Robot AI model
π0
π0 combines PaliGemma with a flow-matching action expert; its paper reports 3.3B parameters. Repository code uses Apache-2.0; Gemma Terms of Use apply to the inherited Gemma model components.
Records last verified Oct 13, 2026 · Send a correction
Also known as pi0, pi-zero
- Organization
- Physical Intelligence
- Type
- VLA
- Released / introduced
- Oct 31, 2024
- Public weights
- Public weights
- Licence / scope
- Apache-2.0; Gemma Terms of Use
- Parameters
- 3.3B
- Base model
- PaliGemma 3B
- Humanoid association
- None reported
- Inputs
- vision, language, proprioception
- Outputs
- continuous action chunks
Release dates can mark an announcement or paper introduction. Public checkpoints, code licences and weight terms are distinct; follow the publisher’s links for the stated scope.
Documented embodiments
Source-associated hardware; this list does not establish plug-and-play compatibility or commercial robot capability.
- ALOHA
Fine-tuned ALOHA checkpoints are published in openpi.
- DROID Franka setup
Fine-tuned DROID checkpoint is published in openpi.
Disclosed training data
- Open X-Embodiment subset (OXE Magic Soup) →
- Physical Intelligence robot demonstrations
- DROID →
- BridgeData V2 →
More robot AI models
Evidence
Sources
- [s1] π0: A Vision-Language-Action Flow Model for General Robot Control ↗
Physical Intelligence · paper · published Oct 31, 2024 · accessed Oct 13, 2026
- [s2] π0 paper: architecture and training data ↗
Physical Intelligence · paper · published Jan 8, 2026 · accessed Oct 13, 2026
- [s3] openpi: models, checkpoints and training examples ↗
Physical Intelligence · official · accessed Oct 13, 2026
- [s4] openpi Apache License 2.0 ↗
Physical Intelligence · official · accessed Oct 13, 2026
- [s5] Gemma Terms of Use distributed with openpi ↗
Physical Intelligence / Google · official · published Feb 21, 2024 · accessed Oct 13, 2026