Modelling Human Behaviour at Work using Fuzzy Logic: The Challenge of Work Teams Configuration

One of the first steps in the planning of a new engineering project in industry is its partition into subtasks and the configuration of a work team to execute it. This decision making process is typically performed by a project manager based on his/her past experience and the available (though frequently scarce, uncertain and dynamic) information about the cognitive and personal characteristics of the available team members. This paper presents our first results in the development of a knowledge-based tool that aims to help project managers in their decision-making process. Software agents are used to model social human behaviour at work, where human characteristics are represented by a set of fuzzy values, and fuzzy rules model the interaction between the agents to generate the possible performance of a work team. As a first validation step, a comparison of the results predicted by our model with the performance of an engineering team in a real industrial project is made