vix.ing · top · new · best · stats · spec

π0.5: a Vision-Language-Action Model with Open-World Generalization

2025/04/22 by Physical Intelligence, Intelligence, Physical, Kevin Black +66 · 303 citations
Social Sciences · #Religion and Sociopolitical Dynamics in Nigeria #Geographic Information Systems Studies #African history and culture analysis

paper · pdf · doi:10.48550/arxiv.2504.16054

Abstract

In order for robots to be useful, they must perform practically relevant tasks in the real world, outside of the lab. While vision-language-action (VLA) models have demonstrated impressive results for end-to-end robot control, it remains an open question how far such models can generalize in the wild. We describe π0.5, a new model based on π0 that uses co-training on heterogeneous tasks to enable broad generalization. π0.5 uses data from multiple robots, high-level semantic prediction, web data, and other sources to enable broadly generalizable real-world robotic manipulation. Our system uses a combination of co-training and hybrid multi-modal examples that combine image observations, language commands, object detections, semantic subtask prediction, and low-level actions. Our experiments show that this kind of knowledge transfer is essential for effective generalization, and we demonstrate for the first time that an end-to-end learning-enabled robotic system can perform long-horizon and dexterous manipulation skills, such as cleaning a kitchen or bedroom, in entirely new homes.

Cited by

Related