Transformer based trajectory prediction

TL;DR

This paper introduces a transformer-based model for autonomous vehicle trajectory prediction that effectively handles domain shifts, achieving top performance in a competitive benchmark.

Contribution

The work presents a simple, effective, and uncertainty-aware transformer model for motion prediction, setting a new state-of-the-art in the 2021 Shifts Vehicle Motion Prediction Competition.

Findings

Achieves top ranking in the 2021 competition.

Demonstrates robustness under domain change.

Provides a strong baseline for future research.

Abstract

To plan a safe and efficient route, an autonomous vehicle should anticipate future motions of other agents around it. Motion prediction is an extremely challenging task which recently gained significant attention of the research community. In this work, we present a simple and yet strong baseline for uncertainty aware motion prediction based purely on transformer neural networks, which has shown its effectiveness in conditions of domain change. While being easy-to-implement, the proposed approach achieves competitive performance and ranks 1$^{st}$ on the 2021 Shifts Vehicle Motion Prediction Competition.