Use the buttons along the top to navigate this webpage.
Welcome I am an Associate Research Professor at Carnegie Mellon University's Robotics Institute. I do research in artificial intelligence and specifically multi-agent systems. At the moment, I am doing a lot of work with teams of autonomous robots under the control of a small number of operators. An key example of this idea is our use of large teams of small, autonomous airboats for applications such as environmental monitoring and flood response. You can read more about that project here . Other projects involve searching for information in large databases, robot retriever dogs and interfaces for UAV or submarine operators.
I am specifically interested in building really big teams to do various different tasks. Fundamentally different research issues need to be addressed when teams are scaled from a few members to hundreds or thousands of members. Over time we have designed a number of algorithms for this task. In conjunction with researchers at the University of Southern California, we have encapsulated these algorithms in a public domain software package called Machinetta. Machinetta is an updated, fully distributed, Java version of Teamcore that has been effectively used in a number of domains to coordinate large teams. Download Machinetta from here.
My PhD research topic was adjustable autonomy, the idea that agents or robots need to flexibly give up control to humans in key situations. The key idea in that work was that the agent needs to plan a sequence of transfer control actions, when the adjustable autonomy is in the context of a team. The critical observation was that agents can't wait indefinitely for human input when other teammates might be impacted by the delay.