HomeArticles

Figure AI's Helix Can Now do Laundry Pretty Good

>
Figure 02, folds laundry autonomously & like a pro. A major breakthrough in Physical AI, solving the challenge of soft object manipulation.
August 14, 2025
  • Figure 02, already being tested in BMW plants, can now autonomously fold towels.
  • This is a significant breakthrough for "Physical AI," which deals with robots interacting with the unpredictable real world.
  • Manipulating soft, deformable objects like towels is a major robotics challenge.
  • The robot demonstrated real intelligence by adapting its grip and self-correcting errors, not just following a script.

Figure AI's humanoid robot, Figure 02, is already getting its hands dirty in the real world, with a fleet of robots being tested in BMW's manufacturing plants. But a recent demonstration shows it’s also mastering tasks closer to home, and in doing so, tackling one of the toughest challenges in robotics. The task? Neatly folding a towel.

This might sound simple, but for a robot, it's a monumental feat of what's called "Physical AI"—the science of getting AI to interact with the messy, unpredictable physical world. It's one thing for a robot to handle a solid, rigid object like a car part, which always has the same shape. It's another thing entirely to handle a soft, floppy towel.

Think about it: a towel can be in a million different crumpled states. It has no fixed geometry, it bends unpredictably, and it's easy to grab a bunch or miss a corner. The video shows Figure 02 starting with a messy towel, intelligently finding the edges, and even making corrective actions when its grip isn't quite right. This isn't just a pre-programmed sequence; the robot is observing, adapting, and problem-solving in real-time. By mastering the deceptively complex art of folding laundry, Figure 02 is proving it can handle the chaos of the real world, one towel at a time.

Subscribe for updates

Receive weekly updates when new robots, companies, AI or drones are added to the Aparobot directory.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.