|
An intelligent agent is an entity capable of combining cognition, perception and action in behaving autonomously, purposively and flexibly in some environment. One major class of intelligent agents we investigate is ones that access and manage distributed information and systems. Such agents provide information and assistance to both people and other software systems in network and web-based environments. A second major class we investigate is intelligent agents that behave, and frequently even look, like people. These virtual humans model, guide, educate, train, or entertain real people in simulation, web, and virtual environments. A third major class we investigate are robotic agents, which may include both mobile robots and distributed intelligent sensors, that often act as a group to accomplish complex tasks in real-world environments.
A Multiagent system is a cohort of intelligent agents and people capable of coordinating itself in behaving autonomously, purposively and flexibly in some environment. A multiagent system might consist of a set of web-based intelligent information agents that extract and integrate information from a set of distributed sources; a group of people and virtual humans working, or playing, together in a virtual world; or a combination of people and intelligent interface agents (to people and other software and hardware systems) that provide a coordinated virtual enterprise embedded in the real world.
|
|
