Ongeveer 7 uur geleden - Universiteit Twente (UT) - Enschede
PhD in Efficient Deep Learning for Mapping and Localization of Intelligent Vehicles
computer science or software development, artificial intelligence, experience in machine learning and in computer vision and/or robot localization
- Mekelweg, Delft, Zuid-Holland
- Tijdelijk contract / Tijdelijke opdracht
- Uren per week:
- 38 - 40 uur
- € 2266 - € 2897 per maand
The Intelligent Vehicles group at the TU Delft is seeking a PhD candidate with an interest in performing cutting edge research in the active and exciting research area of self-driving vehicles, in collaboration with TomTom, a global leader in mapping and navigation products.
Currently, highly automated vehicles commonly rely on detailed 3D maps created with SLAM algorithms and LIDAR data for accurate self-localization. However, these representations do not scale, are sensitive to changes in the environment, are sensor specific, and also computationally intensive. TomTom’s research product RoadDNA takes an alternative approaches to represent the road environment more efficiently. However, it uses a hand-engineered representation, which is mainly target at highway environments sensed with LIDAR at a fixed compression rate.
This PhD will instead develop optimized representations for mapping and localization in complex urban environments by learning robust semantic feature representations through end-to-end weakly-supervised deep-learning. The novel methods can additionally support rough priors provided by GPS, structural priors from aerial imagery and existing map data, or even temporal context. A learned representation can thus focus on features which matter most in the local area, and henceforth reduce its size, and increase localization efficiency. Higher-level features are additionally more robust against environmental changes, and could be transferred between multi-modal sensor setups or multiple viewpoints.
Prospective applicants should have a strong academic record in computer science, artificial intelligence or robotics with solid background in machine learning, probabilistic graphical models, computer vision and/or robot localization. Good software development and programming skills are expected, preferably in C++ and Python/MATLAB. Knowledge of deep-learning frameworks (Torch/TensorFlow/Caffe) and CUDA/OpenCV/ROS is a plus. A certain affinity towards turning complex concepts into real-world practice (i.e. vehicle demonstrator) is desired. All applicant(s) are expected to be able to act independently as well as to collaborate effectively with members of a larger team. Good English skills are required.
Research will be performed in collaboration with TomTom R&D, in Amsterdam, where the candidate is expected to work on average about 0,2 FTE.
TU Delft offers a customisable compensation package, a discount for health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. An International Children’s Centre offers childcare and an international primary school. Dual Career Services offers support to accompanying partners. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities.
As a PhD candidate you will be enrolled in the TU Delft Graduate School. TU Delft Graduate School provides an inspiring research environment; an excellent team of supervisors, academic staff and a mentor; and a Doctoral Education Programme aimed at developing your transferable, discipline-related and research skills. Please visit www.tudelft.nl/phd for more information.
To apply, please prepare:
- a letter of motivation explaining why you are the right candidate,
- a detailed CV,
- a complete record of Bachelor and Master courses (including grades),
- your Master’s Thesis,
- any publications, and a list of projects you have worked on with brief descriptions of your contributions (max 2 pages), and the names and contact addresses of two references.
All these items should be combined in one PDF document. Applications should be submitted by email at the earliest convenience to application-3mE@tudelft.nl. When applying for this position, please refer to vacancy number 3mE18-44.
If you still have specific questions about this position, please contact dr J.F.P. (Julian) Kooij, e-mail: J.F.P.Kooij@tudelft.nl. Please do not send applications emails here, but use the specified address above.