Multi-agent geospatial simulation of human interactions and behaviour in bushfires.

Lyuba Mancheva 1 Carole Adam 2 Julie Dugdale 3
3 LIG Laboratoire d'Informatique de Grenoble - HAwAI
Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology, CNRS - Centre National de la Recherche Scientifique : UMR 5217, UGA - Université Grenoble Alpes
Abstract : Understanding human behaviour and interactions in risk situations may help to improve crisis management strategies in order to avoid the worst scenarios. In this paper we present a geospatial agent-based model and simulation of human behaviour in bushfires. We have modelled the social interactions between different actors involved in bushfires such as firefighter, police, emergency centre managers and civilians. We use the Belief, Desire and Intention (BDI) architecture to model realistic human behaviour, and the FIPA-ACL standard to model the communications. We use geospatial data to represent the environment in a realistic way. We show how the model has been implemented and how we have unified the communications model and the BDI architecture. Finally, we compare the processing time of two implementations of our model representing a 2D simple and a 3D GIS environment.
Document type :
Conference papers
Complete list of metadatas

Cited literature [33 references]  Display  Hide  Download
Contributor : Julie Dugdale <>
Submitted on : Tuesday, June 11, 2019 - 5:25:05 PM
Last modification on : Thursday, October 24, 2019 - 10:35:27 AM


  • HAL Id : hal-02091660, version 1



Lyuba Mancheva, Carole Adam, Julie Dugdale. Multi-agent geospatial simulation of human interactions and behaviour in bushfires.. International Conference on Information Systems for Crisis Response and Management, May 2019, Valencia, Spain. ⟨hal-02091660⟩



Record views


Files downloads