arXiv subjects

Simone Formentin

Publications and source records attributed to Simone Formentin.

At least 19 recordsLinked to original sources

arXiv2026

A subspace approach to data-driven predictive control for linear parameter-varying systems

This paper presents a subspace data-driven predictive control method for linear parameter-varying (LPV) systems. Starting from an affine LPV state-space model in innovation form, we derive a multi-step predictor that separates the effects of past data, future inputs, scheduling trajectories, and innovations. By projecting this representation onto the row span of lifted input-output-scheduling data, we obtain an asymptotically unbiased data-driven predictor that can be embedded directly in a receding-horizon control problem, without explicitly identifying an LPV model. To make the resulting LPV data-driven predictive control (DDPC) formulation tractable, we introduce an LPV extension of $\gamma$-DDPC based on an LQ factorization. This formulation fixes the number of online decision variables independently of the length of the dataset. A reduced-order predictor is then proposed to curb the exponential growth of scheduling-dependent regressors, which also relaxes the persistence-of-excitation condition. Simulation studies, including an unbalanced-disk example, show that the proposed controller achieves good tracking performance and, compared to existing LPV DDPC schemes, achieves better robustness to measurement noise and reduced computational cost, making multi-step LPV DDPC practically deployable, even with longer past horizons.

eess.SY↗

arXiv2026

Beyond Shrinkage: Foundations of Data-Driven Control for Piecewise Affine Systems

Data-enabled predictive control (DeePC) has recently attracted attention as a promising approach for controlling systems directly from raw data, without requiring an explicit identification step. However, DeePC has not yet been extended to piecewise affine (PWA) systems, despite their extensive use in the (predictive) control literature and their universal approximation capabilities. To address this gap, in this work, we lay the foundations for data-enabled predictive control of PWA systems, providing: $(i)$ their behavioral characterization; $(ii)$ an extension of Willems' Fundamental Lemma to represent their behavior from raw data; $(iii)$ an analysis of the coherence of DeePC strategies using a linear predictor and shrinkage regularizers; and $(iv)$ a study of the impact of misclassification errors on structuring data for prediction. Our theoretical findings are validated by numerical results on a simple example, emphasizing the need to extend beyond a regularized version of the foundational DeePC framework to design control actions that are both effective and coherent with a PWA system's behavior, thus ensuring the controller's explainability.

eess.SY↗

arXiv2026

Robust data-driven model-reference control of linear perturbed systems via sliding mode generation

This paper introduces a data-based integral sliding mode control scheme for robustification of model-reference controllers, accommodating generic multivariable linear systems with unknown dynamics and affected by matched disturbances. Specifically, an integral sliding mode control (ISMC) law is recast into a data-based framework relying on an integral sliding variable depending only on the reference model, without the need of modeling the plant. The main strength of the proposed approach is the enforcement of the desired reference model in closed-loop under sliding mode conditions, despite the lack of knowledge of the model dynamics and the presence of the matched disturbances. Moreover, the conditions required to guarantee an integral sliding mode generation and the closed-loop stability are formally analyzed in the paper, remarking the generality of the proposed data-driven integral sliding mode control (DD-ISMC) with respect to the related model-based counterpart. Finally, the main practices for the data-based design of the proposed control scheme are deeply discussed in the paper, and the proposed method is tested in simulation on a benchmark example, and experimentally on a real laboratory setup. Simulation and experimental evidence fully corroborates the theoretical analysis, thus motivating further research in this direction.

eess.SY↗

arXiv2025

Generative design of stabilizing controllers with diffusion models: the Youla approach

Designing controllers that simultaneously achieve strong performance and provable closed-loop stability remains a central challenge in control engineering. This work introduces a diffusion-based generative framework for linear controller synthesis grounded in the Youla-Kucera parameterization, enabling the construction of stabilizing controllers by design. The diffusion model learns a conditional mapping from plant dynamics and desired performance metrics to feasible Youla parameters, guaranteeing internal stability while flexibly accommodating user-specified targets. Trained on synthetically generated stable SISO plants with fixed-order Youla parameters, the proposed approach reliably synthesizes controllers that meet prescribed sensitivity and settling-time specifications on previously unseen systems. To the best of our knowledge, this work provides the first demonstration that diffusion models can generate stabilizing controllers, combining rigorous control-theoretic guarantees with the versatility of modern generative modeling.

