Tobias Fleck (M.Sc.)
Wissenschaftlicher Mitarbeiter
Werdegang
Tobias Fleck studierte bis 2016 Informatik am Karlsruher Institut für Technologie (KIT). Während seines Masterstudiums beschäftigte er sich mit Kognitiven Systemen, insbesondere probabilistische Schätz- und Modellierungsmethoden bildeten seine Schwerpunkte.
Seine Masterarbeit "Trajectory Estimation and Prediction in the Context of Autonomous Driving" führte er in der Abteilung Technisch Kognitive Systeme (TKS) durch.
Seit Februar 2017 ist Tobias Fleck als wissenschaftlicher Mitarbeiter am FZI Forschungszentrum Informatik in der Abteilung TKS tätig.
Publikationen
Buch (1)
- Validation and Verification of Automated Systems - Results of the ENABLE-S3 ProjectDetails
Philipp Rosenberger, Martin Holder, Marc René Zofka, Tobias Fleck, Thomas D’hondt, Benjamin Wassermann, Juraj Prstek, Springer, 2019
Konferenzbeitrag (6)
- (accepted) Robust Tracking of Reference Trajectories for Autonomous Driving in Intelligent Roadside InfrastructureDetails
Tobias Fleck, Sven Ochs, Marc René Zofka and J. Marius Zöllner, 2020
- (accepted) From Traffic Sensor Data To Semantic Traffic Descriptions: The Test Area Autonomous Driving Baden-Wurttemberg Dataset (TAF-BW Dataset)Details
Maximilian Zipfl, Tobias Fleck, Marc Rene Zofka and J. Marius Zollner, 2020
- Benchmarking and Functional Decomposition of Automotive Lidar Sensor ModelsInfoDetails
Philipp Rosenberger, Martin Holder, Sebastian Huch, Hermann Winner, Tobias Fleck, Marc René Zofka, J. Marius Zöllner, Thomas D’hondt and Benjamin Wassermann, 2019
Simulation-based testing is seen as a major re- quirement for the safety validation of highly automated driving. One crucial part of such test architectures are models of environment perception sensors such as camera, lidar and radar sensors. Currently, an objective evaluation and the comparison of different modeling approaches for automotive lidar sensors are still a challenge. In this work, a real lidar sensor system used for object recognition is first functionally decomposed. The resulting sequence of processing blocks and interfaces is then mapped onto simulation methods. Subsequently, metrics applied to the aforementioned interfaces are derived, enabling a quantitative comparison between simulated and real sensor data at different steps of the processing pipeline. Benchmarks for several existing sensor models at a concrete selected interface are performed using those metrics by comparing them to measurements gained from the real sensor. Finally, we outline how metrics on low-level interfaces can correlate with results on more abstract ones. A major achievement of this work lies within the commonly accepted interfaces and a common understanding of real and virtual lidar sensor systems and, even more important, an initial guideline for the quantitative comparison of sensor models with the ambition to support future validation of virtual sensor models.
- The sleepwalker framework: Verification and validation of autonomous vehicles by mixed reality LiDAR stimulationDetails
M. R. Zofka and M. Essinger and T. Fleck and R. Kohlhaas and J. M. Zöllner, 2018
- Towards Large Scale Urban Traffic Reference Data: Smart Infrastructure in the Test Area Autonomous Driving Baden-WuerttembergDetails
Tobias Fleck, Karam Daaboul, Michael Weber, Philip Schoerner, Marek Wehmer, Jens Doll, Stefan Orf, Nico Sußmann, Christian Hubschneider, Marc Rene Zofka, Florian Kuhnt, Ralf Kohlhaas, Ingmar Baumgart, Raoul Zoellner and J. Ma, 2018
- Traffic Participants in the Loop: A Mixed Reality-Based Interaction Testbed for the Verification and Validation of Autonomous VehiclesInfoDetails
M. R. Zofka and S. Ulbrich and D. Karl and T. Fleck and R. Kohlhaas and A. Rönnau and R. Dillmann and J. M. Zöllner, 2018
In order to verify and validate autonomous vehicles, testbeds integrating the whole system from perception to actuation are necessary. Above all, this applies to the assessment of the autonomous vehicle's performance in the presence of vulnerable road users' behavior: While experiments for the interaction between autonomous vehicles and pedestrians in critical traffic scenarios are hardly conductable in reality, virtual experiments often suffer from plausibility. In order to solve this issue, we present a mixed reality testbed for the verification and validation of autonomous vehicles faced with realistic road user behavior in critical, worst case traffic scenarios. We achieve this by registering an immersed pedestrian and the automated driving function within a common environment model, providing challenging traffic scenarios. The testbed is applicable within different integration levels of the automated driving function and enables a high level of behavioral realism. The testbed is evaluated qualitatively and discussed within a concrete use case.
Export Suchergebnis .bib
Kontakt
Telefon: +49 721 9654-216
E-Mail: Tobias.Fleck@ fzi.de- Validation and Verification of Automated Systems - Results of the ENABLE-S3 ProjectDetails