Dobb·E — towards home robots with an open-source platform. It was shared on Show HN in 2023 and received 394 upvotes on Hacker News. 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. Dishwashers, laundry machines, stand mixers, and robot vacuums are just a few recent examples. The concept of a “generalist machine” in homes - a domestic assistant that can adapt and learn from our needs, all while remaining cost-effective - has long been a goal in robotics that has been steadily pursued for decades. Dobb·E can learn a new task with only five minutes of a user showing it how to do it, thanks to a demonstration collection tool ("The Stick") we built out of cheap parts and iPhones. We use the Stick to collect 13 hours of data in 22 homes of New York City, and train Home Pretrained Representations (HPR). Here are sample rollouts from each of the tasks. To address this, we built the Stick , a demonstration collection tool we built out of a $25 Reacher-grabber stick, some 3D printed parts, and an iPhone. HPR is a ResNet-34 model trained on the HoNY dataset using the MoCo-v3 self-supervised learning objective. During deployment,we used HPR to initialize a policy, the trunk of which was simply our pretrained ResNet-34 model followed by two linear layers on top. The website content is licensed CC ANS 4.0 .