Adapting one robot policy across nine platforms
Octo is a generalist manipulation policy trained on the Open X-Embodiment dataset and evaluated as a reusable starting point for robots with different sensors, action spaces, and physical forms.
- Maturity
- Demonstrated, stage 3 of 4
- Support
- 3 sources · paper, repository
- Evidence detail
- How we know ↓
A new robot setup often needs a policy rebuilt from scarce demonstrations before it can attempt even familiar manipulation tasks.
Earlier generalist policies were often unavailable or locked to the observations and action spaces used during pretraining.
A transformer-based diffusion policy converts language or goal-image instructions and robot observations into action sequences.
What was shown, and what wasn’t
Shown
The Robotics: Science and Systems 2024 paper reports fine-tuning experiments across nine robot platforms, and the project publishes pretrained Octo 1.5 checkpoints plus training, fine-tuning, inference, and real-robot evaluation code.
Not shown · limits
- The experiments are research evaluations on specific tasks and hardware, not evidence of safe autonomous deployment. Repository code and the named Octo 1.5 checkpoint are MIT; the Open X-Embodiment source datasets still require their own provenance and terms review.
- The reported cross-platform results come from the model authors and were published at RSS 2024. The project exposes MIT-licensed code and downloadable Octo 1.5 checkpoints; those artifacts do not establish unattended robot safety.
Bright editorial interpretation
Released code and weights give independent labs a common policy they can inspect and adapt, while physical safety and task reliability remain local responsibilities.
How we know3 sources · checked 2026-09-19 · no corrections
Original sources
- Octo: An Open-Source Generalist Robot Policy ↗ · paper
- Octo generalist robot policy ↗ · repository
- Octo: An Open-Source Generalist Robot Policy ↗ · paper
Institutions: UC Berkeley, Stanford University, Carnegie Mellon University, and Google DeepMind collaborators
- Maturity
- Demonstrated
- Source published
- 2024-05-20
- Captured
- 2026-09-19
- Last source review
- 2026-09-19
- Editorial method
- AI-assisted source review
Bright compared this account with the linked original and supporting sources and kept reported, budgeted, projected, and observed claims distinct. Bright did not independently audit the underlying records.
Maturity describes the tested or operational setting. Confidence describes support for the particular claim; one does not determine the other.
Revision & correction history
2026-09-19 · Bright added this source-checked open-model application record. The cited source publication date is 2024-05-20; 2026-09-19 is when Bright added this record.
No corrections recorded.
Keep exploring
Explore the shared question in another setting. These connections do not imply replication.