Argoverse: 3D Tracking and Forecasting with Rich Maps

TLDR

Argoverse was collected by a fleet of autonomous vehicles in Pittsburgh and Miami. We present Argoverse, two datasets designed to support autonomous vehicle machine learning tasks such as 3D tracking and motion forecasting, and we hope it will enable the research community to explore these problems in greater depth. The Argoverse 3D Tracking dataset provides 360‑degree camera images, long‑range LiDAR point clouds, 6‑DOF pose, and 3‑D track annotations, while the Motion Forecasting dataset offers over 300,000 five‑second tracked scenarios with a target vehicle for trajectory forecasting. Argoverse uniquely offers forward‑facing stereo imagery and the first AV dataset to include 290 km of HD lane maps with geometric and semantic metadata, and baseline experiments show that detailed map information such as lane direction, drivable area, and ground height improves 3‑D object tracking and motion forecasting accuracy, though the work represents only an initial exploration. All data is released under a Creative Commons license at www.argoverse.org.

Abstract

We present Argoverse -- two datasets designed to support autonomous vehicle machine learning tasks such as 3D tracking and motion forecasting. Argoverse was collected by a fleet of autonomous vehicles in Pittsburgh and Miami. The Argoverse 3D Tracking dataset includes 360 degree images from 7 cameras with overlapping fields of view, 3D point clouds from long range LiDAR, 6-DOF pose, and 3D track annotations. Notably, it is the only modern AV dataset that provides forward-facing stereo imagery. The Argoverse Motion Forecasting dataset includes more than 300,000 5-second tracked scenarios with a particular vehicle identified for trajectory forecasting. Argoverse is the first autonomous vehicle dataset to include "HD maps" with 290 km of mapped lanes with geometric and semantic metadata. All data is released under a Creative Commons license at www.argoverse.org. In our baseline experiments, we illustrate how detailed map information such as lane direction, driveable area, and ground height improves the accuracy of 3D object tracking and motion forecasting. Our tracking and forecasting experiments represent only an initial exploration of the use of rich maps in robotic perception. We hope that Argoverse will enable the research community to explore these problems in greater depth.