308-765B - Mobile Robotics

Winter term (January)


Also known in Minerva as "Advanced Topics - Systems 2"

Russian Mars exploration prototype, seen at NASA Ames research center This course serves as an introduction to robotics for graduate students. Walking robot

Recent assingments, news and updates are listed below. (Only relevant when class is in session.)

Abstract

Robots are on the verge of becoming genuinely commonplace. We consider current issues in robotics and embedded intelligent systems. How to combine sensing, action and planning in an uncertain and changing world. How we approach the three key issues in mobile robotics: building a map of our surroundings, knowing where we are, and formulating a plan to get use where we want to go? The course is a mixture of lectures, discussion, guest lectures and class presentations. It's target audience is graduate students, and especially those interested in research in robotics, artificial intelligence, cognitive science or computer vision. Emphasis is on algorithms, inference mechanisms and behavior strategies although we will briefly survey the kinds of mechanical and electronic systems that constitute a robot today. There is a premium on class presentation and discussion, and the final project can be demanding.

Instructor:


Professor G. Dudek

School of Computer Science.
Class times (Winter 2013): 10am Monday and Wednesday.

Office hours: Right after class, or by appointment (arranged by email or after class).

Format

A large fraction of the course takes place as conventional lectures, although there is lots of room for discussion and feedback from the class.

Syllabus

Description
This course serve as an introduction the broad area of robotics, intelligent machines that can act of their work, and specifically mobile robotics. We will deal with algorithmic issues and will only consider hardware in passing.

How can be approach the three key issues in mobile robotics: building a map of our surroundings, knowing where we are, and formulating a plan to get use where we wat to go (mapping, localization and path planning)?

Some broader aspects of spatial representation related to computational vision and graphics, and more tangential issues in mobile robotics will be examined. The emphasis will be on algorithms and techniques.

Topics include

In addition to the textbook, reference material will consist primarily of papers from the research literature. Students are expected to participate in class discussions and to present their summaries and commentary on several papers.

Reference material

Text: Computational Principles of Mobile Robotics, by Dudek and Jenkin. Cambridge University Press, 2010 (second edition).
Selected readings from the research literature, to be distributed in class.
Supplementary text: Autonomous Robot Vehicles, by Cox and Wilfong. Springer-Verlag. (Old, but still useful.)

Evaluation

The details of the course evaluation scheme and format of some classes will depend of the enrollment and hence will not be fixed until after the first lecture (based on attendance and student mix in the first lecture). Evaluation will be based on three types of activity: class participation, independent work (homework/project), and in-class formal presentation.

The tentative scheme is as follows. Homework will involve (1) an short literature survey in an approved sub-topic, (2) a more extensive assignment on a selected sub-topic, (3) a final project (typically related to the literature survey), (4) one or more in-class presentations (depending partly on enrollment and individual interests).

The final project will consist of summary of, and suggested extension to, a selected research problem accompanied by a term-paper and an in-class presentation. In most cases it will involve implementation of an algorithm.

Background

A knowledge of linear algebra and geometry is essential. Some background in graphics, artificial intelligence, computational vision or complexity theory would also be useful, but is not mandatory. The course is aimed at computer science students, but students with a background in Engineering or Physics are generally comfortable with the material. Students from other domains such as Psychology/Cognitive Science take the course are regular intervals and are typically comfortable althought some topics may appear obscure. I attempt to adjust the course content and expectations to the students in any given year.


Hot news and announcements





Technicalities to note

Whereas, McGill University values academic integrity; Whereas, every term, there are new students who register for the first time at McGill and who need to be informed about academic integrity; Whereas, it is beneficial to remind returning students about academic integrity;

Be it resolved that instructors include the following statement on all course outlines:

McGill University values academic integrity. Therefore all students must understand the meaning and consequences of cheating, plagiarism and other academic offences under the Code of Student Conduct and Disciplinary Procedures (see www.mcgill.ca/integrity for more information).

Be it further resolved that failure by an instructor to include a statement about academic integrity on a course outline shall not constitute an excuse by a student for violating the Code of Student Conduct and Disciplinary Procedures.

dudek@cim.mcgill.ca