Robot AI model
Helix
Helix couples a vision-language system with a faster visuomotor policy for continuous humanoid upper-body control. Figure demonstrates household object handling and collaborative manipulation, with later logistics updates on Figure 02 and Helix-enabled Figure 03 hardware.
Records last verified Oct 13, 2026 · Send a correction
- Organization
- Figure AI
- Type
- VLA
- Released / introduced
- Feb 20, 2025
- Public weights
- Not established
- Licence / scope
- Not established
- Parameters
- Not disclosed
- Base model
- Not disclosed
- Humanoid association
- Humanoid-native
- Inputs
- vision, language, proprioception
- Outputs
- continuous upper-body joint commands
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.
- Figure 02 →
Figure's June 2025 logistics update names this robot.
- Figure 03 →
The October 2025 robot announcement names Helix; Helix 02 is cataloged separately.
Disclosed training data
- Figure teleoperated robot demonstrations
More robot AI models
Evidence
Sources
- [s1] Helix: A Vision-Language-Action Model for Generalist Humanoid Control ↗
Figure AI · official · published Feb 20, 2025 · accessed Oct 13, 2026
- [s2] Scaling Helix: humanoid logistics ↗
Figure AI · official · published Jun 7, 2025 · accessed Oct 13, 2026
- [s3] Introducing Figure 03 ↗
Figure AI · official · published Oct 9, 2025 · accessed Oct 13, 2026