arXiv subjects

Pablo Krupa

Publications and source records attributed to Pablo Krupa.

At least 19 recordsLinked to original sources

arXiv2026

Learning practically stabilizing output-feedback nonlinear controllers

This paper addresses the problem of learning an output-feedback surrogate controller offline that approximates a given, possibly computationally expensive, nonlinear controller-observer pair. The surrogate is modeled as a recurrent dynamical system and is trained to imitate closed-loop input/output trajectories generated by the given controller. Beyond imitation accuracy, the offline training problem promotes input-to-state practical stability by incorporating estimated state trajectories to learn a candidate Lyapunov function. The approach is validated on a nonlinear continuous stirred tank reactor, where constraint satisfaction and practical stability are assessed through a probabilistic validation approach. The numerical results highlight the benefit of jointly learning the Lyapunov function by comparing against an imitation-only baseline.

eess.SY↗

arXiv2026

Active Learning MPC Objective Functions from Preferences

Designing the objective function in Model Predictive Control (MPC) is challenging when performance assessment criteria are available only from human judgment. We adopt a preference-based learning (PbL) approach to learn the MPC objective function from preferences over trajectory pairs. However, the real-world application of PbL is often restricted by the significant cost or limited availability of human preference queries. To address this, Active Learning (AL) strategies seek to improve sampling efficiency, reducing the labeling effort required to obtain a well-performing classifier. We present two AL strategies for learning the MPC objective function from human preferences over pairwise system trajectories: a pool-based strategy that selects trajectory pairs that are both uncertain under the current surrogate and diverse relative to previously labeled comparisons, and a query-synthesis strategy that incorporates new trajectories using the current surrogate-driven MPC. Numerical results show that the proposed strategies yield closed-loop behaviors that align more with the expressed preference using fewer number of queries compared to a random sampling approach.

eess.SY↗

arXiv2026

Learning generalized Nash equilibria from pairwise preferences

Generalized Nash Equilibrium Problems (GNEPs) arise in many applications, including non-cooperative multi-agent control problems. Although many methods exist for finding generalized Nash equilibria, most of them rely on assuming knowledge of the objective functions or being able to query the best responses of the agents. We present a method for learning solutions of GNEPs only based on querying agents for their preference between two alternative decisions. We use the collected preference data to learn a GNEP whose equilibrium approximates a GNE of the underlying (unknown) problem. Preference queries are selected using an active-learning strategy that balances exploration of the decision space and exploitation of the learned GNEP. We present numerical results on game-theoretic linear quadratic regulation problems, as well as on other literature GNEP examples, showing the effectiveness of the proposed method.

cs.GT↗

arXiv2025

Learning the MPC objective function from human preferences

In Model Predictive Control (MPC), the objective function plays a central role in determining the closed-loop behavior of the system, and must therefore be designed to achieve the desired closed-loop performance. However, in real-world scenarios, its design is often challenging, as it requires balancing complex trade-offs and accurately capturing a performance criterion that may not be easily quantifiable in terms of an objective function. This paper explores preference-based learning as a data-driven approach to constructing an objective function from human preferences over trajectory pairs. We formulate the learning problem as a machine learning classification task to learn a surrogate model that estimates the likelihood of a trajectory being preferred over another. The approach provides a surrogate model that can directly be used as an MPC objective function. Numerical results show that we can learn objective functions that provide closed-loop trajectories that align with the expressed human preferences.

eess.SY↗

arXiv2025

Artificial-reference tracking MPC with probabilistically validated performance on industrial embedded systems

