Online Calibration for Autonomous Racing

Kurzbeschreibung

Beschreibung The TUM Autonomous Motorsport team made history by winning the Abu Dhabi Autonomous Racing League (A2RL) in 2025 at the Yas Marina Circuit. A2RL is a premier competition where teams develop software for identical autonomous vehicles that compete at speeds exceeding 200 km/h. Every perception and localization module depends on precisely known sensor extrinsics. However, vibrations, aerodynamic load, and other changes to the car shift sensor mounts over a race weekend. These theses develop targetless methods that estimate and continuously refine the calibration online, developed and validated on real A2RL racetrack data. Voraussetzungen • Enthusiasm for perception, autonomous driving and racing • Very good coding skills • The ability to collaborate in a team