A BDI approach to agent-based modelling of pedestrians

The modelling of pedestrian behaviour in a real-world environment is a complex problem, mainly due to the unpredictable nature of human decision making. Agentoriented simulation moves away from the traditional allknowing and 'controlling' simulations and towards reality, where pedestrians exhibit different behaviours depending on their knowledge of the environment and other personal characteristics. We look the behaviours that pedestrians may exhibit and the different techniques used for pedestrian modelling. We then explore whether the belief-desire-intention (BDI) architecture is appropriate for this domain. The simulation requirements and constraints are presented, followed by a high-level conceptual design using Prometheus, an agent-oriented design methodology, and a discussion of the implementation using JACK, an agent-oriented programming language based on the BDI architecture. Although the BDI architecture is useful for high-level decision making, further work is required in representing and updating the environment.