eess.SY↗

arXiv2025

Efficient Reinforcement Learning from Human Feedback via Bayesian Preference Inference

Learning from human preferences is a cornerstone of aligning machine learning models with subjective human judgments. Yet, collecting such preference data is often costly and time-consuming, motivating the need for more efficient learning paradigms. Two established approaches offer complementary advantages: RLHF scales effectively to high-dimensional tasks such as LLM fine-tuning, while PBO achieves greater sample efficiency through active querying. We propose a hybrid framework that unifies RLHF's scalability with PBO's query efficiency by integrating an acquisition-driven module into the RLHF pipeline, thereby enabling active and sample-efficient preference gathering. We validate the proposed approach on two representative domains: (i) high-dimensional preference optimization and (ii) LLM fine-tuning. Experimental results demonstrate consistent improvements in both sample efficiency and overall performance across these tasks.

cs.LG↗

arXiv2025

Regularized GLISp for sensor-guided human-in-the-loop optimization

Human-in-the-loop calibration is often addressed via preference-based optimization, where algorithms learn from pairwise comparisons rather than explicit cost evaluations. While effective, methods such as Preferential Bayesian Optimization or Global optimization based on active preference learning with radial basis functions (GLISp) treat the system as a black box and ignore informative sensor measurements. In this work, we introduce a sensor-guided regularized extension of GLISp that integrates measurable descriptors into the preference-learning loop through a physics-informed hypothesis function and a least-squares regularization term. This injects grey-box structure, combining subjective feedback with quantitative sensor information while preserving the flexibility of preference-based search. Numerical evaluations on an analytical benchmark and on a human-in-the-loop vehicle suspension tuning task show faster convergence and superior final solutions compared to baseline GLISp.

cs.LG↗

arXiv2025

Feedback dynamics in Politics: The interplay between sentiment and engagement

We investigate feedback mechanisms in political communication by testing whether politicians adapt the sentiment of their messages in response to public engagement. Using over 1.5 million tweets from Members of Parliament in the United Kingdom, Spain, and Greece during 2021, we identify sentiment dynamics through a simple yet interpretable linear model. The analysis reveals a closed-loop behavior: engagement with positive and negative messages influences the sentiment of subsequent posts. Moreover, the learned coefficients highlight systematic differences across political roles: opposition members are more reactive to negative engagement, whereas government officials respond more to positive signals. These results provide a quantitative, control-oriented view of behavioral adaptation in online politics, showing how feedback principles can explain the self-reinforcing dynamics that emerge in social media discourse.

cs.SI↗

arXiv2025

Toward Federated DeePC: borrowing data from similar systems

Data-driven predictive control approaches, in general, and Data-enabled Predictive Control (DeePC), in particular, exploit matrices of raw input/output trajectories for control design. These data are typically gathered only from the system to be controlled. Nonetheless, the increasing connectivity and inherent similarity of (mass-produced) systems have the potential to generate a considerable amount of information that can be exploited to undertake a control task. In light of this, we propose a preliminary federated extension of DeePC that leverages a combination of input/output trajectories from multiple similar systems for predictive control. Supported by a suite of numerical examples, our analysis unveils the potential benefits of exploiting information from similar systems and its possible downsides.