Industrial embedded systems are typically used to execute simple control algorithms due to their low computational resources. Despite these limitations, the implementation of advanced control techniques such as Model Predictive Control (MPC) has been explored by the control community in recent years, typically considering simple linear formulations or explicit ones to facilitate the online computation of the control input. These simplifications often lack features and properties that are desirable in real-world environments. This article presents an efficient implementation for embedded systems of MPC for tracking with artificial reference, solved via a recently developed structure-exploiting ADMM-based algorithm. This formulation is tailored to a wide range of applications by incorporating essential practical features at a small computational cost, including integration with an offset-free scheme, back-off parameters that enable constraint tightening, and soft constraints that preserve feasibility under disturbances or plant-model mismatch. This is accompanied with a framework for probabilistic performance validation of the closed-loop system over long-term operation. The applicability of the approach is illustrated on a Programmable Logic Controller (PLC), incorporated in a hardware-in-the-loop setup to control a nonlinear continuous stirred-tank reactor. The behavior of the closed-loop system is probabilistically validated with respect to constraint violations and the number of iterations required at each time step by the MPC optimization algorithm.

eess.SY↗

arXiv2024

Recent advancements on MPC for tracking: periodic and harmonic formulations

The main benefit of model predictive control (MPC) is its ability to steer the system to a given reference without violating the constraints while minimizing some objective. Furthermore, a suitably designed MPC controller guarantees asymptotic stability of the closed-loop system to the given reference as long as its optimization problem is feasible at the initial state of the system. Therefore, one of the limitations of classical MPC is that changing the reference may lead to an unfeasible MPC problem. Furthermore, due to a lack of deep knowledge of the system, it is possible for the user to provide a desired reference that is unfeasible or non-attainable for the MPC controller, leading to the same problem. This chapter summarizes MPC formulations recently proposed that have been designed to address these issues. In particular, thanks to the addition of an artificial reference as decision variable, the formulations achieve asymptotic stability and recursive feasibility guarantees regardless of the reference provided by the user, even if it is changed online or if it violates the system constraints. We show a recent formulation which extends this idea, achieving better performance and larger domains of attraction when working with small prediction horizons. Additional benefits of these formulations, when compared to classical MPC, are also discussed and highlighted with illustrative examples.

eess.SY↗

arXiv2024

Model predictive control for tracking using artificial references: Fundamentals, recent results and practical implementation

This paper provides a comprehensive tutorial on a family of Model Predictive Control (MPC) formulations, known as MPC for tracking, which are characterized by including an artificial reference as part of the decision variables in the optimization problem. These formulations have several benefits with respect to the classical MPC formulations, including guaranteed recursive feasibility under online reference changes, as well as asymptotic stability and an increased domain of attraction. This tutorial paper introduces the concept of using an artificial reference in MPC, presenting the benefits and theoretical guarantees obtained by its use. We then provide a survey of the main advances and extensions of the original linear MPC for tracking, including its non-linear extension. Additionally, we discuss its application to learning-based MPC, and discuss optimization aspects related to its implementation.

eess.SY↗

arXiv2024

A sparse ADMM-based solver for linear MPC subject to terminal quadratic constraint

Model Predictive Control (MPC) typically includes a terminal constraint to guarantee stability of the closed-loop system under nominal conditions. In linear MPC this constraint is generally taken on a polyhedral set, leading to a quadratic optimization problem. However, the use of an ellipsoidal terminal constraint may be desirable, leading to an optimization problem with a quadratic constraint. In this case, the optimization problem can be solved using Second Order Cone (SOC) programming solvers, since the quadratic constraint can be posed as a SOC constraint, at the expense of adding additional slack variables and possibly compromising the simple structure of the solver ingredients. In this paper we present a sparse solver for linear MPC subject to a terminal ellipsoidal constraint based on the alternating direction method of multipliers algorithm in which we directly deal with the quadratic constraints without having to resort to the use of a SOC constraint nor the inclusion of additional decision variables. The solver is suitable for its use in embedded systems, since it is sparse, has a small memory footprint and requires no external libraries. We compare its performance against other approaches from the literature.

math.OC↗

arXiv2024

Implementation of soft-constrained MPC for Tracking using its semi-banded problem structure

