Figure 03 Humanoid Robot Climbs Ladder Autonomously in New Demo

A face of a humanoid robot, side view on black background.

Humanoid robots are being trained to navigate environments built for people as companies such as Figure push autonomous mobility beyond flat floors. Image: Gabriele Malaspina/Unsplash

Aug 4, 2026
3 minute read
eWeek content and product recommendations are editorially independent. We may make money when you click on links to our partners. Learn More

A ladder just became the latest proving ground in the race to build humanoid robots that can move through the human world.

Figure CEO Brett Adcock released a video showing the company’s Figure 03 robot gripping and climbing a short ladder. Adcock described the demonstration as “fully autonomous,” although Figure has not published success rates or a technical breakdown of the run.

The slow, controlled climb offers another glimpse of what whole-body robotic autonomy could eventually enable — and how much testing remains before such machines can safely work in unpredictable environments.

According to Figure, the robot completed the task autonomously using its Helix AI system rather than relying on remote control or a scripted sequence. 

Ladder climbing is widely considered one of the tougher mobility challenges for humanoid robots because it requires continuous balance adjustments, precise coordination between the arms and legs, and accurate awareness of the surrounding environment.

The demonstration follows a recent update to Figure's Helix System 0 AI model, which now combines visual perception with whole-body motion control.

Previously, the system depended on proprioception, allowing the robot to monitor its own body position and movement. The upgraded model adds input from onboard stereo cameras, enabling the robot to build a three-dimensional view of its surroundings while tracking its own posture in real time.

Figure said the AI was trained end-to-end with reinforcement learning in simulated environments featuring randomized terrain. The company says the system transfers those learned behaviors directly to physical robots without additional calibration, helping them navigate stairs, ladders, and uneven ground more effectively.

The company also recently said it has increased production of Figure 03 from one robot per day to one per hour and has delivered more than 350 units.

More than a viral robot video

The ladder demonstration comes as humanoid robotics companies face growing pressure to prove their machines can perform practical work beyond carefully staged demos.

Advertisement

Potential applications include factories, warehouses, construction sites, and maintenance jobs where workers regularly encounter stairs, ladders, and uneven surfaces. A robot that can safely move through those environments could take on a wider range of tasks than one limited to flat floors.

Still, the latest demonstration leaves important questions unanswered. Figure has not disclosed success rates, testing conditions, or how the robot performs under more demanding scenarios, such as carrying equipment or operating in poor weather.

The bigger picture

Figure's latest video highlights how the focus of humanoid robotics is shifting from simply walking to navigating environments built for people. Mobility skills such as climbing, balancing, and adapting to changing terrain may ultimately matter more to commercial customers than eye-catching demonstrations alone.

For businesses evaluating humanoid robots, the milestone is encouraging but not conclusive. The real measure will be whether robots can repeat these tasks reliably, safely, and at scale in unpredictable workplaces where mistakes carry high operational and safety costs.

Read more: Google’s Gemini AI Is Learning to Control Humanoid Robots, extending the race to give machines the intelligence and physical coordination needed to operate in the real world.


Aminu Abdullahi

Aminu Abdullahi is a B2C and B2B technology and finance writer with more than six years of experience covering enterprise IT, cybersecurity, cloud computing, artificial intelligence, fintech, business software, and emerging technologies. His work has appeared in publications including TechRepublic, eWEEK, Channel Insider, Geekflare, Enterprise Networking Planet, eSecurity Planet, CIO Insight, and Webopedia. With a technical background in computer science, he specializes in translating complex technology topics into clear, accessible content for business leaders and decision-makers.

eWeek Logo

eWeek has the latest technology news and analysis, buying guides, and product reviews for IT professionals and technology buyers. The site's focus is on innovative solutions and covering in-depth technical content. eWeek stays on the cutting edge of technology news and IT trends through interviews and expert analysis. Gain insight from top innovators and thought leaders in the fields of IT, business, enterprise software, startups, and more.

Property of TechnologyAdvice. © 2026 TechnologyAdvice. All Rights Reserved

Advertiser Disclosure: Some of the products that appear on this site are from companies from which TechnologyAdvice receives compensation. This compensation may impact how and where products appear on this site including, for example, the order in which they appear. TechnologyAdvice does not include all companies or all types of products available in the marketplace.