arXiv subjects

John Lygeros

Publications and source records attributed to John Lygeros.

At least 127 records · Page 7Linked to original sources

arXiv2022

Reconfigurable Plug-and-play Distributed Model Predictive Control for Reference Tracking

A plug-and-play model predictive control (PnP MPC) scheme is proposed for varying-topology networks to track piecewise constant references. The proposed scheme allows subsystems to occasionally join and leave the network while preserving asymptotic stability and recursive feasibility and comprises two main phases. In the redesign phase, passivity-based control is used to ensure that asymptotic stability of the network is preserved. In the transition phase, reconfigurable terminal ingredients are used to ensure that the distributed MPC problem is initially feasible after the PnP operation. The efficacy of the proposed scheme is evaluated by applying it to a network of mass-spring-damper systems and comparing it to a benchmark scheme. It is found that the novel redesign phase results in faster PnP operations, whereas the novel transition phase increases flexibility by accepting more requests.

eess.SY↗

arXiv2022

Drone-based Volume Estimation in Indoor Environments

Volume estimation in large indoor spaces is an important challenge in robotic inspection of industrial warehouses. We propose an approach for volume estimation for autonomous systems using visual features for indoor localization and surface reconstruction from 2D-LiDAR measurements. A Gaussian Process-based model incorporates information collected from measurements given statistical prior information about the terrain, from which the volume estimate is computed. Our algorithm finds feasible trajectories which minimize the uncertainty of the volume estimate. We show results in simulation for the surface reconstruction and volume estimate of topographic data.

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↗

arXiv2022

Follow the Clairvoyant: an Imitation Learning Approach to Optimal Control

We consider control of dynamical systems through the lens of competitive analysis. Most prior work in this area focuses on minimizing regret, that is, the loss relative to an ideal clairvoyant policy that has noncausal access to past, present, and future disturbances. Motivated by the observation that the optimal cost only provides coarse information about the ideal closed-loop behavior, we instead propose directly minimizing the tracking error relative to the optimal trajectories in hindsight, i.e., imitating the clairvoyant policy. By embracing a system level perspective, we present an efficient optimization-based approach for computing follow-the-clairvoyant (FTC) safe controllers. We prove that these attain minimal regret if no constraints are imposed on the noncausal benchmark. In addition, we present numerical experiments to show that our policy retains the hallmark of competitive algorithms of interpolating between classical $\mathcal{H}_2$ and $\mathcal{H}_\infty$ control laws - while consistently outperforming regret minimization methods in constrained scenarios thanks to the superior ability to chase the clairvoyant.

eess.SY↗

arXiv2022

A Stackelberg game for incentive-based demand response in energy markets

In modern buildings renewable energy generators and storage devices are spreading, and consequently the role of the users in the power grid is shifting from passive to active. We design a demand response scheme that exploits the prosumers' flexibility to provide ancillary services to the main grid. We propose a hierarchical scheme to coordinate the interactions between the distribution system operator and a community of smart prosumers. The framework inherits characteristics from price-based and incentive-based schemes and it retains the advantages of both. We cast the problem as a Stackelberg game with the prosumers as followers and the distribution system operator as leader. We solve the resulting bilevel optimization program via a KKT reformulation, proving the existence and the convergence to a local Stackelberg equilibrium. Finally, we provide numerical simulations to corroborate our claims on the benefits of the proposed framework.

eess.SY↗

arXiv2022

Inexact GMRES Policy Iteration for Large-Scale Markov Decision Processes

Policy iteration enjoys a local quadratic rate of contraction, but its iterations are computationally expensive for Markov decision processes (MDPs) with a large number of states. In light of the connection between policy iteration and the semismooth Newton method and taking inspiration from the inexact variants of the latter, we propose \textit{inexact policy iteration}, a new class of methods for large-scale finite MDPs with local contraction guarantees. We then design an instance based on the deployment of GMRES for the approximate policy evaluation step, which we call inexact GMRES policy iteration. Finally, we demonstrate the superior practical performance of inexact GMRES policy iteration on an MDP with 10000 states, where it achieves a $\times 5.8$ and $\times 2.2$ speedup with respect to policy iteration and optimistic policy iteration, respectively.

math.OC↗

arXiv2022

Data-Driven Process Optimization of Fused Filament Fabrication based on In Situ Measurements

