Robot Utility Models: open-source robots working in new envs zero shot
Hi all! Sharing our latest work on Robot Utility Models: open source robot models for some useful tasks like door or drawer opening at ~90% success rate that should just work out of the box (given that you have a robot, of course.) Why is this exciting? The state of the art for robot learning thus far has been reliant on pre-training/fine-tuning paradigm: models are first trained on large datasets, then you bring it to your own environment, collect more data, and fine-tune the model on that data. This is not ideal if you want to make robots that work in every home out of the box of…
In plain words
Robot Utility Models provides open-source robot models designed to perform tasks like door and drawer opening with approximately 90% success rate without requiring environment-specific training. Built for roboticists and developers, these models work out-of-the-box across different homes and environments. The approach prioritizes high-quality, diverse training data collected across multiple environments rather than requiring fine-tuning in each new setting, addressing a key limitation in existing robot learning methods.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi all! Sharing our latest work on Robot Utility Models: open source robot models for some useful tasks like door or drawer opening at ~90% success rate that should just work out of the box (given that you have a robot, of course.) Why is this exciting? The state of the art for robot learning thus far has been reliant on pre-training/fine-tuning paradigm: models are first trained on large datasets, then you bring it to your own environment, collect more data, and fine-tune the model on that data. This is not ideal if you want to make robots that work in every home out of the box of course. We're finally free of this status quo! We showed experimentally how the key to this discovery is getting data that is both HIGH QUALITY and DIVERSE. High quality means don't just let anyone collect robot data, and diversity means go to as many different environments as you can to collect your data. We have a final piece that helps the robot get even better, which is simply asking GPT! You give a series of your environment images to GPT and ask it if the robot failed or succeeded. If it says the robot failed, you reset and retry! Just this simple trick helps the algorithm a lot. We've also open sourced all of our code, models, data, and training code. We believe people should be able to go out there and create their own utility models for tasks that they care about, which I find very exciting! Would love to hear your thoughts, or suggestions for next steps.
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 1d ago · opentrailpaper.com
Launched alongside, September 2024
the whole month →
BeforeSunset AI 2.0▲1,267Personalized AI daily planning that suits your life
AI · 2024 · beforesunset.ai
