Leonard Bauersfeld
Papers
7
Total Citations
809
H-Index
7
About
Leonard Bauersfeld is a robotics researcher whose work sits at the intersection of autonomous systems, agile flight, and machine learning. He is best known for his landmark contribution to "Champion-level Drone Racing using Deep Reinforcement Learning" (2023), a groundbreaking study demonstrating that an AI agent could outperform professional human pilots in first-person view drone racing — a result that garnered over 560 citations and attracted widespread attention across both academic and mainstream media. This work exemplifies his broader focus on pushing autonomous aerial vehicles to their performance limits using learning-based control strategies. Beyond competitive drone racing, Bauersfeld has made substantial contributions to the quadrotor research community through Agilicious (2022, 127 citations), an open-source and open-hardware platform designed to democratize agile flight research. His work also spans practical aeronautical concerns, including multicopter range and endurance optimization, visual-inertial odometry, aerodynamic disturbance modeling, and scene-transfer robustness for vision-based navigation. His research on user-conditioned neural control policies further reflects a commitment to making learning-based systems more flexible and deployable in real-world settings. Together, these contributions establish Bauersfeld as a versatile and impactful voice in modern autonomous robotics research.
Research Focus
Key Achievements
Top Papers
- 1Champion-level drone racing using deep reinforcement learning562 citations · 2023
- 2
- 3Range, Endurance, and Optimal Speed Estimates for Multicopters70 citations · 2022
- 4
- 5
- 6
- 7User-Conditioned Neural Control Policies for Mobile Robotics9 citations · 2023