arXiv subjects

Giancarlo Ferrari-Trecate

Publications and source records attributed to Giancarlo Ferrari-Trecate.

At least 55 records · Page 3Linked to original sources

arXiv2024

Unconstrained learning of networked nonlinear systems via free parametrization of stable interconnected operators

This paper characterizes a new parametrization of nonlinear networked incrementally $L_2$-bounded operators in discrete time. The distinctive novelty is that our parametrization is \emph{free} -- that is, a sparse large-scale operator with bounded incremental $L_2$ gain is obtained for any choice of the real values of our parameters. This property allows one to freely search over optimal parameters via unconstrained gradient descent, enabling direct applications in large-scale optimal control and system identification. Further, we can embed prior knowledge about the interconnection topology and stability properties of the system directly into the large-scale distributed operator we design. Our approach is extremely general in that it can seamlessly encapsulate and interconnect state-of-the-art Neural Network (NN) parametrizations of stable dynamical systems. To demonstrate the effectiveness of this approach, we provide a simulation example showcasing the identification of a networked nonlinear system. The results underscore the superiority of our free parametrizations over standard NN-based identification methods where a prior over the system topology and local stability properties are not enforced.

eess.SY↗

arXiv2024

Stable Linear Subspace Identification: A Machine Learning Approach

Machine Learning (ML) and linear System Identification (SI) have been historically developed independently. In this paper, we leverage well-established ML tools - especially the automatic differentiation framework - to introduce SIMBa, a family of discrete linear multi-step-ahead state-space SI methods using backpropagation. SIMBa relies on a novel Linear-Matrix-Inequality-based free parametrization of Schur matrices to ensure the stability of the identified model. We show how SIMBa generally outperforms traditional linear state-space SI methods, and sometimes significantly, although at the price of a higher computational burden. This performance gap is particularly remarkable compared to other SI methods with stability guarantees, where the gain is frequently above 25% in our investigations, hinting at SIMBa's ability to simultaneously achieve state-of-the-art fitting performance and enforce stability. Interestingly, these observations hold for a wide variety of input-output systems and on both simulated and real-world data, showcasing the flexibility of the proposed approach. We postulate that this new SI paradigm presents a great extension potential to identify structured nonlinear models from data, and we hence open-source SIMBa on https://github.com/Cemempamoi/simba.

eess.SY↗

arXiv2024

Neural Distributed Controllers with Port-Hamiltonian Structures

Controlling large-scale cyber-physical systems necessitates optimal distributed policies, relying solely on local real-time data and limited communication with neighboring agents. However, finding optimal controllers remains challenging, even in seemingly simple scenarios. Parameterizing these policies using Neural Networks (NNs) can deliver good performance, but their sensitivity to small input changes can destabilize the closed-loop system. This paper addresses this issue for a network of nonlinear dissipative systems. Specifically, we leverage well-established port-Hamiltonian structures to characterize deep distributed control policies with closed-loop stability guarantees and a finite $\mathcal{L}_2$ gain, regardless of specific NN parameters. This eliminates the need to constrain the parameters during optimization and enables training with standard methods like stochastic gradient descent. A numerical study on the consensus control of Kuramoto oscillators demonstrates the effectiveness of the proposed controllers.

eess.SY↗

arXiv2024

Neural Exponential Stabilization of Control-affine Nonlinear Systems

This paper proposes a novel learning-based approach for achieving exponential stabilization of nonlinear control-affine systems. We leverage the Control Contraction Metrics (CCMs) framework to co-synthesize Neural Contraction Metrics (NCMs) and Neural Network (NN) controllers. First, we transform the infinite-dimensional semi-definite program (SDP) for CCM computation into a tractable inequality feasibility problem using element-wise bounds of matrix-valued functions. The terms in the inequality can be efficiently computed by our novel algorithms. Second, we propose a free parametrization of NCMs guaranteeing positive definiteness and the satisfaction of a partial differential equation, regardless of trainable parameters. Third, this parametrization and the inequality condition enable the design of contractivity-enforcing regularizers, which can be incorporated while designing the NN controller for exponential stabilization of the underlying nonlinear systems. Furthermore, when the training loss goes to zero, we provide formal guarantees on verification of the NCM and the exponentional stabilization under the NN controller. Finally, we validate our method through benchmark experiments on set-point stabilization and increasing the region of attraction of a locally pre-stabilized closed-loop system.

