# Simulation of collision avoidance behavior in crowd movement by data-driven approach

arXiv: https://arxiv.org/abs/2605.31210 · HTML: https://mlsanity.com/paper/2605.31210/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 46 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [Human Trajectory Prediction via Neural Social Physics](https://mlsanity.com/paper/2207.10435/) (2022)
- [Human Trajectory Forecasting with Explainable Behavioral Uncertainty](https://mlsanity.com/paper/2307.01817/) (2023)
- [Visual-information-driven model for crowd simulation using temporal convolutional network](https://mlsanity.com/paper/2311.02996/) (2023)
- [Improved visual-information-driven model for crowd simulation and its modular application](https://mlsanity.com/paper/2504.03758/) (2025)

## Abstract (arXiv)

Crowd movement simulation is essential for pedestrian safety management and facility layout optimization. Data-driven models enhance trajectory prediction accuracy under Euclidean metrics, yet they suffer from excessively high collision rates, especially in bidirectional and multidirectional flows. In this paper, we establish a novel data-driven crowd simulation model that incorporates the pedestrian collision mechanism into the loss function to reduce collisions. A new lateral-acceleration-based collision loss function and a Voronoi-based motion feature extraction approach are proposed. The model is based on a Generative Adversarial Network (GAN) architecture and is termed CPGAN (Collision-Penalized GAN). We evaluate CPGAN in bidirectional flow scenarios, which involve frequent collision avoidance behaviors. Results show that the proposed lateral-acceleration-based collision loss significantly reduces opposite-direction pedestrian collision rates to levels comparable with controlled experiments. CPGAN effectively simulates bidirectional flow, reproducing lane formation and N-t curves. The research outcomes can provide inspiration for integrating pedestrian dynamics mechanisms into loss functions in data-driven crowd simulation.