Interpretable Interaction Modeling for Trajectory Prediction via Agent Selection and Physical Coefficient
This work addresses interpretability and efficiency in trajectory prediction for autonomous systems, but it is incremental as it builds on existing Transformer-based methods with simplified modifications.
The paper tackles trajectory prediction by manually selecting interacting agents and using a physical correlation coefficient instead of attention scores, which improves interpretability and performance while reducing computational costs. Experiments on three datasets show it outperforms state-of-the-art methods.
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.