CSE 553S: Mobile Robotics

Spring 2006

[What] [Who] [Where] [Textbook] [Collaboration] [Grading]
[Lectures] [Projects] [Deliverables]
[Player/Stage] [Robot Framework]

What's New?

First deliverable: The first deliverable, worth 5% of your final grade, is the initial project description document. Find out more here. [4 February, 2006]
Web page!: The web page is here (obviously). [20 January, 2006]

What

CSE 553 builds on the material covered in CSE 550, and takes an in-depth look at some of the current research in mobile robotics. As with CSE 550, we concentrate on robotics from a software perspective. The class involves a substantial implementation project, which gives students the change to work on a real research robot platform. Lectures will involve presentations of work from the recent research literature.

From the course catalog:

This course covers advanced topics from the theory and practice of mobile robotics. Students will read, present and discuss papers from the current research literature. There will be a substantial programming project, in which students implement and test ideas from the current research literature on one of the department´s research robot platforms. Prerequisites: CSE 550A and strong programming skills (preferably in C++).

Who

Instructor:

When and Where

Classes:: Tuesday and Thursday, 11:30am-1:00pm, Eads 210
Office Hours:

Textbook

There is no required textbook for the class. The reading material will generally be available on the web or will be handed out in class. However, if you're interested in the material, and want to have a reference, here are a couple of suggestions:

"Probabilistic Robotics", Sebastian Thrun, Wolfram Burgard, and Dieter Fox. The MIT Press, 2005. ISBN 0-262-20162-3.
"Principles of Robot Motion: Theory, Algorithms, and Implementations", Howie Choset, Kevin M. Lynch, Seth Hutchinson, George Kantor, Wolfram Burgard, Lydia E. Kavraki, and Sebastian Thrun. The MIT Press, 2005. ISBN 0-262-03327-5.
"Introduction to Autonomous Mobile Robots", Roland Siegwart and Illah R. Nourbakhsh. Bradford Books, 2004. ISBN 0-262-19502-X.
"Computational Principles of Mobile Robotics", Gregory Dudek and Michael Jenkin. Cambridge University Press, 2000. ISBN 0-521-56876-5.

Collaboration Policy

You are encouraged to discuss the class material and your projects with other students in the class. There is enough overlap between some of the projects that this will help you a lot. Also, it's nice to get another perspective on problems that you might be having. However, you should never misrepresent someone else's work as your own. If you got an idea from someone else in class, from a friend, or from the web, you must acknowledge this. The ability to synthesize ideas from other sources is an important skill, but you must be honest about where those ideas come from. Obviously, in the quizzes, all of your answers must be your own. The "official" statement on collaboration is given below:

Unless explicitly instructed otherwise, everything that you turn in for this course must be your own work. If you willfully misrepresent someone else's work as your own, you are guilty of cheating. Cheating, in any form, will not be tolerated in this class.
If you are guilty of cheating on any assignment or exam, you will be penalized the number of points that the assignment is worth. For example, if you are guilty of cheating on an assignment worth 10 points, your score on that assignment will be -10. If you copy from anyone in the class both parties will be penalized, regardless of which direction the information flowed. Two or more instances of cheating in the course will result in a grade of F for the class, and will be referred to the School of Engineering Discipline Committee.
We will follow the guidelines of the University Undergradate Academic Integrity Policy, but we reserve the right to make the final determination of what constitutes cheating for this class. If you suspect that you may be entering an ambiguous situation, it is your responsibility to clarify it before the professor or TAs detect it. If in doubt, please ask

Grading

This class will use WUgrade for grade reporting.

Project: 75%

Most of your grade for the class will come from your implementation project. This will be broken down as follows:

Design and project plan:	5
Initial implementation:	15
Milestone:	20
Final system:	20
Project presentation and writeup:	15

Quizzes: 25%

We will have in-class quizzes after every three papers, to test your knowledge on the material in those papers.

Grades in this class will be assigned as follows:

85% A
75% B
65% C
50% D
0% F

The late policy for the class is 10% per day late. If you have some valid reason for needing more time on an assignment, then you should contact me at least two days before the deadline to request an extension. Last-minute requests will only be met in exceptional circumstances.

