Probabilistic Robotics

6 EC

Semester 1, period 1

5204PRRO6Y

Owner Master Artificial Intelligence
Coordinator dr. Arnoud Visser
Part of Master Artificial Intelligence, year 2

Course manual 2018/2019

Course content

Probabilistic robotics is a subfield of robotics concerned with the perception and control part. It relies on statistical techniques for representing information and making decisions. By doing so, it accommodates the uncertainty that arises in most contemporary robotics applications.

This course is based on the book 'Probabilistic Robotics', from Sebastian Thrun, Wolfram Burgard and Dieter Fox. The book concentrates on the algorithms, and only offers a limited number of exercises. Their suggestion is to accompany the book with a number of practical, hands-on assignments for each chapter. The assignments of this course are designed to understand the basic problems concerning mobile robotics.

Study materials

Literature

  • Sebastian Thrun, Wolfram Burgard and Dieter Fox, Probabilistic Robotics, The MIT Press, 2005. ISBN: 9780262201629, 3rd edition.

Software

  • Matlab, Python

Objectives

At the end of the course, the student is able to:

  • develop robust software for robots operating in real-world environments,
  • understand the mathematical underpinnings of their software.  

Teaching methods

  • Lecture
  • Computer lab session/practical training

The lectures are to understand the mathematical foundations of the algorithms, the computer lab session are intended to translate the algorithms to software to control robots in the real-world.

Learning activities

Activity

Number of hours

Lectures

24

Lab sessions

24

Self study

120

Attendance

The programme does not have requirements concerning attendance (OER-B).

Assessment

Item and weight Details

Final grade

1 (50%)

Final Exam

1 (50%)

Practical Assignments

1 (12%)

Assignment 2 - Gaussian Filter

1 (12%)

Assignment 3 - Nonparametric Filters

2 (25%)

Assignment 4 - Kalman Localization and Mapping

4 (50%)

Assignment 5 - Particle SLAM on Nao field

Inspection of assessed work

Feedback on the assignments will be directly given on the reports uploaded to Blackboard.

The final exam can be inspected at the coordinator's office (C3.157),

Assignments

Assignment 1 - Bayes Filter - Exercise 2.8.4

  • individual assignment

- Gaussian Filter - Exercise 3.8.1 & 3.8.2

  • individual assignment

Assignement 3 - Nonparametric Filters - Exercise 4.6.1 & 4.6.4

  • individual assignment

Assignment 4 - Assignment 4 - Kalman Localization and Mapping

  • pair assignment

Assignment 5 - Particle SLAM on a Nao field

  • groups assignment

Fraud and plagiarism

The 'Regulations governing fraud and plagiarism for UvA students' applies to this course. This will be monitored carefully. Upon suspicion of fraud or plagiarism the Examinations Board of the programme will be informed. For the 'Regulations governing fraud and plagiarism for UvA students' see: www.student.uva.nl

Course structure

Week Chapters Assignment Deadline
1 1 & 2 Exercise 2.8.4, 11/09/2018 13:00
2 3 & 4 Exercise 3.8.1 & 3.8.2 18/09/2018 13:00
3 5 - 8 Exercise 4.6.1 & 4.6.4 25/09/2018 13:00
4 9 & 10 Kalman localization and SLAM  
5 11 & 12   07/10/2018 23:59
6 13 & 14 Particle SLAM on a Nao field  
7 17   21/10/2018 23:59

Timetable

The schedule for this course is published on DataNose.

Contact information

Coordinator

  • dr. Arnoud Visser

Staff