Joshua Näf

PhD Researcher, ETH Zürich
naefjo [AT] ethz.ch
Scholar / LinkedIn / GitHub

Joshua Näf

About Me

Hi! I am a PhD student at the Mobile Robotics Lab at ETH Zürich where I am advised by Stefan Leutenegger (ETH Zürich) and Jonas Frey (Stanford). I am currently working on human motion estimation (HME) and forecasting with an emphasis on applications for humanoids. I am particularly interested in how HME can inform robot learning and how we can infer robot actions from human demonstrations.

Prior to my PhD, I obtained my BSc in Mechanical Engineering and a MSc in Robotics, Systems and Control from ETH Zurich with distinction. My focus during my master was on data-driven predictive control methods with partial system information. The extreme case, where no system information is available, was the focus of my master thesis. Therein, I investigated predictive control methods for nonlinear systems where data is available but an explicit system model is not, which was distinguished with the ETH Medal for exceptional master theses.

My Research

You can find the full list of publications on Google Scholar.

Highlights

Choose Wisely: Data-driven Predictive Control for Nonlinear Systems Using Online Data Selection

L4DC 2026

J Näf, K Moffat, J Eising, F Dörfler

L4acados: Learning-Based Models for acados, Applied to Gaussian Process-Based Predictive Control

IEEE TCST 2026

A Lahr, J Näf, K Wabersich, J Frey, P Siehl, A Carron, M Diehl, M Zeilinger

Design of prismav: An omnidirectional aerial manipulator based on a 3-puu parallel mechanism

IEEE ICUAS 2023 (Best Paper)

M Rubio, J Näf, F Bühlmann, P Brigger, M Hüsser, M Inauen, N Ospelt, D Gisler, M Tognon, R Siegwart

Students

I have had the privilege to supervise and collaborate with some awesome students for thesis and semester projects. If you are a student and are interested in working with me, feel free to reach out!

Learning Whole-Body Humanoid Locomanipulation from Egocentric Video

Semester Project 2026

Silke Fülster

Precise End-Effector Placement using VLAs

MSc Thesis 2026

Matteo Zucchelli

Visual Servoing-Based Precision Drilling with a Humanoid Robot

MSc Thesis 2026

Simon Arnold