Yunlong Song - 宋运龙

I am a Co-Founder & Robotics Scientist at a stealth robotic startup based in Bay Area. Previously, I was a Research Scientist at Skild AI. I completed my PhD under the supervision of Prof. Davide Scaramuzza at the Robotics and Perception Group, part of the Department of Informatics and Institute of Neuroinformatics (University of Zurich & ETH Zurich). During my PhD, I was an associated researcher at the ETH AI Center and a visiting researcher at MIT. My work has involved close collaboration with leading researchers and institutions tackling foundational problems in AI and robotics. These include developing the first superhuman car racing agent with Sony AI; pushing the limits of autonomous drone racing with Matthias Müller and Vladlen Koltun; advancing legged locomotion with Prof. Sangbae Kim; developing perceptive quadruped control with Prof. Fan Shi and Prof. Marco Hutter; and investigating fundametal reinforcement learning with Boris Belousov and Prof. Jan Peters.

PhD Defense

Research Interests

My research focuses on developing next-generation robotic systems capable of learning, adapting, and understanding in complex real-world environments. I have explored various topics in robotics and machine learning, including optimal control, reinforcement learning, differentiable simulation, representation learning, and vision-based control. Beyond theoretical understanding, I have hands-on experience with a range of robotic platforms, including the Furuta Pendulum, Barrett WAM Arm, high-performance FPV drone, MIT Mini Cheetah, and robotic manipulators. My past research has primarily focused on developing robust skill-level policies for diverse robotic tasks. Currently, I am particularly interested in integrating large vision-language-action models with low-level robotic skills to enable autonomous systems to perform complex, real-world tasks with greater efficiency and adaptability. My current research interests include:

  • Large-scale Reinforcement Learning
  • Reinforcement Learning for Mobile/Whole-body Manipulation
  • Direct Policy Optimization for Pixel-to-Action Control
  • Post-training of Robotics Foundation Models
  • Multimodal Policy Learning

Selected Pulications

Some peronal favorites from my publication list:
  • Learning Vision-based Agile Flight via Differentiable Physics
    Y. Zhang*, Y. Hu*, Y. Song*, D. Zou and W. Lin
  • Learning Quadruped Locomotion Using Differentiable Simulation
    Y. Song, S. Kim, and D. Scaramuzza
  • Reaching the Limit in Autonomous Racing: Optimal Control Versus Reinforcement Learning
    Y. Song, A. Romero, M. Müller, V. Koltun, and D. Scaramuzza
  • Policy Search for Model Predictive Control for Agile Drone Flight
    Y. Song and D. Scaramuzza
  • Flightmare: A Flexible Quadrotor Simulator
    Y. Song, S. Naji, E. Kaufmann, A. Loquercio, D. Scaramuzza
  • Learning High-level Policies for Model Predictive Control
    Y. Song and D. Scaramuzza