1 dépôt
Awesome GitHub RepositoriesAction Inference
The process of generating physical control commands from multimodal vision-language model outputs.
Distinct from Vision-Language Models: Specifically targets the generation of physical actions, whereas Vision-Language Models covers the general architecture.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Action Inference. Refine with filters or upvote what's useful.
Awesome Action Inference GitHub Repositories
Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
- physical-intelligence/openpi
Physical-Intelligence/openpi
12,377Voir sur GitHubOpenPi is a vision-language-action robot control framework designed to generate physical control actions for robotic systems. It functions as a distributed robot model trainer, a model format converter, and a robot action streaming server. The framework provides tools for transforming model checkpoints between different framework formats to ensure interoperability across various development environments. It also includes a server that uses websocket connections to stream model-generated control actions from remote inference servers to physical robot hardware in real-time. The system supports
Generates direct physical control commands for robots by processing visual and textual inputs through VLA models.
Python
