Annual Reviews in Control最新文献

{"title":"AI-empowered modeling and control for automotive propulsion system: Challenges, solutions and prospects","authors":"Jian Tang ,&nbsp;Tianyi He ,&nbsp;Wenpeng Wei ,&nbsp;Guoming Zhu","doi":"10.1016/j.arcontrol.2026.101048","DOIUrl":"10.1016/j.arcontrol.2026.101048","url":null,"abstract":"<div><div>This paper comprehensively reviews the modeling and control of automotive propulsion systems, with a particular focus on the integration of emerging artificial intelligence (AI) techniques. The highlights of this review paper include: (1) This review specially focuses on AI-empowered modeling and control for automotive propulsion systems, filling the blank in existing surveys; (2) Different approaches to leverage AI in propulsion applications are summarized, categorized and analyzed. Prospects for possible future directions are discussed based on state-of-the-art researches; and (3) Case studies and examples are given to demonstrate the effectiveness of AI techniques applied to automotive propulsion systems.</div><div>The review starts with the introduction of the fundamental principles of propulsion systems for Internal Combustion engine Vehicles (ICVs), Hybrid Electric Vehicles (HEVs) and Battery Electric Vehicles (BEVs), along with discussions of traditional modeling developments and their advantages and disadvantages. Motivations and prospects of leveraging AI techniques for automotive propulsion systems are highlighted. Subsequently, this paper summarizes the modeling approaches into white-, gray- and black-box methods and discusses their respective strengths and limitations. More importantly, this paper defines the AI approaches, outlines its typical methodologies, and highlights its peculiar significance in automotive propulsion systems, where challenges in modeling and control are identified, and solutions provided by emerging AI techniques are discussed. Particularly, various AI applications in propulsion systems are addressed, including direct and indirect data-driven modeling and control techniques such as Gaussian process-based models, neural networks etc. The effectiveness of these techniques are demonstrated through several representative examples. In the sequel, the unique challenges and limitations of AI applications to propulsion systems are discussed, and future research directions are envisioned. Finally, this paper concludes by summarizing the key points and emphasizing the pivotal role of AI in advancing automotive propulsion systems.</div></div>","PeriodicalId":50750,"journal":{"name":"Annual Reviews in Control","volume":"61 ","pages":"Article 101048"},"PeriodicalIF":10.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Control theory in the era of intelligent systems: Applications, trends, and future directions","authors":"Maria Trigka,&nbsp;Elias Dritsas","doi":"10.1016/j.arcontrol.2026.101049","DOIUrl":"10.1016/j.arcontrol.2026.101049","url":null,"abstract":"<div><div>Control theory has established itself as a fundamental discipline for the analysis and design of dynamical systems. From its classical foundations, including proportional–integral–derivative (PID) control, state–space representations, and stability analysis, it has progressively expanded toward advanced, robust, and predictive control frameworks. The increasing complexity of modern systems, characterized by large-scale integration, data-driven operations, and stringent safety requirements, is reshaping their methodological foundations. However, despite extensive progress, the field of control remains fragmented, and an integrative viewpoint connecting the different topics is still lacking. This survey provides a unified cross-domain perspective that consolidates established principles and emerging intelligent paradigms. Specifically, it addresses this research gap by synthesizing classical control theory with contemporary artificial intelligence (AI)-driven and cyber–physical systems (CPS) methodologies within a mathematically consistent framework. To the best of our knowledge, no prior survey has provided a unified analytical framework that jointly treats all the aforementioned topics. A distinctive contribution is the mathematically rigorous treatment of nonlinear observer design through Laguerre polynomial approximations, positioned in direct comparison with extended Kalman filters (EKF), high-gain observers (HGO), and hybrid estimation methods. Beyond the classical scope, this survey addresses the convergence of control with AI, machine learning (ML), deep learning (DL), Internet of Things (IoT) infrastructures, digital twins, and quantum-edge computing, emphasizing their implications for scalability, adaptability, and resilience. The novelty of this review lies in articulating an integrative framework that bridges robust analytical tools with intelligent, data-driven architectures, highlighting both methodological coherence and cross-domain applicability. Key challenges include managing nonlinear complexity, ensuring robustness under uncertainty, embedding ethical and governance-aware mechanisms, and bridging the gap between theoretical innovation and practical deployment. Future trends indicate a shift towards reinforcement learning (RL)-augmented control, hybrid physics–AI architectures, distributed CPS architectures, and sustainability-driven designs. By combining historical depth with forward-looking integration, this survey serves as both a consolidated reference and a roadmap for the next generation of intelligent and resilient control systems.