About Me

My name is Johannes Heeg. I hold a master's degree from TU Darmstadt in Computational Enginnering and am looking for PhD positions. My interests are at the intersection of robot learning and optimization. I want to dive deeper into how and why learning mechanisms work, and how algoritmic design choices and physics influence the optimization that drives the learning process. If you are interested in my profile, feel free to reach out.

In the past, I worked primarily on robot reinforcement learning together with Davide Scaramuzza at University of Zurich and Jan Peters at TU Darmstadt. Currently, I study math and work as a research assistant at University of Stuttgart at the Institute for Systems Theory and Automatic Control.

In my free time, I like to sing and play music. I am a member of several ensembles and my favorite composer is J. S. Bach.

Education

Publications

Learning Quadrotor Control From Visual Features Using Differentiable Simulation, 2024
Johannes Heeg, Yunlong Song, Davide Scaramuzza

Task Space Exploration in Robot Reinforcement Learning, 2023
Master's Thesis supervised by Prof. Jan Peters, Ph.D. at Intelligent Autonomous Systems Group, TU Darmstadt

Modeling of Thermochemical Manifolds With Machine Learning Methods, 2020
Bachelor's Thesis supervised by Prof. Dr.-Ing. Christian Hasse at Simulation of Reactive Thermo-Fluid Systems, TU Darmstadt

Projects