|Presentation Date||April 13, 2013|
|Topic(s)||FEAR and It's Innovative Game AI|
F.E.A.R.: First Encounter Assault Recon is a first-person shooter where the player helps contain supernatural phenomenon and armies of cloned soldiers. One of its particular claims to fame is its innovations in artificial intelligence in video games. Some of the innovations in AI include using a planner to generate context-sensitive behaviors, which was a first in a mainstream game. This technology used as a reference for many studios still today. Another innovation is that enemies are capable of using the environment very cleverly depending on the situation and using the environment for their own gain, such as finding cover behind tables, tipping bookshelves, opening doors, and crashing through windows. Lastly, squad tactics are used to great effect. The enemies perform flanking maneuvers, use suppression fire, and interaction with one another in order to fight the player.
The planner described above works by analyzing dependencies of each action, and figuring out how to realize them. For example, enemies can satisfy the goal of eliminating a threat by firing a gun at the threat, but to fire the gun, it needs to be loaded, or we can use a melee attack, but we have to move close enough to attack. By spending more time to develop a planner, less work is required to implement specific behaviors. To simulate squad behavior, the developers used one “AI programmer”, in which it the programming of AI was delegated to the AI itself. The effort required to build the many different AI characters and squad behaviors was reduced because of it. Other small innovations were used to help develop the AI, including a dynamic blackboard where multiple facts can be added dynamically, based on events that happen in the world around each AI actor, as well as the sharing of data between multiple different behaviors and goals.
Jeff Orkin, “Three States and a Plan: The A.I. of F.E.A.R.” MIT Media Lab, Cognitive Machines Group, 2006. http://web.media.mit.edu/~jorkin/gdc2006_orkin_jeff_fear.pdf
Jeff Orkon, “Agent Architecture Considerations for Real-Time Planning in Games” Monolith Productions, 2005 http://web.media.mit.edu/~jorkin/aiide05OrkinJ.pdf
Alex J. Champandard, “Top 10 Most Influential AI Games”, AIGameDev.com, 2007. http://aigamedev.com/open/highlights/top-ai-games/