Releases

Physical Intelligence introduced π0.7, a steerable general-purpose robot model with stronger compositional generalization across tasks and embodiments.

Physical Intelligence released reinforcement-learning-specialized π*0.6 policies for high-performance dexterous robot tasks alongside π0.6.

Physical Intelligence introduced the π0.6 generalist robot model and reinforcement-learning-specialized π*0.6 variants for dexterous tasks.

Physical Intelligence introduced π0.5, a vision-language-action model focused on open-world generalization and unseen environments.

Physical Intelligence released π0 model weights, code and supporting resources for research use.

Physical Intelligence introduced π0-FAST, using efficient FAST action tokenization for autoregressive robot control.

Physical Intelligence introduced π0, a general-purpose vision-language-action flow model trained on diverse robot data.