Independent product intelligence · Worldwide · 2026-05-01 → 2026-07-31
Dobb·E is an open-source system for learning robotic manipulation in household settings. It uses a demonstration collection tool and pre-trained models to quickly learn and execute new tasks.
Traffic & engagement
Search demand
AI referral visibility
Product profile
Traffic makes more sense when you can connect it to the actual product promise.
“Dobb·E”
Dobb·E is an open-source system for learning robotic manipulation in household settings. It uses a demonstration collection tool and pre-trained models to quickly learn and execute new tasks.
4 of 8 signal groups are available for this product: identity, authority and backlinks, AI referrals, search demand.
Not measured for this domain: traffic and engagement, audience demographics, country distribution, acquisition mix. Those sections are left out of the page rather than filled with estimates.
Canonical website: https://dobb-e.com
Observed across 1 discovery source.
Research questions
Every answer is tied to a source we collected, and the questions with no evidence behind them are left unanswered rather than guessed.
Dobb·E is used for learning and executing new robotic manipulation tasks in household settings. It is designed for situations where a general-purpose robot needs to adapt to novel tasks in a home environment, such as in the 10 New York City homes where it was tested across 109 different tasks.
Dobb·E is targeted at robotics researchers, developers, and enthusiasts who want to build and deploy household robots. The system is open-source and designed to accelerate research on home robots, providing a full pipeline from hardware designs to models and code.
Dobb·E includes a demonstration collection tool called 'The Stick', a dataset called Homes of New York (HoNY), a pretrained representation learning model (Home Pretrained Representations or HPR), and the full software stack. It features a 81% average success rate on 109 tested tasks and can learn a new task in 20 minutes.
Dobb·E achieves an average success rate of 81% on new tasks. The system can learn a new task in about 20 minutes, which includes five minutes of demonstration collection and fifteen minutes of model adaptation in a new home.
Dobb·E is an open-source system for teaching robots to perform household tasks through imitation learning. It addresses the problem of creating a generalist domestic assistant that can adapt and learn new tasks, unlike single-purpose machines like dishwashers or robot vacuums. The system allows a user to demonstrate a task and have the robot learn it in about 20 minutes.
Dobb·E is an open-source, general framework for learning household robotic manipulation, which uses imitation learning to teach robots new tasks with a simple demonstration tool and pre-trained models.
Behind the lock
Worldwide estimates · Data period 2026-05-01 → 2026-07-31. Figures are measured estimates intended for market research. Signals we have not measured for this domain are omitted, never estimated; a measured zero is still reported as zero. How this was measured