Website
Module guide

Modul RO5500-KP12

Autonomous Vehicles (AVS)

Duration:


2 Semester
Turnus of offer:


starts every winter semester
Credit points:


12
Course of studies, specific field and terms:
  • Master Robotics and Autonomous Systems 2019 (advanced curriculum), advanced curriculum, 1st and 2nd semester
Classes and lectures:
  • Technology of Autonomous Vehicles (seminar, 2 SWS)
  • Perception for Autonomous Vehicles (exercise, 2 SWS)
  • Perception for Autonomous Vehicles (lecture, 2 SWS)
  • Vehicle Dynamics and Control (exercise, 2 SWS)
  • Vehicle Dynamics and Control (lecture, 2 SWS)
Workload:
  • 60 Hours exam preparation
  • 220 Hours private studies
  • 80 Hours in-classroom work
Contents of teaching:
  • Content of teaching of the course Vehicle Dynamics and Control:
  • Review of control methods and rigid body dynamics
  • Basic terminology of vehicle dynamics
  • Vehicle dynamic models (lateral, longitudinal, vertical)
  • Component models (engine, transmission, brake, steering)
  • Tire modeling
  • Stability analysis
  • Handling performance
  • Active safety systems
  • Autonomous driving
  • Content of teaching of the course Perception for Autonomous Driving:
  • The architecture of autonomous-driving systems
  • Tracking, detection, classification
  • Models of stochastic signals
  • Transform-based analysis of stochastic signals
  • System theory
  • Parameter estimation
  • Linear optimal filters and adaptive filters
  • Graphical models and dynamic Bayes networks
  • Neural networks
  • Hidden Markov Models, Kalman Filter, Particle Filter, etc.
  • Applications in the domain of autonomous driving
  • Content of teaching of the seminar Current Topics in Autonomous Vehicles:
  • Current algorithms in machine learning and artificial intelligence related to autonomous driving
Qualification-goals/Competencies:
  • Educational objectives of the course Vehicle Dynamics and Control:
  • Students master basic terminology and concepts of vehicle dynamics.
  • Students obtain a comprehensive understanding of the dynamics of a vehicle.
  • Students understand the main objectives of vehicle control.
  • Students can derive basic vehicle dynamics models for control design.
  • Students are able to apply concepts of basic and advanced control and estimation to practical problems.
  • Students get an insight into the field of active safety systems, driver assistance, and autonomous driving.
  • Students are able to perform independent design, research and development work in this field.
  • Educational objectives of the course Perception for Autonomous Driving:
  • Students get an overview on autonomous-driving systems.
  • Students become thoroughly acquainted with the perception layer of the architecture of an autonomous-driving system.
  • Students get a comprehensive introduction to stochastic signals.
  • Students master tools for the analysis of stochastic signals.
  • Students are able to make use of various models for stochastic signals.
  • Students are able to design tracking algorithms.
  • Students are able devise algorithmic solutions to decision problems, while making use of prior knowledge.
  • Educational objectives of the seminar Current Topics in Autonomous Vehicles:
  • Students are able to research and understand current literature.
  • Students are able to reproduce and evaluate current algorithms based on research literature.
  • Students are able reproduce, extend and present results from current research literature.
Grading through:
  • Written or oral exam as announced by the examiner
Requires:
Responsible for this module:
  • Prof. Dr. Georg Schildbach
Teachers:
  • Prof. Dr. Georg Schildbach
  • PD Dr.-Ing. habil. Alexandru Paul Condurache
Literature:
  • Rajamani, R: Vehicle Dynamics and Control (2nd edition) - Springer, 2012, ISBN 978-1-4614-1432-2
  • Mitschke, M; Wallentowitz, H.: Dynamik der Kraftfahrzeuge (5th edition) - Springer, 2014 (ISBN: 978-3-658-05067-2)
  • Charles W. Therrien: Decision estimation and classification - J. Wiley and Sons, 1991.
  • Simon Haykin: Adaptive Filter Theory - Prentice Hall, 1996
  • Christopher M. Bishop: Pattern recognition and machine learning - Springer, 2006
  • A. Mertins: Signaltheorie: Grundlagen der Signalbeschreibung, Filterbänke, Wavelets, Zeit-Frequenz-Analyse, Parameter- und Signalschätzung - Springer-Vieweg, 3. Auflage, 2013
Language:
  • offered only in English
Notes:

Admission requirements for taking the module:
- None

Admission requirements for participation in module examination(s):
- Successful completion of exercises as specified at the beginning of the semester.

Module Examination(s):
- RO5500-L1: Vehicle Dynamics and Control, written exam, 60min, 50% of module grade
- RO5500-L2: Perception for Autonomous Vehicles, written exam, 60min, 50% of the module grade
- RO5500-L3 Technology of Autonomous Vehicles; Seminar; ungraded; 0% of module grade, must be passed

Letzte Änderung:
7.10.2021