Robot Competitions as Class Projects
Lisa Meeden
Computer Science Program
Swarthmore College
meeden@cs.swarthmore.edu

Douglas Blank
Dep0artment of Computer Science
University of Arkansas, Fayetteville
dblank@uark.edu

Curriculum Descant
From ACM Intelligence Magazine
Volume 9, Number 2, Fall 1998
ACM Press

 

We have recently returned from the 1998 AAAI robot competition where we were judges and members of the rules committee for the "Life on Mars" contest. At the 1997 AAAI robot competition we both entered teams, and at the 1999 AAAI conference Meeden will chair the competition. We have seen first hand how robot competitions can be used to motivate and excite students about computer science in general and artificial intelligence in particular. We would like to encourage other instructors to consider incorporating robot competitions into their courses. There are certainly obstacles to starting up such an endeavor, including finding an appropriate robot platform and the funds to purchase it. However, the benefits can be enormous. By attending a conference such as AAAI in conjunction with the competition, students are exposed to a large and active research community. By attempting to solve the competition tasks as a team, students take on much harder problems than they would normally try on their own. In order to solve the tasks, students delve into the primary literature to find out about state of the art methods. In addition, when a team does well, the institution typically receives quite a bit of publicity.

At Swarthmore College, we have incorporated robot competitions into three different courses. The first course, entitled "Building Intelligent Robots," has no prerequisites and draws students from many non-science disciplines (see online references below). The students build small, mobile robots out of LEGOs. Periodically we hold competitions within the class to allow the students to demonstrate their robots. However, one could instead have the course focus on attending a competition such as the Trinity College Fire-Fighting Contest, or one could host a Botball-like tournament as created by the KISS Institute for Practical Robots.

The second course is a seminar course for senior majors in computer science. Each year it focuses on a different topic, and in 1997 the topic was "Embodied Intelligence." Throughout the semester, nine students worked toward the 1997 AAAI competition, with three of the students actually attending the conference. The team placed third in the "Home Vacuuming" contest.

The third course which includes robot competitions is "Artificial Intelligence." This course begins with building LEGO-based robots, and moves on to off-the-shelf robots such as the Pioneer and Khepera. The course culminates in a long-term research project. The students must propose the project by mid-semester and present a paper about the project at the end of term. As one possible project, the students will be encouraged to consider entering the upcoming AAAI competition to be held in Orlando, Florida on July 18-22, 1999.

The University of Arkansas has a much younger history with robotics in the curriculum, but we have incorporated robot building into traditional undergraduate and graduate AI courses. Although there is not much time for a thorough exposure to all of the aspects given to robotics in the Swarthmore courses, students do get hands-on experience with a few small and medium-sized robots. In addition, many students end up doing their course project in robotics, and thereby get additional experience. For example, one student's project took third place in last year's "Find Life on Mars" contest. Connecting traditional AI concepts to robotics has shown to be quite motivating for computer science students at Arkansas. A seminar course, "Intelligent Robot Control," will be taught in the spring and is planned to be similar to Swarthmore's second course. Here too, students will be encouraged to consider entering the upcoming AAAI competition.

At the 1999 AAAI conference there are plans to incorporate robots in four different ways:

  1. Papers accepted for presentation with a robotics demonstration;
  2. An open-ended exhibition;
  3. A competition aimed at challenging researchers to push the state of the art in robotics;
  4. A competition aimed at students exploring the state of the practice in robotics.

It is the fourth avenue in which students are highly encouraged to participate. Note that AAAI offers substantial travel scholarships to help student teams make the trip to the competition. We hope to see some new institutions join the competition this year. Please contact us for more information.

Online References

Getting Started with AAAI Competitive Robotics (http://dangermouse.uark.edu/robots/)

1999 AAAI Competition (http://www.aic.nrl.navy.mil/~schultz/aaai99/)

Swarthmore Robotics

University of Arkansas Robotics (http://dangermouse.uark.edu/~dblank/ailab/)

LEGO Robots (http://mainline.brynmawr.edu/Robots/ResourceKit/)

Trinity College Fire-Fighting Contest (http://www.trincoll.edu/~robot/rules99.html)

KISS Institute for Practical Robots (http://kipr.org/)

Alternate Competition formats (http://web.mit.edu/6.270/www/contest.html)

Descants

Fall 1997
Welcome
Inaugural Installment of the new column.
(Deepak Kumar)

Summer 1998
Teaching about Embedded Agents
Using small robots in AI Courses
(Deepak Kumar)

Fall 1998
Robot Competitions as Class Projects
A report of the 1998 AAAI Robot Competition and how robot competitions have been successfully incorporated in the curriculum at Swarthmore College and The University of Arkansas
(
Lisa Meeden & Doug Blank)

Winter 1998
Nilsson's New Synthesis
A review of Nils Nilsson's new AI textbook
(Deepak Kumar)

Spring 1999
Pedagogical Dimensions of Game Playing
The role of a game playing programming exercise in an AI course
(Deepak Kumar)

Summer 1999
A New Life for AI Artifacts
A call for the use of AI research software in AI courses
(Deepak Kumar)

Fall 1999
Beyond Introductory AI
The possibility of advanced AI courses in the undergraduate curriculum
(Deepak Kumar)

January 2000
The AI Education Repository
A look back at AAAI's Fall 1994 Symposium on Improving the Instruction of Introductory AI and the resulting educational repository
(Deepak Kumar)

Spring 2000
Interdisciplinary AI
A challenge to AI instructors for designing a truly interdisciplinary AI course
(Richard Wyatt)

Summer 2000
Teaching "New AI"
Authors of a new text (and a new take) on AI present their case
(Rolf Pfeifer)

Fall 2000
Ethical and Social Implications of AI: Stories and Plays
Descriptions of thought provoking stories and plays that raise ethical and social issues concerning the use of AI
(Richard Epstein)

January 2001
How much programming? What kind?
A discussion on the kinds of programming exercises in AI courses
(Deepak Kumar)

Spring 2001
Predisciplinary AI
A follow-up to Richard Wyatt's column (above) and a proposal for a freshman-level course on AI
(Deepak Kumar)

Spring 2001
Machine Learning for the Masses
Machine Learning comes of age in undergraduate AI courses
(Clare Congdon)


About Curriculum Descant
Curriculum Descant has been a regular column in ACM's Intelligence magazine (formerly published as ACM SIGART's Bulletin). The column is edited by Deepak Kumar. The column features short essays on any topic relating to the teaching of AI from any one willing to contribute. If you would like to contribute an essay, please contact Deepak Kumar.