Dipl.-Math. oec. Christian Hubschneider
Stellv. Abteilungsleiter
Werdegang
Christian Hubschneider studierte von 2006 bis 2012 Wirtschaftsmathematik am Karlsruher Institut für Technologie (KIT). Seine Studienschwerpunkte lagen dabei in den Gebieten Stochastic Calculus, Financial Engineering und Machine Learning.
Seine Diplomarbeit mit dem Titel „Bayesian Unit Root Tests in Stochastic Volatility Models with Applications in Finance“ schrieb er während eines Forschungssemesters am Institut für Statistik an der Universität von Auckland (UoA), Neuseeland. Anschließend war er zunächst für dreieinhalb Jahre bei der EXXETA AG als Berater im Energiehandelsumfeld tätig.
Seit März 2016 ist Herr Hubschneider wissenschaftlicher Mitarbeiter in der Abteilung Technisch Kognitive Systeme (TKS) des FZI.
Publications
Conference Proceedings (4)
- Adding Navigation to the Equation: Turning Decisions for End-to-End Vehicle ControlInfoDetails
Christian Hubschneider and André Bauer and Michael Weber and J. Marius Zöllner, 2017
Navigation and obstacle avoidance are two problems that are not easily incorporated into direct control of autonomous vehicles solely based on visual input. However, they are required if lane following given proper lane markings is not enough to incorporate trained systems into larger architectures. This paper presents a method to allow for obstacle avoidance while driving using a single, front-facing camera as well as navigation capabilities such as taking turns at junctions and lane changes by feeding turn indicator signals into a Convolutional Neural Network. Both situations share the difficulty intrinsic to single camera setups of limited field of views. This problem is handled by using a spatial history of input images to extend the field of view regarding static obstacles. The trained model named DriveNet is evaluated in real world driving scenarios, using the same model for lateral vehicle control to both dynamically drive around obstacles as well as perform lane changing and turning in intersections.
- Integrating End-to-End Learned Steering into Probabilistic Autonomous DrivingInfoDetails
Christian Hubschneider and André Bauer and Jens Doll and Michael Weber and Sebastian Klemm and Florian Kuhnt and J. Marius Zöllner, 2017
In this paper, we propose an integrated approach of combining end-to-end learned trajectory proposals with a probabilistic sampling based planning algorithm for autonomous driving. A convolutional neural network is trained based on monocular image data to predict prospective steering angles. By using a local history of image data, we achieve an implicit spatial representation of parking cars or other obstacles commonly found in urban and residential areas. Through this local history, calculated using the vehicle's velocity data, the trajectory proposals are not only capable of lane following, but also comfortably circumnavigate obstacles. Training data is collected by recording video data and the vehicles CAN bus during human driving, thus imitating human behavior. The integration of end-to-end learning into a modularized architecture allows for additional safety constraints and complementary sensor information to be combined with intuitive steering. Our first results take a promising step towards general architectures for autonomous vehicles that combine deep learning with factorized probabilistic modeling.
- Learning how to drive in a real world simulation with deep Q-NetworksDetails
P. Wolf and C. Hubschneider and M. Weber and A. Bauer and J. Härtl and F. Dürr and J. M. Zöllner, 2017
- Towards a framework for end-to-end control of a simulated vehicle with spiking neural networksDetails
J. Kaiser and J. C. V. Tieck and C. Hubschneider and P. Wolf and M. Weber and M. Hoff and A. Friedrich and K. Wojtasik and A. Roennau and R. Kohlhaas and R. Dillmann and J. M. Zöllner, 2016
Export search result as .bib
Kontakt
Telefon: +49 721 9654-384
E-Mail: Hubschneider@ fzi.de- Adding Navigation to the Equation: Turning Decisions for End-to-End Vehicle ControlInfoDetails