Building the internet of human action
🤖
Joined March 2026
- Tweets19
- Following1
- Followers1.9K
- Likes102
We’re already collecting tactile data across several industrial & commercial environments. If you’re interested in partnering up, please reach out at [email protected]
Mitts come with full-hand tactile sensing, built in:
-450+ sensing points across the palm and fingers
-Detect as little as 5g, captured at 30 Hz
-Synchronised recording with your favorite phone or camera rig, including iPhone and RoboCap by @BitRobotNetwork
Today, we are proud to introduce… Mitts 🧤
State of the art tactile gloves that capture high-precision touch data for robots.
Vision alone isn’t enough. Mitts record touch and movement with world-class precision, helping robots learn to work in the physical world.
We’re already collecting tactile data across several industrial & commercial environments. If you’re interested in partnering up, please reach out at [email protected]
Mitts come with full-hand tactile sensing, built in:
-450+ sensing points across the palm and fingers
-Detect as little as 5g, captured at 30 Hz
-Synchronised recording with your favorite phone or camera rig, including iPhone and RoboCap by @BitRobotNetwork
4/ Now we want to push it further.
If you’re exceptional at SLAM, tracking, sensing, or robotics hardware, we’re hiring:
[email protected]
And if you want access to the data these rigs produce, we’d love to chat:
[email protected]
3/ Our stack combines synchronized stereo egocentric vision + wrist-mounted UMI + SLAM to recover precise 6-DoF human manipulation trajectories in a common world frame.
At 2 mm median TCP error, we’ve made high-fidelity action capture deployable at real-world scale.
2/ Why does this matter?
We’re trying to solve a deceptively hard problem:
Turn arbitrary human activity, anywhere in the world, into robot-usable trajectories with millimeter-level spatial accuracy.
No mocap room. No instrumented factory.
Just put the rig on and go 🏎️ 💨
1/ 2 mm.
That’s the median TCP tracking error we’re now achieving across our latest collection activities with our in-house SLAM stack.
This clip was captured inside a 300-person manufacturing site in Delhi, India.
Neocambrian AI retweeted
Why see less when more see do trick? 👀
1900*1280 @ 30 FPS with 6 cam frame sync under 120us boundary skew.
Another first in India for @NeocambrianAI 🔥
Neocambrian AI retweeted
India is a goldmine of diverse data. People looking down on data businesses don’t take the bitter lesson and history of DL seriously enough. Creating imagenet as one of the first hills to climb was as key a contribution as running NNs on GPUs.
The “scale” of these businesses in *each* domain - text, vision, driving, speech has been crazy and embodied intelligence is both the most starved and likely the hardest.
Today, we announce @NeocambrianAI
The future of AI will be physical. But Physical AI has no internet scale dataset to learn from.
We’re building the data foundation of Physical AI - a high fidelity, pre training scale database of Human Action.
From India. For the world.
Neocambrian AI retweeted
huge. @NeocambrianAI is upto some amazing stuff
Today, we announce @NeocambrianAI
The future of AI will be physical. But Physical AI has no internet scale dataset to learn from.
We’re building the data foundation of Physical AI - a high fidelity, pre training scale database of Human Action.
From India. For the world.
Neocambrian AI retweeted
Bullish
Today, we announce @NeocambrianAI
The future of AI will be physical. But Physical AI has no internet scale dataset to learn from.
We’re building the data foundation of Physical AI - a high fidelity, pre training scale database of Human Action.
From India. For the world.
Neocambrian AI retweeted
Today, we announce @NeocambrianAI
The future of AI will be physical. But Physical AI has no internet scale dataset to learn from.
We’re building the data foundation of Physical AI - a high fidelity, pre training scale database of Human Action.
From India. For the world.
Neocambrian AI retweeted
Scaling laws came for language. Now they’re coming for hands.
One bottle. One episode. Millions more to go.
@NeocambrianAI
Neocambrian AI retweeted
Slowly, slowly, then all at once ✌️ @NeocambrianAI