RoboTrack242026

RoboTrack Real v3

An evaluation dataset of 318 real-world video clips with sparse 2D point trajectories and visibility annotations for point tracking in robotic scenarios. Each example includes the original RGB video, a rendered visualization of point tracks, and NumPy annotation archives.

Downloads41
Episodes318

Why This Matters for Physical AI

RoboTrack Real v3 provides annotated point trajectory data essential for training and evaluating visual tracking algorithms that enable robots to follow object features and understand scene dynamics during manipulation tasks.

Technical Profile

Modalities
rgbpoint_tracks
Environment
lab
Task Types
point_tracking
Episodes
318
Data Format
mp4, npz, parquet
Annotation Types
point_trajectoriesvisibility_labelsquery_frames
Part of the RoboTrack Real v3 family

Access

Need custom rgb data?

Claru builds purpose-built datasets for lab applications with dense human annotations and quality assurance.

Request a Sample Pack

Related Datasets