Other, Quadruped
Open X-Embodiment
Cross-embodiment robotic manipulation and generalist policy learning
A standardized federation of 60 datasets supplies over one million real-robot trajectories across 22 embodiments.
Access links
Primary places to inspect, download, read about, or reproduce the dataset.
Quick facts
- Vehicle type
- Other, Quadruped
- Environment
- Not reported
- Data origin
- Real-world
- Sensor count
- 1
- Ground truth
- Not reported
- Calibration
- Not reported
- Annotations
- Available
Sensor overview
High-level sensor availability before the detailed sensor records below.
Ground truth
Reference scope, method, rate, coverage, and provenance.
Not reported
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 reportedKnown or intentional limitations
Reported constraints and characteristics to check before using the dataset.
This is one unified RLDS repository release assembled from multiple contributed datasets. The selected paper describes sixty datasets and twenty-two embodiments; individual contributors are not new entries generated by this paper.
Camera configurations, action spaces, sample rates, calibration, licenses and reference products vary by component. No single fixed sensor rig or exact unversioned trajectory total is asserted.
Recorded actions and proprioception are supervision, not independent platform-pose truth. The seven-dimensional model action convention does not imply common source coordinate frames.
Component download availability and schemas can vary. Later additions are not silently merged into paper-era statistics, and constituent citations remain relevant for reuse.
Cameras
Camera 1
- Model
- Not reported
- Setup
- Other
- Count
- 1
- Effective cameras
- 1
- Modality
- Rgb
- Resolution
- Not reported
- Rate
- Not reported
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- Not reported
- VFOV
- Not reported
- Notes
- Heterogeneous RGB camera observations; no single physical inventory, image resolution or rate applies across 60 datasets.
IMUs
Not reported
GNSS
Not reported
LiDAR
Not reported
Radar
Not reported
Additional sensors
Other sensor
- Name
- Robot actions and proprioceptive observations
- Count
- 1
- Notes
- Component-specific RLDS episodes contain action and state observations with differing coordinate conventions and physical inventories. Model action preprocessing is not a shared physical sensor specification.
Annotations
Reported annotation availability and task support.
- Availability
- Available
- Format
- Natural-language task annotations; constituent-dataset schemas vary.
- Class count
- Not reported
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.
@misc{open2023openxembodiment,
author = {{Open X-Embodiment Collaboration}},
title = {Open X-Embodiment: Robotic Learning Datasets and RT-X Models},
year = {2023},
url = {https://arxiv.org/abs/2310.08864v9}
}Dataset corrections
Notice a specific issue after reviewing the page?
Report an inaccuracy