Open X-Embodiment
by Google DeepMind / Consortium · open-source · Last verified 2026-03-17
Open X-Embodiment (OXE) is a large-scale robotics dataset aggregating demonstrations from 22 different robot embodiments across 527 skills and over 1 million episodes, curated by a consortium of research labs. It is designed to train generalist robot policies that transfer across hardware platforms, and serves as the foundation dataset for RT-2 and similar vision-language-action models.
https://robotics-transformer-x.github.io ↗B
B—Above Average
Adoption: B+Quality: AFreshness: ACitations: AEngagement: F
Specifications
- License
- Apache 2.0
- Pricing
- open-source
- Capabilities
- robot-learning, imitation-learning, multi-embodiment-transfer
- Integrations
- Use Cases
- generalist-robot-policy-training, embodied-ai-research, manipulation
- API Available
- No
- Tags
- robotics, manipulation, multi-robot, imitation-learning, embodied-ai
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
66.1Adoption
70
Quality
88
Freshness
80
Citations
82
Engagement
0
Put AI to work for your business
Deploy this dataset alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.