Model Predictive Control (MPC) is a popular control approach due to its ability to consider constraints, including input and state restrictions, while minimizing a cost function. However, in practice, these constraints can result in feasibility issues, either because the system model is not accurate or due to the existence of external disturbances. To mitigate this problem, a solution adopted by the MPC community is the use of soft constraints. In this article, we consider a not-so-typical methodology to encode soft constraints in a particular MPC formulation known as MPC for Tracking (MPCT), which has several advantages when compared to standard MPC formulations. The motivation behind the proposed encoding is to maintain the semi-banded structure of the ingredients of a recently proposed solver for the considered MPCT formulation, thus providing an efficient and fast solver when compared to alternative approaches from the literature. We show numerical results highlighting the benefits of the formulation and the computational efficiency of the solver.

eess.SY↗

arXiv2024

Efficient implementation of MPC for tracking using ADMM by decoupling its semi-banded structure

Model Predictive Control (MPC) for tracking formulation presents numerous advantages compared to standard MPC, such as a larger domain of attraction and recursive feasibility even when abrupt changes in the reference are produced. As a drawback, it includes some extra decision variables in its related optimization problem, leading to a semi-banded structure that differs from the banded structure encountered in standard MPC. This semi-banded structure prevents the direct use of the efficient algorithms available for banded problems. To address this issue, we present an algorithm based on the alternating direction method of multipliers that explicitly takes advantage of the underlying semi-banded structure of the MPC for tracking.

eess.SY↗

arXiv2023

Learning disturbance models for offset-free reference tracking

This work presents a nonlinear control framework that guarantees asymptotic offset-free tracking of generic reference trajectories by learning a nonlinear disturbance model, which compensates for input disturbances and model-plant mismatch. Our approach generalizes the well-established method of using an observer to estimate a constant disturbance to allow tracking constant setpoints with zero steady-state error. In this paper, the disturbance model is generalized to a nonlinear static function of the plant's state and command input, learned online, so as to perfectly track time-varying reference trajectories under certain assumptions on the model and provided that future reference samples are available. We compare our approach with the classical constant disturbance model in numerical simulations, showing its superiority.

eess.SY↗

arXiv2023

Efficient online update of model predictive control in embedded systems using first-order methods

Model Predictive Control (MPC) is typically characterized for being computationally demanding, as it requires solving optimization problems online; a particularly relevant point when considering its implementation in embedded systems. To reduce the computational burden of the optimization algorithm, most solvers perform as many offline operations as possible, typically performing the computation and factorization of its expensive matrices offline and then storing them in the embedded system. This improves the efficiency of the solver, with the disadvantage that online changes on some of the ingredients of the MPC formulation require performing these expensive computations online. This article presents an efficient algorithm for the factorization of the key matrix used in several first-order optimization methods applied to linear MPC formulations, allowing its prediction model and cost function matrices to be updated online at the expense of a small computational cost. We show results comparing the proposed approach with other solvers from the literature applied to a linear time-varying system.

eess.SY↗

arXiv2023

Certification of the proximal gradient method under fixed-point arithmetic for box-constrained QP problems

In safety-critical applications that rely on the solution of an optimization problem, the certification of the optimization algorithm is of vital importance. Certification and suboptimality results are available for a wide range of optimization algorithms. However, a typical underlying assumption is that the operations performed by the algorithm are exact, i.e., that there is no numerical error during the mathematical operations, which is hardly a valid assumption in a real hardware implementation. This is particularly true in the case of fixed-point hardware, where computational inaccuracies are not uncommon. This article presents a certification procedure for the proximal gradient method for box-constrained QP problems implemented in fixed-point arithmetic. The procedure provides a method to select the minimal fractional precision required to obtain a certain suboptimality bound, indicating the maximum number of iterations of the optimization method required to obtain it. The procedure makes use of formal verification methods to provide arbitrarily tight bounds on the suboptimality guarantee. We apply the proposed certification procedure on the implementation of a non-trivial model predictive controller on 32-bit fixed-point hardware.

math.OC↗

arXiv2023

Harmonic model predictive control for tracking sinusoidal references and its application to trajectory tracking

