ACIT4810 Advanced Methods in Modelling, Simulation, and Control Course description

Se emneplan.

The assessment will be based on a portfolio of the following:

• A group project delivery (2-4 students), consisting of a report (7500-3000 words) and code
• An individual oral examination

The weight of the two parts is 50 % each.

The project report should be between 7500-3000 words. Both the code/program and the report will be evaluated. The comprehensiveness of the code/program is evaluated with the assumption that each student in the group has committed about 60 hours towards developing the solution. As a general guideline, the code/program carries a stronger weight than the report.

The portfolio will be assessed as a whole and the exam cannot be appealed.

;

New/postponed exam

In case of failed exam or legal absence, the student may apply for a new or postponed exam. New or postponed exams are offered within a reasonable time span following the regular exam. The student is responsible for applying for a new/postponed exam within the time limits set by OsloMet. The Regulations for new or postponed examinations are available in Regulations relating to studies and examinations at OsloMet.

No formal requirements over and above the admission requirements.

Upon successful completion of the course, the student:

Knowledge:

• can develop data-driven dynamic modeling methods, can evaluate suitability of different model structures and choose appropriate models for chosen industrial application
• can develop and apply state estimation techniques for linear systems
• can develop control strategy and evaluate different model-based control algorithms for multivariate systems
• can select and argue for suitable combination of model-based control algorithms for a chosen industrial application.

Skills:

• can obtain dynamic models with data-driven dynamic modelling methods for a chosen industrial application
• can implement, test and validate linear techniques for state estimation
• can implement, test and validate model-based control algorithms for multivariate systems
• can implement, test and validate different model-based control and estimation algorithms in a simulation environment.

General competence:

• can develop, implement, test and validate control strategies for multivariate system using different model-based control and estimation methods.

All aids are permitted. For the oral exam, students will not have access to computers or other aids.

Weekly lectures and exercises, assignments in groups of 2-3 students and one individual semester project.

Two guest lectures on selected topics given by experts from industry and academia.

The following required coursework must be approved before the student can take the exam:

Four assignments in groups of 1 - 3 students (1000 - 2000 words per assignment)

This course will present complex systems (cellular automata, networks, and agent-based) modelling and programming through state-of-the-art artificial intelligence methods that take inspiration from biology (sub-symbolic and bio-inspired AI methods), such as evolutionary algorithms, neuro-evolution, artificial development, swarm intelligence, evolutionary and swarm robotics.

During this course, students will get both theoretical and practical experience within complex systems and bio-inspired/sub-symbolic AI methods.

All, computer with MATLAB and Simulink.

On successful completion of the course, students should have the following learning outcomes defined in terms of knowledge, skills, and general competence.

Knowledge

The student:

• has a deep understanding of complex systems modelling and analysis
• has advanced knowledge in sub-symbolic and bio-inspired AI methods
• has a clear understanding of key concepts in AI such as emergence, adaptation, evolution.

Skills

The student:

• can model and analyse complex systems using cellular automata, networks and agent- based models
• can program complex systems using bio-inspired AI methods
• can design and implement evolutionary and swarm robotic systems

General Competence

The student:

• has theoretical and practical understanding of complex and biologically-inspired AI methods and evolutionary robotics methods
• can understand and discuss relevance, strength and limitations of complex and biologically inspired systems
• is able to work in relevant research projects.

The course consists of lectures and seminars on techniques and methods, as well as a project to be carried out in groups (2-4 students). The project will be chosen from a portfolio of available problems. The students will work in groups and will submit the code and a project report.;

Practical training

Lab sessions.

None.