A Novel Deep Neural Network for Trajectory Prediction in Automated Vehicles Using Velocity Vector Field

TL;DR

This paper introduces a deep neural network that integrates a velocity vector field derived from fluid dynamics into trajectory prediction models for automated vehicles, enhancing accuracy over various time horizons and observation lengths.

Contribution

It presents a novel approach combining fluid-inspired velocity vector fields with deep learning for improved trajectory prediction in automated driving.

Findings

Improved prediction accuracy for short and long-term horizons.

Consistency in accuracy despite decreasing observation windows.

Enhanced performance over state-of-the-art methods on the HighD dataset.

Abstract

Anticipating the motion of other road users is crucial for automated driving systems (ADS), as it enables safe and informed downstream decision-making and motion planning. Unfortunately, contemporary learning-based approaches for motion prediction exhibit significant performance degradation as the prediction horizon increases or the observation window decreases. This paper proposes a novel technique for trajectory prediction that combines a data-driven learning-based method with a velocity vector field (VVF) generated from a nature-inspired concept, i.e., fluid flow dynamics. In this work, the vector field is incorporated as an additional input to a convolutional-recurrent deep neural network to help predict the most likely future trajectories given a sequence of bird's eye view scene representations. The performance of the proposed model is compared with state-of-the-art methods on the HighD dataset demonstrating that the VVF inclusion improves the prediction accuracy for both short and long-term (5~sec) time horizons. It is also shown that the accuracy remains consistent with decreasing observation windows which alleviates the requirement of a long history of past observations for accurate trajectory prediction. Source codes are available at: https://github.com/Amir-Samadi/VVF-TP.