Instructor

Mani Bhushan

Semester

Autumn ‘20

Course Difficulty

Depends on previous exposure. But all preliminaries are covered from the basics, so it is manageable.

Time Commitment Required

Can vary highly from person to person. More or less like an average core course

Grading Policy and Statistics

Grading was done based on 4 assignments(15 %), midsem(15 %), endsem (45 %) and course projects (25 %).

Attendance Policy

None

Pre-requisites

Prior knowledge of probability theory and statespace representations would be advantageous and not necessary.

Evaluation Scheme

4 assignments(15 %), midsem(15 %), endsem (45 %) and course projects (25 %).

Topics Covered in the Course

The course starts with an introduction to the basics of probability theory, system modelling and weighted least squares, followed by various estimation algorithms (mainly Kalman filters).

Teaching Style

Despite the course content being new, all the topics are taught from scratch, so its not that difficult to follow.

Tutorials/Assignments/Projects

Actual implementation of the algorithms provides a much better understanding. Assignments and projects were both really well designed.

Feedback on Exams

Midsems and Endsems were comparatively easier than the content covered in class.

Motivation for taking this course

I am interested in the study of control systems, of which estimation is an integral part. Kalman filters in particular have been applied to a wide range of fields. This course provides an intuitive understanding, rigorous maths as well as implementation of Kalamn filters.

Course Highlights

Better understanding of the algorithms thorugh implementation to real life physical systems

How strongly would I recommend this course?

I think this is something which is required in almost all engineering disciplines. The course structure is really good, so is the teaching. Overall I feel this is a pretty good course for those who are interested in core engineering.

When to take this course?

5th semester; 5th or 7th semester is ideal in my opinion

Going Forward

You can always chose to continue your course project with the professor even after the semester.

References Used

1. A. Gelb (editor), “Applied Optimal Estimation”, M.I.T. Press, 1988.
2. D. Simon, “Optimal State Estimation: Kalman, H∞ and Nonlinear Approaches”, Wiley Interscience.
3. J. L. Crassidis, J. L. Junkins, “Optimal Estimation of Dynamic Systems”, CRC Press.
4. T. Soderstorm, “Discrete-time Stochastic Systems: Estimation and Control”, Springer,
   2nd Ed., 2002.
5. P. S. Maybeck, “Stochastic Models, Estimation and Control”, Vol. 1, Academic Press,
7. A. H. Jazwinski, “Stochastic Processes and Filtering Theory”, Academic Press, 1979.
8. R. Branko, S. Arulampalam, N. Gordon, “Beyond the Kalman Filter: Particle Filters
   for Tracking Applications”, Boston: Artech House, 2004

CL 653 Review By: Mitalee Oza