The tuning of fused filament fabrication parameters is notoriously challenging. We propose an autonomous data-driven method to select parameters based on in situ measurements. We use a laser sensor to evaluate the surface roughness of a printed part. We then correlate the roughness to the mechanical properties of the part, and show how print quality affects mechanical performance. Finally, we use Bayesian optimization to search for optimal print parameters. We demonstrate our method by printing liquid crystal polymer samples, and successfully find parameters that produce high-performance prints and maximize the manufacturing process efficiency.

eess.SY↗

arXiv2022

Data-driven distributionally robust MPC for systems with uncertain dynamics

We present a novel data-driven distributionally robust Model Predictive Control formulation for unknown discrete-time linear time-invariant systems affected by unknown and possibly unbounded additive uncertainties. We use off-line collected data and an approximate model of the dynamics to formulate a finite-horizon optimization problem. To account for both the uncertainty related to the dynamics and the disturbance acting on the system, we resort to a distributionally robust formulation that optimizes the cost expectation while satisfying Conditional Value-at-Risk constraints with respect to the worst-case probability distributions of the uncertainties within an ambiguity set defined using the Wasserstein metric. Using results from the distributionally robust optimization literature we derive a tractable finite-dimensional convex optimization problem with finite-sample guarantees for the class of convex piecewise affine cost and constraint functions. The performance of the proposed algorithm is demonstrated in closed-loop simulation on a simple numerical example.

math.OC↗

arXiv2022

A Novel Control-Oriented Cell Transmission Model Including Service Stations on Highways

In this paper, we propose a novel model that describes how the traffic evolution on a highway stretch is affected by the presence of a service station. The presented model enhances the classical CTM dynamics by adding the dynamics associated with the service stations, where the vehicles may stop before merging back into the mainstream. We name it CTMs. We discuss its flexibility in describing different complex scenarios where multiple stations are characterized by different drivers' average stopping times corresponding to different services. The model has been developed to help design control strategies aimed at decreasing traffic congestion. Thus, we discuss how classical control schemes can interact with the proposed \gls{CTMs}. Finally, we validate the proposed model through numerical simulations and assess the effects of service stations on traffic evolution, which appear to be beneficial, especially for relatively short congested periods.

eess.SY↗

arXiv2022

Advanced Manufacturing Configuration by Sample-efficient Batch Bayesian Optimization

We propose a framework for the configuration and operation of expensive-to-evaluate advanced manufacturing methods, based on Bayesian optimization. The framework unifies a tailored acquisition function, a parallel acquisition procedure, and the integration of process information providing context to the optimization procedure. \cmtb{The novel acquisition function is demonstrated, analyzed and compared on state-of-the-art benchmarking problems. We apply the optimization approach to atmospheric plasma spraying and fused deposition modeling.} Our results demonstrate that the proposed framework can efficiently find input parameters that produce the desired outcome and minimize the process cost.

cs.LG↗

arXiv2022

Data-driven Reference Trajectory Optimization for Precision Motion Systems

We propose a data-driven optimization-based pre-compensation method to improve the contour tracking performance of precision motion stages by modifying the reference trajectory and without modifying any built-in low-level controllers. The position of the precision motion stage is predicted with data-driven models, a linear low-fidelity model is used to optimize traversal time, by changing the path velocity and acceleration profiles then a non-linear high-fidelity model is used to refine the previously found time-optimal solution. We experimentally demonstrate that the proposed method is capable of simultaneously improving the productivity and accuracy of a high precision motion stage. Given the data-based nature of the models, the proposed method can easily be adapted to a wide family of precision motion systems.

eess.SY↗

arXiv2022

On the Regret of $\mathcal{H}_{\infty}$ Control

The $\mathcal{H}_{\infty}$ synthesis approach is a cornerstone robust control design technique, but is known to be conservative in some cases. The objective of this paper is to quantify the additional cost the controller incurs planning for the worst-case scenario, by adopting an approach inspired by regret from online learning. We define the \textit{disturbance-reality gap} as the difference between the predicted worst-case disturbance signal and the actual realization. The regret is shown to scale with the norm of this \textit{gap}, which turns out to have a similar structure to that of the certainty equivalent controller with inaccurate predictions, obtained here in terms of the \textit{prediction error} norm.

math.OC↗

arXiv2022

Moving-Horizon State Estimation for Power Networks and Synchronous Generators

Power network and generators state estimation are usually tackled as separate problems. We propose a dynamic scheme for the simultaneous estimation of the network and the generator states. The estimation is formulated as an optimization problem on a moving-horizon of past observations. The framework is a generalization of static state estimation; it can handle incomplete model knowledge and does not require static network observability by PMUs. The numerical results show an improved estimation accuracy compared to static state estimation. Moreover, accurate estimation of the internal states of generators without PMUs on their terminals can be achieved. Finally, we highlight the capability of the proposed estimator to detect and identify bad data.

