List of Datasets

Automotive

Argoverse 2 Motion Forecasting

Multi-agent motion forecasting

Two hundred fifty thousand eleven-second urban scenarios with planar actor histories, futures, headings and vector maps; no raw sensor streams.

Metadata: Complete Metadata source documented Released 2022

Primary places to inspect, download, read about, or reproduce the dataset.

Quick facts

Vehicle type
Automotive
Environment
Outdoor
Data origin
Real-world
Sensor count
0
Ground truth
Available
Calibration
Not reported
Annotations
Available

Sensor overview

High-level sensor availability before the detailed sensor records below.

Cameras

Not reported

IMUs

Not reported

GNSS

Not reported

LiDAR

Not reported

Radar

Not reported

Magnetometers

Not reported

Barometers

Not reported

UWB

Not reported

Ground truth

Reference scope, method, rate, coverage, and provenance.

Scope Method Reference system Count Rate Coverage Reference provenance
External
Measured using equipment independent of the platform’s normal onboard sensor pipeline.
Derived
Computed primarily from the dataset’s own recorded sensors.
Hybrid
Combines independent reference equipment with onboard measurements.
2D + heading Other Perception-derived actor tracks Not reported 10 Hz Partial Reference provenance
External
Measured using equipment independent of the platform’s normal onboard sensor pipeline.
Derived
Computed primarily from the dataset’s own recorded sensors.
Hybrid
Combines independent reference equipment with onboard measurements.
Derived
Reference notes
Focal/scored tracks have completeness guarantees; other tracks can be incomplete. No raw sensor inventory or 3D extents is released in this product.

Calibration and synchronization

Reported calibration level, reproducibility signals, and supporting notes.

Level
Not reported
Processed parameters
Not reported
Raw calibration data
Not reported
Calibration targets
Not reported

Calibration data

Calibration reproducibility details are not reported.

Notes

Not reported

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

The release contains derived actor trajectories and local maps, not raw camera, LiDAR, IMU or GNSS inputs. Physical acquisition hardware belongs to the related sensor products.

Eleven-second windows are sampled at 10 Hz. Nominal window-duration sums do not establish independent or unique driving coverage; focal/scored tracks have stronger completeness requirements than other actors.

The ten-class actor taxonomy differs from the Sensor detection taxonomy. Tracks can be fragmented and their perception-derived states are not independent surveyed motion references.

The maintained AV2 page now publishes single-agent and multi-world test annotations after moving away from hosted evaluation. Exact task/version protocols must be checked rather than assuming all test futures remain withheld.

Cameras

Not reported

IMUs

Not reported

GNSS

Not reported

LiDAR

Not reported

Radar

Not reported

Additional sensors

Not reported

Automotive

Argoverse 2 LiDAR

Twenty thousand thirty-second LiDAR scenarios with map-aligned ego poses and local vector maps, without imagery or object-box annotations.

Automotive

Argoverse 2 Sensor

One thousand fifteen-second driving scenarios with nine cameras, paired LiDAR sweeps, tracked 3D boxes and scenario-local HD maps.

Annotations

Reported annotation availability and task support.

Availability
Available
Format
Planar actor histories and futures, velocity/heading/type, focal/scored designation and local vector map
Class count
10
Semantic segmentation Not reported
Instance segmentation Not reported
Object detection Not reported
Optical flow Not reported
Depth ground truth Not reported

Citation

Citation key and BibTeX kept at the end of the page for reference.

Citation key
wilson2021argoverse2

BibTeX

@INPROCEEDINGS { wilson2021argoverse2,
  author = {Benjamin Wilson and William Qi and Tanmay Agarwal and John Lambert and Jagjeet Singh and Siddhesh Khandelwal and Bowen Pan and Ratnesh Kumar and Andrew Hartnett and Jhony Kaesemodel Pontes and Deva Ramanan and Peter Carr and James Hays},
  title = {Argoverse 2: Next Generation Datasets for Self-driving Perception and Forecasting},
  booktitle = {Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks 2021)},
  year = {2021}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy