TUM autonomous motorsport: An autonomous racing software for the Indy Autonomous Challenge

For decades, motorsport has been an incubator for innovations in the automotive sector and brought forth systems like disk brakes or rearview mirrors. Autonomous racing series such as Roborace, F1Tenth, Indy Challenge (IAC) are envisioned playing a similar role within autonomous vehicle sector, serving proving ground new technology at limits of capabilities. This paper outlines software stack approach TUM Motorsport team their participation Challenge, which holds two competitions: A single-vehicle competition on Indianapolis Motor Speedway passing Las Vegas Speedway. Nine university teams used identical platform: modified Lights chassis equipped with sensors, computing platform, actuators. All developed different algorithms object detection, localization, planning, prediction, control race cars. The from placed first secured second place Vegas. During final competition, reached speeds accelerations close to limit vehicle, peaking around 270 km/h 28 ms2. will present details hardware algorithms, workflow test enhance applied during two-year project. We derive deep insights into vehicle's behavior high speed acceleration by providing detailed analysis. Based this, we deduce list lessons learned provide promising areas future work based real-world evaluation displayed concepts.