Studying the Effect of Explicit Interaction Representations on Learning Scene-level Distributions of Human Trajectories

TL;DR

This paper investigates how explicit versus implicit interaction representations between agents affect the accuracy of scene-level human trajectory predictions, finding that well-defined explicit interactions improve model performance.

Contribution

It provides a comparative analysis of implicit and explicit interaction modeling methods within the same neural network framework for trajectory prediction.

Findings

Explicit interaction modeling improves prediction accuracy.

Implicit interaction learning can negatively impact performance.

Well-defined interaction rules boost model effectiveness.

Abstract

Effectively capturing the joint distribution of all agents in a scene is relevant for predicting the true evolution of the scene and in turn providing more accurate information to the decision processes of autonomous vehicles. While new models have been developed for this purpose in recent years, it remains unclear how to best represent the joint distributions particularly from the perspective of the interactions between agents. Thus far there is no clear consensus on how best to represent interactions between agents; whether they should be learned implicitly from data by neural networks, or explicitly modeled using the spatial and temporal relations that are more grounded in human decision-making. This paper aims to study various means of describing interactions within the same network structure and their effect on the final learned joint distributions. Our findings show that more often than not, simply allowing a network to establish interactive connections between agents based on data has a detrimental effect on performance. Instead, having well defined interactions (such as which agent of an agent pair passes first at an intersection) can often bring about a clear boost in performance.