Wenhan (Winston) Cao

I am a Ph.D. candidate at the School of Vehicle and Mobility, Tsinghua University, under the guidance of Prof. Shengbo Eben Li and Prof. Chang Liu. I also receive supervision from Prof. Jianyu Chen and Prof. Stephen S.-T. Yau. Additionally, I have spent wonderful time as a visiting student at the University of Manchester, working with Prof. Wei Pan, and at the Technical University of Munich, working with Prof. Sandra Hirche.

I am actively seeking opportunities for postdoc position!

Email  /  CV  /  Scholar  /  Github  /  ResearchGate

My research lies at the intersection of learning and control, aiming to develop trustworthy autonomous systems. Simply put, I explore how AI can improve the performance of control systems, while leveraging control theory to ensure the reliability and predictability of AI-driven systems.

11/2024 - Our paper: Robust Bayesian Inference for Moving Horizon Estimation has been accepted by Automatica.
08/2024 - Invited talk on NANO filter: Bayesian Filtering with Natural Gradient Gaussian Approximation at the Department of Astronomy, Tsinghua University, hosted by Prof. Zheng Cai.
08/2024 - Our paper: Convolutional Unscented Kalman Filter for Multi-Object Tracking with Outliers is accepted by IEEE TIV.
05/2024 - Our paper: Computation-Aware Learning for Stable Control with Gaussian Process is accepted by RSS 2024!
05/2024 - I am happy to attend ICLR2024 in Vienna and meet all the excellent researchers. Here is our poster.
04/2024 - I am happy to attend the Probnum Spring School in Southampton and meet all the excellent researchers.
02/2024 - Invited talk on Convolutional Bayesian Filtering at the Department of Mathematical Sciences, Tsinghua University, hosted by Prof. Stephen S.-T. Yau.
01/2024 - Our paper: Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control has been accepted by ICLR 2024 as a spotlight paper.
05/2023 - Our paper: On the Optimization Landscape of Dynamic Output Feedback Linear Quadratic Control has been accepted by IEEE TAC.

Selected Preprints

Nonlinear Bayesian Filtering with Natural Gradient Gaussian Approximation Wenhan Cao, Tianyi Zhang, Zeju Sun, Chang Liu, Stephen S.-T. Yau, Shengbo Eben Li Under Review in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) [paper] [code] [slides]

Convolutional Bayesian Filtering Wenhan Cao, Shiqi Liu, Chang Liu, Zeyu He, Stephen S.-T. Yau, Shengbo Eben Li Under Review in IEEE Transactions on Automatic Control (TAC) [paper] [slides]

Robust State Estimation for Legged Robots with Dual Beta Kalman Filter Tianyi Zhang, Wenhan Cao, Chang Liu, Tao Zhang, Jiangtao Li, Shengbo Eben Li Under Review in IEEE Robotics and Automation Letters (RA-L) [paper]

Projects Networked Modeling and Cooperative Control of Connected and Automated Electric Vehicles Project Leader, Nov 2020 State Estimation for Warehouse Automated Logistics Vehicles Project Leader, May 2022 Supported by Geek+ company, the technology has already been implemented in the company's product lineup Software General Optimal control Problems Solver (GOPS) GOPS is an easy-to-use reinforcement learning (RL) solver package designed to build real-time, high performance controllers for industrial applications. I was primarily responsible for the core design and implementation of the trainer, sampler, and buffer modules. [docs] [code] Awards Study Abroad Fund from Tsinghua University 2020 Student Best Paper Finalist of Modeling, Estimation and Control Conference 2021 China National Scholarship 2016 The First Prize Scholarship from Beijing Jiaotong University 2016, 2017 & 2018 Services Conference Reviewer: CDC, ACC, L4DC, ICLR, AAMAS & IFAC NMPC Journal Reviewer: Automatica, RA-L, T-ITS, T-ASE & TNNLS Website template from Jon Barron.