PedNStream: Scalable Network Flow Simulation for Pedestrian Traffic Management
06:00 · July 2, 2026 · arXiv cs.AI RSS
Large-scale crowd management requires pedestrian simulations that are both computationally efficient and compatible with feedback-based control. However, most open-source tools are either microscopic or not designed for network-scale closed-loop evaluation. This paper presents PedNStream (Pedestrian Network Flow Simulation), an open-source, Python-native simulator for macroscopic pedestrian network loading based on the Link Transmission Model (LTM). The framework extends LTM-based pedestrian models by incorporating stochastic link dynamics that capture diffusion and activity-induced variability, and replaces dynamic user equilibrium route choice with a utility-based formulation suited to uncertain, intervention-driven settings. PedNStream is implemented as a modular framework with built-in controller interfaces for interventions such as gating, flow separation, and route guidance. We evaluate the framework in a staged manner. Synthetic scenarios verify key mechanisms, including queue formation, spillback, congestion dissipation, and adaptive rerouting. Real-network experiments assess large-scale behavior and consistency with observed pedestrian counts. A closed-loop case study demonstrates controller integration, and a runtime analysis quantifies scalability. These results establish PedNStream as an efficient and practical testbed for large-scale pedestrian network simulation and control.
Summary
Large-scale crowd management at events or in urban settings demands simulations that remain computationally tractable while supporting real-time feedback control, yet most existing open-source tools are either microscopic agent-based models or lack native support for network-scale closed-loop evaluation. PedNStream addresses this gap as an open-source, Python-native framework for macroscopic pedestrian network loading built on the Link Transmission Model. It extends earlier LTM formulations by adding stochastic link dynamics that represent diffusion effects and activity-induced flow variability, and it substitutes dynamic user equilibrium route choice with a utility-based formulation better suited to uncertain or intervention-driven conditions.
The framework is structured as a modular package that exposes controller interfaces for common operational measures such as gating, flow separation, and route guidance. This design enables direct integration of control algorithms that update interventions on the basis of evolving network states. Evaluation proceeds in stages: synthetic test cases confirm core mechanisms including queue formation, spillback, congestion dissipation, and adaptive rerouting; real-network experiments compare simulated flows against observed pedestrian counts; a closed-loop case study verifies controller integration; and runtime profiling quantifies scalability across network sizes.
By positioning itself at the macroscopic level with explicit support for control-oriented workflows, PedNStream complements rather than replaces microscopic simulators such as JuPedSim or Vadere and multimodal platforms such as SUMO or MATSim. The source code and installable package are publicly released, providing a reproducible testbed for researchers developing network-wide pedestrian management strategies.
Why it matters
This research is highly relevant to the Dutch AI market as it is authored by prominent researchers from TU Delft and addresses smart city and crowd management challenges prevalent in dense Dutch urban areas. The open-source Python framework provides actionable, scalable tools for local AI practitioners and urban planners.
