OSM vs HD Maps: Map Representations for Trajectory Prediction

TL;DR

This paper explores using OpenStreetMap instead of HD Maps for long-term vehicle trajectory prediction, demonstrating competitive performance and providing detailed analysis across various scenarios to enhance autonomous driving scalability.

Contribution

It extends OSM application to long-horizon forecasting, improves model performance with expanded receptive fields and intersection priors, and offers comprehensive scenario analysis.

Findings

OSM-based models achieve performance close to HD Map-based models.

Extended forecasting horizon doubles previous long-term prediction capabilities.

Detailed scenario and class-aware analysis provides new insights into motion forecasting.

Abstract

While High Definition (HD) Maps have long been favored for their precise depictions of static road elements, their accessibility constraints and susceptibility to rapid environmental changes impede the widespread deployment of autonomous driving, especially in the motion forecasting task. In this context, we propose to leverage OpenStreetMap (OSM) as a promising alternative to HD Maps for long-term motion forecasting. The contributions of this work are threefold: firstly, we extend the application of OSM to long-horizon forecasting, doubling the forecasting horizon compared to previous studies. Secondly, through an expanded receptive field and the integration of intersection priors, our OSM-based approach exhibits competitive performance, narrowing the gap with HD Map-based models. Lastly, we conduct an exhaustive context-aware analysis, providing deeper insights in motion forecasting across diverse scenarios as well as conducting class-aware comparisons. This research not only advances long-term motion forecasting with coarse map representations but additionally offers a potential scalable solution within the domain of autonomous driving.