eess.SY↗

arXiv2024

Closing the Gap to Quadratic Invariance: a Regret Minimization Approach to Optimal Distributed Control

In this work, we focus on the design of optimal controllers that must comply with an information structure. State-of-the-art approaches do so based on the H2 or Hinfty norm to minimize the expected or worst-case cost in the presence of stochastic or adversarial disturbances. Large-scale systems often experience a combination of stochastic and deterministic disruptions (e.g., sensor failures, environmental fluctuations) that spread across the system and are difficult to model precisely, leading to sub-optimal closed-loop behaviors. Hence, we propose improving performance for these scenarios by minimizing the regret with respect to an ideal policy that complies with less stringent sensor-information constraints. This endows our controller with the ability to approach the improved behavior of a more informed policy, which would detect and counteract heterogeneous and localized disturbances more promptly. Specifically, we derive convex relaxations of the resulting regret minimization problem that are compatible with any desired controller sparsity, while we reveal a renewed role of the Quadratic Invariance (QI) condition in designing informative benchmarks to measure regret. Last, we validate our proposed method through numerical simulations on controlling a multi-agent distributed system, comparing its performance with traditional H2 and Hinfty policies.

eess.SY↗

arXiv2024

Moving horizon partition-based state estimation of large-scale systems -- Revised version

This report presents three Moving Horizon Estimation (MHE) methods for discrete-time partitioned linear systems, i.e. systems decomposed into coupled subsystems with non-overlapping states. The MHE approach is used due to its capability of exploiting physical constraints on states in the estimation process. In the proposed algorithms, each subsystem solves reduced-order MHE problems to estimate its own state and different estimators have different computational complexity, accuracy and transmission requirements among subsystems. In all cases, conditions for the convergence of the estimation error to zero are analyzed.

eess.SY↗

arXiv2023

Homothetic tube model predictive control with multi-step predictors

We present a robust model predictive control (MPC) framework for linear systems facing bounded parametric uncertainty and bounded disturbances. Our approach deviates from standard MPC formulations by integrating multi-step predictors, which provide reduced error bounds. These bounds, derived from multi-step predictors, are utilized in a homothetic tube formulation to mitigate conservatism. Lastly, a multi-rate formulation is adopted to handle the incompatibilities of multi-step predictors. We provide a theoretical analysis, guaranteeing robust recursive feasibility, constraint satisfaction, and (practical) stability of the desired setpoint. We use a simulation example to compare it to existing literature and demonstrate advantages in terms of conservatism and computational complexity.

math.OC↗

arXiv2023

A Coverage Control-based Idle Vehicle Rebalancing Approach for Autonomous Mobility-on-Demand Systems

As an emerging mode of urban transportation, Autonomous Mobility-on-Demand (AMoD) systems show the potential in improving mobility in cities through timely and door-to-door services. However, the spatiotemporal imbalances between mobility demand and supply may lead to inefficiencies and a low quality of service. Vehicle rebalancing (i.e., dispatching idle vehicles to high-demand areas), is a potential solution for efficient AMoD fleet management. In this paper, we formulate the vehicle rebalancing problem as a coverage control problem for the deployment of a fleet of mobile agents for AMoD operation in urban areas. Performance is demonstrated via microscopic simulations representing a large urban road network of Shenzhen, China. Results reveal the potential of the proposed method in improving service rates and decreasing passenger waiting times.

eess.SY↗

arXiv2023

Unconstrained Parametrization of Dissipative and Contracting Neural Ordinary Differential Equations

