Artificial Intelligence: Commercial Middleware
Through its tight integration with in-game physics engines, AI.implant offers massive destructibility in physical worlds, making it easier to radically change the game environment during game-play. Using AI.implant, game developers can create dynamic environments as well as characters who are so aware of their surroundings that they can make informed decisions based on input from any given situation. AI.implant - the only AI Middleware to win the Frontline award ... twice.
Artificial Contender™ (AC) is an AI technology, AI middleware and set of tools that introduces a new type of AI agent to games - learning, adaptable AC agents capable of behavior-capture. AC agents learn the playing styles of humans and adapt to achieve set goals if required. AC is not a "black-box". As the technology deploys instance-based reasoning (reasoning by example) principles, all decisions made by AC agents are transparent and easily explainable even to non-programmers. Artificial Contender's learning and decision making takes place in real time and - crucially - is economical with system resources.
DirectIA® stands for "Direct Intelligent Adaptation". It is the world's first generic artificial life & behavior SDK. DirectIA® was built to create agents that adapt to unpredictable situations (situations which were neither predicted nor programmed), look alive and seem to have intelligent behaviors. At its higher level, DirectIA® is a motivational system , that is, a system that can be viewed as a set of motivations which compete over what should be done. The best analogy for DirectIA® technology is a highly connected and flexible graph, which allows activity propagation similar to the propagation in a brain.
AIseek provides innovative technologies to power tomorrow’s computer games. AIseek's flagship product, the IntiaTM processor, is the first dedicated processor for artificial intelligence (AI). By accelerating and optimizing behavioral computations, the Intia processor empowers developers to build entirely new game worlds, populated by intelligent life. By accelerating CPU-intensive, low-level AI routines, AIseek frees developers to create sophisticated, higher-level AI on a massive scale. Moreover, with accelerated AI, game worlds can be large, complex and constantly changing without compromising on the number or intelligence of the NPCs inhabiting those worlds.
Kynogon markets Kynapse for games the most widely used A.I. middleware within the game development community with clients such as A2M, Atari, Digital Illusion CE, Electronic Arts, Lionhead Studios, Real Time World, Spark Unlimited, SEGA, Turbine, etc. Kynapse for games also exists as integrated into the Unreal Engine 3 developed by Epic Games. It brings innovation (3D dynamic topology analysis, hierarchical 3D dynamic pathfinding, ...) as well as efficient production tools (automatic pathfinding and perception data generator, ...).
LiveCombat gives you the power to build AI characters that learn how to behave by observing the actions of human players. It provides very deep learning that occurs in real time while you play. Your AI characters learn in seconds to be trusted companions or deadly foes. LiveCombat is ideal for action games that emphasize hand-to-hand combat and/or squad-based games that involve larger-scale battles. LiveCombat employs breakthrough machine learning technology that models human game play in real-time. The models are behavior policies that represent decision-making in millions upon millions of distinct game contexts.
LiveMove is a motion recognizer for the Nintendo Wii. # Create motion recognizers with LiveMove in minutes simply by showing examples of motions; no coding or scripting is required. At run time, a motion recognizer can robustly determine which motion a player is performing from the set of developer-provided examples. Recognize up to 40 different motions on 8 Wii remotes or nunchuks simultaneously using less than 5% of the Wii CPU. Total memory usage is typically below 700K.
PathEngine is a sophisticated middleware tool-kit for the implementation of intelligent agent movement, built around an advanced implementation of points-of-visibility pathfinding on 3D ground surfaces. At the heart of the SDK is a well-defined agent 'movement model', with pathfinding and collision both provided in tight integration against this movement model. This kind of integrated collision architecture is key to the implementation of fundamentally robust movement. The toolkit also comes with powerful content processing and ground management functionality, a graphical testbed and associated tools.
SimBionic® is an award-winning AI middleware tool that simplifies the process of creating intelligent behavior for games and simulations. Using SimBionic, you can specify how game characters and simulated entities dynamically react to events and player actions. SimBionic enables everyone on the development team to write smarter behaviors that are more realistic, challenging, and engaging. By accelerating development and encouraging collaboration, SimBionic increases productivity and frees your team to focus on innovation.
The xait-Engine is a modular AI Engine that controls the bots in computer games. It is based on a multiagent system that allows simple implementation of autonomous and intelligent bots. A multiagent system provides a platform that enables each single agent/bot to work together with the other agents/bots in a team. The game designer can assign different skill sets to various bots. Complex goals can then be reached by applying these skills and individual knowledge cooperatively. The modular architecture of the xait-Engine includes a core system and genre specific components for different game genres and crossovers.