A Conceptual Framework for Modelling Crowd Behaviour

Abstract

This paper presents a framework for modelling emotionally driven, context aware crowd behaviour in real time. It explores a scalable approach for applying dynamic drives to the behaviour of the crowd members, allowing their agendas to be changed according to context. A survey of previous work on crowd modelling, emotion modelling and large-scale multi-agent systems leads to the definition of a conceptual framework, which is applied to a prototype system for building the agendas of people in a railway station environment. The system is evaluated by varying the emotional drives, to assess the impact on agenda-building, and tested for real-time performance, in order to evaluate the scalability of the framework.