Dobb·E

Project webpage · Documentation (gitbooks) · Paper

Authors: Mahi Shafiullah*, Anant Rai*, Haritheja Etukuru, Yiqian Liu, Ishan Misra, Soumith Chintala, Lerrel Pinto

Open-source repository of the Home Pretrained Representation (HPR) of Dobb·E and the associated paper, On Bringing Robots Home

What's on this repo

You can find our Home Pretrained Models (HPR), which is a ResNet34 model trained on our dataset, Homes of New York (HoNY), in this repo. You can download the weights if you want, or you can get started by using Timm.

import timm

model = timm.create_model("hf_hub:notmahi/dobb-e", pretrained=True)

You can read more about it on our paper or our website.

Let's bring some robots home!