This is an old revision of the document!
Practical Course: Learning For Self-Driving Cars and Intelligent Systems (10 ECTS)
WS 19, TU München
Organizers: Yuesong Shen, Qadeer Khan, Patrick Wenzel,
Correspondence
Please forward any queries related to the lab to: intellisys-ws19@vision.in.tum.de
Course Registration
Important: right now the course can only be found on the matching system by its German title, which is "Master-Praktiukum - Lernbasierte Ansätze für autonome Fahrzeuge und intelligente Systeme". We are trying to solve this issue.
Assignment to the lab will be done via the matching system. Please additionally send your application documents to the correspondence email. See the preliminary meeting slides for more details.
The preliminary meeting (recommended) to take took place on Wednesday, 10 July 2019 at 4pm in HS 2 (00.04.011).
Course Content
Learning-based approaches have recently made tremendous progress in the computer vision and robotics research community. In this practical
course, we will solve challenging real-world problems in the area of
self-driving cars and intelligent systems. Topics will be in the
direction of perception, control, and environmental understanding. This
may also involve working on massive datasets including unstructured or
unordered data.
Pre-requisites
- Good knowledge of the Python language and basic mathematics such as linear algebra, analysis, and numerics is required.
- Good knowledge of a deep learning framework such as PyTorch, TensorFlow, etc.
- Participation in at least one of the offered deep learning lectures at TUM is required.
Structure
Students will work in groups of 2 persons on research oriented projects from the beginning of the semester. Assignment of projects to groups will be done in the first week. There will be biweekly presentations to share results/findings among the groups. To review progress and assist with resolving any issues, students are invited to meet the supervisors on a weekly basis.
Schedule
Time: Tuesdays 2-4pm
Room: 03.11.018