Trajectory Prediction with Linguistic Representations

TL;DR

This paper introduces a novel trajectory prediction model that leverages linguistic intermediate representations to improve accuracy and interpretability, using partially-annotated captions to learn and generate descriptive trajectories.

Contribution

The model uniquely integrates linguistic representations into trajectory prediction, enabling better long-term forecasts and interpretability without requiring detailed per-word supervision.

Findings

Improved trajectory prediction accuracy on Argoverse dataset

Model generates meaningful linguistic descriptions of trajectories

Enhanced interpretability through caption-based reasoning

Abstract

Language allows humans to build mental models that interpret what is happening around them resulting in more accurate long-term predictions. We present a novel trajectory prediction model that uses linguistic intermediate representations to forecast trajectories, and is trained using trajectory samples with partially-annotated captions. The model learns the meaning of each of the words without direct per-word supervision. At inference time, it generates a linguistic description of trajectories which captures maneuvers and interactions over an extended time interval. This generated description is used to refine predictions of the trajectories of multiple agents. We train and validate our model on the Argoverse dataset, and demonstrate improved accuracy results in trajectory prediction. In addition, our model is more interpretable: it presents part of its reasoning in plain language as captions, which can aid model development and can aid in building confidence in the model before deploying it.