Autonomous systems are systems that are designed to work without, or with limited, human intervention. The objective of this course is to give a broad understanding of the wide area of autonomous systems and the foundational knowledge in some topic areas required to understand and develop autonomous systems. The course covers topics from sensing and perception to control and decision making. Learning outcomes include the notion of autonomy and understanding the different components that typically are found in these systems. Other learning outcomes are fundamental techniques for autonomous systems from the areas of automatic control, sensor fusion, learning, and software. The examination consists of assignments done individually and in groups.

Course Type:

  • AI track: elective
  • AS track: mandatory* (replaces Autonomous systems 1)
  • Joint Curriculum: foundational

Time: Given yearly from 2022, autumn

Teachers: Bo Bernhardsson (LU), Patric Jensfelt (KTH), Gustaf Hendeby (LiU)

Examiner: Daniel Axehill (LiU)

*The course is only mandatory for those in the AS track who have not taken “Autonomous Systems 1”.

The participants are assumed to have a background in mathematics corresponding to the contents of the WASP-course “Mathematics and Machine Learning”. Basic programming skills are required.

Autonomous systems are systems that are designed to work in their target environment without, or with limited, human intervention. The objective with this course is to give a broad understanding of the wide area of autonomous systems and the foundational knowledge in the topic areas required to understand and develop autonomous systems. The course covers topics from sensing and perception to control and decision making.

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

  • Explain what autonomy is and what challenges it poses for a system.
  • Explain the operational principles of common sensors.
  • Describe strengths and weaknesses of different sensors.
  • Explain the principles of approaches to common perception problems in autonomous systems.
  • Use learning-based methods for perception in autonomous systems.
  • Explain the principles of automatic control and the problems it addresses related to autonomous systems.
  • Describe planning and decision-making problems at different levels of abstraction in autonomous systems.
  • Use some common software tools for design of autonomous systems.

In this course we will look at some of the building blocks for autonomous systems along with some common software tools. A traditional and highly simplified model of a system divides it into sensing, planning and acting. The course consists of two modules where the first covers sensing and the second planning and acting.

Sensors allow autonomous system, be it an autonomous truck, a service robot, or a mobile phone to gather information about the internal state (temperature, currents, etc) and the state of the world around and the position in that world. We will look at different sensors and cover the principles by which they work, where they are applicable and what their strengths and weaknesses are. The raw data from the sensors often needs some form of processing to extract information that can be used by the autonomous system. This is the problem of perception where image recognition is an example that is often mentioned. Coming back to the previous example, perception also helps determine the position of the truck, the mood of the human that the service robot is assisting or the best channel to transmit the signal on for the mobile phone.

In the second part we cover control and decision making. In this course we leave out the physical part of acting as this is often quite specific to each system. Coming back to the example with the truck we would look at questions such as controlling the steering to stay in the lane, adjusting the speed to avoiding colliding, deciding when to change, lane, in what order to deliver a set of good.

Lecture material (slides) and hand-in assignments distributed via the course homepage.

The examination assignments are to be completed individually and in groups.

Examination formats: Written report, written assignments, seminars given by participants, miscellaneous. The examination consists of exercises, labs, and projects.

If you are not a student at KTH you must login via https://canvas.kth.se/login/canvas