Figure AI’s Helix 2.5 Solves the Generalization Problem in 30 Unknown Homes

Figure AI unveiled Helix 2.5, a new neural network for humanoid robots, on September 17, 2026, demonstrating robots performing extended household chores such as tidying, towel folding, and bed making in 30 homes where no prior data collection had occurred. The company said Helix 2.5 uses a pre-trained foundational model to generalize across varied, unknown settings, unlike its earlier Helix 02, which required extensive data collection within the specific operational environment. Figure AI framed the result as a step toward practical general-purpose humanoids that move beyond environment-specific learning.

Figure AI’s Helix 2.5 Solves the Generalization Problem in 30 Unknown Homes Figure AI unveiled Helix 2.5, a new neural network for humanoid robots, on September 17, 2026. AsiaAI Publisher · September 18, 2026 · 2 min read · Source: ロボスタ Robot Start · Issue 100 East Asian Technology Intelligence Japan & China tech news — translated, contextualized, and delivered for Western readers. Free. Unsubscribe anytime. This story ran in Issue 100, alongside three other stories. Robotics & Automation Figure AI unveiled Helix 2.5, a new neural network for humanoid robots, on September 17, 2026. The company demonstrated its robots performing extended household chores like tidying, towel folding, and bed making in 30 homes where no prior data collection had occurred, showcasing adaptation to unknown environments. This represents a step towards practical general-purpose humanoids, moving beyond environment-specific learning. Previous humanoid robot deployments, including Figure AI’s own Helix 02, required extensive data collection within the specific operational environment. Helix 2.5 aims to overcome this limitation by using a pre-trained foundational model and demonstrating generalizability across varied, unknown settings.