Artificial Intelligence for Robust Estimation, Intelligent Control, and Advanced Applications in Nonlinear Engineering Systems

Artificial Intelligence is transforming modern engineering by enabling adaptive, autonomous, and data-driven decision-making in increasingly complex systems. However, many nonlinear and safety-critical engineering applications still require robust state estimation, stability guarantees, resilience against disturbances and uncertainties, interpretability, computational efficiency, and real-time performance. These requirements are not always adequately addressed by purely data-driven approaches. Consequently, there is growing interest in hybrid methodologies that integrate Artificial Intelligence and machine learning with nonlinear systems theory, robust and adaptive control, state observers, optimization, and physics-based modeling.This Research Topic aims to gather original research articles, review papers, methodological contributions, and application-oriented studies at the intersection of Artificial Intelligence, nonlinear control, robust state estimation, intelligent monitoring, optimization, and autonomous decision-making. Particular emphasis will be placed on approaches combining model-based and data-driven methodologies to improve reliability, explainability, safety, resilience, autonomy, and real-time implementation. The collection will welcome theoretical developments, numerical studies, experimental validations, benchmark comparisons, hardware-in-the-loop implementations, industrial case studies, and real-world applications in robotics, automotive and autonomous systems, smart manufacturing, process engineering, energy systems, water and environmental systems, biomedical engineering, and other complex engineering domains.Themes of interest include, but are not limited to:- Learning-based, neural, high-gain, finite-time, and sliding-mode observers for nonlinear systems- State and parameter estimation under disturbances, uncertainty, noise, and partial observability- Hybrid model-based and data-driven identification, modeling, and control design- Robust, adaptive, and intelligent control with stability and performance guarantees- Reinforcement learning and learning-enhanced model predictive control for constrained nonlinear systems- Physics-informed machine learning and digital twins for estimation and controlFault diagnosis, fault-tolerant control, and prognosis in nonlinear and networked systems- Explainable, safe, resilient, and real-time embedded implementation of intelligent estimation and control- Applications in robotics, autonomous and automotive systems, smart manufacturing, process and energy systems, water and environmental systems, and biomedical engineeringWe welcome Original Research, Review, Mini Review, Methods, and Perspective articles. Purely data-driven studies with no estimation or control component, and applications of standard machine learning pipelines without a systems-theoretic contribution, fall outside the scope of this collection. Topic editors: Abraham Efraim Rodriguez, Victor Gonzalez-huitron Source: https://www.frontiersin.org/research-topics/85379/artificial-intelligence-for-robust-estimation-intelligent-control-and-advanced-applications-in-nonlinear-engineering-systems