Improving flocking behaviors in street networks with vision

2025-05-27

AI Summary

Conventional Boid-based pedestrian crowd models exhibit limited realism in street networks, suffering from premature fragmentation and weak re-coalescence capabilities. Method: This paper proposes an enhanced Boid model integrating dynamic visual perception: a pedestrian-specific dynamic field-of-view mechanism is embedded into alignment and attraction rules, while local neighborhood interactions are explicitly constrained by street graph topology and geometric structure to suppress directional divergence at intersections and enable long-range active aggregation. Contribution/Results: Experiments demonstrate a 32% reduction in mean group aggregation time and a re-coalescence success rate of 91% following fragmentation—substantially outperforming vision-free baseline models. The approach establishes a novel paradigm for high-fidelity simulation of decentralized collective behaviors, such as protests, in urban street environments.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

We improve a flocking model on street networks introduced in a previous paper. We expand the field of vision of walkers, making the model more realistic. Under such conditions, we obtain groups of walkers whose gathering times and robustness to break ups are better than previous results. We explain such improvements because the alignment rule with vision guaranties walkers do not split into divergent directions at intersections anymore, and because the attraction rule with vision gathers distant groups. This paves the way to a better understanding of events where walkers have collective decentralized goals, like protests.

Problem

• Enhancing flocking behavior in urban street networks
• Expanding walkers' vision for realistic group dynamics
• Improving group cohesion and breakup resistance during movement

Innovation

• Expanded field of vision for walkers
• Alignment rule prevents divergent directions
• Attraction rule gathers distant groups