arXiv subjects

Meichen Guo

Publications and source records attributed to Meichen Guo.

6 recordsLinked to original sources

arXiv2025

Data-driven nonlinear output regulation via data-enforced incremental passivity

This work proposes a data-driven nonlinear regulator design that achieves asymptotic reference tracking under external disturbances, where the reference and disturbances are generated by a linear exosystem. The key idea is to design a data-driven feedback controller such that the closed-loop system is incrementally passive with respect to the regulation error and a virtual input. By interconnecting the closed-loop system with an internal model and carefully designing the virtual input, we solve the data-driven nonlinear output regulation problem. We characterize the passivation feedback controller by a set of data-dependent linear matrix inequalities, which is independent of the internal model. This decoupled design offers high data efficiency and design flexibility. The proposed approach also solves the non-zero equilibrium stabilization problem of a class of nonlinear systems with unknown equilibrium input. Numerical examples are presented to illustrate the effectiveness of the proposed designs.

eess.SY↗

arXiv2023

Regret Analysis of Learning-Based Linear Quadratic Gaussian Control with Additive Exploration

In this paper, we analyze the regret incurred by a computationally efficient exploration strategy, known as naive exploration, for controlling unknown partially observable systems within the Linear Quadratic Gaussian (LQG) framework. We introduce a two-phase control algorithm called LQG-NAIVE, which involves an initial phase of injecting Gaussian input signals to obtain a system model, followed by a second phase of an interplay between naive exploration and control in an episodic fashion. We show that LQG-NAIVE achieves a regret growth rate of $\tilde{\mathcal{O}}(\sqrt{T})$, i.e., $\mathcal{O}(\sqrt{T})$ up to logarithmic factors after $T$ time steps, and we validate its performance through numerical simulations. Additionally, we propose LQG-IF2E, which extends the exploration signal to a `closed-loop' setting by incorporating the Fisher Information Matrix (FIM). We provide compelling numerical evidence of the competitive performance of LQG-IF2E compared to LQG-NAIVE.

eess.SY↗

arXiv2022

Data-driven stabilizer design and closed-loop analysis of general nonlinear systems via Taylor's expansion

For data-driven control of nonlinear systems, the basis functions characterizing the dynamics are usually essential. In existing works, the basis functions are often carefully chosen based on pre-knowledge of the dynamics so that the system can be expressed or well-approximated by the basis functions and the experimental data. For a more general setting where explicit information on the basis functions is not available, this paper presents a data-driven approach for stabilizer design and closed-loop analysis via the Lyapunov method. First, based on Taylor's expansion and using input-state data, a stabilizer and a Lyapunov function are designed to render the known equilibrium locally asymptotically stable. Then, data-driven conditions are derived to check whether a given sublevel set of the found Lyapunov function is an invariant subset of the region of attraction. One of the main challenges is how to handle Taylor's remainder in the design of the local stabilizers and the analysis of the closed-loop performance.

math.OC↗

arXiv2020

Data-driven stabilization of nonlinear polynomial systems with noisy data

In a recent paper we have shown how to learn controllers for unknown linear systems using finite-sized noisy data by solving linear matrix inequalities. In this note we extend this approach to deal with unknown nonlinear polynomial systems by formulating stability certificates in the form of data-dependent sum of squares programs, whose solution directly provides a stabilizing controller and a Lyapunov function. We then derive variations of this result that lead to more advantageous controller designs. The results also reveal connections to the problem of designing a controller starting from a least-square estimate of the polynomial system.

math.OC↗

arXiv2020

Learning control for polynomial systems using sum of squares relaxations

This paper considers the problem of learning control laws for nonlinear polynomial systems directly from the data, which are input-output measurements collected in an experiment over a finite time period. Without explicitly identifying the system dynamics, stabilizing laws are directly designed for nonlinear polynomial systems using experimental data alone. By using data-based sum of square programming, the stabilizing state-dependent control gains can be constructed.

eess.SY↗

arXiv2019

Network games with dynamic players: Stabilization and output convergence to Nash equilibrium

This paper addresses a class of network games played by dynamic agents using their outputs. Unlike most existing related works, the Nash equilibrium in this work is defined by functions of agent outputs instead of full agent states, which allows the agents to have more general and heterogeneous dynamics and maintain some privacy of their local states. The concerned network game is formulated with agents modeled by uncertain linear systems subject to external disturbances. The cost function of each agent is a linear quadratic function depending on the outputs of its own and its neighbors in the underlying graph. The main challenge stemming from this game formulation is that merely driving the agent outputs to the Nash equilibrium does not guarantee the stability of the agent dynamics. Using local output and the outputs from the neighbors of each agent, we aim at designing game strategies that achieve output Nash equilibrium seeking and stabilization of the closed-loop dynamics. Particularly, when each agents knows how the actions of its neighbors affect its cost function, a game strategy is developed for network games with digraph topology. When each agent is also allowed to exchange part of its compensator state, a distributed strategy can be designed for networks with connected undirected graphs or connected digraphs.

math.OC↗