Repository
Research
Diffusion Policy
A visuomotor policy approach using diffusion to generate robot actions.
Robot policies
Models / Research
Gemini Robotics
Google DeepMind robotics models connecting perception and action.
Overview
Google DeepMind robotics models connecting perception and action.
Compare observation inputs, action representations, adaptation data and inference requirements. Code licensing and model-weight licensing may differ; review both before deployment. A source repository may have an open code license while its checkpoints have separate terms.
Browse this resource’s categories
Explore related collections
Vision-language-action models ↗More in Models
Repository
Research
Website
Research
openpi
Code and model resources for Physical Intelligence robot policies.
Vision-language-action
Repository
Research
NVIDIA Isaac GR00T
Robot foundation-model resources for humanoid learning workflows.
Vision-language-action
Repository
Research
Octo
A generalist robot policy framework for adapting across manipulation tasks.
Robot policies
Repository
Research
alpamayo1.5 · NVlabs
NVIDIA Alpamayo 1.5 Nano is an open 10B reasoning VLA model for autonomous vehicles with reinforcement-learning enhanced reasoning, navigation guidance, and visual question answering.
Vision-language-action
Repository
Research
iros20 6d pose tracking · wenbowen123
se(3)-TrackNet provides 6D object-pose tracking research and visual-feedback-control examples.
Perception models