Some new links to papers have been added to our database and now appear on our Papers and Presentations page. All of these papers are from past years of the Artificial Intelligence in Interactive Digital Entertainment (AIIDE) conference sponsored by the AAAI. The papers added are:
Agent Architecture Considerations for Real-Time Planning in Games – Jeff Orkin, AIIDE 2005
Abstract: Planning in real-time offers several benefits over the more typical techniques of implementing Non-Player Character (NPC) behavior with scripts or finite state machines. NPCs that plan their actions dynamically are better equipped to handle unexpected situations. The modular nature of the goals andactions that make up the plan facilitates re-use, sharing, and maintenance of behavioral building blocks. These benefits, however, come at the cost of CPU cycles. In order to simultaneously plan for several NPCs in real-time, while continuing to share the processor with the physics, animation, and rendering systems, careful consideration must taken with the supporting architecture. The architecture must support distributed processing and caching of costly calculations. These considerations have impacts that stretch beyond the architecture of the planner, and affect the agent architecture as a whole. This paper describes lessons learned while implementing real-time planning for NPCs for F.E.A.R., a AAA first person shooter shipping for PC in 2005.
A Goal-Based Architecture for Opposing Player AI – Kevin Dill and Denis Papp, AIIDE 2005
Abstract: This paper describes a goal-based architecture which provides a single source for all high level decisions made by AI players in real-time strategy games. The architecture is easily extensible, flexible enough to be rapidly adapted to multiple different games, and powerful enough to provide a good challenge on a random, unexplored map without unfair advantages or visible cheating. This framework was applied successfully in the development of two games at TimeGate Studios – Kohan2: Kings of War and Axis & Allies.
Implementation of a Homegrown “Abstract State Machine” Style System in a Commercial Sports Game – Brian Schwab, AIIDE 2008
Abstract: When I began working at Sony Computer Entertainment of America in 2002, the AI system they were using was very dated. Over the next few years, I designed and developed an almost completely data driven system that has proven to be very powerful, extremely extensible, and designer friendly. This system uses a homegrown data structure, the use of which in many ways resembles the software method of using Abstract State Machines for decomposing complex logical constructs iteratively. This paper will provide an overview of the construction and usage of the system, as well as the pros and cons of this type of game AI engine.
Otello: A Next-Generation Reputation System For Humans and NPCs – Mike Sellers, AIIDE 2008
Abstract: This paper introduces Online Alchemy’s Otello technology as a way to enable reputational capabilities beyond any found in games or other online social contexts today. This technology allows participants to quickly and easily assess another’s reputation in ways meaningful to them, and enables individuals — both players and non-player characters (NPCs) — to contribute to an individual’s reputation in unique and novel ways. Otello also enables new forms of ‘relational gameplay’ that feature social management, effectively an extension of resource management into the social realm. The player’s actions and opinions affect others, including how they see the player, and how ideas and opinions propagate through a population.
Abstract: This talk describes the motivation, design and implementation behind the AI for the NPC Skateboarders in skate. The complexity of the physically driven locomotion used in skate means that, at any given point, there is an extremely large number of degrees of freedom in potential motion. In addition to this, the rules governing whether it is possible to navigate from any given point A to a secondary point B are entirely dependent on the skateboarder’s state at point A. The state required at point A involves a large number of variables, as well as a complex set of previously executed maneuvers to have reached it.
AI Wall Building in Empire Earth II – Tara Teich, Ian Davis, AIIDE 2006
Abstract: Real-Time Strategy games are among the most popular genres of commercial PC games, and also have widely applicable analogs in the field of Serious Games such as military simulations, city planning, and other forms of simulation involving multi-agent coordination and an underlying economy. One of the core tasks in playing a traditional Real-Time Strategy game is building a base in an effective manner and defending it well. Creating an AI that can construct a successful wall was one of the more challenging areas of development on Empire Earth® II, as building a wall requires analysis of the terrain and techniques from computational geometry. An effective wall can hold off enemy troops and keep battles away from the delicate economy inside the base.