Technische Universität München Robotics and Embedded Systems

Seminar Context Prediction in Autonomous Driving

Organizer M.Sc. Sina Shafaei
Modul IN2107
Type MasterSeminar
Semester WS 2017/2018
ECTS 4.0
Time & Location 02.09.023 / 15:00-17:00


The first session of the seminar (Agenda: Details, Sessions, Team Members) took place on 20.10.2017 at 02.09.023 15:00-17:00 Slides

The preliminary talk took place on 12th of July 2017, 13:00 - 14:00 at 02.09.023 on the second floor. Slides


Challenged by the increasing complexity of today's software and physical environments specially in the domain of autonomous driving, new technologies are required which seamlessly integrate with driver and other occupants needs. The development of suitable context prediction methodologies to provide the proactive behavior for the intelligent applications, is however a challenge. The reason is that future context information, hidden in the raw context traces left by users in the real world, is not immediately accessible to applications. Therefore, sophisticated context prediction approaches are required that are able to discover and mine patterns (e.g. of a driver's behavior) from observed context history. In this seminar various topics will be discussed which are among the state-of-the-art in the domain of context prediction and autonomous driving

Topic Assignment

Topic Team Members Presentation (Date)
C- Driver Behavior Modeling For Context Prediction   12.01.2018
D- Challenges of Deploying Neural Nets for Context Prediction in Fully Automated Driving   12.01.2018
E- Neural Networks and Deep Learning in Context Prediction   19.01.2018
F- Context Prediction and Reinforcement Learning   19.01.2018
G- Approaches for Optimizing the Accuracy of the Prediction Results   26.01.2018
H- Limitations of Deep Learning Methods in Context Prediction   26.01.2018
I- Trajectory Prolongation Approach (Interpolation/Approximation)   02.02.2018
J- Ambient Intelligent Systems   02.02.2018
A- Challenges in Designing a Context Prediction Architecture   09.02.2018
L- Enabling Proactiveness through Context Prediction   09.02.2018