eess.SY↗

arXiv2025

eXplainable AI for data driven control: an inverse optimal control approach

Understanding the behavior of black-box data-driven controllers is a key challenge in modern control design. In this work, we propose an eXplainable AI (XAI) methodology based on Inverse Optimal Control (IOC) to obtain local explanations for the behavior of a controller operating around a given region. Specifically, we extract the weights assigned to tracking errors and control effort in the implicit cost function that a black-box controller is optimizing, offering a more transparent and interpretable representation of the controller's underlying objectives. This approach presents connections with well-established XAI techniques, such as Local Interpretable Model-agnostic Explanations (LIME) since it is still based on a local approximation of the control policy. However, rather being limited to a standard sensitivity analysis, the explanation provided by our method relies on the solution of an inverse Linear Quadratic (LQ) problem, offering a structured and more control-relevant perspective. Numerical examples demonstrate that the inferred cost function consistently provides a deeper understanding of the controller's decision-making process, shedding light on otherwise counterintuitive or unexpected phenomena.

eess.SY↗

arXiv2025

In-Context Learning for Zero-Shot Speed Estimation of BLDC motors

Accurate speed estimation in sensorless brushless DC motors is essential for high-performance control and monitoring, yet conventional model-based approaches struggle with system nonlinearities and parameter uncertainties. In this work, we propose an in-context learning framework leveraging transformer-based models to perform zero-shot speed estimation using only electrical measurements. By training the filter offline on simulated motor trajectories, we enable real-time inference on unseen real motors without retraining, eliminating the need for explicit system identification while retaining adaptability to varying operating conditions. Experimental results demonstrate that our method outperforms traditional Kalman filter-based estimators, especially in low-speed regimes that are crucial during motor startup.

eess.SY↗

arXiv2025

Insights into the explainability of Lasso-based DeePC for nonlinear systems

Data-enabled Predictive Control (DeePC) has recently gained the spotlight as an easy-to-use control technique that allows for constraint handling while relying on raw data only. Initially proposed for linear time-invariant systems, several DeePC extensions are now available to cope with nonlinear systems. Nonetheless, these solutions mainly focus on ensuring the controller's effectiveness, overlooking the explainability of the final result. As a step toward explaining the outcome of DeePC for the control of nonlinear systems, in this paper, we focus on analyzing the earliest and simplest DeePC approach proposed to cope with nonlinearities in the controlled system, using a Lasso regularization. Our theoretical analysis highlights that the decisions undertaken by DeePC with Lasso regularization are unexplainable, as control actions are determined by data incoherent with the system's local behavior. This result is true even when the available input/output samples are grouped according to the different operating conditions explored during data collection. Our numerical study confirms these findings, highlighting the benefits of data grouping in terms of performance while showing that explainability remains a challenge in control design via DeePC.

eess.SY↗

arXiv2025

Automating the loop in traffic incident management on highway

Effective traffic incident management is essential for ensuring safety, minimizing congestion, and reducing response times in emergency situations. Traditional highway incident management relies heavily on radio room operators, who must make rapid, informed decisions in high-stakes environments. This paper proposes an innovative solution to support and enhance these decisions by integrating Large Language Models (LLMs) into a decision-support system for traffic incident management. We introduce two approaches: (1) an LLM + Optimization hybrid that leverages both the flexibility of natural language interaction and the robustness of optimization techniques, and (2) a Full LLM approach that autonomously generates decisions using only LLM capabilities. We tested our solutions using historical event data from Autostrade per l'Italia. Experimental results indicate that while both approaches show promise, the LLM + Optimization solution demonstrates superior reliability, making it particularly suited to critical applications where consistency and accuracy are paramount. This research highlights the potential for LLMs to transform highway incident management by enabling accessible, data-driven decision-making support.

cs.AI↗

arXiv2024

One controller to rule them all

Imagine having a system to control and only know that it belongs to a certain class of dynamical systems. Would it not be amazing to simply plug in a controller and have it work as intended? With the rise of in-context learning and powerful architectures like Transformers, this might be possible, and we want to show it. In this work, within the model reference framework, we hence propose the first in-context learning-based approach to design a unique contextual controller for an entire class of dynamical systems rather than focusing on just a single instance. Our promising numerical results show the possible advantages of the proposed paradigm, paving the way for a shift from the "one-system-one-controller" control design paradigm to a new "one-class-one-controller" logic.

