A Data-driven Crowd Simulation Framework Integrating Physics-informed Machine Learning with Navigation Potential Fields

TL;DR

This work proposes a novel data-driven crowd simulation framework that integrates physics-informed machine learning (PIML) with navigation potential fields and exhibits enhanced adaptability and superior interpretability compared with methods that rely solely on deep learning for trajectory generation.

Abstract

Traditional rule-based physical models are limited by their reliance on singular physical formulas and parameters, making it difficult to effectively tackle the intricate tasks associated with crowd simulation. Recent research has introduced deep learning methods to tackle these issues, but most current approaches focus primarily on generating pedestrian trajectories, often lacking interpretability and failing to provide real-time dynamic simulations.To address the aforementioned issues, we propose a novel data-driven crowd simulation framework that integrates Physics-informed Machine Learning (PIML) with navigation potential fields. Our approach leverages the strengths of both physical models and PIML. Specifically, we design an innovative Physics-informed Spatio-temporal Graph Convolutional Network (PI-STGCN) as a data-driven module to predict pedestrian movement trends based on crowd spatio-temporal data. Additionally, we construct a physical model of navigation potential fields based on flow field theory to guide pedestrian movements, thereby reinforcing physical constraints during the simulation. In our framework, navigation potential fields are dynamically computed and updated based on the movement trends predicted by the PI-STGCN, while the updated crowd dynamics, guided by these fields, subsequently feed back into the PI-STGCN. Comparative experiments on two publicly available large-scale real-world datasets across five scenes demonstrate that our proposed framework outperforms existing rule-based methods in accuracy and fidelity. The similarity between simulated and actual pedestrian trajectories increases by 10.8%, while the average error is reduced by 4%. Moreover, our framework exhibits greater adaptability and better interpretability compared to methods that rely solely on deep learning for trajectory generation.

Figures (11)

• Figure 1: A multi-agent crowd simulation framework based on Physics-informed Machine Learning and navigation potential fields.
• Figure 2: The structure of the Physics-informed Spatio-temporal Graph Convolutional Network.
• Figure 3: Discretization of the environment with regular two-dimensional grids. (a) Crowd environment. (b) Discretized grids.
• Figure 4: Potential fields generated by different types of sources. (a) Source that attracts crowds. (b) Source that repels crowds.
• Figure 5: Calculate navigation potential fields based on the predicted results of pedestrian's position distribution. (a) Sampling based on the predicted position distribution function. (b) Moving trend line. (c) Guiding direction vector. (d) Navigation potential field.