
@BitRobotNetworki
iAccount based inSingapore
About this account
- Account based in
- Singapore
- Connected via
- Web
Account-level information from X, not a live location or the device used for a specific post.
The world's open robotics lab. Apply now.
bitrobot.ai
Joined November 2024
- Tweets1.6K
- Following1.8K
- Followers11K
- Likes4.6K
Pinned Tweet
1/ Better robot models come from better data.
That takes two things: hardware that captures it fully, and tooling that turns it into training signal.
We built the first. Today, @GroundedSI launches the second: Grounded API. Access both hardware + API ↓
BitRobot 🦾 retweeted
💎 Thanks to @BitRobotNetwork for being a Diamond Sponsor of #CoRL2026! 🤖
📊 Scaling robot learning starts with better real-world data
🧢 Their RoboCap wearable enables scalable egocentric data collection, with synced head + hand tracking xitter.cf/BitRobotNetwork/status…
1/ Better robot models come from better data.
That takes two things: hardware that captures it fully, and tooling that turns it into training signal.
We built the first. Today, @GroundedSI launches the second: Grounded API. Access both hardware + API ↓
BitRobot 🦾 retweeted
Special Shoutout to our friends in @anvil_robotics @AGIBOTofficial @MeckaAI @xdofai @robocurve @cortexairobot @makermodsai @GenrobotAI @eastworlds_io @BitRobotNetwork @ScaleAILabs @LeRobotHF @huggingface @roborobots @ROBOTIS for helping us with our early beta testing across Asia, Europe, and the Americas Europe and America 🌍.
A truly global stress test of Dream-1 before our launch!
Replying to @dreamlabs_ai @robocurve
Anywhere you have an internet connection, you can prompt Dream-1 to control your robot.
Here are rollouts from beta testers from 8 countries, and from our office in SF.
Congrats to @axisrobotics on their TGE.
SN/04 contributors who completed the Axis Alliance tasks were rewarded twice, in Axis points and BitRobot Bolts.
We're building the world's open robotics lab. Start here and earn: app.bitrobot.ai
Thanks @KhalaResearch for this deep dive into robot learning and how industry leaders are tackling the data bottleneck.
Great to see our subnet partner @axisrobotics featured alongside BitRobot’s ecosystem crowdsourcing data across teleoperation, simulation, and ego video!
Robotics is still waiting for its "ChatGPT" moment
Language models had the internet to learn from, while robots need diverse physical demonstrations that are expensive to collect
Bessemer estimated just 300,000 hours of robot manipulation data globally in April, while others believe robotics could require 100M+ training hours
Bessemer projects $3B+ in robot-data spending over two years
Open networks are using crypto incentives to coordinate contributors across simulation, teleoperation and human video collection
Axis reports 7M+ trajectories from 220K+ contributors, with its data lifting task success from 83.9% to 88.8% on the LIBERO-Plus simulation benchmark
Our latest report explores the data opportunity through Axis, BitRobot, Eastworlds & THOR
Full report in the next post below
We're joining @TheHumanoidHub for their inaugural conference in SF today and tomorrow alongside @GroundedSI
Meet the team, get hands-on with our RoboCap + RoboWrist bundle, and see SOTA data enrichment in action.
Register below ↓
Join us and other teams from Dyna, 1X, Physical Intelligence, and more. luma.com/humanoid-hub-confer…
Thank you @atlasberry008 for this in-depth intro to the RoboCap platform with data enrichment from @GroundedSI
We're cooking new earning opportunities for the RoboCap subnet in the coming weeks. Stay tuned 👀
BitRobot will pay you to wear a $500 hat at work.
Six cameras, pointed at your hands.
Robots have almost no training data, but people have all of it.
So the hats are going into bakeries, hotels and factories.
I would rather own what the humanoids learn from than fund the humanoids.
The first Humanoid IKEA Assembly Challenge, co-organized with @UnitreeRobotics, @LightwheelAI and @singaporetech, took place at @ieeeiros.
9 global teams tested their loco-manipulation policies to assemble an IKEA UTTER children’s table. Full results ↓
A major robotics challenge is getting lab-trained policies to work reliably in the real world. Lighting, noise, crowds, and unfamiliar settings are all externalities.
That’s why we run the Grand Challenges: to test generalization in new environments, measure consistency, and set benchmarks that push robotics beyond the lab.
Congrats to the 9 teams and thanks to the co-organizers @lightwheelAI @singaporetech @unitreerobotics for making the first humanoid IKEA assembly challenge happen.
Excited to see where the benchmark goes. Follow here for info about the next competition: humanoid-ikea-assembly-chall…
BitRobot 🦾 retweeted
A really cool competition that pushes the frontier of what's possible in embodied ai. This is a really hard task -- paper is unforgiving -- and no one nailed it but substantial progress was made. Excited to see what people can do next year
The first ever Origami Challenge with @SharpaRobotics at @ieeeiros IROS 2026 concluded.
We asked teams to fold a paper airplane to test policies in dexterous manipulation.
14 global teams made it to the final round. Here are the results ↓
BitRobot 🦾 retweeted
A simple paper airplane. A serious challenge for robotic dexterity. ✈️🤖
Proud to team up with @BitRobotNetwork for the first-ever Origami Challenge at #IROS2026.
Huge congratulations to all 14 finalist teams! Excited to see how far we can push the boundaries of dexterous manipulation together.
The first ever Origami Challenge with @SharpaRobotics at @ieeeiros IROS 2026 concluded.
We asked teams to fold a paper airplane to test policies in dexterous manipulation.
14 global teams made it to the final round. Here are the results ↓
The first ever Origami Challenge with @SharpaRobotics at @ieeeiros IROS 2026 concluded.
We asked teams to fold a paper airplane to test policies in dexterous manipulation.
14 global teams made it to the final round. Here are the results ↓
Every team ran identical hardware: bimanual arms with Sharpa Hands, the same rig in sim, in the remote eval lab, and on the floor at IROS.
@SharpaRobotics is ahead of the field on tactile sensing and DoF (with 10 fingertips and 6-axis tactile, a 65-D joint space), making this challenging task more attemptable.
DUM-E (@aakash_hash) earned the top placement with a score of 50/100.
Congrats to DUM-E and all 14 teams in the first origami challenge, and thanks to our co-organizers: Sharpa, Lightwheel, Nippon Origami Association, and more.
Stay tuned for the next iteration of the challenge: robotic-origami-challenge.gi…
The Earth Rover Challenge at @ieeeiros IROS 2026 is a wrap.
12 teams from all over the world, 4 tracks, 3 days, and one question: can an AI policy drive a sidewalk rover the way a human can?
We heard directly from participants and posted the full leaderboard below ↓
Every team drove the same hardware across every track: the @frodobots Earth Rover Mini+, on city streets, off-road trails, indoors and on the marathon route.
They trained on Berkeley-FrodoBots-7K, our open-source dataset of human teleop driving on @huggingface.
Thank you to every team that traveled from around the world and @ieeeiros for allowing us to host the 3rd iteration of the Earth Rover Challenge
Congrats @ITC_TampereUni team on 1st place: @suomela_L @bhowmik_abhi @Sasakuruppu
The datasets and the SDK are open, and the benchmark remains unbeaten. See you at the next one: earth-rover-challenge.github…














