X. Yu, B. Ram, D. Mountjoy, and J. Russell (USA)
Agent-based simulation, distributed team training
Team members in a single project may often be physically located in separate geographical areas. It can be costly to schedule and bring team members together. It is difficult to form a common mental model of the environment in a team when expertise differs from member to member. Intelligent agent technique is promising to deal with these issues by its power in distributed problem solving, redundant information storage, and automatic learning and making decision. This paper describes the ways in which modeling and simulation are used to explore the possibilities for distributed team training using agents. A simulation platform for multi-agent based training is proposed in order to eliminate the scheduling issues and expenses associated with training distributed team members. A production planning team is used as the example to demonstrate the modeling procedure. Four functions included in the team are represented by their corresponding agents that are located in geographically distributed machines. The platform has the ability to substitute a real person for one or more of these functions. The objective of this research is to exploit the details of building training platform using agent based simulation, and evaluate the effectiveness of such training using human subjects.
Important Links:
Go Back
