Colin McMillen

Objective:

An internship in the field of computer science, preferably in artificial intelligence or robotics.

Research Interests:

My primary research interests lie in artificial intelligence and multi-robot systems. For my doctoral thesis research, I am investigating how agents can act near-optimally in timed, zero-sum games. I am particularly interested in challenging, dynamic domains such as robot soccer. Since agents need to reason about winning (being ahead when time runs out), the optimal policy in these domains is nonstationary and score-dependent. However, in challenging domains such as robot soccer, optimal reasoning is computationally complex. In practice, researchers often ignore score and time remaining because the resulting problem is considerably easier to solve. In my thesis research, I am investigating a variety of techniques that allow for approximately optimal solutions to timed, zero-sum domains.

In general, my research interests include the application of artificial intelligence or machine learning techniques to improve the performance of real-world systems.

Education:

August 2003 -- present: Carnegie Mellon University

Ph.D. student, Computer Science Department
Dissertation title: Optimal and Approximate Policies for Winning Timed, Zero-Sum Games
Advisor: Prof. Manuela Veloso
GPA: 4.0/4.0
Expected completion: August 2008

September 1999 -- May 2003: University of Minnesota, Twin Cities

B.S. Computer Science
GPA: 3.9/4.0
Graduated summa cum laude

Work Experience:

June 2007 -- present: reCAPTCHA.net (Pittsburgh, Pennsylvania)

Intern
Reference: Prof. Luis von Ahn

This summer, I am working with Prof. von Ahn on the reCAPTCHA project, which aims to use distributed human computation to digitize books. I am primarily responsible for analyzing the accuracy of our book digitizations, detecting malicious users and "bots", and importing book scans from a variety of sources into the reCAPTCHA system.

June 2005 -- October 2005: Sony Corporation (Tokyo, Japan)

Intern, Intelligent Systems Research Laboratory
References: Dr. Steffen Gutmann, Dr. Masahiro Fujita

While interning at Sony in Tokyo, I worked on the Sony QRIO humanoid robot. I developed a multi-robot, topological, simultaneous localization and mapping (SLAM) algorithm. This algorithm allows multiple QRIO robots to explore and map an unknown area. The robots do not need prior knowledge of teammates' positions. Instead, each robot maintains an independent map; these maps are merged together when one teammate visually recognizes another. This work was one of the first multi-robot research projects for the Sony QRIO robot. This work is patent pending (Japanese patent application #2005-349630).

August 1998 -- July 2003: Trade Cycles Creative Services (Plymouth, Minnesota)

Web developer
Reference: Jon Zydenbos

Programming, design, and database administration for several local business web sites, mostly related to automobile sales, warranties, and insurance policies.

Research Experience:

Robot Soccer (August 2003 -- present):

References: Prof. Manuela Veloso, Dr. Paul E. Rybski

I am currently doing research as a member of Carnegie Mellon University's robot soccer lab. Our team (CMDash) competes in the RoboCup 4-Legged League; in this league, teams of four Sony AIBO ERS-7 robots compete in twenty-minute games of soccer. My research has focused primarily on the development of team behaviors, including team positioning, role assignment, shared world state, and passing. I have also written lower-level networking code, embedded a Python interpreter in the lower-level C++ behavior architecture (for the rapid development of behaviors), and developed a simulation framework which our team has used heavily for the development and testing of single-robot and multi-robot behaviors. I have also worked on single-robot behaviors such as the goalie and attacker.

Distributed Robotics (May 2001 -- July 2003):

Reference: Prof. Nikolaos Papanikolopoulos

I worked on improvements to the software architecture used by a group of miniature mobile robots known as the Scouts. The Scouts are a team of very small, cylindrical robots—approximately 11 cm in length and 4 cm in diameter. The Scouts are therefore very limited in processing capability, and rely on communication with more powerful robots or workstations in order to perform autonomous behaviors. My work with the Scouts included the development of a component that schedules access to limited resources such as robots, video and radio frequencies, framegrabbers, and so on. Additional work included designing and implementing an API for controlling the hardware of a new robotic platform (the MegaScout).

Trading Agent Competition (January 2003 -- July 2003):

Reference: Prof. Maria Gini

I worked on an agent for the supply-chain management game of the 2003 Trading Agent Competition. My undergraduate honors thesis provided an extensive analysis of the game, including proofs of theoretical results, metrics by which the performance of agents could be measured, and suggestions of strategies that may be of use in the implementation of sophisticated TAC SCM agents. I worked on the production and delivery aspects of an agent that competed in the 2003 competition. This agent advanced to the semi-final round.

Intelligent Transportation Systems (January 2003 -- July 2003):

Reference: Prof. Nikolaos Papanikolopoulos

I worked on an intelligent transportation systems project sponsored by the Minnesota Department of Transportation. The main goal of our research was to develop a collision warning system for intersections. Detection and tracking of moving vehicles is obtained through computer vision; detection of potential collisions utilizes techniques from the field of computational geometry. I performed some preliminary work on integrating data from multiple cameras into this system. This should allow for greater accuracy in vehicle tracking. However, I left this project (to pursue graduate study) before we had any solid experimental results showing that this was indeed the case.

Recent Publications:

I am a co-author on 2 journal articles and 10 refereed conference papers. The papers listed here are a sample of my recent work. For a complete list of the papers and other publications I've co-authored, please see my web site at: http://www.colinm.org/publications.

Thresholded Rewards: Acting Optimally in Timed, Zero-Sum Games.
Colin McMillen and Manuela Veloso.
Proceedings of the Twenty-Second Conference on Artificial Intelligence (AAAI-07), July 2007 (to appear).
AAAI-07 Best Paper Award (1 of 2)

Distributed, Play-Based Role Assignment for Robot Teams in Dynamic Environments.
Colin McMillen and Manuela Veloso.
Proceedings of Distributed Autonomous Robotic Systems, Minneapolis, MN, July 2006.

Skills:

Programming Languages:

Fluent in Python, C/C++, and Java
Familiar with Perl, Lisp, Prolog, Standard ML, and JavaScript

Other languages:

SQL, HTML, XML, LaTeX, UNIX/Linux shell scripting

Version control:

Have used CVS, Subversion and Mercurial extensively; also familiar with Darcs and GNU Arch.

Robotics:

Sony OPEN-R SDK: Sony AIBO ERS-210 and ERS-7 quadruped robot and Sony QRIO humanoid robot.
Also familiar with the following robotic hardware: UMN Scout and MegaScout, Handyboard, Acroname BrainStem, Palm Pilot Robot Kit, and Lego Mindstorms.

References:

Prof. Manuela Veloso: 412-268-1474, veloso@cs.cmu.edu
Dr. Paul E. Rybski: 412-268-7417, prybski@cs.cmu.edu
Dr. Steffen Gutmann: +81-3-5448-2140, steffen@pdp.crl.sony.co.jp