Gregory J. Barlow

Robotics Institute
Carnegie Mellon University

About

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

I recently completed my Ph.D. in Robotics at Carnegie Mellon. My thesis focused on improving memory for optimization and learning algorithms on problems with dynamic environments. I developed two novel classes of explicit memory to exploit information from previous solutions as a problem changes.

I am interested in the application of optimization, learning, and search to real-world problems, particularly problems with dynamic or uncertain environments. One of my other research interests is evolutionary robotics, the design of robot controllers using evolutionary computation.

Education

Recent publications

  • Xiao-Feng Xie, Gregory J. Barlow, Stephen F. Smith, and Zachary B. Rubinstein. "Self-Scheduling Agents for Real-Time Traffic Signal Control." IEEE Conference on Intelligent Transportation Systems. Washington, DC. October 2011. (bib)
  • Gregory J. Barlow. "Improving memory for optimization and learning in dynamic environments." Doctoral dissertation. Carnegie Mellon University. Pittsburgh, PA. July 2011. (abstract, bib, pdf)
  • Gregory J. Barlow. "Generalized Density-Estimate Memory for Dynamic Problems." Thesis Proposal. Carnegie Mellon University. Pittsburgh, PA. June 2009. (pdf)
  • Andrew L. Nelson, Gregory J. Barlow, and Lefteris Doitsidis. "Fitness Functions in Evolutionary Robotics: A Survey and Analysis." Robotics and Autonomous Systems. Volume 57, Issue 4, pages 345-370. April 2009. (abstract, bib, pdf)
  • Gregory J. Barlow and Stephen F. Smith. "Using Memory Models to Improve Adaptive Efficiency in Dynamic Problems." IEEE Symposium on Computational Intelligence in Scheduling. Nashville, Tennessee. March 2009. (abstract, bib, pdf)