Founder 🖖@menloresearch. Building @asimovinc, @jandotai
Joined December 2008
- Tweets1.7K
- Following3.7K
- Followers2.1K
- Likes8.3K
Daniel Ong retweeted
@asimovinc has been spotted walking in HF office 👀🤗
Some say it also dances 🕺 should I show it here ?
Daniel Ong retweeted
Using simulation to teach robots would unblock the massive scale of robotics data that seems to be missing right now. The issue is usually sim-to-real transfer; MolmoBOT aims to solve this with sufficient diversity of simulation data, so that no real data is necessary for robot deployment. It has a few parts: MolmoBot-Engine produces diverse pick-and-place demonstrations across many different simulated environments; MolmoBot-Data is a dataset of 1.7 million expert trajectories for item manipulation and pick-and-place tasks; and they train a number of VLA policies which can achieve strong performance on real-world pick-and-place tasks with zero real robot data. @rosemhendrix, @SnehalJauhri, Abhay Deshpande, and Maya Guru join us to give us the details.
To learn more, watch RoboPapers episode 113 with @chris_j_paxton and @ruijie_sg!
Daniel Ong retweeted
Trained a new stand up policy from scratch for the @asimovinc.
Used the lab I’ve been building and did all the training on my MacBook Pro.
Learned a whole lot about torque limits.
You can train your own sim and I’ve uploaded everything I learned & weights ⬇️
Daniel Ong retweeted
AI for CAD is Great in creating assembly work instructions. I build this for @menloresearch , the assembly of Asimov arm.
I shared this on LinkedIn and 9 companies sent me their CAD files.
Try the instruction below
Daniel Ong retweeted
Unitree's CEO just shrank his own timeline for robotics' "ChatGPT moment".
August: 2-3 years best case, up to a decade.
Now: 1-2 years.
What changed? GPT-6 Astra.
Independent test, YAM robot arms, zero robot-specific training:
Block into a bowl: 19/20
Puzzle piece into a slot: 2/20
The "brain" for rough pick-and-place is basically here. Precision contact work is not.
Wang's own bar is 80% of tasks in 80% of unfamiliar environments. ChatGPT Astra clears the easy half.
Winners: actuators, reducers, dexterous hands (the exact bottleneck Astra exposed).
Under pressure: robot-specific model startups.
source: SCMP
Daniel Ong retweeted
Today, I’m excited to introduce @safeworldai!
Our mission: improve robot safety for the next billion machines.
AI is moving from screens into the physical world. Robots are becoming more capable, more autonomous, and increasingly operating around people.
But more capable robots require more capable ways to test them. 🧵
Daniel Ong retweeted
Your next robotics project could start with these steps.
Today, we're open-sourcing Asimov 1's locomotion policy and the training code behind it, giving developers a foundation to build on.
Alongside the trained policy checkpoint, we're sharing our Isaac Lab-based training code, including reward definitions, hardware-tuned actuator configurations, and domain randomization settings.
That foundation gives you a starting point for your own experiments. Adapt the training setup to hardware changes. Explore different walking styles. Build toward new capabilities.
We've taken the first steps.
Build what comes next.
Asimov 1 locomotion: github.com/menloresearch/isa…
Daniel Ong retweeted
Napkin to 20 countries in a year. Hardware isn’t supposed to move like that. Love it.
Daniel Ong retweeted
10,000+ microducks were pre-ordered in just five days!
We weren't expecting that many (it's more than the total number of reachy mini in a year) and it will generate delays so from now on, it will be first-ordered, first shipped to make it fair for everyone!
Daniel Ong retweeted
People don't realize it, but even with only 1 GB of RAM, the memory alone is already 10–15% of Microduck's total price.
Crazy when you consider there are 15 actuators in the robot.
Daniel Ong retweeted
After coming back to Singapore, I’m convinced we have all the ingredients to become a global leader in Embodied AI: world-class talent, a growing industry, strong resources, strategic advantages, and most importantly, the ambition to make it happen.
My group at NUS is looking for highly motivated students at all levels: magiclab-nus.github.io
Daniel Ong retweeted
What makes something a "ChatGPT moment" is decided by industry benchmarks and academic evals but mostly by real users.
But that say, really kudos to see promptable robot.
Daniel Ong retweeted
Asimov 1 is shipping to its first owners this month.
Less than a year after the project started, @menloresearch is putting its open-source humanoid into customer hands.
Asimov 1:
🟠 $20,000 complete DIY kit
🟠 1.2m / 35kg
🟠 25 actuated DOF
🟠 Open CAD + BOM
🟠 Simulation support
🟠 Developer API
🟠 ~20 hours to assemble after recent design improvements
But Menlo's ambition extends well beyond selling robots.
The company wants Asimov to become an open reference platform supported by OEMs, manufacturers, service partners and eventually 100,000 robot developers.
🎥 Credits: @asimovinc
