Polynomial Trajectory Predictions for Improved Learning Performance

TL;DR

This paper proposes training neural networks to predict polynomial coefficients of trajectories over time, enhancing prediction accuracy and generalization for automotive safety systems.

Contribution

It introduces a novel approach of predicting polynomial trajectory coefficients directly, improving the reliability of short to mid-term movement predictions.

Findings

Enhanced trajectory prediction accuracy

Improved generalization in neural network models

Potential for safer automotive active safety systems

Abstract

The rising demand for Active Safety systems in automotive applications stresses the need for a reliable short to mid-term trajectory prediction. Anticipating the unfolding path of road users, one can act to increase the overall safety. In this work, we propose to train artificial neural networks for movement understanding by predicting trajectories in their natural form, as a function of time. Predicting polynomial coefficients allows us to increased accuracy and improve generalisation.