Greg Barlow

I am a project scientist in the Robotics Institute at Carnegie Mellon University, where I work in the Intelligent Coordination and Logistics Laboratory.

My current research is on real-time adaptive traffic signal control for urban road networks. We have developed a system called Surtrac that we've been pilot testing in Pittsburgh since 2012. The original pilot site was nine intersections in the East Liberty neighborhood, and the site is scheduled to grow to 49 intersections by early 2015.

I received my Ph.D. in Robotics from Carnegie Mellon in 2011. My dissertation 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. My general research interests are in the application of optimization, learning, and search to real-world problems, particularly problems with dynamic or uncertain environments.