Dobb-E

Visit Tool

Dobb·E is an open-source framework for learning household robotic manipulation. It provides hardware and software components to build and program robots for domestic tasks.

Claim this tool

2Views

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is dobb-e?

Dobb·E is an open-source, general framework designed for learning household robotic manipulation. It provides both hardware and software components, including 3D printable STL files for a demonstration collection tool called "The Stick," and software for processing collected data. The framework also includes code for training policies using pretrained models and deploying learned policies on robots. Dobb·E aims to enable robots to learn new tasks with minimal user demonstration, leveraging a dataset of 1.5 million RGB-D frames collected in various home environments. This initiative seeks to accelerate research in home robotics and address unique challenges encountered in real-world household settings.

Best used for

Ideal for developers and researchers who need to build and program robots for household tasks, train robotic policies with minimal data, and deploy these systems in novel home environments. Especially valuable for accelerating research in general-purpose home robotics.

Common actions

develop robotic systems

train robot policies

collect robotic data

deploy home robots

"AI Agents"face swappinggithub copilotlow-code/no-codecollaborationworkflowsopen-sourceautomated workflowdeepfake

Capabilities

Key features

Open-source hardware designs
Data collection software
Pretrained vision models
Robot policy training
Robot deployment code

Target Audience

developerdata scientistresearcher

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What hardware components does Dobb·E provide?

Dobb·E provides open-source 3D printable STL files for "The Stick," a hardware tool designed for comfortably collecting robotic demonstrations in homes. Instructions for setting up The Stick are also included in the repository.

How does Dobb·E enable robots to learn new tasks quickly?

Dobb·E utilizes a demonstration collection tool ("The Stick") to gather data, and then trains Home Pretrained Representations (HPR) on a large dataset. With just five minutes of user demonstrations and fifteen minutes of adapting the HPR model, Dobb·E can reliably solve new tasks.

What is the Homes of New York (HoNY) dataset?

The HoNY dataset is a collection of 1.5 million RGB-D frames, gathered using The Stick across 22 homes and 216 environments in New York City. This dataset is used to train the lightweight foundational vision model called Home Pretrained Representations (HPR).

Trending

Subcategories trending in AI Agents & Automation

AI Frameworks & Infra Chatbots & Conversational AI General-Purpose Agents Workflow Agents Personal Assistants RAG & Document AI

Trending

Also listed in

This tool also appears in

Coding & Development › Open Source & Models Content & Design › Product & Industrial Design

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce