Understanding Human Behaviors in Crowds by Imitating the Decision-Making Process

TL;DR

This paper introduces SA-GAIL, a novel framework that models and predicts pedestrian behavior in crowds by mimicking their decision-making process using unsupervised learning and social-aware modeling techniques.

Contribution

The paper presents a new Social-Aware Generative Adversarial Imitation Learning framework that disentangles decision-making factors and improves trajectory prediction accuracy.

Findings

Effective in disentangling latent decision factors

Improves future trajectory prediction accuracy

Demonstrates potential in crowd behavior understanding

Abstract

Crowd behavior understanding is crucial yet challenging across a wide range of applications, since crowd behavior is inherently determined by a sequential decision-making process based on various factors, such as the pedestrians' own destinations, interaction with nearby pedestrians and anticipation of upcoming events. In this paper, we propose a novel framework of Social-Aware Generative Adversarial Imitation Learning (SA-GAIL) to mimic the underlying decision-making process of pedestrians in crowds. Specifically, we infer the latent factors of human decision-making process in an unsupervised manner by extending the Generative Adversarial Imitation Learning framework to anticipate future paths of pedestrians. Different factors of human decision making are disentangled with mutual information maximization, with the process modeled by collision avoidance regularization and Social-Aware LSTMs. Experimental results demonstrate the potential of our framework in disentangling the latent decision-making factors of pedestrians and stronger abilities in predicting future trajectories.