UNIK4560 – Applied parameter and state estimation

Course content

System identification: Observability, parameter estimation using augmented Kalman filter and the maximum likelihood method. Bayes estimation in nonlinear non-gaussian systems: optimal solution, point mass and particle filters. Hidden Markov models (HMM): simulation, prediction, filtering, smoothing and parameter estimation. The multiple-model estimation algorithm for static and dynamic systems used for parameter estimation and target trackning. Algortihms: optimal, pseudo bayesian and IMM.

Learning outcome

The student will gain a thorough knowledge of methods used for parameter estimation in state space models and state estimation in nonlinear non-gaussian dynamic systems. The methods will be applied to navigation and tracking problems.

Admission

Students who are admitted to study programmes at UiO must each semester register which courses and exams they wish to sign up for in Studentweb.

If you are not already enrolled as a student at UiO, please see our information about admission requirements and procedures.

Prerequisites

Formal prerequisite knowledge

None.

Recommended previous knowledge

MAT1110-Kalkulus og lineær algebra, MAT1120-Lineær algebra, MAT-INF1310-Ordinary differential equations, MAT2310-Optimal kontrollteori, STK1100-Sannsynlighetsregning og statistisk modellering, UNIK4500 – Stokastiske systemer.

Teaching

Three hours of lectures and one houre of problem solving sessions per week in the autumn term. In the spring term the course is offered as a guided self-tuition course. The student will get a DVD containing videos of the lectures and copies of all written material including what was written on the whiteboard. The students must hand in and pass on mandatory project task before they are admitted to take the exam.

Examination

Oral or written examination. Graded marks.

Facts about this course

Credits
10
Level
Master
Teaching
Every spring
Examination
Every spring
Teaching language
Norwegian