Gregory J. Barlow :: Robotics Institute :: Carnegie Mellon University

About

I am a Ph.D. candidate in the Robotics Institute at Carnegie Mellon University, where I work with Stephen Smith in the Intelligent Coordination and Logistics Laboratory.

I am interested in the application of population-based search to real-world problems, particular problems with dynamic or uncertain fitness landscapes. Recently, I have been working on memory-enhanced evolutionary algorithms for dynamic problems, including dynamic scheduling. I am also interested in evolutionary robotics, the design of robot controllers using evolutionary computation.

I am originally from Greensboro, North Carolina, and I am an alumnus of the North Carolina School of Science and Mathematics (c/o 99) in Durham, NC. I received B.S. degrees in electrical and computer engineering in 2003 and an M.S. degree in electrical engineering in 2004 from North Carolina State University in Raleigh, NC.

I live in Pittsburgh, PA with my wife, and at the moment I am spending a lot of my free time learning to play clawhammer style banjo.

Research interests

Dynamic and noisy optimization

I am interested in optimization for problems with dynamic or uncertain fitness functions. I am also interested in the evolution of robust solutions for noisy fitness functions.

Evolutionary robotics

Much of my undergraduate and master's work was on evolutionary robotics, the design of controllers for mobile robotics using evolutionary computation.

Evolutionary computation

I am interested in many EC techniques, including genetic programming and multi-objective optimization.

Education

Carnegie Mellon University (Pittsburgh, PA), Ph.D. student, Robotics.

National Defense Science and Engineering Graduate Fellow

North Carolina State University (Raleigh, NC), M.S. Electrical Engineering, 2004.
North Carolina State University (Raleigh, NC), B.S. Electrical Engineering and B.S. Computer Engineering, summa cum laude, 2003.

John T. Caldwell Scholar, Barry M. Goldwater Scholar

North Carolina School of Science and Mathematics (Durham, NC), high school, 1999.

Recent publications

Gregory J. Barlow, Choong K. Oh, and Stephen F. Smith. "Evolving Cooperative Control on Sparsely Distributed Tasks for UAV Teams Without Global Communication." Proceedings of the 2008 Genetic and Evolutionary Computation Conference. Atlanta, Georgia. July 2008. (abstract, bib)
Gregory J. Barlow and Choong K. Oh. "Evolved Navigation Control for Unmanned Aerial Vehicles." Frontiers in Evolutionary Robotics. Ed. Hitoshi Iba. Vienna: I-Tech Education and Publishing, 2008. 353-378. (bib)
Gregory J. Barlow and Stephen F. Smith. "A Memory Enhanced Evolutionary Algorithm for Dynamic Scheduling Problems." Applications of Evolutionary Computing: EvoWorkshops 2008. Naples, Italy. March 2008. EvoSTOC Best Paper Award. (abstract, bib, ps, ps.gz, pdf)