Recap of the Seventh AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE)
Bulitko, Vadim, Riedl, Mark, Jhala, Arnav, Buro, Michael, Sturtevant, Nathan, AI Magazine
The Seventh AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE) was held October 10-14, 2011, at Stanford University, adjacent to Palo Alto, California. AIIDE is a premier interaction forum for researchers in artificial intelligence and interactive entertainment. The conference, which includes a research and industry track as well as a demonstration program, aims at bringing together both academic and industrial communities for the purpose of idea exchange and networking.
For the first time in AIIDE's history, the main program of the conference was preceded by three workshops: Intelligent Narrative Technologies workshop, the workshop on Nonplayer Character AI, and the Artificial Intelligence in the Game Design Process workshop. All three attracted a substantial audience and led to exciting debates and fruitful discussions (figure 1). In total, 24 papers were presented in the three workshops. The Intelligent Narrative Technologies workshop included papers on story representation, dialogue generation, narrative visualization, and authoring interfaces for interactive narrative, and a panel on corpus-based approaches to modeling narrative. The Intelligent Narrative Technologies and the Nonplayer Character AI workshops shared a session on intelligent virtual characters. The Artificial Intelligence in the Game Design Process workshop was attended by a number of game industry AI programmers and included papers on automated design, procedural content generation, and intelligent tools for assisting in the game design process. This workshop also featured a panel on how humans and machines can complement each other during the design process and a hands-on session on designing games with AI and procedurally generated content. The overall workshop program was successful due to the hard work of the cochairs of all workshops, their respective program committees, and attendees.
[FIGURE 1 OMITTED]
The main program featured 17 paper presentations, 17 posters, three demonstrations, and five invited speakers. The conference also hosted the second StarCraft AI competition, which, once again, was an exciting highlight of the conference. In addition, the conference had two panels on topics of relevance to the community: the first on the StarCraft AI competition and its implications on AI, and a second on data mining player behavior in games.
The main program started on Wednesday, October 12, 2011, with a highly anticipated talk by Bob Fitch from Blizzard Entertainment. The main figure behind the AI in the StarCraft and WarCraft series lifted the curtain and showed the inner workings of the pathfinding and combat algorithms in the renown series, as well as their evolution over the years. Fitch's talk was followed up with a session on planning in games. The afternoon opened with the second invited talk by Akhil Madhani, Walt Disney Company Research and Development. Full of exciting multimedia and a host of trivia, Madhani took the audience on a walk through the backstage of Disney, showing the challenges of creating animatronic versions of Disney's movie Characters such as WALL-E. While the current incarnations are puppeteered, there are numerous opportunities for AI controllers and assistants. After Madhani's talk, Michael Buro and David Churchill introduced the second AI StarCraft competition and presented two prerecorded exhibition games of the tournament winner playing against a strong amateur player. Both games were won by the human. The presentation was followed by a session on character agents. Workshop reports and a reception closed the day.
The reception featured an award presentation (figure 2) which recognized the best paper, the best student paper, and the best reviewer. The best paper award was awarded to Eun Ha, Jonathan Rowe, Bradford Mott, and James Lester of North Carolina State University for their use of Markov logic networks to infer player behavior in serious games. …