Accelerating fuzzy cellular automata for modeling crowd dynamics

Abstract

Pedestrian and crowd dynamics are physical phenomena that are fundamentally characterized by non-linear complexity. In the same time, the need of modern way of living seeks for such dynamics real time modeling also enabling computationally efficient and affordable solutions for sake of safety and easiness of people located in gathering places all over the world. Towards this direction, Cellular Automata (CAs), a parallel computational model combining macro- and microscopic inherent attributes that could severely help with adequate modeling of the aforementioned dynamics, are one of the best compromises among different competing computational techniques. In order to overcome CAs deterministic nature, in this paper the incorporation of fuzzy logic principles in a CA model that simulates crowd dynamics and crowd evacuation processes, with the usage of a Mamdani type fuzzy inference system, is proposed. More specifically, basic concepts of fuzzy logic such as linguistic variables and if-then rules are attributed to the proposed CA model to preserve fuzzy consequents and fuzzy antecedents thus resulting in a realistic and rather efficient modeling approach. Furthermore, in the paper the implementation of fuzziness in CA dynamics is tackled with the acceleration of the proposed model through fully parallel execution on Graphics Processing Units (GPU). The GPU implementation of the fuzzy CA model is analyzed in full detail and stressed against CPU corresponding implementation resulting to an important speed up of fuzzy CA execution. This is further explored through the GPU applications of the fuzzy CA model in a real building, namely the museum `CONSTANTIN XENAKIS', in Serres, Greece.