arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.02776cs.RO
收藏

XR-1:通过学习统一的视觉-运动表示实现多功能的视觉-语言-动作模型

XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations

Beijing Innovation Center of Humanoid Robotics, Beijing, China(北京人形机器人创新中心,北京,中国);School of Mechanical Engineering and Automation, Beihang University, Beijing, China(北京航空航天大学机械工程及自动化学院,北京,中国);State Key Laboratory of Virtual Reality Technology and Systems, SCSE, Beihang University, Beijing, China(虚拟现实技术与系统国家重点实验室,SCSE,北京航空航天大学,北京,中国);State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China(多媒体信息处理国家重点实验室,计算机科学学院,北京大学,北京,中国)

Shichao Fan, Kun Wu, Zhengping Che, Xinhua Wang, Di Wu, Fei Liao, Ning Liu, Yixue Zhang, Zhen Zhao, Zhiyuan Xu, Meng Li, Qingjie Liu, Shanghang Zhang, Min Wan, Jian Tang

AI总结:

XR-1通过学习统一的视觉-运动表示,解决视觉-语言-动作模型在低级动作生成和跨数据源领域差距的挑战,提出三阶段训练方法并验证了其在多种机器人和任务上的优越性能。

摘要:

XR-1通过学习统一的视觉-运动表示,解决视觉-语言-动作模型在低级动作生成和跨数据源领域差距的挑战,提出三阶段训练方法并验证了其在多种机器人和任务上的优越性能。

英文摘要:

Recent progress in large-scale robotic datasets and vision-language models (VLMs) has advanced research on vision-language-action (VLA) models. However, existing VLA models still face two fundamental challenges: (i) producing precise low-level actions from high-dimensional observations, (ii) bridging domain gaps across heterogeneous data sources, including diverse robot embodiments and human demonstrations. Existing methods often encode latent variables from either visual dynamics or robotic actions to guide policy learning, but they fail to fully exploit the complementary multi-modal knowledge present in large-scale, heterogeneous datasets. In this work, we present X Robotic Model 1 (XR-1), a novel framework for versatile and scalable VLA learning across diverse robots, tasks, and environments. XR-1 introduces the \emph{Unified Vision-Motion Codes (UVMC)}, a discrete latent representation learned via a dual-branch VQ-VAE that jointly encodes visual dynamics and robotic motion. UVMC addresses these challenges by (i) serving as an intermediate representation between the observations and actions, and (ii) aligning multimodal dynamic information from heterogeneous data sources to capture complementary knowledge. To effectively exploit UVMC, we propose a three-stage training paradigm: (i) self-supervised UVMC learning, (ii) UVMC-guided pretraining on large-scale cross-embodiment robotic datasets, and (iii) task-specific post-training. We validate XR-1 through extensive real-world experiments with more than 14,000 rollouts on six different robot embodiments, spanning over 120 diverse manipulation tasks. XR-1 consistently outperforms state-of-the-art baselines such as $π_{0.5}$, $π_0$, RDT, UniVLA, and GR00T-N1.5 while demonstrating strong generalization to novel objects, background variations, distractors, and illumination changes. Our project is at https://xr-1-vla.github.io/.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