EL2320 Applied Estimation 7.5 credits
The overall goal of the course is to give the participants theoretical as well practical skills and experience in estimation applications. In estimation we try to determine some property of a system or some other quantity based on noise corrupted measurements from sensors. The course will start from a number concrete examples taken from e.g. robitics and target tracking, to motivate the need for various filtering techniques such as Kalman filters and particle filters.
Education cycleSecond cycle
Main field of studyElectrical Engineering
Grading scaleA, B, C, D, E, FX, F
Autumn 18 P2 (7.5 credits)
Language of instruction
Form of study
Number of places
P2: D1, I1, D2, I2. more info
John Folkesson <firstname.lastname@example.org>
John Folkesson <email@example.com>
TSCRM åk1, TEBSM åk1, TMAIM åk1, TSYBM åk2, öppen för alla program
Part of programme
- Master's Programme, Computer Science, 120 credits, year 1, CSCS, Recommended
- Master's Programme, Computer Science, 120 credits, year 1, CSDA, Recommended
- Master's Programme, Computer Science, 120 credits, year 2, CSCS, Recommended
- Master's Programme, Computer Science, 120 credits, year 2, CSDA, Recommended
- Master's Programme, Embedded Systems, 120 credits, year 1, INSR, Mandatory
- Master's Programme, Industrial Engineering and Management, 120 credits, year 1, MAIG, Conditionally Elective
- Master's Programme, Machine Learning, 120 credits, year 1, Conditionally Elective
- Master's Programme, Machine Learning, 120 credits, year 2, Conditionally Elective
- Master's Programme, Systems, Control and Robotics, 120 credits, year 1, NCSS, Conditionally Elective
- Master's Programme, Systems, Control and Robotics, 120 credits, year 1, RASM, Mandatory
- Master's Programme, Systems, Control and Robotics, 120 credits, year 2, NCSS, Conditionally Elective
Intended learning outcomes
The overall goal of the course is to give the participants theoretical as well as practical skills and experience in estimation. The course will start from a number of concrete examples to motivate the need for various filtering techniques such as Kalman filters and particle filters. After completing the course the student should:
- be able to describe the parts of a Bayesian recursive filter in terms of the underlying probabilities, compare and contrast different estimation techniques, and select and apply appropriate techniques to problems.
- have reflected on the relationship between measurement uncertainty, probability theory and estimation methods.
- have gained experience in finding information from current scientific literature including recently published journal articles. As well as presentation of results in well structured scientific reports.
Course main content
The course focuses on giving the participants practical experience in using different estimation techniques on real problems. Examples used in the course are, for example, from navigation with mobile robots.
The following will be covered in the course: Observability, the Markov assumption, data association, estimation techniques such as Kalman filter, extended Kalman filter, particle filter, Rao-Blackwellized particle filter, Unscented Kalman Filter
There are 12 lectures. Both theory and practice of estimation will be covered. Getting practical skills in anything requires you to get hands-on experience and as such the work between the lectures will be very important.
Two labs solved individually cover the Kalman filter and the particle filter.
For the final project, the student should work in pairs and implement an estimation method. Each student needs to write an individual report including a literature study. It is also possible for a single student to write an individual report in the form of only a literature study (i.e. without an implementation) to pass the minimum requirement for the final project assignment. See the examination comment below on the difference in grading between these two options.
For single course students: 120 credits and documented proficiency in English B or equivalent.
Courses corresponding to SF1624 Algebra and Geometry, SF1901 Probability Theory and Statistics, SF1635 Signals and Systems, part I. Being able to program in MATLAB.
The official course book is "Probabilistic robotics" by Thrun, Burgard and Fox, The MIT Press, ISBN 0-262-20162-3 covers most of the material in the course from a robotics points of view. Letcures notes will also be made available. This course is at advanced level so some of the material will be in the form of research publications. The students are assumed able to research for additional material to solve the project assignment.
No special equipment needed, you only need access to a computer
- PRO1 - Project, 2.0, grading scale: P, F
- PRO2 - Project, 2.0, grading scale: P, F
- TEN1 - Examination, 3.5, grading scale: P, F
The basic part of the examination in the course consists of two lab assignments (PRO1), a project (PRO2) and an exam (TEN1). These are credited as,
Each of these will be reported to the system with a P/F grade and passing them means that the student has passed the course. The final grade is then an assessment based on the level above passing on these moments as described below.
The final grade for the course will be an average of the grade on the exam and the implementation project. This project assignment can be completed in groups of two students but each needs to write a separate report and will be assessed separately.
Not opting to do an implementation project (ie. only doing a literature study) thus gives a final grade of half the exam grade.
Requirements for final grade
To get a passing grade in the course the students need to pass the labs, the mandatory part of the project assignments and the exam.
John Folkesson (firstname.lastname@example.org)
John Folkesson <email@example.com>
There is a rich set of courses on related estimation, control, signal processing, systems theory, etc such as EQ2800 Optimal filtering, EQ2300 Digital signal processing, EQ2400 Adaptive signal processing, SF2842 Mathematical Systems Theory, EQ2810 Estimation theory
Course syllabus valid from: Autumn 2015.
Examination information valid from: Spring 2008.