Embodied-R1：强化的具身推理用于通用机器人操作
Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
AI总结：
本文提出Embodied-R1，通过引入指向作为统一的中间表示，结合强化微调方法，实现通用机器人操作中的具身推理，展示了在多个基准测试中的卓越性能和零样本泛化能力。
摘要：
在具身AI中，泛化能力受制于“感知-行动鸿沟”，这源于数据稀缺和具身异质性。为了解决这一问题，我们开创性地引入“指向”作为统一的、与具身无关的中间表示，定义了四种核心具身指向能力，连接高级视觉语言理解与低级动作原语。我们引入了专门设计用于具身推理和指向的3B视觉语言模型（VLM）Embodied-R1。我们使用各种具身和通用视觉推理数据集构建大规模数据集Embodied-Points-200K，以支持关键的具身指向能力。然后，我们使用双阶段强化微调（RFT）课程训练方法，结合专门的多任务奖励设计来训练Embodied-R1。Embodied-R1在11个具身空间和指向基准测试中实现了最先进的性能。关键的是，它通过在SIMPLEREnv中达到56.2%的成功率，在8个现实世界XArm任务中达到87.5%的成功率，无需任何任务特定的微调，比强基线提高了62%。此外，该模型在多样化的视觉干扰下表现出高度的鲁棒性。我们的工作表明，以指向为中心的表示结合RFT训练范式，为闭合机器人中的感知-行动鸿沟提供了一条有效且可泛化的路径。
英文摘要：
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.
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。
