Figure AI CEO Brett Adcock has released video of the company’s Figure 03 robot climbing a short ladder autonomously, describing the demonstration as completed without remote control or scripted sequences using the robot’s Helix AI system. Figure has not published success rates or a detailed technical breakdown of the run.
Ladder climbing is considered one of the more demanding mobility challenges for humanoid robots because it requires continuous balance adjustment, precise coordination between arms and legs simultaneously, and accurate spatial awareness of the surrounding structure – a combination that tests whole-body control more comprehensively than walking on flat surfaces.
F.03 can now climb a ladder, fully autonomous pic.twitter.com/tNJeGuvVhm
— Brett Adcock (@adcock_brett) August 1, 2026
The Helix System Upgrade
The demonstration follows a recent update to Figure’s Helix System 0 AI model. The previous version relied on proprioception – the robot’s internal awareness of its own body position and movement. The upgraded model adds input from onboard stereo cameras, allowing the robot to build a three-dimensional view of its surroundings while simultaneously tracking its own posture in real time.
Figure says the AI was trained end-to-end using reinforcement learning in simulated environments with randomized terrain, and that the learned behaviors transfer directly to physical robots without additional calibration. The end-to-end training approach – where a single model learns to map visual and proprioceptive input directly to motor output rather than using a modular pipeline of separate perception and control systems – is the same methodology driving improvements across the physical AI field, including at Boston Dynamics, Google DeepMind, and 1X Technologies.
Production Context
The ladder demonstration arrives as Figure is scaling production significantly. The company recently disclosed it has increased Figure 03 production from one robot per day to one per hour, and has delivered more than 350 units. Figure 03 is currently deployed at BMW’s Spartanburg plant for logistics sequencing tasks, and Figure is evaluating additional use cases at the same facility.
The progression from body shop sheet metal handling with Figure 02 to logistics sequencing with Figure 03 to autonomous ladder climbing demonstrates Figure’s systematic expansion of the robot’s operational envelope – from structured, flat-floor, repetitive tasks toward dynamic, multi-surface navigation that would allow the robot to access the full three-dimensional workspace of a factory or warehouse.
What Remains Unproven
The demonstration leaves significant questions unanswered. Figure has not disclosed the success rate of the ladder climb across multiple attempts, the conditions under which it was tested, or how the robot performs carrying equipment or operating on ladders in less controlled environments. Ladder climbing while loaded – carrying tools, parts, or equipment – places substantially different demands on balance and grip than unloaded climbing.
For industrial customers evaluating humanoid robots for environments that include ladders, stairs, and uneven surfaces, the milestone is directionally significant but not operationally conclusive. The commercial test will be whether Figure 03 can repeat the task reliably and safely at scale in the unpredictable conditions of real worksites.
Disclaimer: RobotsBeat is an independent media brand owned and operated by NuvexMedia LLC, publishing news, research, and insights on artificial intelligence, emerging technologies, automation, and related industries. NuvexMedia LLC invests in and collaborates with companies across the AI, Robotics, technology, software, and digital innovation sectors. These relationships do not influence RobotsBeat's editorial coverage, and the publication maintains full editorial independence to provide accurate, timely, and objective information. © 2026 NuvexMedia LLC. All rights reserved. This content is for informational purposes only and should not be considered legal, tax, investment, financial, or other professional advice.
