Yuhao Zhang

About Me

I am currently pursuing a Ph.D. in Mechanical Engineering at the University of Wisconsin–Madison, conducting research at the UW ARC Lab, under the guidance of Prof. Xiangru Xu. I earned my MSE in Mechanical Engineering from the University of Michigan–Ann Arbor in 2019, where I was mentored by Prof. Necmiye Ozay and Prof. Jean-Baptiste Jeannin. Prior to that, I completed my Bachelor of Engineering in Energy and Power Engineering at Peking University, with a double major in Economics from the National School of Development, in 2017.

I specialize in the theoretical analysis and application of autonomous and controlled systems and familiar with various programming languages, including MATLAB, Python, and C++. My research focuses on control systems, incorporating optimization and machine learning techniques. The goal of my research is to develop principled analysis and control methodologies for building trustworthy autonomous intelligent systems.

I am actively seeking full-time employment starting in 2025. Feel free to contact me at yuhao.zhang2[at]wisc[dot]edu for connections and collaboration!

Efficient Reachability Analysis for Convolutional Neural Networks Using Hybrid Zonotopes
Efficient Reachability Analysis for Convolutional Neural Networks Using Hybrid Zonotopes

This work introduces an efficient approach to compute the reachable sets for convolutional neural networks.

Mar 13, 2025

Robust Stability of Neural Network Control Systems with Interval Matrix Uncertainties
Robust Stability of Neural Network Control Systems with Interval Matrix Uncertainties

This paper addresses the challenge of certifying robust stability in neural network control systems with interval matrix uncertainties.

Mar 5, 2025

🎉 Our work 'Robust Stability of Neural Feedback Systems with Interval Matrix Uncertainties' was accepted by Automatica!

Feb 24, 2025

We will give an oral presentation at the 2025 American Control Conference (ACC) on July 08, 2025

Jan 16, 2025

🎉 I successfully passed the PhD Preliminary Examination

Oct 21, 2024

Hybrid Zonotope-Based Backward Reachability Analysis for Neural Feedback Systems With Nonlinear Plant Models
Hybrid Zonotope-Based Backward Reachability Analysis for Neural Feedback Systems With Nonlinear Plant Models

This work introduces a novel approach to compute the over-approximation of backward reachable sets for neural feedback systems with non-linear plant models and general activation functions.

Sep 5, 2024

We will give an oral presentation at the 63rd IEEE Conference on Decision and Control (CDC) on Dec. 19, 2024

Jul 24, 2024

Reachability Analysis of Neural Network Control Systems With Tunable Accuracy and Efficiency
Reachability Analysis of Neural Network Control Systems With Tunable Accuracy and Efficiency

This paper introduces a novel tunable hybrid zonotope-based method for computing both forward and backward reachable sets of neural network control systems.

Jun 17, 2024

Presentation at 2023 IEEE CDC
Presentation at 2023 IEEE CDC

A novel approach for computing the exact backward reachable sets of neural feedback systems.

Dec 15, 2023

Reachability Analysis and Safety Verification of Neural Feedback Systems via Hybrid Zonotopes
Reachability Analysis and Safety Verification of Neural Feedback Systems via Hybrid Zonotopes

This paper presents novel hybrid zonotope-based methods for the reachability analysis and safety verification of neural feedback systems. Algorithms are proposed to compute the input-output relationship of each layer of a feed-forward neural network, as well as the exact reachable sets of neural feedback systems.

Jul 3, 2023