</div></div>","PeriodicalId":50750,"journal":{"name":"Annual Reviews in Control","volume":"61 ","pages":"Article 101049"},"PeriodicalIF":10.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Control-oriented system identification: Classical, learning, and physics-informed approaches","authors":"S. Sivaranjani,&nbsp;Yuanyuan Shi,&nbsp;Nikolay Atanasov,&nbsp;Thai Duong,&nbsp;Jie Feng,&nbsp;Tim Martin,&nbsp;Yuezhu Xu,&nbsp;Vijay Gupta,&nbsp;Frank Allgöwer","doi":"10.1016/j.arcontrol.2026.101067","DOIUrl":"10.1016/j.arcontrol.2026.101067","url":null,"abstract":"<div><div>This article surveys classical, machine learning, and data-driven system identification approaches to learn control-relevant and physics-informed models of dynamical systems. In recent years, machine learning approaches have enabled system identification from noisy, high-dimensional, and complex data. However, their utility in control applications is limited by their ability to provide provable guarantees on control-relevant properties. Meanwhile, traditional control theory has identified several properties of physical systems that are useful in analysis and control synthesis, such as dissipativity, monotonicity, energy conservation, and symmetry-preserving structures. In this paper, we postulate that merging system identification algorithms with such control-relevant or physics-informed properties can provide useful inductive bias, enhance explainability, enable control synthesis with provable guarantees, and improve sample complexity. We formulate system identification as an optimization problem where control-relevant properties can be enforced in three ways, namely, direct parameterization (constraining the model structure to satisfy a desired property by construction), soft constraints (encouraging control-relevant properties through regularization or penalty terms), and hard constraints (imposing control-relevant properties as constraints in the optimization problem). Through this lens, we survey methods to learn physics-informed and control-relevant models spanning classical linear and nonlinear system identification techniques, machine learning-based approaches, as well as direct identification through data-driven and behavioral representations. Taken together, these perspectives suggest that control-oriented identification should be viewed not only as a problem of minimizing prediction error, but also as one of selecting model structures and learning methods that preserve the properties needed for downstream analysis and control synthesis. Throughout the paper, we provide several expository examples that are accompanied by code and brief tutorials on a public Github repository. We also describe several challenging directions for future research in this area, including identification in networked, switched, and time-varying systems, experiment design, and bridging the gaps between data-driven, learning-based, and control-oriented system identification.</div></div>","PeriodicalId":50750,"journal":{"name":"Annual Reviews in Control","volume":"62 ","pages":"Article 101067"},"PeriodicalIF":14.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148634695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Control theory and artificial intelligence integration in manufacturing and supply chain management: conceptual synthesis and perspectives","authors":"Alexandre Dolgui,&nbsp;Dmitry Ivanov,&nbsp;Ilya Kovalenko,&nbsp;Anand Nair,&nbsp;Suresh Sethi","doi":"10.1016/j.arcontrol.2026.101073","DOIUrl":"10.1016/j.arcontrol.2026.101073","url":null,"abstract":"<div><div>Control theory (CT) offers rigorous mathematical methods and models for stability, feedback, and performance analysis. Artificial intelligence (AI) is also rooted in the principles of feedback, stability, and performance control, but views them from a different perspective: model-agnostic, data-driven adaptability and predictive capabilities. This paper reviews CT applications and the mutual enhancements between CT and AI in manufacturing and supply chain operations. Based on literature analysis, we develop a learning-control framework based on a conceptual synthesis of CT and AI and grounded in feedback control, dynamic optimization, and learning-based adaptation. Generalized mathematical formulations illustrate how classical control concepts can integrate with AI-based models, including machine and reinforcement learning, multi-agent systems, and agentic AI. Potential barriers and future research areas are discussed. The paper concludes with implications for designing next-generation industrial and supply chain systems capable of learning, adapting, and stabilizing in uncertain and data-rich environments in the AI era.</div></div>","PeriodicalId":50750,"journal":{"name":"Annual Reviews in Control","volume":"62 ","pages":"Article 101073"},"PeriodicalIF":14.