Haoming Zhang

Welcome to my page!

I am a robotics researcher, and my current research interests include:

• robust state estimation under non-Gaussian noise,
• SLAM and its derived problem statements,
• variational Bayesian inference for online model identification, and
• learning-based methods for outlier handling.

Building on my current research experience, I am also exploring new topics such as:

• reinforcement learning for online hyperparameter tunning,
• planning and control through inference, and
• active perception from both intrinsic and extrinsic system perspectives.

Starting from Oct. 2025, I am happy to join the Learning Systems and Robotics Lab at the Technical University of Munich as a postdoctoral researcher under the supervision of Prof. Angela Schoellig, Prof. Stefan Leutenegger, and Prof. Daniel Roth.

From 2020 to 2024, I worked as a research associate (wiss. Mitarbeiter) at the Institute of Automatic Control, RWTH Aachen University, Germany.

From 2017 to 2020, I worked as a research engineer at the Cybernetics Lab, RWTH Aachen University, Germany (which, unfortunately, no longer exists ).

I find the problem statement of the state estimation within the Bayesian framework particularly attractive. At its core, we are basically solving a “trust” problem in the presence of inconsistent information (or inconsistent “truth” parameterization).

I believe this fundamental inconsistency resonates with many researchers working in this area. After all, we are all, in one way or another, disturbed by twisted truths or violations of integrity—whether in data, models, or life.

This happens to be one reason why I started writing my blogs—a space where I share my experiences and thoughts with you.