Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Mapping the Urban Mobility Intelligence Frontier: A Scientometric Analysis of Data-Driven Pedestrian Trajectory Prediction and Simulation

Junhao Xu, Hui Zeng

TL;DR

This paper maps the evolution of data-driven pedestrian trajectory prediction and crowd simulation through a scientometric analysis of 560 Web of Science-indexed publications up to 2025. It combines SciExplorer and Bibliometrix to characterize growth, interdisciplinarity, geography, venues, and thematic frontiers, highlighting shifts from physics-inspired to deep learning and graph-based methods. Key findings include strong global collaboration, dominant contributions from Computer Science and Engineering, and emergent frontiers in graph neural networks, transformers, and generative models with urban mobility applications. The study underscores the practical impact on urban planning, safety, and digital twin development, while calling for improved interpretability, inclusivity, and cross-domain transferability to ensure socially responsible mobility intelligence in future cities.

Abstract

Understanding and predicting pedestrian dynamics has become essential for shaping safer, more responsive, and human-centered urban environments. This study conducts a comprehensive scientometric analysis of research on data-driven pedestrian trajectory prediction and crowd simulation, mapping its intellectual evolution and interdisciplinary structure. Using bibliometric data from the Web of Science Core Collection, we employ SciExplorer and Bibliometrix to identify major trends, influential contributors, and emerging frontiers. Results reveal a strong convergence between artificial intelligence, urban informatics, and crowd behavior modeling--driven by graph neural networks, transformers, and generative models. Beyond technical advances, the field increasingly informs urban mobility design, public safety planning, and digital twin development for smart cities. However, challenges remain in ensuring interpretability, inclusivity, and cross-domain transferability. By connecting methodological trajectories with urban applications, this work highlights how data-driven approaches can enrich urban governance and pave the way for adaptive, socially responsible mobility intelligence in future cities.

Mapping the Urban Mobility Intelligence Frontier: A Scientometric Analysis of Data-Driven Pedestrian Trajectory Prediction and Simulation

TL;DR

This paper maps the evolution of data-driven pedestrian trajectory prediction and crowd simulation through a scientometric analysis of 560 Web of Science-indexed publications up to 2025. It combines SciExplorer and Bibliometrix to characterize growth, interdisciplinarity, geography, venues, and thematic frontiers, highlighting shifts from physics-inspired to deep learning and graph-based methods. Key findings include strong global collaboration, dominant contributions from Computer Science and Engineering, and emergent frontiers in graph neural networks, transformers, and generative models with urban mobility applications. The study underscores the practical impact on urban planning, safety, and digital twin development, while calling for improved interpretability, inclusivity, and cross-domain transferability to ensure socially responsible mobility intelligence in future cities.

Abstract

Understanding and predicting pedestrian dynamics has become essential for shaping safer, more responsive, and human-centered urban environments. This study conducts a comprehensive scientometric analysis of research on data-driven pedestrian trajectory prediction and crowd simulation, mapping its intellectual evolution and interdisciplinary structure. Using bibliometric data from the Web of Science Core Collection, we employ SciExplorer and Bibliometrix to identify major trends, influential contributors, and emerging frontiers. Results reveal a strong convergence between artificial intelligence, urban informatics, and crowd behavior modeling--driven by graph neural networks, transformers, and generative models. Beyond technical advances, the field increasingly informs urban mobility design, public safety planning, and digital twin development for smart cities. However, challenges remain in ensuring interpretability, inclusivity, and cross-domain transferability. By connecting methodological trajectories with urban applications, this work highlights how data-driven approaches can enrich urban governance and pave the way for adaptive, socially responsible mobility intelligence in future cities.

Paper Structure

This paper contains 13 sections, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Study Aims
  4. Journal selection
  5. Data Analysis Tools
  6. Results
  7. R1
  8. R2
  9. R3
  10. R4
  11. R5
  12. Discussion and Conclusion
  13. Data availability

Figures (4)

  • Figure 1: Literature statistics overview.
  • Figure 2: Global Map of Science, with different colors representing distinct disciplines.
  • Figure 3: Geographic distribution of corresponding authors, collaboration patterns (SCP vs. MCP), and citation impact. SCP = Single Country Publications, MCP = Multiple Country Publications.
  • Figure 4: Research Hotspots and Intellectual Evolution in Data-Driven Pedestrian Trajectory Prediction and Simulation.