Harmonic model predictive control (HMPC) is a recent model predictive control (MPC) formulation for tracking piece-wise constant references that includes a parameterized artificial harmonic reference as a decision variable, resulting in an increased performance and domain of attraction with respect to other MPC formulations. This article presents an extension of the HMPC formulation to track periodic harmonic/sinusoidal references and discusses its use for tracking arbitrary trajectories. The proposed formulation inherits the benefits of its predecessor, namely its good performance and large domain of attraction when using small prediction horizons, and that the complexity of its optimization problem does not depend on the period of the reference. We show closed-loop results discussing its performance and comparing it to other MPC formulations.

eess.SY↗

arXiv2022

Efficiently solving the harmonic model predictive control formulation

Harmonic model predictive control (HMPC) is a model predictive control (MPC) formulation which displays several benefits over other MPC formulations, especially when using a small prediction horizon. These benefits, however, come at the expense of an optimization problem that is no longer the typical quadratic programming problem derived from most linear MPC formulations due to the inclusion of a particular class of second order cone constraints. This article presents a method for efficiently dealing with these constraints in operator splitting methods, leading to a computation time for solving HMPC in line with state of the art solvers for linear MPC. We show how to apply this result to the alternating direction method of multipliers algorithm, presenting a solver which we compare against other solvers from the literature, including solvers for other linear MPC formulations. The results show that the proposed solver, and by extension the HMPC formulation, is suitable for its implementation in embedded systems.

math.OC↗

arXiv2022

Tractable robust MPC design based on nominal predictions

Many popular approaches in the field of robust model predictive control (MPC) are based on nominal predictions. This paper presents a novel formulation of this class of controller with proven input-to-state stability and robust constraint satisfaction. Its advantages are: (i) the design of its main ingredients are tractable for medium to large-sized systems, (ii) the terminal set does not need to be robust with respect to all the possible system uncertainties, but only for a reduced set that can be made arbitrarily small, thus facilitating its design and implementation, (iii) under certain conditions the terminal set can be taken as a positive invariant set of the nominal system, allowing us to use a terminal equality constraint, which facilitates its application to large-scale systems, and (iv) the complexity of its optimization problem is comparable to the non-robust MPC variant. We show numerical closed-loop results of its application to a multivariable chemical plant and compare it against other robust MPC formulations.

eess.SY↗

arXiv2022

Restart of accelerated first order methods with linear convergence under a quadratic functional growth condition

Accelerated first order methods, also called fast gradient methods, are popular optimization methods in the field of convex optimization. However, they are prone to suffer from oscillatory behaviour that slows their convergence when medium to high accuracy is desired. In order to address this, restart schemes have been proposed in the literature, which seek to improve the practical convergence by suppressing the oscillatory behaviour. This paper presents a restart scheme for accelerated first order methods for which we show linear convergence under the satisfaction of a quadratic functional growth condition, thus encompassing a broad class of non-necessarily strongly convex optimization problems. Moreover, the worst-case convergence rate is comparable to the one obtained using a (generally non-implementable) optimal fixed-rate restart strategy. We compare the proposed algorithm with other restart schemes by applying them to a model predictive control case study.

math.OC↗

arXiv2021

Implementation of model predictive control for tracking in embedded systems using a sparse extended ADMM algorithm

This article presents a sparse, low-memory footprint optimization algorithm for the implementation of the model predictive control (MPC) for tracking formulation in embedded systems. This MPC formulation has several advantages over standard MPC formulations, such as an increased domain of attraction and guaranteed recursive feasibility even in the event of a sudden reference change. However, this comes at the expense of the addition of a small amount of decision variables to the MPC's optimization problem that complicates the structure of its matrices. We propose a sparse optimization algorithm, based on an extension of the alternating direction method of multipliers, that exploits the structure of this particular MPC formulation. We describe the controller formulation and detail how its structure is exploited by means of the aforementioned optimization algorithm. We show closed-loop simulations comparing the proposed solver against other solvers and approaches from the literature.

eess.SY↗