实体化R1：面向通用机器人操作的强化实体推理

Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation

August 19, 2025

作者: Yifu Yuan, Haiqin Cui, Yaoting Huang, Yibin Chen, Fei Ni, Zibin Dong, Pengyi Li, Yan Zheng, Jianye Hao

cs.AI

摘要

在具身人工智能中，泛化能力受到“视知行动鸿沟”的制约，这一鸿沟源于数据稀缺性与具身形态的多样性。为解决此问题，我们开创性地将“指向”作为一种统一、与具身形态无关的中间表示，定义了四项核心的具身指向能力，以此连接高层次的视觉语言理解与低层次的动作基元。我们推出了Embodied-R1，一个专为具身推理与指向设计的30亿参数视觉语言模型（VLM）。通过整合广泛的具身及通用视觉推理数据集，我们构建了大规模数据集Embodied-Points-200K，该数据集支持关键的具身指向能力。随后，我们采用两阶段强化微调（RFT）课程，配合专门的多任务奖励设计，对Embodied-R1进行训练。Embodied-R1在11项具身空间与指向基准测试中达到了业界领先水平。尤为重要的是，它展现了强大的零样本泛化能力，在SIMPLEREnv环境中取得了56.2%的成功率，并在无需任务特定微调的情况下，在8项真实世界XArm任务中平均达到87.5%的成功率，相较于强劲基线提升了62%。此外，该模型在面对多种视觉干扰时表现出极高的鲁棒性。我们的研究表明，以指向为核心的表示方法，结合RFT训练范式，为缩小机器人领域的感知-行动差距提供了一条有效且可泛化的途径。

English

Generalization in embodied AI is hindered by the "seeing-to-doing gap," which stems from data scarcity and embodiment heterogeneity. To address this, we pioneer "pointing" as a unified, embodiment-agnostic intermediate representation, defining four core embodied pointing abilities that bridge high-level vision-language comprehension with low-level action primitives. We introduce Embodied-R1, a 3B Vision-Language Model (VLM) specifically designed for embodied reasoning and pointing. We use a wide range of embodied and general visual reasoning datasets as sources to construct a large-scale dataset, Embodied-Points-200K, which supports key embodied pointing capabilities. We then train Embodied-R1 using a two-stage Reinforced Fine-tuning (RFT) curriculum with a specialized multi-task reward design. Embodied-R1 achieves state-of-the-art performance on 11 embodied spatial and pointing benchmarks. Critically, it demonstrates robust zero-shot generalization by achieving a 56.2% success rate in the SIMPLEREnv and 87.5% across 8 real-world XArm tasks without any task-specific fine-tuning, representing a 62% improvement over strong baselines. Furthermore, the model exhibits high robustness against diverse visual disturbances. Our work shows that a pointing-centric representation, combined with an RFT training paradigm, offers an effective and generalizable pathway to closing the perception-action gap in robotics.