Autonomous systems rely on artificial intelligence and machine learning to achieve autonomy. It is therefore a challenge to ensure dependability of an autonomous system and guarantee that the risks associated with the system are acceptable. The course will introduce modeling, verification and analysis techniques for achieving dependability of autonomous systems.
Course memo Autumn 2021
Course presentation
Headings denoted with an asterisk ( * ) is retrieved from the course syllabus version Autumn 2021
Content and learning outcomes
Course contents
Techniques to achieve dependability, safety analysis, derivation of dependability requirements from safety analysis, modelling and verification of safety requirements, safety assurance case, multi-agent systems, emergent behaviour, goal-oriented modelling and verification of safe and reliable multi-agent autonomous systems, evolutionary algorithms and learning algorithms for mission planning and navigation, safety of mission planning.
Intended learning outcomes
After passing the course, the student shall be able to
- describe dependability attributes formally
- specify dynamic behaviour of autonomous systems and their properties
- use risk assessment and safety analysis techniques to define dependability requirements
- model and verify autonomous systems by means of automatic tools
in order to
- be able to work with autonomous safety critical systems in research and/or development
- be able to identify risks in connection with autonomous systems and use modelling, verification and security techniques to prevent them.
Detailed plan
Learning activities | Content | Preparations |
---|---|---|
Modelling dependable autonomous systems | Use of UML models | Review UML modelling language |
Design of dependable autonomous systems | Programming | Brush-up programming skills |
Modelling and assessment of dependability of autonomous systems | Analytical work | Review probability theory and statistics |
Preparations before course start
Literature
No information insertedSupport for students with disabilities
Students at KTH with a permanent disability can get support during studies from Funka:
Examination and completion
Grading scale
A, B, C, D, E, FX, F
Examination
- LAB2 - Laboratory work, 6.5 credits, Grading scale: A, B, C, D, E, FX, F
- QUI1 - Digital quiz, 1.0 credits, Grading scale: P, F
Based on recommendation from KTH’s coordinator for disabilities, the examiner will decide how to adapt an examination for students with documented disability.
The examiner may apply another examination format when re-examining individual students.
The section below is not retrieved from the course syllabus:
Laboratory work ( LAB2 )
Digital quiz ( QUI1 )
Ethical approach
- All members of a group are responsible for the group's work.
- In any assessment, every student shall honestly disclose any help received and sources used.
- In an oral assessment, every student shall be able to present and answer questions about the entire assignment and solution.
Further information
No information inserted
Contacts
Course Coordinator
Teachers
Teacher Assistants
Examiner
Round Facts
Start date
1 Nov 2021
Course offering
- relaut21 Autumn 2021-51084
Language Of Instruction
English