Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction

TL;DR

This paper introduces UNIN, a novel trajectory prediction model that captures unlimited, non-local, and heterogeneous social interactions among agents, significantly improving prediction accuracy.

Contribution

The paper proposes the Unlimited Neighborhood Interaction Network (UNIN), which models unlimited, non-local, and heterogeneous interactions among agents for trajectory prediction.

Findings

Significant performance improvement over state-of-the-art methods.

Effective modeling of unlimited and non-local interactions.

Handles heterogeneous agent categories with diverse reactions.

Abstract

Understanding complex social interactions among agents is a key challenge for trajectory prediction. Most existing methods consider the interactions between pairwise traffic agents or in a local area, while the nature of interactions is unlimited, involving an uncertain number of agents and non-local areas simultaneously. Besides, they treat heterogeneous traffic agents the same, namely those among agents of different categories, while neglecting people's diverse reaction patterns toward traffic agents in ifferent categories. To address these problems, we propose a simple yet effective Unlimited Neighborhood Interaction Network (UNIN), which predicts trajectories of heterogeneous agents in multiple categories. Specifically, the proposed unlimited neighborhood interaction module generates the fused-features of all agents involved in an interaction simultaneously, which is adaptive to any number of agents and any range of interaction area. Meanwhile, a hierarchical graph attention module is proposed to obtain category-to-category interaction and agent-to-agent interaction. Finally, parameters of a Gaussian Mixture Model are estimated for generating the future trajectories. Extensive experimental results on benchmark datasets demonstrate a significant performance improvement of our method over the state-of-the-art methods.