This is the official Mobile Robotics course website for the Winter 2019 Semester at the University of Michigan. We had 64 graduate students across the College of Engineering this semester.
Here is a photo of all of us together, right before the midterm exam.
Maani Ghaffari Jadidi, email@example.com
Office Hours: Mon 4-5 pm - Room 204 NAME
Lectures: Mon-Thu 5-7 pm - Room 107 GFL
First class: Thursday, January 10
Maithili Varang Patel, firstname.lastname@example.org
Office hours: Tue 1:30-3:30 pm - Room 204 NAME
Micheal Potter, email@example.com
Office hours: Wed 2-4 pm - Room 204 NAME
Help outside of office hours: Use Piazza. Students are expected to help one another via Piazza.
Theory and application of probabilistic techniques for autonomous mobile robotics. This course will present and critically examine contemporary algorithms for robot perception. Topics include Bayesian filtering; stochastic representations of the environment; motion and sensor models for mobile robots; algorithms for mapping, localization; application to autonomous marine, ground, and air vehicles.
The course material is based on previous UM courses imparted by Prof. Ryan Eustice and Prof. Edwin Olson.
Learn the math and algorithms underneath state-of-the-art robotic systems. The majority of these techniques are heavily based on probabilistic reasoning---an area with extensive applicability in modern robotics. An intended side-effect of the course is to strengthen your expertise in this area.
Note: the focus of the course is on math and algorithms. We will not study mechanical or electrical design of robots.
S. Thurn, W. Burgard, and D. Fox
MIT Press, Cambridge, MA, September 2010.
ISBN-13: 978-0-262-20162-9, Third Printing
Errata for the third printing can be found at the book's website: http://www.probabilistic-robotics.org. It is strongly recommended that you annotate your text copy with the errata corrections. Otherwise, some variables, equations, and statements appear misleadingly wrong---causing all sorts of confusion!
State Estimation for Robotics
Timothy D. Barfoot, University of Toronto, 2018
Exposure to Linear Algebra, Probability and Statistics, Estimation, Matrix Calculation, basic Calculus such as Taylor series and function approximation would be useful. We will review them in the class.
For programming throughout the course, we use MATLAB. For your final project, you are free to choose MATLAB, Python, or C++ as your coding language. Also, see resources from the previous year's course website.
This exam is closed-book: you may not use the textbook, lecture slides, or notes, except for one 8.5” by 11” double-sided, hand-written formula sheet. Calculators may be used only for arithmetic calculations. Write your uniqname at the top of every page.
Late Submission PolicyLate submissions will lose Late submissions will lose 25%, 50%, and 100% of the initial mark per day, respectively; effectively, having 0 marks on the third day after the deadline. You may submit one assignment late with no penalty, this will be applied ONLY to your first late submission; you do not need to contact us and explain it.
IMPORTANT: If you update your documents once the submission is due, we will consider a late submission based on the last update on canvas
If you believe we graded a problem-set or an exam of yours incorrectly, you can submit a regrade request no later than one week after the graded work is originally returned. Regrade requests can be submitted in writing or by email to any member of the instructional staff.
The final project is one of the most important parts of this subject and requires substantial efforts and teamwork. The project could be either of the following (the topic should be closely related to the course):
Ideally, the project covers an interesting new ground and might be the basis for a future conference paper submission or product. You are encouraged to come up with your project ideas, yet make sure to pass them by your Lecturer (Maani) before you submit your abstract.
Here are a few examples from Winter 2018:
Download all code used in the slides as one zip file, umich_na568_code.zip .
There are a massive amount of related resources available online for free. I list some of the most related of them here so you can choose based on your preference and priorities.
This list was compiled off the top of my head and should not be considered exhaustive!
Open-Source Robotics Data Sets
MaeBot Robotics Platform
Used in EECS 467 and ROB 550 http://april.eecs.umich.edu/maebot/
Open-Source Robotics Software