I am a PhD student at the Robotics and Perception Group led by Prof. Davide Scaramuzza at the University of Zurich and ETH Zurich. My research interests lie at the intersection between machine learning and optimal control. I am currently working on combining deep reinforcement learning and model predictive control with appilcations to high-speed autonomous quadrotor control. Prior to RPG, I obtained my Msc degree in Information and Communication Engineering (iCE) from Technische Universität Darmstadt. My master thesis entitled "Minimax and Entropic Proximal Policy Optimization" was written under the supervision of Boris Belousov and Prof. Jan Peters.

Research Interests: Reinforcement Learning, Robot Learning, Autonomous Drone Racing

Google Scholar, LinkedIn

---

News

• [March 2021]: 🔥 Our work (Autonomous Drone Racing with Deep Reinforcement Learning) is available on arXiv 2021. (YouTube)


• [February 2021]: 🎆 Our paper (Super-Human Performance in GTS Using Deep Reinforcement Learning) is accepted to RAL 2021. ( Tech Xplore, IEEE Spectrum,Synced)


• [January 2021]: 🔥 Our Book (Reinforcement Learning Algorithms: Analysis and Applications) has been published and is available for purchase on Springer.
(I have authored the Chapter Information-Loss-Bounded Policy Optimization. )


• [October 2020]: 🔥 Our simulator (Flightmare: A Flexible Quadrotor simulator) is accepted to CoRL 2020. Star (IEEE Spectrum)


• [June 2020]: 🔥 Our paper (High-MPC: Learning High-Level Policies for Model Predictive Control) is accepted to IROS 2020. Star (YouTube)

---

Contact

Yunlong Song
University of Zurich
Department of Informatics
Robotics and Perception Group
Andreasstrasse 15, AND 2.08
8050 Zurich
Switzerland

Email: song (at) ifi (dot) uzh (dot) ch
Office: +41 44 635 45 89