Figure AI has achieved a significant milestone in robotics: two humanoid robots successfully completed a full bedroom reset, including making a bed together, using only visual communication and no human intervention. The breakthrough demonstrates that machines can coordinate shared tasks by reading each other's movements, head nods, and body language, much like humans do, rather than relying on coded instructions or remote control.

How Do These Robots Coordinate Without Explicit Commands?

The two F.03 humanoid robots operate using Helix-02, a single Vision-Language-Action system that controls each machine's entire body. Unlike traditional robotic setups that rely on separate planners, message passing, or a central coordinator, these humanoids read the room through their own cameras and infer each other's intent purely from motion. The system runs entirely on edge computing, meaning each robot processes visual information and makes decisions locally without needing network connectivity or external guidance.

In the demonstration, the robots opened doors, hung clothes on a coat tree, put away headphones, closed a book, took out rubbish, pushed an office chair under a desk, and worked together to make the bed. The bed-making task proved particularly demanding because it required the robots to lift, unfurl, spread, fold, and smooth a duvet while correcting wrinkles and bunched edges as the fabric settled. Every step happened at normal speed, with no teleoperation and no human intervention.

What Makes Multi-Robot Coordination So Difficult?

• Dynamic Problem Solving: Two humanoids in one room are not simply two single-robot tasks running side by side. Every move one machine makes changes the problem the other must solve, and each robot must constantly read and predict its partner's next action while its own actions are altering the scene.
• Deformable Object Handling: The central object, the duvet, has no fixed shape, no rigid geometry, and no natural divide between "your half" and "mine." Each robot commits to a contact point while predicting what its partner will do, updating those predictions tens of times per second as the fabric folds, drapes, and slides under shared tension.
• Speed and Seamless Transitions: The entire sequence runs in under two minutes, requiring the robots to walk naturally between locations, balance dynamically on one leg to operate a pedal bin, and switch seamlessly between rigid, deformable, articulated, and collaborative manipulation, all without scripted handoffs between subtasks.

The underlying Helix-02 system was not built specifically for bedrooms. It is a single learned policy that expands its skills as it is fed more data. Earlier this year, the same approach allowed a Figure robot to load a dishwasher in a full-sized kitchen in four minutes, and in March, a solo F.03 tidied a living room, spraying and wiping surfaces, sorting toys, and replacing cushions on a sofa. The bedroom reset represents the latest layer on top of those earlier capabilities, all achieved without altering the core algorithm.

"There is no explicit messaging between these robots; they coordinate their actions fully visually, e.g. head nods," stated Brett Adcock, Figure AI's Chief Executive.

Brett Adcock, Chief Executive at Figure AI

What Does This Achievement Mean for the Future of Robotics?

Figure describes the demonstration as an important first step toward a future in which intelligent humanoids routinely work together in homes, warehouses, and factories, handling shared goals in spaces where people, objects, and other machines are constantly on the move. The company's broader vision extends beyond single-task demonstrations. Figure is currently running a 64-plus-hour continuous autonomous livestream where humanoid robots sort packages at a rate of roughly 2.9 seconds per item, processing over 80,000 packages without mechanical failure.

The company is also aggressively onshoring its production to reduce geopolitical risk. Figure forecasts zero supply chain exposure to China by next quarter, having successfully moved the production of custom motors, gearboxes, sensors, and printed circuit boards (PCBs) out of China or to diversified suppliers. This strategic shift reflects the company's confidence in scaling humanoid manufacturing; Figure is currently producing between 60 and 70 humanoid robots per week, representing an annual production run rate in the thousands.

Looking further ahead, Figure has locked the architecture for its next-generation Figure 4 robot following a critical design review. The company describes this upcoming machine as "unrecognizable" from prior iterations, comparing its impending launch to the industry's "iPhone 1 moment." A focal point of this leap is a complete reimagining of the humanoid hand, which will pack more actuators than the entire rest of the robot's body combined, built with watchmaker-level precision to achieve full range-of-motion parity with human anatomy.

To break through the generalization bottleneck, where robots can handle unseen environments and novel tasks, Figure launched a dedicated 70-person AI laboratory called HARK and has deployed a brand-new cluster of Nvidia Blackwell B200 GPUs to train its largest AI models. The company's strategy signals a shift in robotics from narrow, task-specific automation toward machines that can learn, coordinate, and adapt in real-world environments alongside humans.