Scenario Generalization of Data-driven Imitation Models in Crowd Simulation

TL;DR

This paper investigates how different training data and methods affect the ability of imitation models to generalize in crowd simulation, demonstrating that simpler methods and diverse training data improve performance in new scenarios.

Contribution

It introduces a comparative analysis of Behavior Cloning and GAIL in crowd simulation, emphasizing the importance of diverse training data for better generalization.

Findings

Simpler training methods outperform complex ones.

Diverse training data reduces collisions in new scenarios.

Models trained on representative data generalize to real-world crowds.

Abstract

Crowd simulation, the study of the movement of multiple agents in complex environments, presents a unique application domain for machine learning. One challenge in crowd simulation is to imitate the movement of expert agents in highly dense crowds. An imitation model could substitute an expert agent if the model behaves as good as the expert. This will bring many exciting applications. However, we believe no prior studies have considered the critical question of how training data and training methods affect imitators when these models are applied to novel scenarios. In this work, a general imitation model is represented by applying either the Behavior Cloning (BC) training method or a more sophisticated Generative Adversarial Imitation Learning (GAIL) method, on three typical types of data domains: standard benchmarks for evaluating crowd models, random sampling of state-action pairs, and egocentric scenarios that capture local interactions. Simulated results suggest that (i) simpler training methods are overall better than more complex training methods, (ii) training samples with diverse agent-agent and agent-obstacle interactions are beneficial for reducing collisions when the trained models are applied to new scenarios. We additionally evaluated our models in their ability to imitate real world crowd trajectories observed from surveillance videos. Our findings indicate that models trained on representative scenarios generalize to new, unseen situations observed in real human crowds.