Skip to Main content Skip to Navigation
Conference papers

Data-Driven Crowd Simulation with Generative Adversarial Networks

Abstract : This paper presents a novel data-driven crowd simulation method that can mimic the observed traffic of pedestrians in a given environment. Given a set of observed trajectories, we use a recent form of neural networks, Generative Adversarial Networks (GANs), to learn the properties of this set and generate new trajectories with similar properties. We define a way for simulated pedestrians (agents) to follow such a trajectory while handling local collision avoidance. As such, the system can generate a crowd that behaves similarly to observations, while still enabling real-time interactions between agents. Via experiments with real-world data, we show that our simulated trajectories preserve the statistical properties of their input. Our method simulates crowds in real time that resemble existing crowds, while also allowing insertion of extra agents, combination with other simulation methods, and user interaction.
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/hal-02134282
Contributor : Javad Amirian <>
Submitted on : Monday, May 20, 2019 - 4:49:14 PM
Last modification on : Wednesday, June 24, 2020 - 4:19:53 PM

File

CASA2019-DataDrivenCrowdSimula...
Files produced by the author(s)

Identifiers

Citation

Javad Amirian, Wouter van Toll, Jean-Bernard Hayet, Julien Pettré. Data-Driven Crowd Simulation with Generative Adversarial Networks. CASA '19 - International Conference on Computer Animation and Social Agents, Jul 2019, Paris, France. pp.1-4, ⟨10.1145/3328756.3328769⟩. ⟨hal-02134282⟩

Share

Metrics

Record views

98

Files downloads

983