Autonomous systems are systems that are designed to work without, or with limited, human intervention. This course covers autonomous systems concepts and focuses on mobile physical systems. The objective of this course is to give a basic understanding of some of the core components that make up autonomous systems, from sensing and perception to planning and control, and to illustrate how these interact.

Intended learning outcomes

On completion of the course, the student should be able to

Explain what autonomy is and what challenges it poses for a system.
Describe basic properties of common sensors in autonomous systems.
Explain the principles for fusing sensor information in autonomous systems.
Use learning-based methods for perception in autonomous systems.
Explain the principles of motion planning in autonomous systems.
Explain the principles of automatic control in autonomous systems.
Use some common software tools for the design of autonomous systems.

Entry requirements

The course requires

solid programming experience in a high-level language; the programming assignments will use Python and Matlab.
a background in mathematics corresponding to the contents of the WASP-course “Mathematics and Machine Learning”.

Course schedule

The schedule in some detail is available here. The 2-day sessions will start day 1 at 11:30am with lunch to 15:00 day 2.

Taking part in the course

The whole world can read the content of these pages but only registered students can hand in assignments, i.e., actually follow the course. If you think that you should be registered contact the WASP administration and they will help you.

You log in using one of the following links (once you have the login information).

https://kth.instructure.com/login/canvas (if you do not have a KTH account)
https://kth.instructure.com/login/saml (if you have a KTH account)

NOTE: If someone only wants to look at the content of the course pages it might be simplest to do so in a private browsing window so that the system does not asks you to log into KTH.

For some discussions slack might be a more convenient communication channel than the discussion forum in Canvas. We have a private channel for the course called #2024_course_as in the wasp-sweden workspace. We have invited those of you that were already part of that workspace. Not a member of that workspace? Ask info@wasp-sweden.org. To be added to the #2024_course_as channel send a slack message to Patric Jensfelt in the wasp-sweden workspace.

Course setup

The course will consists of a combination of self-study done on your own and lectures, group work and other activities during two 2-day meetings in Linköping and Stockholm.

To provide a common platform for the assignments we use the Robot Operating System (ROS) for the core parts of the assignments. These assignments introduce the topics. These core parts will focus on

motivating what the problem is
and introduce some basic theory.

In addition to the mandatory core tasks there are conditionally elective tasks that provide an opportunity to focus a bit more on some topics.

We want you to step outside of your comfort zone and learn mostly about things you know less about. That is, rather than deepening your expertise, broaden your toolbox and work on other things. If you are an expert we want you to spend your energy in that topic on teaching others and sharing your knowledge and experience as much as possible.

The 2-day meetings bring all students together. There will be presentations and activities. Besides the content of the course, building the WASP network is an import objective for these. These meetings are mandatory. If you cannot attend you will have to do the make up assignment.

Course material

A basic design principle in the course is that the assignments define what you should learn as a minimum in the course. The course material is therefore worked into the course assignments.

You find a link to all assignments under the modules page (click Modules in the left hand menu).

Given the breadth of the course we have had to be a bit selective so not all your favorite topics within the scope of autonomous systems might be covered explicitly but do talk to your fellow students about them to make the learning experience even richer.

Course requirements and reporting results

Please see Course requirements (published before kick-off)

Not attending activities or not doing things on time

There are many students taking the course so we will have to be quite strict with the deadlines. Make sure to allocate time for the course. Please consult this page for routines for what is expected of you should you be late with an assignment or miss one of the two 2-day sessions mandatory for all course students.