Course Probabilistic Robotics
Bachelor Artificial Intelligence
This is the information of Fall 2011
This is the information of the previous course (Spring 2011
The course is now given at the Master Artificial Intelligence (Spring 2017
The description is available in the course catalogue with code BAIPR6. The course is a free choice in the Bachelor Artificial Intelligence Curriculum.
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, and are based on the assignments that accompany the book 'Robotics Primer' of Maja Matarić. Maja's book and assignments are loosely coupled, so Maja's book is not required (although fun to read). The assignments will take place in a virtual world (don't tell Maja). Julian Kooij will assist with the assignments this year.
The official schedule
should be found here.
The course will take place in A1.30, which we will use as studio class room. A list of Frequent Asked Questions will be maintained.
Students, who were not able to attend a lecture, can catch up by listing to the recordings of my (Dutch) or Burghard's lectures (English). Download Lecturnity Player and listen to lecture, synchronized with the sheets.
Week 44: Chapter 1 & 2 - Introduction & Robot Paradigms & State Estimation
recording Introduction, Robot Paradigms and Recursive State Estimation part 1
Assignment 2.8.1, Assignment 2.8.2 & 2.8.3 and Assignment 2.8.4.
Week 44: Chapter 3.2 - Gaussian Filters - Kalman Filter
discussed Burghard's lecture
Discussed solutions of assignments
2.8.1, 2.8.2 and 2.8.4
Week 45: Chapter 3.3 - 3.5 Extended Kalman Filters
& Chapter 4 - Nonparametric Filters
Dutch recording Extended Kalman Filters (Part1, Part2) & Particle Filters
Assignment 3.8.1 and 3.8.2.
Week 46: Chapter 5 - Wheeled Locomotion & Robot Motion Models
Dutch recording locomotion lecture
and English recording motion-model lecture 1 and lecture 2
Battlefield Extraction-Assist Robot movie
Assignment 4.6.1 and 4.6.4.
Week 46: Chapter 6 - Sensors & Robot Perception Models
Dutch recordings Sensors and Sensor Models
Stanley's RaceDay movie and Stanley's Tech lecture recording (Dutch)
Week 47: 'Partial Exam' of Chapter 1-6 of the book, Wednesday November 23, 13:00-15:00, G4.15.
Week 48: Recap - Kalman Filter Geometric Approach (Slides and Dutch recording)
Only slides 9-45.
Note the slightly different notation for the intermediate prediction;
x(k+1|k) by Choset et al.and x(t) by Thrun et al.
The Localization Assignment.
Week 48: Chapter 7 - Markov and Gaussian Localization
Dutch recordings Likelihood Field and Kalman Localization.
Week 48: Chapter 8 - Particle Filters, Grid
and Monte Carlo localization, including KLD-sampling.
Dutch recording Particle Filters & Grid Localization.
Discussion of Burghard's Particle Filter lecture
MCL Animations belonging to the lecture:
Chapter 9 - Occupancy Grid Mapping
Chapter 10 - SLAM
animation of raw data of Intel Research Lab, animation of CMU's Wean Hall
The Warmup Assignment.
Chapter 17 - Exploration, including (UvA approach
Exploration and UvA approach recording
video CMU 1999 multi-robot exploration, video exploration with limited communication
multi-robot exploration recording 1 and recording 2
Week 50: Final - Sebastian Thrun's TED talk.
Week 51: Partial Exam ('open book') of Chapter 7-11 & 17 of the book, Thursday December 22, 13:00-15:00, G4.15.
Week 13: Reexam ('open book'), February 27, 15:00-17:00
Sebastian Thrun, Wolfram Burgard and Dieter Fox, Probabilistic Robotics, The MIT Press, 2005.
- Thursday November 3rd: page 38
- Tuesday November 8th: page 84
- Tuesday November 10th: page 116
- Tuesday November 17th: page 147
- Thursday November 19th: page 187
- Tuesday November 29th: page 236
- Thursday December 1st: page 278
- Monday December 5th: page 308
- Monday December 12th: page 336
Embedding in AI curriculum
This course is supported by the following chapters of 'Artificial Intelligence - A Modern Approach'
3rd edition, by Stuart Russell and Peter Norvig:
- Chapter 13: Quantifying Uncertainty
- Chapter 14: Probabilistic Reasoning
- Chapter 15: Probabilistic Reasoning over Time
- Chapter 25: Robotics
The course was this year evaluated by the participants with a 7.3:
Albert-Ludwigs-University Freiburg: Introduction to Mobile Robotics (2011) by Wolfram Burgard, Cyrill Stachniss, Maren Bennewitz, Kai O. Arras, Juergen Hess, Joerg Mueller.
City College of New York G3300: Advanced Mobile Robotics (2011) by John (Jizhong) Xiao
Stanford University CS 226: Statistical Techniques in Robotics (2010) by Sebastian Thrun and Alex Teichman.
Albert-Ludwigs-University Freiburg: Introduction to Mobile Robotics (2009) by Wolfram Burgard, Cyrill Stachniss, Maren Bennewitz, Kai O. Arras, Giorgio Grisetti, Daniel Meyer-Delius, Boris Lau
City College of New York G3300: Advanced Mobile Robotics (2009) by John (Jizhong) Xiao
University of Washington CSE 571: Probabilistic Robotics (2007) by Dieter Fox, Jonathan Ko, Brian Ferris
University of Southern California CSCI 445: Introduction to Robotics (2007) by Maja Mataric, Hadi Moradi, Randolph Voorhies and Christopher Wojno.
Technische Universitaet Dresden: Probabilistic Robotics (2007) by Axel Grossmann.
Albert-Ludwigs-University Freiburg: Introduction to Mobile Robotics (2007) by Wolfram Burgard, Kai O. Arras, Cyrill Stachniss, Giorgio Grisetti, Jürgen Sturm, Boris Lau
Stanford University CS 226: Statistical Techniques in Robotics (2006) by Sebastian Thrun and Jason Chuang.
University of Washington CSE 481: Robotics Capstone (2006) by Dieter Fox, Dirk Haehnel, Fred Potter
Stanford University CS 226: Statistical Techniques in Robotics (2004) by Sebastian Thrun and Rahul Biswas.
Last updated December 3, 2012
This web-page and the list of participants to this course is maintained by
University of Amsterdam