Associate Professor for North Carolina State University
Arnav Jhala, associate professor of computer science, joined NC State in August 2016 as the Director of the Chancellor’s Faculty Excellence Cluster in Visual Narrative, and as the co-director of the Digital Games Research Initiative. Jhala’s research group investigates computational structures and methods that are useful in representing and mediating human interpretation and communication of narrative in interactive visual media, such as film and games. The Jhala research group uses symbolic and probabilistic tools to represent and construct coherent visual discourse and apply generative techniques for automated and semi-automated tools to interpret and collaboratively create visual narratives. Past projects include development of games for eliciting aesthetic preferences in domains such as photographic composition, aesthetics of play for highly skilled game players, and gestural aesthetics of dance.
Jhala holds a Ph.D. in computer science from NC State and bachelor’s degree in computer engineering from Gujarat University in India. Prior to joining NC State, Jhala served as one of the founding faculty members of the Computational Media Department at University of California, Santa Cruz. He has worked at a variety of institutions including the IT University of Copenhagen, University of Southern California’s Institute for Creative Technologies, Duke University’s Talent Identification Program(TIP), Virtual Heroes Inc. — a leading serious games developer, and the Indian Space Research Organization’s Space Applications Center.
Reactive Planning Techniques and Programming Idioms for Game AI
This talk will provide a brief review of current AI planning techniques in games and focus on implementation and programming idioms from two AI projects, a Starcraft bot — EISBot and a Skyrim NPC mod — SocialNPCs. EISBot uses an agent programming language ABL (A Behavior Language) that was developed for the interactive drama Facade. One of the challenges for AI in RTS games is reasoning along multiple competencies and scales. EISBot handles this through message passing idioms across ABL behaviors to dynamically generate behavior trees. I will present recent results on using gameplay traces to learn behavior preconditions to reduce authorial burden. Planners for NPC behavior for narrative-based games require knowledge representation of social interactions and reasoning about social context to achieve emergent behavior. The SocialNPCs Skyrim mod implements a social reasoning architecture called Comme il Faut (CiF) that embeds social reasoning knowledge into Skyrim’s Creation Kit. I will describe implementation of CiF in Papyrus script and some idioms for scaling up the architecture.