Florian SauerbeckTechnische Universität München | TUM · Department for Machine and Vehicle Technology
Currently pursuing a PhD at the Institute of Automotive Technology at TUM in the field of autonomous driving.
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
Citations since 2017
11 Research Items
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, or the Indy Autonomous Challenge (IAC) are envisioned as playing a similar role within the autonomous vehicle sector, serving as a proving ground...
End-to-end deep reinforcement learning (DRL) is emerging as a promising paradigm for autonomous driving. Although DRL provides an elegant framework to accomplish final goals without extensive manual engineering, capturing plans and behavior using deep neural networks is still an unsolved issue. End-to-end architectures, as a result, are currently l...
In this paper, we present a novel method for integrating 3D LiDAR depth measurements into the existing ORB-SLAM3 by building upon the RGB-D mode. We propose and compare two methods of depth map generation: conventional computer vision methods, namely an inverse dilation operation, and a supervised deep learning-based approach. We integrate the form...
Although robotics courses are well established in higher education, the courses often focus on theory and sometimes lack the systematic coverage of the techniques involved in developing, deploying, and applying software to real hardware. Additionally, most hardware platforms for robotics teaching are low-level toys aimed at younger students at midd...
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, or the Indy Autonomous Challenge (IAC) are envisioned as playing a similar role within the autonomous vehicle sector, serving as a proving ground f...
Motorsport has always been an enabler for technological advancement, and the same applies to the autonomous driving industry. The team TUM Autonomous Motorsports will participate in the Indy Autonomous Challenge in October 2021 to benchmark its self-driving software-stack by racing one out of ten autonomous Dallara AV-21 racecars at the Indianapoli...
Motorsport has always been an enabler for technological advancement, and the same applies to the autonomous driving industry. The team TUM Auton-omous Motorsports will participate in the Indy Autonomous Challenge in Octo-ber 2021 to benchmark its self-driving software-stack by racing one out of ten autonomous Dallara AV-21 racecars at the Indianapo...
Solving a Minimum Lap Time Problem (MLTP), under the constraints stemming from a race car's driving dynamics, can be considered to be state of the art. Nevertheless, when dealing with electric race vehicles as in Formula E or the Roborace competition, solving an MLTP is not enough to form an appropriate competition strategy: Maximum performance ove...
Autonomous Racing is gaining increasing publicity as an attractive showcase of state-of-the-art technologies and the enhanced algorithms used for autonomous driving. The Indy Autonomous Challenge (IAC) tackled autonomous high-speed wheel-to-wheel racing at the famous Indianapolis Motor Speedway (IMS) in October 2021. To solve this problem, advanced...
Autonomous Driving Software Engineering - Lecture 02: Perception I - Basics of Mapping and Localization
The Institute of Automotive Technology has launched the new lecture "Autonomous Driving Software Engineering" in summer term 2021. The lecture gives a comprehensive overview about methods and challenges in the current state of the art of the software modules for self-driving cars. The goal is to improve the system knowledge of students and engineers in the field of automated driving and to identify further research directions on the way to level 5 of automated driving on public roads.
The goal of the TUM Autonomous Motorsport Team is the development of a software which is able to handle an autonomous Level-5 vehicle at the vehicle dynamic limits on the racetrack with several vehicles. To achieve this goal, the individual team members work on sub-projects, each of which contributes to the overall software architecture of the autonomous vehicle. The focus is on dynamic path planning with several vehicles in the driving dynamic limit range on the one hand, and on the other hand on the perception of the environment and localization at high speeds. In order to achieve these goals, the behavior of the opposing racing vehicle must be predicted quickly and reliably on the one hand, and on the other hand, the driving dynamics limit for controlling the vehicle must be determined. The team has successfully participated in several Roborace challenges within 2018 and 2019, reaching from the Human vs. Machine Challenge at the Berlin Formula-E track up to the first autonomous overtakes at speeds of 160kph with full size racecars at the Monteblanco Circuit.