eess.SY↗

arXiv2022

Scenario-based Stochastic MPC for systems with uncertain dynamics

Model Predictive Control is an extremely effective control method for systems with input and state constraints. Model Predictive Control performance heavily depends on the accuracy of the open-loop prediction. For systems with uncertainty this in turn depends on the information that is available about the properties of the model and disturbance uncertainties. Here we are interested in situations where such information is only available through realizations of the system trajectories. We propose a general scenario-based optimization framework for stochastic control of a linear system affected by additive disturbance, when the dynamics are only approximately known. The main contribution is in the derivation of an upper bound on the number of scenarios required to provide probabilistic guarantees on the quality of the solution to the deterministic scenario-based finite horizon optimal control problem. We provide a theoretical analysis of the sample complexity of the proposed method and demonstrate its performance on a simple simulation example. Since the proposed approach leverages sampling, it does not rely on the explicit knowledge of the model or disturbance distributions, making it applicable in a wide variety of contexts.

math.OC↗

arXiv2022

Online Computation of Terminal Ingredients in Distributed Model Predictive Control for Reference Tracking

A distributed model predictive control scheme is developed for tracking piecewise constant references where the terminal set is reconfigured online, whereas the terminal controller is computed offline. Unlike many standard existing schemes, this scheme yields large feasible regions without performing offline centralized computations. Although the resulting optimal control problem (OCP) is a semidefinite program (SDP), an SDP scalability method based on diagonal dominance is used to approximate the derived SDP by a second-order cone program. The OCPs of the proposed scheme and its approximation are amenable to distributed optimization. Both schemes are evaluated using a power network example and compared to a scheme where the terminal controller is reconfigured online as well. It is found that fixing the terminal controller results in better performance, noticeable reduction in computational cost and similar feasible region compared to the case in which this controller is reconfigured online.

eess.SY↗

arXiv2022

Data-Driven Optimal Control of Affine Systems: A Linear Programming Perspective

In this letter, we discuss the problem of optimal control for affine systems in the context of data-driven linear programming. First, we introduce a unified framework for the fixed point characterization of the value function, Q-function and relaxed Bellman operators. Then, in a model-free setting, we show how to synthesize and estimate Bellman inequalities from a small but sufficiently rich dataset. To guarantee exploration richness, we complete the extension of Willem's fundamental lemma to affine systems.

eess.SY↗

arXiv2022

Dynamic Programming Through the Lens of Semismooth Newton-Type Methods (Extended Version)

Policy iteration and value iteration are at the core of many (approximate) dynamic programming methods. For Markov Decision Processes with finite state and action spaces, we show that they are instances of semismooth Newton-type methods to solve the Bellman equation. In particular, we prove that policy iteration is equivalent to the exact semismooth Newton method and enjoys local quadratic convergence rate. This finding is corroborated by extensive numerical evidence in the fields of control and operations research, which confirms that policy iteration generally requires few iterations to achieve convergence even when the number of policies is vast. We then show that value iteration is an instance of the fixed-point iteration method. In this spirit, we develop a novel locally accelerated version of value iteration with global convergence guarantees and negligible extra computational costs.

math.OC↗

arXiv2022

Robust and Kernelized Data-Enabled Predictive Control for Nonlinear Systems

This paper presents a robust and kernelized data-enabled predictive control (RoKDeePC) algorithm to perform model-free optimal control for nonlinear systems using only input and output data. The algorithm combines robust predictive control and a non-parametric representation of nonlinear systems enabled by regularized kernel methods. The latter is based on implicitly learning the nonlinear behavior of the system via the representer theorem. Instead of seeking a model and then performing control design, our method goes directly from data to control. This allows us to robustify the control inputs against the uncertainties in data by considering a min-max optimization problem to calculate the optimal control sequence. We show that by incorporating a proper uncertainty set, this min-max problem can be reformulated as a nonconvex but structured minimization problem. By exploiting its structure, we present a projected gradient descent algorithm to effectively solve this problem. Finally, we test the RoKDeePC on two nonlinear example systems - one academic case study and a grid-forming converter feeding a nonlinear load - and compare it with some existing nonlinear data-driven predictive control methods.

eess.SY↗