Master Seminar "Multimodal Temporal Data Processing in Autonomous Driving"
Organizer: Emec Ercelik
Contact: emec.ercelik(at)tum.de
Modul: IN2107
Registration: Via Matching System
Type: MasterSeminar
Semester: Winter Semester 2020/2021
ECTS: 5.0/4.0
Time & Location: Friday, 9.00-11.00 online
News (Registration)
- [09.11.2020] Slides of introduction session can be found here.
- [27.10.2020] Topics can be found here.
- [23.10.2020] Preliminary topics (below) are updated.
- [23.10.2020] The first session as an introduction takes place on 06.11.2020, Friday online. The link for the online session will be sent via e-mail.
- Please provide a CV and a motivation letter that states your achievements and aims related to this seminar until the end of 25.07.2020 ( Please send your documents to "emec.ercelik(at)tum.de" with the subject line "Seminar: Multimodal Temporal Data Processing in Autonomous Driving" ).
- For the slides of the last year's introductory session, please click here.
- Please check the preliminary topics of last year added below.
- There is no scheduled preliminary session.
Content
Control systems that steer cars autonomously on the road should have the capability of making sense of the environment. It is a remaining problem that sensors mounted on cars only function in certain conditions. Therefore, the control system should consider a variety of sensory information (images, depth, velocity, map, etc.) at the same time to give rise to a reasonable control output. In addition, human drivers constantly observe the environment while driving, taking into account the past observations with the future predictions. In this seminar, we will be looking into the methods to have an understanding of the environment with processing multivariate sensory information at the same time with temporal information.
In this seminar course, students gain knowledge in sensor fusion and temporal data processing methods, challenges in autonomous driving related tasks, and how learning is applied to problems in this domain.
Keywords
- Stereo vision
- Sensor fusion
- Recurrent Neural Networks
- Temporal Data Processing
- Object Detection
Examples of sensor types that will be considered in this seminar
- Camera
- Lidar
- Radar
- GPS
Datasets that contain multimodal temporal data
Preliminary topics
- Graph Neural Networks for object detection and tracking in autonomous driving
- Attention-based networks for object detection in autonomous driving
- Recurrent neural networks for object detection and tracking in autonomous driving
- Representation learning (object association and matching) with multi-modal data