APPLICTIONS OF INTELLIGENT AGENTS

 

Intelligent agents are the next major computing paradigm and will be pervasive in every market by the year 2000. Agents can be applied in a wide range of applications and they include the following applications.
  1. Industrial Applications
    2.

Industrial applications of agent technology were among the first to be developed: as early as 1987, Parunak reports experience with applying the contract net task allocation protocol in a manufacturing environment. Agents, are today being applied in a wide range of industrial applications. These include:

1.1 Process Control:Process control is a natural application for intelligent agents and multi-agent systems, since process controllers are themselves autonomous reactive systems. The best known agent-based process control applications is ARCHON. It is a software platform for building multi-agent systems. ARCHON has been applied in several process control applications, including electricity transportation management and particle accelerator control. It also has the distinction of being one of the earliest field-tested multi-agent systems in the world.

1.2 Manufacturing :Parunak (1987) describes the YAMS (Yet Another Manufacturing System), which applies the well-known Contract Net Protocol (Smith 1980) to manufacturing control.YAMS adopts a multi-agent approach, where for instance each factory and factory component in a company is represented as an agent. Each agent has a collection of plans, representing its capabilities.
  1. Air Traffic Control: OASIS is a sophisticated agent-realized air traffic control system. In this system, which is undergoing field trials at Sydney airport in Australia, agents are used to represent bothaircraft and the various air traffic control systems in operation. As an aircraft entersSydney airspace, an agent is allocated for it, and the agent is instantiated with theinformation and goals corresponding to the real world aircraft.

3 Commercial Applications

3.1 Information management

In this situation agents carry out searches on behalf of the user by acting autonomously. Among the many projects, there are three projects which describes how agents can act autonomously. These are:

Maxims: (Maes, 1994) describes an electronic mail filtering agent called Maxims. The program ‘learns to prioritorize, delete, forward, sort, and archive mail messages on behalf of a user’ (p.35).

Newt: (Maes, 1994) also describes an example of an Internet news filtering program called Newt. This program, implemented in C++ on a UNIX platform, takes as input a stream of usenet news articles, and as output gives a subset of these articles that is recommended the user reads.

The Zuno Digital Library: The Zuno Digital Library (ZDL) system is a multi-agent system that enables a user to obtain a single, coherent view of incoherent, disorganised data sources such as World Wide Web, a user’s own data, collections of articles on publishing house sites, and so on (Zuno, 1997).

3.2 Electronic Commerce: Commercial decision making can be placed in the hands of agents. Widespread electronic commerce is likely to lie some distance in the future but in the near term, electronic trading applications are likely to be much more mundane and small scale.
  1. Medical Applications: Medical informatics is a major growth area in computer science: new applications are being found for computers every day in the health industry. Therefore, it is not surprising, that agents should be applied in this domain. Two of the earliest applications are in the areas of health care and patient monitoring.
  2. Entertainment. Games: There are several applications of agent technology to computer games(Wavish and colleagues). For instance, they have developed a version of the popular Tetris computer game, where a user must try to make a wall out of irregularly shaped falling blocks. The agent in the game takes the part of the user, who must control where the blocks fall. This approach (using traditional symbolic AI techniques) would be entirely unrealistic for a game like Tetris which has had real-time constraints. Alternatively, a reactive agent called RTA (Real Time Able) can be used. In this approach, agents are programmed in terms of behaviours. Interactive Theater and Cinema: Interactive theater and cinema means, a system that allows a user to play out a role analogous to the roles played by real, human actors in plays or films, interacting with artificial , computer characters that have the behavioural character of real people.

HOME | INTRODUCTION | WHAT IS AN AGENT| EXAMPLES |

|WHY DO WE NEED AGENTS | AGENTS AND SEARCH ENGINES| LIMITATIONS OF AGENTS|

|APPLICATIONS OF INTELLIGENT AGENTS | FUTURE OF AGENTS | REFERENCES|