Please note! Course description is confirmed for two academic years (1.8.2018-31.7.2020), which means that in general, e.g. Learning outcomes, assessment methods and key content stays unchanged. However, via course syllabus, it is possible to specify or change the course execution in each realization of the course, such as how the contact sessions are organized, assessment methods weighted or materials used.
1. can recognise intelligent vehicle functions, ranging from non-autonomous to fully autonomous systems.
2. can design, simulate and implement autonomous vehicle localisation, mapping and navigation.
3. can perceive an intelligent vehicle system as a sum of subsystems and study their functionalities.
4. can work in a team that designs the control and analyses a autonomous miniature vehicle.
5. can evaluate and compare different autonomous vehicle control and performance, including the comparison of own design to scientific state-of-the-art.
Schedule: 26.10.2020 - 02.12.2020
Teacher in charge (valid 01.08.2020-31.07.2022): Kari Tammi, Kari Tammi
Teacher in charge (applies in this implementation): Kari Tammi, Kari Tammi
Contact information for the course (applies in this implementation):
CEFR level (applies in this implementation):
Language of instruction and studies (valid 01.08.2020-31.07.2022):
Teaching language: English
Languages of study attainment: English
CONTENT, ASSESSMENT AND WORKLOAD
Week, Lecture, Exercise, Other
- Introduction to intelligent vehicles, ADAS control exercises (MATLAB)
- Decision-making under uncertainty, Markov Decision process (MATLAB)
- Reinforced learning for autonomous vehicles, Reinforced learning (Python)
- Introduction to Turtlebots (incl. videos), Turtlebots: SLAM & Navigation (Python), in addition to the lecture: 2 hours of videos
- Advanced Turtlebot functions (incl. videos), Turtlebots: Basic Programming (Python)
- Wrap up, no excercise, project presentations
Assessment Methods and Criteria
1. Lecture quiz: weight 20 %
2. Exercises: weight 50 %
3. Project: weight 30 %
To pass the course at least 50 % of the points in all three categories much be achieved. The final grade is defined by the sum of points of each categories in respect to the weights given above. Peer evaluation may be used in the course.
Learning activity: Workload calculation (hours), Remarks
- Lectures: 6x2h
- Independent videos: 2h
- Learning portfolio (learning diary): 6x0.5h lecture quizzes
- Computer exercises: 5x8h, Python and MATLAB exercises including 1,5h of contact sessions.
- Group work (project): 60h, outcome: summary and slides
- Wrap up (project gala): 3h
Automated Driving by Watzenig & Horn
Substitutes for Courses
MEC-E5006 Vehicle mechatronics is being split in two courses: Vehicle Mechatronics: Control L and Vehicle Mechatronics: Powertrain L. The first course is being taught in 2020, second in 2021.
Required: Proven skills with Python and MATLAB.
Recommended courses (not all are needed, but some would be beneficial):
- MEC-E5001 Mechatronic Machine Design 5 cr
- KON-C2004 Mechatronics Basics 5 cr
- ELEC-C1230 Säätötekniikka 5 cr
- CSE-A1141 Tietorakenteet ja algoritmit 5 cr
- ELEC-C1320 Robotics 5 cr
- CS-A1113 Basics in Programming Y1
- CS-EJ3211 Machine Learning with Python
SDG: Sustainable Development Goals
8 Decent Work and Economic Growth
9 Industry, Innovation and Infrastructure
11 Sustainable Cities and Communities
13 Climate Action