GR-3 Technical Report

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Cheang, Chilam, Chen, Sijin, Cui, Zhongren, Hu, Yingdong, Huang, Liqun, Kong, Tao, Li, Hang, Li, Yifeng, Liu, Yuxiao, Ma, Xiao, Niu, Hao, Ou, Wenxuan, Peng, Wanli, Ren, Zeyu, Shi, Haixin, Tian, Jiawen, Wu, Hongtao, Xiao, Xin, Xiao, Yuyang, Xu, Jiafeng, Yang, Yichu
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916857148080128
author Cheang, Chilam
Chen, Sijin
Cui, Zhongren
Hu, Yingdong
Huang, Liqun
Kong, Tao
Li, Hang
Li, Yifeng
Liu, Yuxiao
Ma, Xiao
Niu, Hao
Ou, Wenxuan
Peng, Wanli
Ren, Zeyu
Shi, Haixin
Tian, Jiawen
Wu, Hongtao
Xiao, Xin
Xiao, Yuyang
Xu, Jiafeng
Yang, Yichu
author_facet Cheang, Chilam
Chen, Sijin
Cui, Zhongren
Hu, Yingdong
Huang, Liqun
Kong, Tao
Li, Hang
Li, Yifeng
Liu, Yuxiao
Ma, Xiao
Niu, Hao
Ou, Wenxuan
Peng, Wanli
Ren, Zeyu
Shi, Haixin
Tian, Jiawen
Wu, Hongtao
Xiao, Xin
Xiao, Yuyang
Xu, Jiafeng
Yang, Yichu
contents We report our recent progress towards building generalist robot policies, the development of GR-3. GR-3 is a large-scale vision-language-action (VLA) model. It showcases exceptional capabilities in generalizing to novel objects, environments, and instructions involving abstract concepts. Furthermore, it can be efficiently fine-tuned with minimal human trajectory data, enabling rapid and cost-effective adaptation to new settings. GR-3 also excels in handling long-horizon and dexterous tasks, including those requiring bi-manual manipulation and mobile movement, showcasing robust and reliable performance. These capabilities are achieved through a multi-faceted training recipe that includes co-training with web-scale vision-language data, efficient fine-tuning from human trajectory data collected via VR devices, and effective imitation learning with robot trajectory data. In addition, we introduce ByteMini, a versatile bi-manual mobile robot designed with exceptional flexibility and reliability, capable of accomplishing a wide range of tasks when integrated with GR-3. Through extensive real-world experiments, we show GR-3 surpasses the state-of-the-art baseline method, $π_0$, on a wide variety of challenging tasks. We hope GR-3 can serve as a step towards building generalist robots capable of assisting humans in daily life.
format Preprint
id arxiv_https___arxiv_org_abs_2507_15493
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GR-3 Technical Report
Cheang, Chilam
Chen, Sijin
Cui, Zhongren
Hu, Yingdong
Huang, Liqun
Kong, Tao
Li, Hang
Li, Yifeng
Liu, Yuxiao
Ma, Xiao
Niu, Hao
Ou, Wenxuan
Peng, Wanli
Ren, Zeyu
Shi, Haixin
Tian, Jiawen
Wu, Hongtao
Xiao, Xin
Xiao, Yuyang
Xu, Jiafeng
Yang, Yichu
Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
We report our recent progress towards building generalist robot policies, the development of GR-3. GR-3 is a large-scale vision-language-action (VLA) model. It showcases exceptional capabilities in generalizing to novel objects, environments, and instructions involving abstract concepts. Furthermore, it can be efficiently fine-tuned with minimal human trajectory data, enabling rapid and cost-effective adaptation to new settings. GR-3 also excels in handling long-horizon and dexterous tasks, including those requiring bi-manual manipulation and mobile movement, showcasing robust and reliable performance. These capabilities are achieved through a multi-faceted training recipe that includes co-training with web-scale vision-language data, efficient fine-tuning from human trajectory data collected via VR devices, and effective imitation learning with robot trajectory data. In addition, we introduce ByteMini, a versatile bi-manual mobile robot designed with exceptional flexibility and reliability, capable of accomplishing a wide range of tasks when integrated with GR-3. Through extensive real-world experiments, we show GR-3 surpasses the state-of-the-art baseline method, $π_0$, on a wide variety of challenging tasks. We hope GR-3 can serve as a step towards building generalist robots capable of assisting humans in daily life.
title GR-3 Technical Report
topic Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.15493