jimmyyhwu/tidybot
A mobile manipulator robot that uses large language models to learn and apply personalized user preferences for household cleanup tasks.

TidyBot is a real-world robot system that combines language-based planning and perception with the few-shot summarization capabilities of large language models to infer generalized user preferences. The system learns from a handful of examples how a particular person prefers objects to be organized, then applies those learned preferences to future interactions. The approach achieves 91.2% accuracy on unseen objects in benchmark testing and successfully puts away 85.0% of objects in real-world scenarios.
Frequently asked
- What is jimmyyhwu/tidybot?
- A mobile manipulator robot that uses large language models to learn and apply personalized user preferences for household cleanup tasks.
- Is tidybot open source?
- Yes — jimmyyhwu/tidybot is open source, released under the MIT license.
- What language is tidybot written in?
- jimmyyhwu/tidybot is primarily written in Python.
- How popular is tidybot?
- jimmyyhwu/tidybot has 695 stars on GitHub.
- Where can I find tidybot?
- jimmyyhwu/tidybot is on GitHub at https://github.com/jimmyyhwu/tidybot.