Fluid dynamics-Like Open-source Crowd Knowledge-driven Simulator (FLOCKS)

As urban areas become more densely populated, effectively managing and predicting pedestrian dynamics is critical in areas such as public safety, architecture and transportation. For example, crowd managers could quickly assess different escape routes during an evacuation to minimise injuries; architectural design can be optimised by considering the dynamics of pedestrian movement; and the development of autonomous vehicles could benefit from a better understanding of how people navigate crowded urban spaces. However, current simulation tools lack the ability to model large, dense crowds in real time. On the one hand, the agent-based approach, in which pedestrians are modelled individually, is so computationally expensive that it makes real-time crowd management impossible. On the other hand, current models that liken crowds to continuum 'thinking fluids' are severely limited in their accuracy because, in order to obtain a closed system of equations, they typically make simplistic assumptions about constitutive relationships, such as that relating the local speed of pedestrians at a point to the state of the crowd in the area around that point. This proposal will derive the first fluid dynamics-like crowd model using a data-driven modelling technique to combine the scalability of the continuum description with the accuracy of data-driven approaches. As the opaque 'black box' models provided by most machine learning methods are not suitable for high stakes applications such as those involving crowds, a novel machine learning approach will be developed that extends the current ability to distil mathematical expressions from the data. We will use two complementary data sources - firstly, surrogate pedestrian models, as these provide clean datasets from controlled experiments that are ideal for developing the machine learning tools, and secondly, real crowd observation data to ensure the accuracy of the distilled model. Integrating this model into OpenFOAM (a widely used open-source computational fluid dynamics platform) will create the first high-fidelity simulator of large, dense crowds in real time. The simulator is expected to significantly reduce the time required for crowd management planning, optimise architectural design for better pedestrian flow, and improve the navigation of autonomous vehicles in crowded urban areas, ultimately reducing the risk of crowd related accidents and injuries, which sadly increase every year (an updated list can be found here). The applicant will lead a research team consisting of a postdoctoral research associate (funded by this grant) and a PhD student (funded by the University of Edinburgh). An experienced academic partner will act as a mentor, ensuring effective project management and providing expertise in the application of machine learning tools to fluid dynamics. Two industrial partners will also be involved in the project: Buro Happold's expertise in pedestrian flow analysis will be integrated into the machine learning tools, while ESI-OpenCFD's expertise in fluid dynamics will facilitate the seamless integration of the simulator into OpenFOAM. The results of the project will be disseminated through high impact papers, conference presentations, public engagement at festivals and the open-source release of the simulator. FLOCKS is expected to have a significant impact on the events industry by reducing the time required for crowd management planning and the percentage of crowd related accidents or injuries. The high level of interest shown by the industry partners in their letters of support underlines the importance of the project and their commitment to its success.