Helix Context

Market context

Helix is Figure's vision-language-action model stack for humanoid perception, manipulation and whole-body control.

Target environment: Figure humanoid deployments, logistics demonstrations and household manipulation demos.
Workflow context: Natural-language task execution, object manipulation, collaborative handoff and real-time robot control.
Customer context: Figure AI robot development teams and customers evaluating Figure humanoids for physical work.
Deployment model: Platform-integrated model layer running on Figure robots rather than a standalone third-party software product.
Commercial maturity: Public model layer with technical writeups and demos, tied to Figure's own humanoid platform.
Adoption constraints: Adoption depends on Figure robot availability, task reliability, safety validation and deployment access.
Market position: Robot foundation-model layer for humanoid manipulation and generalist physical task execution.
Adjacent products: GENE-26.5, sudo R1, FluxVLA Engine, Project GR00T

Robot developers

Natural-language task execution, object manipulation, collaborative handoff and real-time robot control.

Figure humanoid deployments, logistics demonstrations and household manipulation demos.

Mobility Class: software_model
Platform Type: robot_foundation_model
Deployment Model: humanoid_intelligence
Platform Role: vla_control_layer
Model Type: generalist humanoid vision-language-action model
Control Scope: perception, reasoning and movement on board Figure robots
Architecture: S2 high-level latent planning model plus S1 low-level control model; control loop: 200 Hz; controlled action space: 35 DoF
Features: system 2 parameters: 7 B parameters; system 1 parameters: 80 M parameters
Deployment Compute: dual low-power embedded GPUs on Figure robots
Demonstrated Tasks: collaborative grocery storage, object picking, container placement, drawers and refrigerator operation