arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.14979cs.RO
收藏

RynnBrain: 开放式具身基础模型

RynnBrain: Open Embodied Foundation Models

DAMO Academy, Alibaba Group（达摩院，阿里巴巴集团）
Ronghao Dang, Jiayan Guo, Bohan Hou, Sicong Leng, Kehan Li, Xin Li, Jiangpin Liu, Yunxuan Mao, Zhikai Wang, Yuqian Yuan, Minghao Zhu, Xiao Lin, Yang Bai, Qian J… 展开作者

Ronghao Dang, Jiayan Guo, Bohan Hou, Sicong Leng, Kehan Li, Xin Li, Jiangpin Liu, Yunxuan Mao, Zhikai Wang, Yuqian Yuan, Minghao Zhu, Xiao Lin, Yang Bai, Qian Jiang, Yaxi Zhao, Minghua Zeng, Junlong Gao, Yuming Jiang, Jun Cen, Siteng Huang, Liuyi Wang, Wenqiao Zhang, Chengju Liu, Jianfei Yang, Shijian Lu, Deli Zhao

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

RynnBrain提出了一种开放的具身基础模型，通过统一框架强化感知、推理、规划等能力，显著优于现有模型，并能高效适应多种具身任务。

摘要：

尽管多模态基础模型在快速进步，但具身智能社区仍然缺乏一个统一的、物理上可信的基础模型，该模型能够在现实世界的空间-时间动态中整合感知、推理和规划。我们引入了RynnBrain，一个开源的空间-时间基础模型，用于具身智能。RynnBrain在统一框架中强化了四项核心能力：全面的以自我为中心的理解、多样的空间-时间定位、物理上可信的推理以及物理感知的规划。RynnBrain家族包括三个基础模型规模（2B、8B和30B-A3B MoE）和四个经过后训练的变体，专门针对下游具身任务（如RynnBrain-Nav、RynnBrain-Plan和RynnBrain-VLA）或复杂的空间推理任务（如RynnBrain-CoP）。在对20个具身基准测试和8个通用视觉理解基准测试的广泛评估中，我们的RynnBrain基础模型在现有具身基础模型上显著领先。经过后训练的模型套件进一步证明了RynnBrain基础模型的两个关键潜力：（i）使物理上可信的推理和规划成为可能，（ii）作为强大的预训练骨干，能够高效适应各种具身任务。

英文摘要：

Despite rapid progress in multimodal foundation models, embodied intelligence community still lacks a unified, physically grounded foundation model that integrates perception, reasoning, and planning within real-world spatial-temporal dynamics. We introduce RynnBrain, an open-source spatiotemporal foundation model for embodied intelligence. RynnBrain strengthens four core capabilities in a unified framework: comprehensive egocentric understanding, diverse spatiotemporal localization, physically grounded reasoning, and physics-aware planning. The RynnBrain family comprises three foundation model scales (2B, 8B, and 30B-A3B MoE) and four post-trained variants tailored for downstream embodied tasks (i.e., RynnBrain-Nav, RynnBrain-Plan, and RynnBrain-VLA) or complex spatial reasoning tasks (i.e., RynnBrain-CoP). In terms of extensive evaluations on 20 embodied benchmarks and 8 general vision understanding benchmarks, our RynnBrain foundation models largely outperform existing embodied foundation models by a significant margin. The post-trained model suite further substantiates two key potentials of the RynnBrain foundation model: (i) enabling physically grounded reasoning and planning, and (ii) serving as a strong pretrained backbone that can be efficiently adapted to diverse embodied tasks.

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。

↑