Recurrent Units neural networks
• POPQORN: Quantifying Robustness of Recurrent Neural Networks
• Nonlinear MPC for Offset-Free Tracking of systems learned by GRU Neural Networks
• Stability of discrete-time feed-forward neural networks in NARX configuration
• Recurrent Neural Network-based Internal Model Control design for stable nonlinear systems

Cited by in corpus (8)

• Generative AI and Process Systems Engineering: The Next Frontier
• From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape
• Nonlinear MPC design for incrementally ISS systems with application to GRU networks
• Robust constrained nonlinear Model Predictive Control with Gated Recurrent Unit model -- Extended version
• Robust offset-free constrained Model Predictive Control with Long Short-Term Memory Networks -- Extended version
• An Offset-Free Nonlinear MPC scheme for systems learned by Neural NARX models
• Robust offset-free nonlinear model predictive control for systems learned by neural nonlinear autoregressive exogenous models
• A PAC-Bayesian Framework for Optimal Control with Stability Guarantees