Crowd Simulation: A Multi-Dimensional Systematic Mapping Study and Taxonomy

Crowd simulation is essential for applications in evacuation planning, transportation systems, urban analytics, virtual reality, and intelligent mobility. Despite substantial progress, research in this field remains fragmented across diverse modeling paradigms, behavioral abstractions, simulation settings, implementation tools, and evaluation practices. To provide a unified overview, this study conducts a Systematic Mapping Study (SMS) of 54 peer-reviewed primary studies published between 2021 and 2025. Guided by a structured set of 15 research questions, the SMS examines dominant modeling paradigms, associated modeling techniques, spatial representations, behavioral layers, learning methods, and agent capabilities. The study further analyses simulation characteristics—including behavior types, granularity levels, temporal modes, environment types, and application domains—alongside implementation aspects such as programming tools and simulation platforms. Additionally, the mapping covers evaluation practices by identifying reported performance metrics and methodological approaches. Based on the extracted evidence, we propose a comprehensive taxonomy. The results highlight prevailing trends, gaps, and fragmentation in crowd simulation research, including uneven reporting of metrics, limited integration of learning-based methods, and inconsistencies in behavioral modeling. The study also synthesizes key technical challenges and corresponding solutions proposed in recent literature, offering a structured foundation for future research.