Figure humanoid robot masters dishwashing after folding laundry

Figure, a California-based robotics company, has advanced its humanoid robot, Figure 02, to perform the complex household task of loading a dishwasher with human-like precision. Powered by the company’s generalist Vision-Language-Action (VLA) model called Helix, the robot can carefully pick up, reorient, and arrange various dishes and glasses in the dishwasher with finger-level accuracy and minimal error tolerance. Remarkably, this capability was achieved without any new algorithms or task-specific programming; instead, the robot learned the task through additional data and observation of human actions, allowing it to recover gracefully from errors or collisions. This development builds on previous demonstrations where Figure 02 folded towels, rearranged packages, and placed garments into a washing machine using the same Helix AI model. The key innovation lies in Helix’s general-purpose architecture, which enables the robot to acquire diverse skills through data-driven learning rather than specialized engineering for each task. While the robot’s growing repertoire brings the vision of a