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149050870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Finite-time stability and stabilization of stochastic nonlinear systems driven by fractional Brownian motion","authors":"Cheng Zhang,&nbsp;Guojian Ren,&nbsp;Yongguang Yu,&nbsp;Wei Hu","doi":"10.1016/j.arcontrol.2026.101076","DOIUrl":"10.1016/j.arcontrol.2026.101076","url":null,"abstract":"<div><div>Finite-time stability (FTS) is crucial for modern engineering systems with stringent real-time requirements. This paper investigates FTS for stochastic nonlinear systems driven by fractional Brownian motion (fBm), a process exhibiting long-range dependence. The non-semimartingale property of fBm presents analytical challenges. Utilizing fractional Wick–Itô–Skorohod integrals and the fractional multidimensional Itô formula, the finite-time dynamics are rigorously analyzed. Sufficient conditions for FTS are established, and an explicit estimate of the settling time is provided. Based on the above theory, the finite-time control for non-local diffusion systems is further discussed. By using a finite-dimensional modal approximation, a finite-time feedback law is constructed from a linear stabilizing component and a non-Lipschitz power-type term. Verifiable gain conditions are derived to compensate for the bounded linear perturbation, the nonlinear drift, and the Malliavin correction induced by the fBm. And an explicit settling-time bound is obtained for the controlled modal system. Numerical simulations validate the theoretical results.</div></div>","PeriodicalId":50750,"journal":{"name":"Annual Reviews in Control","volume":"62 ","pages":"Article 101076"},"PeriodicalIF":14.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149211153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An in-depth review of dual-arm robot learning methods with advances and challenges in variable compliance-aware control for uncertain tasks","authors":"Md Shofiqul Islam ,&nbsp;Zoran Najdovski ,&nbsp;Mohammad Anwar Hosen ,&nbsp;Van Thanh Huynh","doi":"10.1016/j.arcontrol.2026.101050","DOIUrl":"10.1016/j.arcontrol.2026.101050","url":null,"abstract":"<div><div>Advancements in haptic teleoperation enable robots to perform complex tasks with precision. Key progress lies in compliance control strategies that adjust robot stiffness based on task requirements. Despite notable achievements, challenges remain, including the need for robust algorithms capable of learning from sparse data, managing uncertainties, and ensuring stability during dynamic interactions. Furthermore, integrating compliance control with teleoperation systems introduces issues such as real-time feedback, latency, and the fidelity of haptic sensations. These challenges are covered in depth through our contributions in this review. This paper provides an in-depth analysis of the current state of learning variable compliance control in haptic teleoperation with limited demonstrations, outlining key challenges, research gaps, and future research directions. The initial section offers background information, followed by learning from demonstrations and methodologies for various compliance control techniques. The review covers recent research, including methodologies, algorithms, simulations, data generation processes, findings, and research gaps. This critical review of methods and experimental analysis is conducted on leading approaches, recent applications, advancements, particularly challenges, limitations, and future directions. We also conducted an analytical evaluation of different learning methods using robot task based simulation data derived from demonstrated tasks, training models show that imitation learning methods, particularly Imitation Behaviour Cloning (IBC) and LSTM models, achieved the highest accuracies (99.84%), outperforming reinforcement learning models that demonstrated lower accuracy and greater sensitivity to hyperparameter tuning. We also provided the recommendations of optimal approaches are provided for learning compliance control in haptic teleoperation.</div></div>","PeriodicalId":50750,"journal":{"name":"Annual Reviews in Control","volume":"61 ","pages":"Article 101050"},"PeriodicalIF":10.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reinforcement learning in fault tolerance and diagnosis fields: A literature review","authors":"Ziad Noun ,&nbsp;Majd Saied ,&nbsp;Hamze Muhieddine ,&nbsp;Hassan Shraim ,&nbsp;Clovis Francis ,&nbsp;Hassan Noura","doi":"10.1016/j.arcontrol.2026.101055","DOIUrl":"10.1016/j.arcontrol.2026.101055","url":null,"abstract":"<div><div>Reinforcement learning (RL) techniques have increasingly been integrated into fault diagnosis (FD) and fault-tolerant control (FTC) systems due to their robust feature representation capabilities and adaptability. To facilitate related research, this paper presents a synthesis of recent progress in reinforcement learning methodologies for FD and FTC systems. Initially, it outlines key concepts and formulations of RL systems. Subsequently, it reviews the commonly employed RL architectures, with particular emphasis on model-free, model-based and deep learning methods. Finally, it delves into the challenges faced in current applications of RL-based FD and FTC, covering aspects like imbalanced data, safety and robustness, interpretability and explainability, along with potential solutions. This paper strives to offer a comprehensive roadmap for furthering RL-based FD and FTC research within the community.</div></div>","PeriodicalId":50750,"journal":{"name":"Annual Reviews in Control","volume":"61 ","pages":"Article 101055"},"PeriodicalIF":10.