Facts

• Company: Figure AI
• Product type: Robotics Foundation Model
• Status: development
• Capability focus: Generalist Humanoid Vla Control
• Website: https://www.figure.ai/helix

Profile sections

• Summary
• Overview
• Market context
• Audience
• Workflow
• Capability
• Deployment environment
• Positioning tags
• Specifications
• Tags
• Record / Articles
• Timeline / Research
• Sources

Summary

Helix is Figure AI generalist humanoid vision-language-action model. It controls perception, reasoning and movement onboard Figure robots, allowing them to interpret tasks and perform actions without fixed scripts.

Overview

Helix is Figure AI generalist humanoid vision-language-action model. It controls perception, reasoning and movement onboard Figure robots, allowing them to interpret tasks and perform actions without fixed scripts.

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

Audience

Developers

Workflow

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

Capability

Generalist humanoid VLA control

Deployment environment

Figure humanoid deployments, logistics demonstrations and household manipulation demos.

Positioning tags

• Audience: Developers
• Workflow: Natural-language task execution, object manipulation, collaborative handoff and real-time robot control.
• Capability: Generalist humanoid VLA control
• Deployment environment: Figure humanoid deployments, logistics demonstrations and household manipulation demos.

Specifications

• 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
• System 2 Parameters: 7 B parameters
• System 1 Parameters: 80 M parameters
• Control Loop: 200 Hz
• Controlled Action Space: 35 DoF
• Deployment Compute: dual low-power embedded GPUs on Figure robots
• Demonstrated Tasks: collaborative grocery storage, object picking, container placement, drawers and refrigerator operation

Tags

• Peer Group: Robot foundation model

Record / Articles

• 2026-04-18 - Note - This Week in Humanoid Robotics

Timeline / Research

• 2026-05-08 - Demonstration - Figure demonstrates Helix 02 bedroom tidy task with humanoid robot - Figure published an official Helix 02 bedroom-tidy demo showing its humanoid system performing a household soft-object ma…
• 2026-03-09 - Demonstration - Figure AI's Helix 02 Robot Demonstrates Autonomous Home Cleanup - • Figure AI's Helix 02 humanoid robot autonomously performed a comprehensive living room cleanup.
• 2026-01-27 - Capability - Figure introduces Helix 02 for full-body humanoid autonomy - Extends neural network integration across the entire robot, enhancing fluid loco-manipulation capabilities.
• 2025-09-17 - Partnership - Figure partners with Brookfield on humanoid data, infrastructure and deployment pathways - Figure announced a strategic partnership with Brookfield, which it described as a major real-world en…
• 2025-08-12 - Research Publication - Figure AI shows Helix folding laundry as a deformable-object manipulation benchmark - Figure showed the same Helix model extending from logistics package reorientation into autonomous…
• 2025-06-07 - Research Publication - Figure AI scales Helix logistics performance toward human-level throughput - Figure reported that Helix expanded from rigid boxes to poly bags and padded envelopes while cutting avera…
• 2025-02-26 - Research Publication - Figure AI details Helix logistics policy for real-world package manipulation - Figure published a technical report on using Helix for package manipulation and triaging in a real-world…
• 2025-02-20 - Research Publication - Figure AI introduces Helix VLA model for generalist humanoid control - Figure introduced Helix as a Vision-Language-Action model that unifies perception, language understanding, and l…