In this work, we introduce and study a class of Deep Neural Networks (DNNs) in continuous-time. The proposed architecture stems from the combination of Neural Ordinary Differential Equations (Neural ODEs) with the model structure of recently introduced Recurrent Equilibrium Networks (RENs). We show how to endow our proposed NodeRENs with contractivity and dissipativity -- crucial properties for robust learning and control. Most importantly, as for RENs, we derive parametrizations of contractive and dissipative NodeRENs which are unconstrained, hence enabling their learning for a large number of parameters. We validate the properties of NodeRENs, including the possibility of handling irregularly sampled data, in a case study in nonlinear system identification.

eess.SY↗

arXiv2023

Data-Driven Robust Control Using Prediction Error Bounds Based on Perturbation Analysis

For linear systems, many data-driven control methods rely on the behavioral framework, using historical data of the system to predict the future trajectories. However, measurement noise introduces errors in predictions. When the noise is bounded, we propose a method for designing historical experiments that enable the computation of an upper bound on the prediction error. This approach allows us to formulate a minimax control problem where robust constraint satisfaction is enforced. We derive an upper bound on the suboptimality gap of the resulting control input sequence compared to optimal control utilizing accurate measurements. As demonstrated in numerical experiments, the solution derived by our method can achieve constraint satisfaction and a small suboptimality gap despite the measurement noise.

math.OC↗

arXiv2023

On the Guarantees of Minimizing Regret in Receding Horizon

Towards bridging classical optimal control and online learning, regret minimization has recently been proposed as a control design criterion. This competitive paradigm penalizes the loss relative to the optimal control actions chosen by a clairvoyant policy, and allows tracking the optimal performance in hindsight no matter how disturbances are generated. In this paper, we propose the first receding horizon scheme based on the repeated computation of finite horizon regret-optimal policies, and we establish stability and safety guarantees for the resulting closed-loop system. Our derivations combine novel monotonicity properties of clairvoyant policies with suitable terminal ingredients. We prove that our scheme is recursively feasible, stabilizing, and that it achieves bounded regret relative to the infinite horizon clairvoyant policy. Last, we show that the policy optimization problem can be solved efficiently through convex-concave programming. Our numerical experiments show that minimizing regret can outperform standard receding horizon approaches when the disturbances poorly fit classical design assumptions - even when the finite horizon planning is recomputed less frequently.

eess.SY↗

arXiv2023

Regularization for distributionally robust state estimation and prediction

The increasing availability of sensing techniques provides a great opportunity for engineers to design state estimation methods, which are optimal for the system under observation and the observed noise patterns. However, these patterns often do not fulfill the assumptions of existing methods. We provide a direct method using samples of the noise to create a moving horizon observer for linear time-varying and nonlinear systems, which is optimal under the empirical noise distribution. Moreover, we show how to enhance the observer with distributional robustness properties in order to handle unmodeled components in the noise profile, as well as different noise realizations. We prove that, even though the design of distributionally robust estimators is a complex minmax problem over an infinite-dimensional space, it can be transformed into a regularized linear program using a system level synthesis approach. Numerical experiments with the Van der Pol oscillator show the benefits of not only using empirical samples of the noise to design the state estimator, but also of adding distributional robustness. We show that our method can significantly outperform state-of-the-art approaches under challenging noise distributions, including multi-modal and deterministic components.

eess.SY↗

arXiv2023

Universal Approximation Property of Hamiltonian Deep Neural Networks

This paper investigates the universal approximation capabilities of Hamiltonian Deep Neural Networks (HDNNs) that arise from the discretization of Hamiltonian Neural Ordinary Differential Equations. Recently, it has been shown that HDNNs enjoy, by design, non-vanishing gradients, which provide numerical stability during training. However, although HDNNs have demonstrated state-of-the-art performance in several applications, a comprehensive study to quantify their expressivity is missing. In this regard, we provide a universal approximation theorem for HDNNs and prove that a portion of the flow of HDNNs can approximate arbitrary well any continuous function over a compact domain. This result provides a solid theoretical foundation for the practical use of HDNNs.

