TRI Diffusion Policy / Large Behavior ModelsToyota Research Institute
Robot foundation models
Toyota Research Institute · AI model
TRI Diffusion Policy / Large Behavior Models
In September 2023 TRI showed that 'Diffusion Policy', a generative method borrowed from image AI, could teach robots dexterous skills such as pouring and tool use from a few demonstrations, and framed it as a step towards Large Behavior Models for robots. TRI said it had taught over 60 skills and aimed for 1,000 by the end of 2024. In October 2024 it agreed to work with Boston Dynamics on Atlas.
- Kind
- Robot foundation models
- Maker
- Toyota Research InstituteUnited States
- First year
- 2023
- Weights
- —Not published
- Robots
- —Not published
- Country
- United States
Other robot foundation models
Newest first.
- 2026Isaac GR00T N1.7NVIDIA · 2 robot models
- 2026π0.7Physical Intelligence · 1 robot model
- 2026Helix 02 (and Helix 2.5)Figure AI · 1 robot model
- 2026Gemini Robotics 2 (with ER 2 and On-Device 2)Google DeepMind · 1 robot model
- 2025Isaac GR00T N1NVIDIA · 1 robot model
- 2025Isaac GR00T N1.5NVIDIA · 1 robot model
- 2025Isaac GR00T N1.6NVIDIA
- 2025π0.5Physical Intelligence · 1 robot model
- 2025π*0.6 (pi-star 0.6)Physical Intelligence
- 2025HelixFigure AI · 1 robot model
Sources
From the maker, its papers and reputable press.
Statistics only, not advice. No affiliation, sponsorship or endorsement. How we work · Terms