Course content

Mathematical description of stochastic signals and systems by state space modelling. Simulation of stochastic systems. Prediction, filtering and smoothing. Application of the Kalman filter to systems with coloured noise. The information filter and algebraic equivalente forms. Design of suboptimal Kalman filters, divergence and implementation problems. Analysis of suboptimal Kalman filters: Monte Carlo simulation, covariance analysis and error budget. Nonlinear systems: linearised, extended and partial feedback Kalman filters, Bayesian filters and numerical methods. System identification: Augmented Kalman filter and the ML-method. Numerical methods. Applications of the Kalman filter to real world problems.

Learning outcome

Knowledge:
Extencive knowledge about designing and analysing Kalman filters and apply them to physical systems such as navigation and tracking systems. And be able to read and understand methods published in the literature and evaluate and compare these with methods used in practical systems.
Skills:
Independent management of small R&D projects and contribute actively in larger projects.
General competence:
Communicate work related problems with specialists and nonspecialists.

Learning methods and activities

The course is held at UniK, Kjeller. Lectures, exercises and term project. If there is a re-sit examination, the examination form may be changed from written to oral.

Compulsory assignments

• One term project

Recommended previous knowledge

TTK4115 Linear System Theory or equivalent.

Course materials

Textbook and lecture notes.

Credit reductions