Established by: Faculty Board of Science and Technology, 2019-10-29
Revised by: Faculty Board of Science and Technology, 2025-06-13
Contents
Autonomous vehicles can be about cars, trucks, drones, or different types of special vehicles, such as mobile robots. The development of autonomous vehicles can lead to changes in several industries in the not so distant future. An autonomous vehicle is equipped with built-in processors and sensors that can detect the environment, perform sensor fusion for decision making, and have continuous control and steering. The course provides an in-depth introduction to autonomous vehicles where both Artificial Intelligence (AI) algorithms and their system aspects are studied.
The course consists of both theoretical and experimental elements, and is closely related to current research and development. The topics covered include: key concepts of the perception-planning-control pipeline for autonomous driving (AD); key concepts of machine learning (ML), especially reinforcement learning (RL), and deep reinforcement learning (DRL); hands-on exercises with one of the popular open-source ML frameworks such as Tensorflow or PyTorch. Training, deployment and validation ML-based autonomous driving algorithmsin in a simulation environment.
Expected learning outcomes
After completing the course, the student shall be able to:
Understand key concepts of the perception-planning-control pipeline for autonomous driving (AD).
Understand key concepts of machine learning (ML), including supervised learning, reinforcement learning (RL), and deep reinforcement learning (DRL).
Know how to define Markov Decision Processes (MDP) to solve toy problems.
Understand value and policy functions, Bellman equations, policy iteration, and value iteration.
Understand Monte Carlo methods, greedy and epsilon-greedy policies, and trade offs in the exploration-exploitation dilemma.
Know how to implement well-known RL algorithms, such as Q-Learning and policy gradient, in an open-source framework, such as PyTorch or Tensorflow.
Know how to train, deploy and validate RL/DRL-based autonomous driving algorithms in a simulation environment.
Required Knowledge
Admission to the course requires 90 CREDITS of previous studies including courses in the field of Artificial Intelligence or Machine Learning of at least 7.5 Credits.
Form of instruction
The course is conducted in the form of lectures and laboratory exercises.
Examination modes
The examination is based on points assessed on laboratory exercises and a written final exam. One of the grades Fail (U), Pass (3), Pass with Credit (4) or Pass with Distinction (5) is given. To obtain grade (3), at least 50% of the maximum points are required. For grade (4), at least 65% of the maximum points, for grade (5), at least 80% of the maximum points. Students who have passed an exam cannot redo the exam to obtain a higher grade.For students who have not obtained the grade Pass, other examination sessions will be arranged. A student who for two consecutive examinations for the same course or sub-course has not been passed, has the right to apply for another examiner appointed, if there are no special reasons against this (Higher Education Ordinance chapter 6, 22 §). The written request for a new examiner shall be made to the Head of Department at Applied Physics and Electronics.
Examiners may decide to deviate from the modes of assessment in the course syllabus. Individual adaption of modes of assessment must give due consideration to the student's needs. The adaption of modes of assessment must remain within the framework of the intended learning outcomes in the course syllabus. Students who require an adapted examination must submit a request to the department holding the course no later than 10 days before the examination. The examiner decides on the adaption of the examination, after which the student will be notified.
Crediting Credit transfers are always tried individually (see the university guidelines and credit-of-transfer-ordinance). In one degree, this course may not be included together with another course with similar content. If in doubt, the student should consult the study guide at the Department of Applied Physics and Electronics.
Other regulations
In the event that the syllabus ceases to apply or undergoes major changes, students are guaranteed at least three examinations (including the regular examination opportunity) according to the regulations in the syllabus that the student was originally registered on for a period of a maximum of two years from the time that the previous syllabus ceased to apply or that the course ended.