Yiming Meng

Yiming Meng

Postdoctoral Research Associate

University of Illinois Urbana-Champaign

Biography

Yiming Meng is currently a Postdoctoral Research Associate in the Coordinated Science Laboratory at The Grainger College of Engineering, University of Illinois Urbana-Champaign (UIUC), working with Dr. Melkior Ornik. Before joining UIUC, he was a Postdoctoral Fellow at the Department of Applied Mathematics of the University of Waterloo (UWaterloo), where he worked with Dr. Jun Liu. He received his Ph.D. in Applied Mathematics from UWaterloo in October 2022, advised by Dr. Jun Liu and Dr. N.Sri.Namachchivaya.
His research addresses "intelligent" control synthesis for nonlinear dynamical systems operating in uncertain environments from a bottom-up perspective, with applications in diverse fields such as robotics, cyber-physical systems, mechanics, and other physical sciences.
Interests
  • Stochastic hybrid dynamical systems and data-driven control
  • Physics-informed machine learning for decision-making
  • Multi-agent planning, dimension reduction, and optimal control
  • Formal methods for control design
  • Stochastic bifurcation
Education
  • Ph.D. in Applied Mathematics

    University of Waterloo, Canada

  • M.Sc. in Process System Engineering

    Imperial College London, UK

  • B.Eng. in Chemical Engineering

    Tianjin Universiy, China

Academic Positions

 
 
 
 
 
Postdoctoral Research Associate
Coordinated Science Laboratory, University of Illinois Urbana-Champaign
October 2023 – Present Urbana, IL, USA
 
 
 
 
 
Postdoctoral Fellow
Department of Applied Mathematics, University of Waterloo
October 2022 – October 2023 Waterloo, ON, Canada
 
 
 
 
 
Research Assistant
Sustainable Gas Institute, Imperial College London
November 2016 – October 2017 London, UK

Research

*
Learning and Control for Dynamical Systems
For systems with limited knowledge, identifying system properties from observable data is vital to decision-making. We develop data-driven tools to estimate the system transition, winning set (with respect to the control objectives) and safe operation ranges, as well as to synthesize feasible controllers.
Physics-Informed Neural Optimality
In continuous environments, optimality-related quantities for finite-dimensional dynamical systems usually exist in the lifted function/functional spaces, which are solutions to optimality-induced partial differential equations (PDEs). We develop analysis and computation tools in this regard.
Formal Methods
Formal abstractions enable autonomous decision-making of dynamical systems to achieve complex tasks and compute a holistic reference on controllable regions of initial conditions (winning sets) with quantifiable errors. We develop abstraction analysis and computation tools for stochastic formal verification and control synthesis.
Nonlinear System Analysis
As a crucial step before implementing controls for systems with uncertainties, it is necessary to gain a better understanding of the solution’s behaviors, such as the continuity/differentiability, stability, reachability, and safety-related properties. We develop fundamental mathematical analysis and novel analytical tools addressing safety-critical control.

Recent Publications

Quickly discover relevant content by filtering publications.
(2024). Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification. In 2024 International Conference on Machine Learning (ICML), to appear.

Project

(2024). Compositionally Verifiable Vector Neural Lyapunov Functions for Stability Analysis of Interconnected Nonlinear Systems. In 2024 American Control Conference (ACC).

PDF Cite Project

(2024). Zubov-Koopman Learning of Maximal Lyapunov Functions. In 2024 American Control Conference (ACC).

PDF Project

(2024). LyZNet with Control: Physics-Informed Neural Network Control of Nonlinear Systems with Formal Guarantees. In 2024 IFAC Conference on Analysis and Design of Hybrid Systems (ADHS), to appear.

Project

(2024). LyZNet: A Lightweight Python Tool for Learning and Verifying Neural Lyapunov Functions and Regions of Attraction. In 2024 ACM International Conference on Hybrid Systems: Computation and Control (HSCC).

PDF Cite Project

Contact

To learn more about my work, you can explore my Research page, where I’ve summarized some of my representative research outcomes. For scholars interested in my research areas and seeking collaboration, please feel free to get in touch with me if you would like to explore further opportunities.