Influencing Flocks via Ad Hoc Teamwork
University of Texas at Austin Learning Agents Research Group with Peter Stone

Ad hoc teamwork, a newer area of multiagent systems research, studies how new robots can join pre-existing teams and assist the team in accomplishing its goal. My research extends and applies research in ad hoc teamwork towards the general area of flocking, which is an emergent swarm behavior. In particular, my work considers how ad hoc agents --- referred to as influencing agents in my work --- can join a flock, be recognized by the rest of the flock as part of the flock, influence the flock towards particular behaviors through their own behavior, and then separate from the flock. This topic was the main focus on my PhD dissertation, but I'm continuing to study this topic post-dissertation.

UT Austin Villa Standard Platform Robot Soccer Team
University of Texas at Austin Learning Agents Research Group

I've served as team leader for most of my time with the UT Austin Villa team. I've touched many parts of the code base over the years, but my main contributions were to our kicking engine and our high level strategy. I not only designed the kicking engine for standing kicks, but also added the capacity to perform "walk kicks" while the walking engine is still engaged. Before RoboCup 2010, I worked mainly on two technical challenges to become acquainted with the UT Austin Villa code base - the passing challenge and the dribbling challenge. We placed 1st in the passing challenge and 2nd in the dribbling challenge.

Drop-in Player Competition
University of Texas at Austin Learning Agents Research Group with Tim Laue, Patrick MacAlpine, Samuel Barrett, and Peter Stone

We designed, organized, ran, and documented a new Drop-in Player Competition which served as a testbed for cooperation without pre-coordination. In 2013, three RoboCup leagues began the Drop-in Player Competition. Instead of homogeneous robot teams that are each programmed by the same people and hence implicitly pre-coordinated, this competition features ad hoc teams, i.e. teams that consist of robots originating from different RoboCup teams and as such running different software. We wrote an IROS paper on our experiences organizing and running this competition across three leagues. After the initial 2013 competition, we organized and ran a larger Drop-in Player Competition in the Standard Platform League for three additional years. We documented our experiences and the strategies utilized by participants across the first three years of this competition in our JAAMAS article.

Role-based Ad Hoc Teamwork
University of Texas at Austin Learning Agents Research Group with Noa Agmon and Peter Stone

Ad hoc teamwork is a relatively new research area that examines how an agent ought to act when placed on a team with other agents such that there was no prior opportunity to coordinate behaviors. In some team domains, such as search and rescue missions and many team sports, the team behavior can be broken down into roles. As such, I have presented a role-based approach for ad hoc teamwork, in which each teammate is inferred to be following a specialized role that accomplishes a specific task or exhibits a particular behavior. In such cases, the role an ad hoc agent should select depends both on its own capabilities and on the roles currently selected by the other team members.

Undergraduate Research Option Program
Georgia Tech Cognitive Computing Lab with Ashwin Ram and Santi Ontanon.

I worked in Ashwin Ram's Cognitive Computing Lab from Summer 2008 to Spring 2009 as part of Georgia Tech's undergraduate research option program. I worked on the Darmok 2 project, which sought to enable a game artificial intelligence to play strategically and learn from experience in real-time strategy games. My work focused mainly on using first order inductive learning to learn rules for representing opponent strategies. Specifically, I used learned rules to perform plan recognition and classify an opponent strategy as one of multiple learned strategies.

SAIC Scholar Program
Georgia Tech Mobile Robotics Lab with Zsolt Kira

I worked with PhD student Zsolt Kira in Georgia Tech's Mobile Robots lab from Fall 2006 to Fall 2008 on a project attempting to establish a shared understanding between two heterogeneous robots in order to facilitate useful communication and knowledge sharing. My contributions include derivation of three methods for establishing a shared context where each method trades off between accuracy and cost and implementation of a novel remove method for the ID5R algorithm to allow for removal of an attribute that the original robot has, but that is not applicable to the robot with which we are sharing data.