Introducing Helix
We're introducing Helix, a generalist Vision-Language-Action (VLA) model that unifies perception, language understanding, and learned control to overcome multiple longstanding challenges in robotics. Helix is a series of firsts:
Full-upper-body control : Helix is the first VLA to output high-rate continuous control of the entire humanoid upper body, including wrists, torso, head, and individual fingers.
Multi-robot collaboration : Helix is the first VLA to operate simultaneously on two robots, enabling them to solve a shared, long-horizon manipulation task with items they have never seen before.
Pick up anything: Figure robots equipped with Helix can now pick up virtually any small household object, including thousands of items they have never encountered before, simply by following natural language prompts.
One neural network : Unlike prior approaches, Helix uses a single set of neural network weights to learn all behaviors—picking and placing items, using drawers and refrigerators, and cross-robot interaction—without any task-specific fine-tuning.
Commercial-ready: Helix is the first VLA that runs entirely onboard embedded low-power-consumption GPUs, making it immediately ready for commercial deployment.
Video 1: Collaborative grocery storage. A single set of Helix neural network weights runs simultaneously on two robots as they work together to put away groceries neither robot has ever seen before.
New Scaling for Humanoid Robotics
The home presents robotics' greatest challenge. Unlike controlled industrial settings, homes are filled with countless objects–delicate glassware, crumpled clothing, scattered toys–each with unpredictable shapes, sizes, colors, and textures. For robots to be useful in households, they will need to be capable of generating intelligent new behaviors on-demand, especially for objects they've never seen before.
... continue reading