Founder @ REVEL | Making Robot Training Stupid Simple.
US
Joined October 2011
- Tweets427
- Following234
- Followers1.6K
- Likes1.2K
What does a day in our 3D printing team look like? From request to finished robot part, meet the people behind the prints. Building @REVELROBOTICS Ep. 8.
youtube.com/watch?v=opUc8A9r…
Labeling precision CNC parts sounds simple. It isn't. Every part sits a little differently, and people can only do it for a few hours at a stretch. That is the kind of work @REVELROBOTICS was built for: dexterous tasks factories can no longer hire for. youtu.be/SvGjYg5u5Ec
Robots building robots. We spent time with Mazak to see what precision machining looks like when robots join the line. Building REVEL Ep. 10 is out now. youtu.be/9_RCk_0uk_U
Most robot data shows what a hand did. Almost none shows how hard it gripped or what the worker intended. At @REVELROBOTICS we capture from the puppeteer, not the puppet: force, motion and intent from skilled workers. youtu.be/R3SZj6ASw8k
Best weekly read in robotics. The pace this year is wild, and almost every story comes back to one thing: robots need better data to learn real skills.
Building a robotics company takes a little delusional optimism. Kamil and I sat down to talk about why we started @REVELROBOTICS, why we chose real manufacturing problems, and how we use human data to teach robots new skills. Full conversation: youtu.be/4DcYYgHi2W0
A humanoid company hitting Nasdaq is a milestone for the whole category. Public markets are betting on robots that do real work. The next race is teaching them skills fast.
Churchill Capital Corp XI (Nasdaq: CCXI) shareholders today approved the business combination with Agility Robotics.
Closing is expected Nov. 4, with trading expected to begin Nov. 5 on Nasdaq as AGLT.
Thank you to CCXI shareholders and our investors.
Read the announcement: agilityrobotics.com/content/…
Must watch. Foundation models for robots are only as good as the data behind them. Sim and video get you far, but real human hands doing real work is what closes the gap.
From dreaming to doing. 🤖
Join NVIDIA’s @DrJimFan at #CoRL2026 to explore how world models, robot foundation models, and agentic robotics can bring frontier AI into the physical world.
📅 Nov. 9 | 1:50 p.m. CST
Explore the keynote: nvda.ws/3WkMyg7
Big win for European deep tech. Robots shipping to real customers out of Europe is exactly the signal the ecosystem needs. Building @REVELROBOTICS from Prague, we see the talent here every day.
🚨 BREAKING:
@anybotics just started customer deliveries of ANYmal X.
It's the world’s first legged inspection robot certified for explosive atmospheres.
Four years of engineering. More than ten patents, and a problem most experts said was impossible to solve.
I spent some time deploying robots in oil and gas environments. I know exactly how hard this is. Getting ATEX certification for any piece of equipment in a hazardous zone is a brutal process, component by component, failure mode by failure mode, with independent certification bodies scrutinising every decision.
For a fixed sensor or a handheld device it’s already hard. For a legged robot with high-power motors, a large battery, exposed cameras, autonomous docking and the need to climb stairs and navigate narrow walkways?
Most engineers would tell you it can’t be done, but Swiss ANYbotics did it anyway! 🇨🇭
The technical challenge is extraordinary:
→ Every ignition risk across the robot’s entire service life had to be identified and mitigated
→ AI computer and inspection equipment enclosed in nitrogen-filled sealed chambers
→ All twelve leg actuators and battery protected by flameproof casings
→ Tested against shock, vibration, corrosion, solar radiation and salt mist
→ Certified to both ATEX (Europe) and IECEx (global) standards
ANYmal X ships as a complete end-to-end inspection solution, autonomous navigation, industrial AI for data interpretation, and direct integration into SAP, Yokogawa and SLB maintenance systems.
Undetected equipment failures cost the world’s 500 largest companies $1.4 trillion per year in preventable downtime.
In oil and gas, a single hour of unplanned downtime can cost up to $500,000. US extraction workers face a fatality rate seven times the national average.
ANYmal X goes into the zones humans shouldn’t be in. Autonomously. Repeatedly. With full data flowing back into the maintenance system.
@fankhauser put it simply: “The areas that matter most were off-limits to robots like ours. That changes today.”
BIG RESPECT TO THE TEAM BEHIND THIS ROBOT!
~~
♻️ Join the weekly robotics newsletter, and never miss any news → ziegler.substack.com
Humanoids leaving a factory line is the moment the bottleneck moves from hardware to skills. Every robot that ships needs to learn real work. That is the problem we are solving at @REVELROBOTICS with human data.
Brian Walker retweeted
A closer look at the movement and grip of our robotic hand 🖐️
In this demo, our co-founder Kamil shows how the hand moves and what it feels like when the robotic fingers close around a human hand.
With a high degree of freedom, the hand is designed to reproduce complex, human-like movements, bringing us closer to more capable and adaptable humanoid robots.
Follow along as we build the future of manufacturing here at @REVELROBOTICS 🦾
Brian Walker retweeted
This robotic hand can be 3D printed by anyone and assembled in under 8 hours.
Researchers at ETH Zurich created the Orca hand, fully open-sourced with artificial bones and tendons.
For context, advanced robotic hands cost over $100,000 and require constant maintenance...
Orca costs under $2,000. 50x less (!)
A self-calibration system maps every motor to every joint, eliminating the manual tuning that tendon-driven hands usually need.
Each fingertip has built-in tactile sensors covered by silicone skin.
The hand can actually feel when it touches something, giving it feedback to grip objects without crushing them or letting them slip.
It can hold over 20 lbs, learn tasks by watching human demonstrations, and transfer skills trained in simulation directly to the real world.
The team proved its durability by having it pick up and place a cube over 2,000 times across 7 hours with no human intervention.
The full design files and source code are open source, so any robotics lab in the world can start building one today.