Asimov
@asimovinc
Asimov is the most developer-friendly robot by @menloresearch.
Pre-order:
17 Following 24.4K Followers
We're open-sourcing Menlo SDK so you can build your own applications for a humanoid robot.
The SDK connects your code to Asimov 1, letting you control its movements and read its state. With the full source available, you can build on the existing foundation and adapt it to what your project needs.
You can use it to replay a motion, control the robot through a VR headset, or run your trained policy on real hardware.
We're also open-sourcing Asimov Edge, the software that runs on the robot, checks incoming commands, and manages control between your application, a gamepad and other controllers.
- SDK:
- Docs:
- Order yours:
Keep going.
Show more
Asimov 1’s entire training + sim2real code is out there!! Use it to train policies for Asimov!!
This is why we included the training code. As a non-technical team member, I'm using it to train Asimov 1 to get back up after a fall, from different starting positions and on rough ground.
Show more
You can start training a humanoid before you own one.
Asimov 1's open-source training code gives you a foundation to train and evaluate locomotion policies in simulation.
Train your own policy:
Show more
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:
Show more
Unofficial stress test. Asimov 1 locomotion policy keeps getting stronger.
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. 🧵
Show more
Oct 15-16, San Francisco
The first edition of the HUMANOID HUB Conference,
in collaboration with @hackersquadio
Registration link ⏬
Build something that will change the world.
Yes! We've open-sourced everything you need to train a humanoid robot
@freelerobot Humble beginnings of a tai chi policy! This is so fun! Trained on Kaggle
Very excited for @asimovinc to be supported soon in the fantastic @huggingface ecosystem!
100 Microducks vs 1 Asimov who-will-win battle soon 😂?
What we're working on - Menlo Community Talk #21#
Day 2 of training Asimov 1. The first thing I wanted to change was how it walked. It was taking short, shuffling steps, with one knee barely bending. It's better now, with longer steps, feet that clear the ground, and both legs moving more evenly.
Show more
I love the orange accent.
Keep going and make reality catch up.
David is one of the early Asimov 1 builders. He's out to prove that anyone can build a humanoid robot at home.
@tspy @asimovinc We will prove it can be made at home.
Asimov 1 is the humanoid robot you can build your own solutions on.
I trained a new locomotion policy for Asimov 1 using the recipe in @asimovinc's repo. It can now get up and walk.
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:
Show more
See how to bring Asimov 1 from the ground to standing and lower it back down.