eess.SY↗

arXiv2024

Bias correction and instrumental variables for direct data-driven model-reference control

Managing noisy data is a central challenge in direct data-driven control design. We propose an approach for synthesizing model-reference controllers for linear time-invariant (LTI) systems using noisy state-input data, employing novel noise mitigation techniques. Specifically, we demonstrate that using data-based covariance parameterization of the controller enables bias-correction and instrumental variable techniques within the data-driven optimization, thus reducing measurement noise effects as data volume increases. The number of decision variables remains independent of dataset size, making this method scalable to large datasets. The approach's effectiveness is demonstrated with a numerical example.

eess.SY↗

arXiv2024

Meta-learning of data-driven controllers with automatic model reference tuning: theory and experimental case study

Data-driven control offers a viable option for control scenarios where constructing a system model is expensive or time-consuming. Nonetheless, many of these algorithms are not entirely automated, often necessitating the adjustment of multiple hyperparameters through cumbersome trial-and-error processes and demanding significant amounts of data. In this paper, we explore a meta-learning approach to leverage potentially existing prior knowledge about analogous (though not identical) systems, aiming to reduce both the experimental workload and ease the tuning of the available degrees of freedom. We validate this methodology through an experimental case study involving the tuning of proportional, integral (PI) controllers for brushless DC (BLDC) motors with variable loads and architectures.

eess.SY↗

arXiv2024

Sentiment-driven prediction of financial returns: a Bayesian-enhanced FinBERT approach

Predicting financial returns accurately poses a significant challenge due to the inherent uncertainty in financial time series data. Enhancing prediction models' performance hinges on effectively capturing both social and financial sentiment. In this study, we showcase the efficacy of leveraging sentiment information extracted from tweets using the FinBERT large language model. By meticulously curating an optimal feature set through correlation analysis and employing Bayesian-optimized Recursive Feature Elimination for automatic feature selection, we surpass existing methodologies, achieving an F1-score exceeding 70% on the test set. This success translates into demonstrably higher cumulative profits during backtested trading. Our investigation focuses on real-world SPY ETF data alongside corresponding tweets sourced from the StockTwits platform.

cs.CE↗

arXiv2024

Model Predictive Control with adaptive resilience for Denial-of-Service Attacks mitigation on a Regulated Dam

In recent years, SCADA (Supervisory Control and Data Acquisition) systems have increasingly become the target of cyber attacks. SCADAs are no longer isolated, as web-based applications expose strategic infrastructures to the outside world connection. In a cyber-warfare context, we propose a Model Predictive Control (MPC) architecture with adaptive resilience, capable of guaranteeing control performance in normal operating conditions and driving towards resilience against DoS (controller-actuator) attacks when needed. Since the attackers' goal is typically to maximize the system damage, we assume they solve an adversarial optimal control problem. An adaptive resilience factor is then designed as a function of the intensity function of a Hawkes process, a point process model estimating the occurrence of random events in time, trained on a moving window to estimate the return time of the next attack. We demonstrate the resulting MPC strategy's effectiveness in 2 attack scenarios on a real system with actual data, the regulated Olginate dam of Lake Como.

eess.SY↗

arXiv2024

Explainable data-driven modeling via mixture of experts: towards effective blending of grey and black-box models

Traditional models grounded in first principles often struggle with accuracy as the system's complexity increases. Conversely, machine learning approaches, while powerful, face challenges in interpretability and in handling physical constraints. Efforts to combine these models often often stumble upon difficulties in finding a balance between accuracy and complexity. To address these issues, we propose a comprehensive framework based on a "mixture of experts" rationale. This approach enables the data-based fusion of diverse local models, leveraging the full potential of first-principle-based priors. Our solution allows independent training of experts, drawing on techniques from both machine learning and system identification, and it supports both collaborative and competitive learning paradigms. To enhance interpretability, we penalize abrupt variations in the expert's combination. Experimental results validate the effectiveness of our approach in producing an interpretable combination of models closely resembling the target phenomena.

cs.LG↗