cs.LG↗

arXiv2023

Safe Zeroth-Order Optimization Using Linear Programs

To solve unmodeled optimization problems with hard constraints, this paper proposes a novel zeroth-order approach called Safe Zeroth-order Optimization using Linear Programs (SZO-LP). The SZO-LP method solves a linear program in each iteration to find a descent direction, followed by a step length determination. We prove that, under mild conditions, the iterates of SZO-LP have an accumulation point that is also the primal of a KKT pair. We then apply SZO-LP to solve an Optimal Power Flow (OPF) problem on the IEEE 30-bus system. The results demonstrate that SZO-LP requires less computation time and samples compared to state-of-the-art approaches.

math.OC↗

arXiv2022

Neural System Level Synthesis: Learning over All Stabilizing Policies for Nonlinear Systems

We address the problem of designing stabilizing control policies for nonlinear systems in discrete-time, while minimizing an arbitrary cost function. When the system is linear and the cost is convex, the System Level Synthesis (SLS) approach offers an effective solution based on convex programming. Beyond this case, a globally optimal solution cannot be found in a tractable way, in general. In this paper, we develop a parametrization of all and only the control policies stabilizing a given time-varying nonlinear system in terms of the combined effect of 1) a strongly stabilizing base controller and 2) a stable SLS operator to be freely designed. Based on this result, we propose a Neural SLS (Neur-SLS) approach guaranteeing closed-loop stability during and after parameter optimization, without requiring any constraints to be satisfied. We exploit recent Deep Neural Network (DNN) models based on Recurrent Equilibrium Networks (RENs) to learn over a rich class of nonlinear stable operators, and demonstrate the effectiveness of the proposed approach in numerical examples.

eess.SY↗

arXiv2022

Hamiltonian Deep Neural Networks Guaranteeing Non-vanishing Gradients by Design

Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem from the discretization of continuous-time Hamiltonian systems and include several existing DNN architectures based on ordinary differential equations. Our main result is that a broad set of H-DNNs ensures non-vanishing gradients by design for an arbitrary network depth. This is obtained by proving that, using a semi-implicit Euler discretization scheme, the backward sensitivity matrices involved in gradient computations are symplectic. We also provide an upper-bound to the magnitude of sensitivity matrices and show that exploding gradients can be controlled through regularization. Finally, we enable distributed implementations of backward and forward propagation algorithms in H-DNNs by characterizing appropriate sparsity constraints on the weight matrices. The good performance of H-DNNs is demonstrated on benchmark classification problems, including image classification with the MNIST dataset.

cs.LG↗

arXiv2022

Minimal regret state estimation of time-varying systems

Kalman and H-infinity filters, the most popular paradigms for linear state estimation, are designed for very specific specific noise and disturbance patterns, which may not appear in practice. State observers based on the minimization of regret measures are a promising alternative, as they aim to adapt to recognizable patterns in the estimation error. In this paper, we show that the regret minimization problem for finite horizon estimation can be cast into a simple convex optimization problem. For this purpose, we first rewrite linear time-varying system dynamics using a novel system level synthesis parametrization for state estimation, capable of handling both disturbance and measurement noise. We then provide a tractable formulation for the minimization of regret based on semi-definite programming. Both contributions make the minimal regret observer design easily implementable in practice. Finally, numerical experiments show that the computed observer can significantly outperform both H-2 and H-infinity filters.

eess.SY↗

arXiv2022

Safe Control with Minimal Regret

As we move towards safety-critical cyber-physical systems that operate in non-stationary and uncertain environments, it becomes crucial to close the gap between classical optimal control algorithms and adaptive learning-based methods. In this paper, we present an efficient optimization-based approach for computing a finite-horizon robustly safe control policy that minimizes dynamic regret, in the sense of the loss relative to the optimal sequence of control actions selected in hindsight by a clairvoyant controller. By leveraging the system level synthesis framework (SLS), our method extends recent results on regret minimization for the linear quadratic regulator to optimal control subject to hard safety constraints, and allows competing against a safety-aware clairvoyant policy with minor modifications. Numerical experiments confirm superior performance with respect to finite-horizon constrained $\mathcal{H}_2$ and $\mathcal{H}_\infty$ control laws when the disturbance realizations poorly fit classical assumptions.

eess.SY↗