R

RT-1-X

Model

RT-1-X is a member of the RT-X model family, trained on the collaborative Open X-Embodiment Dataset contributed by 34 institutions. It extends the original RT-1 (Robotics Transformer) architecture with cross-embodiment transfer capabilities enabled by large-scale multi-robot training data.

Details

Updated:6/21/2026

open sourcefalse

release date2023-10-17

paper urlhttps://arxiv.org/abs/2310.08864

model familyRT-X

Tags

robotics-transformergoogle-deepmindVLArt-x-familycross-embodimentgeneralist-policymulti-embodiment

Relationships

Open X-Embodiment

Sources

Open X-Embodiment Official Website

website

Open X-Embodiment: Robotic Learning Datasets and RT-X Models

paper

Appears In

Vision-Language-Action Models

An overview of Vision-Language-Action (VLA) models that enable robots to understand language instructions and perform manipulation tasks.