Lectures

[January] [February] [March] [April]

Meeting	Date	Topics	Reading	Links
1	January 17	Introduction
2	January 19	Project descriptions
3	January 24	Better Occupancy Grids	Learning Occupancy Grids With Forward Sensor Models, Sebastian Thrun.	Sebastian Thrun Stanford AI Lab
4	January 26	Better Occupancy Grids The EM Algorithm
5	January 31	Path-planning The front point method
6	February 2	Path-planning Graph-based methods
7	February 7	Path-planning D* and friends	Optimal and Efficient Path Planning for Partially-Unknown Environments, Anthony Stentz.	Tony Stentz
8	February 9	Multi-robot mapping	Multi-Robot Mapping using Manifold Representations, Andrew Howard.
9	February 14	Bayes Filters Gaussian Filters Kalman Filters		Kalman Filter page at UNC
10	February 16	Extended Kalman Filters EKF Localization
11	February 21	Simultaneous Localization and Mapping	FastSLAM: An efficient solution to the simultaneous localization and mapping problem with unknown data association, S. Thrun, M. Montemerlo, D. Koller, B. Wegbreit, J. Nieto, and E. Nebot.
12	February 23	Quiz 1
13	February 28	More SLAM	DP-SLAM: Fast, Robust Simulataneous Localization and Mapping without Predetermined Landmarks, Austin Eliazar and Ronald Parr.
14	March 2	More Kalman Filters	Discriminative Training of Kalman Filters, Pieter Abbeel, Adam Coates, Michael Montemerlo, Andrew Y. Ng, Sebastian Thrun.
15	March 7	Controlling humanoid robots	Automated derivation of Primitives for Movement Classification, A Fod, M. Mataric, and O. Jenkins.
16	March 9	Principal Components Analysis		Wikipedia page
	March 14	Spring Break: No class
	March 16	Spring Break: No class
17	March 21	Finding Roads in the Desert	Adaptive Road Following using Self-Supervised Learning and Reverse Optical Flow, David Lieb, Andrew Lookingbill, and Sebastian Thrun.	DARPA Grand Challenge
18	March 23	The Hough Transform		Bob Fisher's Hough Transform page Wikipedia page
19	March 28	Multi-Robot Conflict Resolution	Rational Aggressive Behaviour Reduces Interference in a Mobile Robot Team, Sarah Brown, Mauricio Zuluaga, Yinan Zhang and Richard Vaughan.
20	March 30	The DARPA Grand Challenge		DARPA Grand Challenge website PBS Nova special
21	April 4	Quiz 2
22	April 6	Learning Control	Robot Juggling: An Implementation of Memory-Based Learning, Stefan Schaal and Christopher G. Atkeson.
23	April 11	SIFT Features	Distinctive Image Features from Scale-Invariant Keypoints, David G. Lowe.
24	April 13	Localization with SIFT Features	sigma-MCL: Monte-Carlo Localization for Mobile Robots with Stereo Vision, Pantelis Elinas and James J. Little.
25	April 18	Anthropomorphic Robots
26	April 20	No Class
27	April 25	Human-Robot Interaction
28	April 27	Human-Robot Interaction	Vehicle Teleoperation Interfaces, Terrence Fong and Charles Thorpe. A Survey of Socially Interactive Robots, Terrence Fong, Illah Nourbakhsh, and Kerstin Dautenhahn.

[January] [February] [March] [April]

Projects

1.	Gesture Interface for Lewis the Robot	Garg
2.	Real-Time Strategy Game Interface for Robots	Blakely
3.	Formation Control for Mobile Robot Groups	Simon
4.	Collaborative Multi-Robot Mapping
5.	Expressive Actions for Mobile Robots	Wilson and Iyun
6.	Path-Planning Bake-off
7.	Auction-Based Task Allocation	Jedynak
8.	Dynamic Tasking Bake-Off
9.	Vision-Based Localization	Emrich and Martignoni (software), Heller (hardware)
10.	FastSLAM Implementation	Heckel
11.	Fast Visualizations of the World
12.	Line Segment Mapping System
13.	Learning Efficient Gaits for a Spider Robot	Sistar
14.	Tracking and Classifying People and Objects

Deliverables

	Description		Due Date
1.	Initial description and timeline		8 Feb 2006, 23:59:59

Player/Stage

If you want to get a copy of the Player/Stage code for your own computer, it can be found at playerstage.sourceforge.net. If you will be using the CEC machines do not install your own copy of the Player or Stage code there.

The example code for C++ that comes with Player is also available locally. The files needed for Stage can be found in /usr/local/share/stage/worlds/ on the CEC linux machines.

Documentation for the robot control framework can be found here.

Page written by Bill Smart.