Control and Perception in Networked and Autonomous Vehicles
Instructors
Jianye Xu, M. Sc.
Assistant Lecturer
Simon Schäfer, M. Sc.
Former Assistant Lecturer
Patrick Scheffe, M. Sc.
Former Assistant Lecturer
Key Facts
The Cyber-Physical Mobility Team at the University of the Bundeswehr Munich offers this course.
We offered this course for the very first time in the winter term 2019/2020.
Due to lab capacity, currently, we are able to host only 30 students per class. We grasped this opportunity to provide a learning experience that is tailored towards the participants and builds on interactions between the lecturer and participants.
Students get six credit points for this course.
This course follows the concept ‘Method. Application. Experiment.’. The course teaches networked control methods applicable to systems consisting of multiple vehicles. The students apply the methods in experiments, which results in a high learning factor.
We designed this course for students in the master’s programs of Computer Science, Automation Engineering, and Computational Engineering Science. The students do lab exercises in teams of two students from two different study programs.
There are no special or necessary requirements to take this course. We start the course with a survey, which we call diagnostic test. The test aims to know the students’ pre-knowledge of various course topics, allowing the lecturer to adapt the content and the pace. Click here to see an example test.
Course Description
This course combines the theory of multi-agent decision-making with practical exercises in the Cyber-Physical Mobility Lab ( CPM Lab, an open-source testbed for Connected and Automated Vehicles (CAVs)).
In the theory part, we focus on distributing the control problem of multi-agent systems coupled via objective function or constraints using Distributed MPC (DMPC). Additionally, the course discusses the application in a multi-vehicle system, which prepares the participants for the practical lab work.
In the CPM Lab, the students implement controllers for vehicle platoons. The CPM Lab supports rapid functional prototyping. It consists of 20 model-scale vehicles for experiments and a simulation environment. Software developed in simulations can be seamlessly transferred to experiments without any adaptions. Additionally, experiments with the 20 vehicles can be extended by unlimited additional simulated vehicles. The CPM Lab allows researchers and students from different disciplines to see their ideas turning into reality. The CPM Lab is completely designed and developed by the Cyber-Physical Mobility Team.
If you cannot access the CPM Lab physically, check out our remote access.
The course covers the following topics
We recommend the following literature
R. Rajamani. Vehicle Dynamics and Control. Springer, 2012. DOI
S. Boyd and L. Vandenberghe. Convex Optimization. Cambridge University Press, 2009. pdf
F. Borrelli, A. Bemporad, and M. Morari. Predictive Control for Linear and Hybrid Systems, Cambridge University Press, 2017. pdf
J. Maciejowski. Predictive Control with Constraints. Prentice Hall, 2002.
B. Alrifaee. Networked Model Predictive Control for Vehicle Collision Avoidance. 2017. pdf
Learning Objectives
Knowledge and Understanding
After successful participation in the course, the students
Skills and Competences
After successful participation in the course, students are able to independently perform the necessary steps for the successful development of control and perception algorithms in CAVs. In doing so, they independently take into account the different aspects of the development and are able to evaluate to what extent the available approaches, methods, and algorithms are applicable. They are also able to synthesize different control and perception algorithms. Furthermore, they can consider practical aspects by testing in the lab.
Lecture Style
The lectures combine the following teaching methods
Each part of the lecture starts with mapping it to the lab architecture.
Lab Style
The students work on lab exercises in pairs, with each pair consisting of two students from different study programs. Each team is given eight lab sessions, each lasting four hours, to complete seven tasks, which include nine checkpoints in total. These checkpoints are assessed on-site by a teaching assistant. Passing these checkpoints earns points for the exam, as outlined in the following Exam section.
Exam
Since the winter term 2023/2024, the final grade is split into two equal parts, each worth 50 points, totaling 100 points. The first 50 points are gained from checkpoints during lab sessions. Meanwhile, the remaining 50 points are obtained from the 60-minute written exam, covering all lecture material.
Until the winter term 2022/2023, exams were conducted orally, with each student allocated 20 minutes. The exam began with a 5-minute presentation using a unified template to discuss lab results, followed by 15 minutes of questions covering lecture content and lab work.
Evaluation
The evaluation scale ranges from 1.0 (best) to 5.0 (worst). Between 2019 and 2023, we offered the lecture three times in person, achieving an average rating of 1.5, and twice online, with an average rating of 1.9. During the same period, we offered the lab exercise four times in person, with an average rating of 1.77, and once online, with an average rating of 1.80. The departmental average rating is approximately 1.80 each year. Further details can be found in our paper:
Schäfer, Simon, Jianye Xu, David Klüner, Armin Mokhtarian, Patrick Scheffel, and Bassam Alrifaee. “Educational Applications of the Cyber-Physical Mobility Lab: A Summary.” In 2024 European Control Conference (ECC), pp. 2666-2671. IEEE, 2024, https://doi.org/10.23919/ECC64448.2024.10591176.
Student Statistics
Our course consistently enrolled around 30 students per term. The majority of students came from Computer Science and Automation Engineering. Average attendance was around two-thirds of students for lectures and more than four-fifths for lab exercises. No substantial difference in attendance was observed between online and on-campus terms. More than 96% of students who participated in the lab exercises also participated in the final exam.
Course Materials
Here are the course materials (lecture slides, exercise sheets, lab tasks, and lecture videos).
Use of Course Materials
Please take care of the following rules
*cas[at]unibw[dot]de
Lecture Slides
Exercise Sheets
Lab Tasks
Coding Materials
Lecture Videos
Recorded from Winter term 2020/2021.