Helix

Helix is Figure AI's generalist Vision-Language-Action (VLA) model that unifies perception, language understanding, and learned control for humanoid robots. First announced in February 2025, Helix was the first VLA to output high-rate continuous control of the entire humanoid upper body (wrists, torso, head, and individual fingers), and the first to operate simultaneously on two robots for shared long-horizon manipulation tasks. It uses a single set of neural network weights to learn all behaviors without task-specific fine-tuning, enabling robots to pick up thousands of previously unseen household objects through natural language prompts. Helix runs entirely onboard low-power-consumption embedded GPUs for commercial deployment. A second iteration, Helix 02, was released in January 2026 and expanded the AI model to the entire body for functional autonomy, including full-body control for tasks like dishwashing, laundry folding, and package handling.