Dobb·E
towards home robots with an open-source platform. Dobb·E is an open-source framework for teaching robots household tasks via imitation learning in 20 minutes. The framework uses a simple tool called the Stick, collects a dataset called Homes of New York (HoNY) with it, and then trains a representation learning model, Home Pretrained Representations (HPR) with it. Then, Dobb·E uses five minutes of collected data in a new home for a novel task and within fifteen minutes, gives a policy that can solve the task with 81% average success rate. Proud to share our open-source robot platform, Dobb·E, a home robot system that needs just 5 minutes of human teaching to learn new tasks.

반응 (1)
비슷한 프로덕트
설명이 비슷한 순
Foosbar
github.comMy autonomous foosball-playing robot
OK-Robot
ok-robot.github.ioopen, modular home robot framework for pick-and-drop anywhere
I've made an AI powered interactive demo builder
news.ycombinator.comHoloib is a platform that allows you to create interactive product demos in minutes and share them via a link or embed them anywhere.
Humbug
github.coman open source AI dev environment mostly built by AI
MyCoder
github.coman open source Claude-Code alternative