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. He completed his M.Sc in Process System Engineering from Imperial College London and his B.Eng in Chemical Engineering from Tianjin University.
Research Vision
My research addresses "intelligent" control synthesis for nonlinear dynamical systems operating in uncertain environments. Leveraging my experience as a control system engineer and my dedication to mathematical rigor, I approach my mission from a more bottom-up perspective encompassing several key areas. These areas include:
Investigating robust system regularities based on underlying topologies and their interrelationships with control objectives and data structures.
Developing novel and efficient computer-aided approaches in control theory, backed by solid theoretical foundations. This is achieved specifically through the development of formal symbolic abstractions, optimal control, and advanced AI techniques.
My work finds applications in diverse fields such as finance, robotic motion planning, cyber-physical systems, mechanics, and other physical sciences.
Research Interests
The following are some current areas of focus:
Multi-agent deception and identification from partial observations
Koopman operator-based learning for decision-making with applications in robotics and high-dimensional dynamical systems
Stochastic dynamical systems and optimal control
Formal methods for control design of stochastic systems
Dimension reduction and stochastic bifurcation analysis in infinite-dimensional systems
Probabilistic generative models
Recent News
(05/2024) Our paper, "Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification" has been accepted to the 2024 International Conference on Machine Learning (ICML'24), Vienna.
(03/2024) Our paper "LyZNet with Control: Physics-Informed Neural Network Control of Nonlinear Systems with Formal Guarantees" has been accepted for presentation at the 8th IFAC Conference on Analysis and Design of Hybrid Systems (ADHS'24).
(01/2024) Two papers, "Zubov-Koopman Learning of Maximal Lyapunov Functions" and "Compositionally Verifiable Vector Neural Lyapunov Functions for Stability", have been accepted to the 2024 American Control Conference (ACC'24), Toronto.
(01/2024) Our paper, "LyZNet: A Lightweight Python Tool for Learning and Verifying Neural Lyapunov Functions and Regions of Attraction" has been accepted to the 2024 ACM International Conference on Hybrid Systems: Computation and Control (HSCC'24), HongKong.
(10/2023) I joined the LEADCAT (LEArning, Decision, Control, AuTonomy) research group at the Aerospace Engineering Department, University of Illinois Urbana-Champaign, and began my role as a Postdoctoral Research Associate.
(09/2023) A novel learning method was developed to enhance the estimation accuracy of regions of attraction for unknown dynamical systems, using the proposed "Zubov-Koopman operator".
(09/2023) Our paper titled "Stochastic Lyapunov-Barrier Functions for Robust Probabilistic Reach-Avoid-Stay Specifications" was accepted by IEEE Transitions on Automatic Control. (TAC'23)
(07/2023) Our work on estimating the maximal Lyapunov exponent for stochastic semilinear PDEs was presented at the "IUTAM Symposium on Nonlinear Dynamics for design of mechanical systems across different length/time scales".
(06/2023) Two research papers were published. (JNLS'23, OJCSYS'23)
(05/2023) Our work on robustly complete stochastic abstractions was presented at the "9th Meeting on System and Control Theory".
Last updated: May 03, 2024