Watch: Figure 03 humanoid climbs ladder autonomously in new robotics milestone

Figure 03 humanoid robot ascending a ladder without visible human assistance.Brett Adcock/X US-based Figure has shared a new video claiming the company’s Figure 03 humanoid robot can climb a ladder fully autonomously. The footage by the firm’s founder, Brett Adcock, posted on X, shows the robot ascending a ladder without visible human assistance. Figure 03 is a general-purpose humanoid robot for everyday use. The company says that by using its Helix AI model, the robot can navigate unpredictable, ever-changing home environments. Recently, Figure announced that it has increased Figure 03 production from one unit per day to one per hour, delivering over 350 robots while boosting manufacturing efficiency and AI development. Figure climbs higher Figure’s new video claims the Figure 03 humanoid robot can climb a ladder fully autonomously, showcasing what the company describes as another milestone in robotic mobility and balance. The footage, shared by Adcock on X, shows the robot ascending a ladder without visible human assistance or remote control. Climbing a ladder is considered one of the more difficult tasks for humanoid robots because it requires precise coordination of the arms and legs, continuous balance adjustments, and accurate perception of the surrounding environment. Successfully performing the task could demonstrate improvements in the robot’s locomotion, whole-body control, and real-time decision-making. The demonstration attracted attention from AI researchers, with some describing it as “good progress” in humanoid robotics. While the video showcases the robot’s apparent ladder-climbing capability, Figure has not disclosed technical details about the underlying system, and the demonstration has not been independently verified. In a separate post, Adcock argued that “wheeled robots are an utter dead end,” reiterating his belief that legged humanoid robots are better suited for environments designed for humans, such as factories, warehouses, offices, and homes. Vision meets motion Figure has also recently unveiled a major upgrade to its Helix System 0 (S0) AI model, giving its humanoid robots the ability to combine visual perception with whole-body motion control for more capable autonomous navigation. Previously, the system relied only on proprioception—the robot’s awareness of its own joint positions, body movements, and balance. While effective for basic locomotion, that approach limited the robot‘s ability to safely navigate complex environments such as staircases, ladders, and uneven terrain. The updated S0 model now incorporates real-time visual data from onboard stereo cameras. It processes RGB images to build a three-dimensional representation of the surrounding environment, allowing the robot to simultaneously “see” the terrain ahead while continuously monitoring its own body position. This combination enables more precise foot placement, improved balance, and smoother movement across challenging surfaces. Figure said the model was trained end-to-end using reinforcement learning in simulation across a wide range of randomized terrains and environmental conditions. According to the company, the learned behaviors transfer directly from simulation to real-world robots without requiring additional calibration or fine-tuning, addressing the long-standing “sim-to-real” challenge in robotics. The company says the upgraded system enables human-like stability while traversing stairs and uneven surfaces, even under changing lighting conditions. Figure believes the perception-driven architecture will support a broader range of environment-aware behaviors, bringing its humanoid robots closer to fully autonomous operation in real-world settings. Recommended ArticlesGet the latest in engineering, tech, space & science - delivered daily to your inbox.Jijo is an automotive and business journalist based in India. Armed with a BA in History (Honors) from St. Stephen's College, Delhi University, and a PG diploma in Journalism from the Indian Institute of Mass Communication, Delhi, he has worked for news agencies, national newspapers, and automotive magazines. In his spare time, he likes to go off-roading, engage in political discourse, travel, and teach languages.