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147849536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Linear algebra based control design: A review with new perspectives","authors":"Pedro Albertos","doi":"10.1016/j.arcontrol.2026.101053","DOIUrl":"10.1016/j.arcontrol.2026.101053","url":null,"abstract":"<div><div>The Linear Algebra Based (LAB) control design (CD) methodology was introduced in the last decade as a simple tool to design tracking control of nonlinear systems. Since then, it has been applied to a variety of processes, with subsequent refinements addressing initial implementation challenges. In this review paper, the LAB CD methodology is revisited and some issues arising in its application are analyzed, providing simple solutions in order to keep the methodology simple to apply and easy to understand by the end users. Some illustrative examples taken from the literature serve as a reference. A number of promising open problems for future research are identified.</div></div>","PeriodicalId":50750,"journal":{"name":"Annual Reviews in Control","volume":"61 ","pages":"Article 101053"},"PeriodicalIF":10.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147849538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fractional calculus in optimal control and game theory: Theory, numerics, and applications — A survey","authors":"Navid Mojahed,&nbsp;Hooman Fatoorehchi,&nbsp;Shima Nazari","doi":"10.1016/j.arcontrol.2026.101075","DOIUrl":"10.1016/j.arcontrol.2026.101075","url":null,"abstract":"<div><div>Many physical, biological, and engineered systems display memory that challenges Markovian models. Fractional calculus offers nonlocal operators that capture such hereditary effects. This survey connects modeling, analysis, and controller/game design for systems with memory.</div><div>On modeling, we unify notation across Caputo, Riemann–Liouville, and Grünwald–Letnikov derivatives and relate them to engineering approximations based on diffusive (sum-of-exponentials) state augmentation and frequency-domain realizations such as the Oustaloup family of fractional-order approximations. On analysis, we synthesize fractional extensions of the calculus of variations and the Pontryagin maximum principle, and we review dynamic-programming formulations with memory, including path-dependent Hamilton–Jacobi–Bellman for optimal control and Hamilton–Jacobi–Isaacs for zero-sum games. On design, we cover single-agent controllers — linear-quadratic regulator, model predictive control, and fractional-order proportional–integral–derivative — and multi-agent formulations such as fractional differential games with Nash, Stackelberg (leader–follower), and minimax equilibria.</div><div>On computation, we compare time-domain schemes (including the L1 and Grünwald–Letnikov methods), frequency-domain approximations (e.g., Oustaloup-type realizations), and diffusive state augmentations, emphasizing accuracy–complexity trade-offs and practical remedies for the “curse of history” using windowing, sum-of-exponentials, and band-limited or low-rank representations. We conclude with applications in viscoelasticity, anomalous transport, electrochemistry, and control of engineered systems; a benchmark template for reproducibility; and open problems on existence and uniqueness of equilibria with memory, refined Isaacs-type conditions, stability under constraints, and scalable fractional-order model predictive control and multi-agent solvers.</div></div>","PeriodicalId":50750,"journal":{"name":"Annual Reviews in Control","volume":"62 ","pages":"Article 101075"},"PeriodicalIF":14.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149153801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synthesis of model predictive control and reinforcement learning: Survey and classification","authors":"Rudolf Reiter ,&nbsp;Jasper Hoffmann ,&nbsp;Dirk Reinhardt ,&nbsp;Florian Messerer ,&nbsp;Katrin Baumgärtner ,&nbsp;Shambhuraj Sawant ,&nbsp;Joschka Bödecker ,&nbsp;Moritz Diehl ,&nbsp;Sebastien Gros","doi":"10.1016/j.arcontrol.2026.101045","DOIUrl":"10.1016/j.arcontrol.2026.101045","url":null,"abstract":"<div><div>model predictive control (MPC) and reinforcement learning (RL) are two successful control techniques for Markov decision processes. Both approaches are derived from similar fundamental principles, and both are widely used in practical applications, including robotics, process control, energy systems, and autonomous driving. Despite their similarities, MPC and RL follow distinct paradigms that emerged from diverse communities and different requirements. Various technical discrepancies, particularly the role of an environment model as part of the algorithm, lead to methodologies with nearly complementary advantages. Due to their orthogonal benefits, research interest in combination methods has recently increased significantly, resulting in a large and growing set of complex ideas that leverage MPC and RL. This work illuminates the differences, similarities, and fundamentals that enable various combination algorithms and categorizes existing work accordingly. Particularly, we focus on the versatile actor–critic RL approach as a basis for our categorization and examine how the online optimization approach of MPC can be used to improve the overall closed-loop performance of a policy.</div></div>","PeriodicalId":50750,"journal":{"name":"Annual Reviews in Control","volume":"61 ","pages":"Article 101045"},"PeriodicalIF":10.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146187395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}