Interpretable Interaction Modeling for Trajectory Prediction via Agent Selection and Physical Coefficient

TL;DR

This paper introduces ASPILin, a more interpretable and efficient trajectory prediction method that manually selects interacting agents and uses physical correlation coefficients, leading to improved accuracy and reduced computational costs.

Contribution

The paper proposes a novel approach replacing learned attention scores with physical correlation coefficients for better interpretability and efficiency in trajectory prediction.

Findings

Outperforms state-of-the-art methods on multiple datasets.

Reduces computational costs significantly.

Enhances interpretability of agent interactions.

Abstract

A thorough understanding of the interaction between the target agent and surrounding agents is a prerequisite for accurate trajectory prediction. Although many methods have been explored, they assign correlation coefficients to surrounding agents in a purely learning-based manner. In this study, we present ASPILin, which manually selects interacting agents and replaces the attention scores in Transformer with a newly computed physical correlation coefficient, enhancing the interpretability of interaction modeling. Surprisingly, these simple modifications can significantly improve prediction performance and substantially reduce computational costs. We intentionally simplified our model in other aspects, such as map encoding. Remarkably, experiments conducted on the INTERACTION, highD, and CitySim datasets demonstrate that our method is efficient and straightforward, outperforming other state-of-the-art methods.