Teaching a robot from demonstrations
OpenVLA gives robotics teams a pretrained vision-language-action model plus instructions for fine-tuning it on their own robot demonstrations.
- Maturity
- Experimental, stage 1 of 4
- Support
- 2 sources · repository, paper
- Evidence detail
- How we know ↓
Every new physical task can demand costly robot data collection and a specialist control pipeline.
Robot policies were commonly narrow, hardware-specific, and difficult for outside teams to reproduce or adapt.
The model reads an image and language instruction, then predicts actions for a robot manipulator.
What was shown, and what wasn’t
Shown
The official release provides checkpoints, LoRA and full fine-tuning paths, configuration files, and evaluation instructions for supported robot environments.
Not shown · limits
- Repository code is MIT, while checkpoints inherit Llama 2 Community License restrictions. Laboratory evaluations do not establish safe unattended operation.
- The repository documents a reproducible research artifact. Its MIT code license does not extend to the released model checkpoints.
Bright editorial interpretation
A reusable starting policy may let more labs test generalization, while responsibility for physical safety stays with the deploying team.
How we know2 sources · checked 2026-09-19 · no corrections
Original sources
- OpenVLA: An open-source vision-language-action model ↗ · repository
- OpenVLA: An Open-Source Vision-Language-Action Model ↗ · paper
Institutions: Stanford, UC Berkeley, and Toyota Research Institute collaborators
- Maturity
- Experimental
- Source published
- 2024-06-13
- 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 2024-06-13; 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.