Saved in:
Bibliographic Details
Main Authors: Jiang, Tao, Yuan, Tianyuan, Liu, Yicheng, Lu, Chenhao, Cui, Jianning, Liu, Xiao, Cheng, Shuiqi, Gao, Jiyang, Xu, Huazhe, Zhao, Hang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.00576
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We present Galaxea Open-World Dataset, a large-scale, diverse collection of robot behaviors recorded in authentic human living and working environments. All demonstrations are gathered using a consistent robotic embodiment, paired with precise subtask-level language annotations to facilitate both training and evaluation. Building on this dataset, we introduce G0, a dual-system framework that couples a Vision-Language Model (VLM) for multimodal planning with a Vision-Language-Action (VLA) model for fine-grained execution. G0 is trained using a three-stage curriculum: cross-embodiment pre-training, single-embodiment pre-training, and task-specific post-training. A comprehensive benchmark spanning tabletop manipulation, few-shot learning, and long-horizon mobile manipulation, demonstrates the effectiveness of our approach. In particular, we find that the single-embodiment pre-training stage, together with the Galaxea Open-World Dataset, plays a critical role in achieving strong performance.