AI News AI资讯 7h ago Updated 5h ago 更新于 5小时前 48

Xiaomi-Robotics-1 shows that more data beats bigger models when training robots to move 小米机器人1号表明,在训练机器人移动时,更多数据比更大的模型更有效

Xiaomi released Xiaomi-Robotics-1, a foundational robot AI model that scales similarly to Large Language Models, with performance improving significantly as training data increases. To bypass the scarcity of robotic movement data, Xiaomi utilized handheld grippers with cameras to collect over 100,000 hours of motion recordings across diverse environments, avoiding expensive physical robot teleoperation. The dataset was efficiently labeled using an auxiliary AI model to generate text descriptions 小米发布Xiaomi-Robotics-1机器人基础模型,遵循类似大语言模型的缩放定律,性能随数据量增加而显著提升。 创新性地使用手持机械臂配合摄像头采集数据,规避了实体机器人操作的高成本与低效问题,构建了超10万小时的多环境运动数据集。 实验表明,在机器人AI中,增加训练数据带来的性能增益远大于增加模型算力,数据规模是提升泛化能力的关键。 该模型在未见过的环境中表现出强大的适应能力,仅需少于10小时的少量数据微调即可在包装、洗衣等任务中达到75%的成功率。 在RoboCasa365和RoboDojo等标准基准测试中,Xiaomi-Robotics-1取得了当前最佳成绩,大幅领先于竞争对手如P

68
Hot 热度
72
Quality 质量
65
Impact 影响力

Analysis 深度分析

TL;DR

  • Xiaomi released Xiaomi-Robotics-1, a foundational robot AI model that scales similarly to Large Language Models, with performance improving significantly as training data increases.
  • To bypass the scarcity of robotic movement data, Xiaomi utilized handheld grippers with cameras to collect over 100,000 hours of motion recordings across diverse environments, avoiding expensive physical robot teleoperation.
  • The dataset was efficiently labeled using an auxiliary AI model to generate text descriptions for each motion segment, allowing for scalable annotation in approximately two weeks.
  • Empirical tests demonstrate that increasing training data yields greater performance gains than increasing model size, with success rates in unfamiliar environments rising from 25% to 75%.
  • The model achieves state-of-the-art results on benchmarks like RoboCasa365 and RoboDojo, adapting to new tasks with less than ten hours of additional training data per task.

Why It Matters

This development addresses the critical data bottleneck in embodied AI, demonstrating that scalable, cost-effective data collection methods can rival traditional, expensive teleoperation techniques. It provides a clear roadmap for researchers and engineers to prioritize massive, diverse dataset accumulation over mere model parameter expansion for robotic generalization.

Technical Details

  • Data Collection Strategy: Replaced physical robot arms with handheld grippers equipped with cameras, enabling data capture in real-world settings (kitchens, offices, outdoors) without dedicated robotic hardware.
  • Automated Annotation: Utilized a separate AI model to automatically generate textual descriptions for over 100,000 hours of motion data, solving the labor-intensive labeling problem.
  • Scaling Laws: Demonstrated that for vision-action models, data volume is a more significant driver of performance improvement than computational budget or model size, diverging from the balanced scaling of pure LLMs.
  • Performance Metrics: Achieved a 75% average success rate on four distinct manipulation tasks (e.g., packing, laundry) with under ten hours of task-specific fine-tuning, outperforming competitors like Physical Intelligence’s pi0.7.
  • Benchmark Leadership: Secured top positions on the RoboCasa365 and RoboDojo leaderboards, particularly excelling in unseen composite tasks and handling deformable materials.

Industry Insight

The industry must shift focus from purely architectural innovation to aggressive, scalable data acquisition strategies, as data diversity and quantity appear to be the primary limiting factors in current robotic AI capabilities. Companies should consider hybrid data collection methods, such as using consumer-grade hardware for broad environmental coverage, to build robust foundation models before deploying them on specialized physical platforms.

TL;DR

  • 小米发布Xiaomi-Robotics-1机器人基础模型,遵循类似大语言模型的缩放定律,性能随数据量增加而显著提升。
  • 创新性地使用手持机械臂配合摄像头采集数据,规避了实体机器人操作的高成本与低效问题,构建了超10万小时的多环境运动数据集。
  • 实验表明,在机器人AI中,增加训练数据带来的性能增益远大于增加模型算力,数据规模是提升泛化能力的关键。
  • 该模型在未见过的环境中表现出强大的适应能力,仅需少于10小时的少量数据微调即可在包装、洗衣等任务中达到75%的成功率。
  • 在RoboCasa365和RoboDojo等标准基准测试中,Xiaomi-Robotics-1取得了当前最佳成绩,大幅领先于竞争对手如Physical Intelligence的pi0.7模型。

为什么值得看

这篇文章揭示了机器人人工智能领域的一个关键转折点:数据规模比模型参数大小更能决定性能上限,这为行业提供了明确的技术演进方向。对于AI从业者和机器人公司而言,它提供了一种低成本、高效率的数据采集范式,解决了长期制约机器人泛化能力的“数据瓶颈”问题。

技术解析

  • 数据采集创新:摒弃昂贵的实体机器人遥操作,采用便携式手持机械臂(UMI)搭配摄像头,由人工直接操控记录动作。这种方法覆盖了厨房、办公室、工厂等1700多种不同环境,收集了超过10万小时的运动数据,极大降低了数据获取成本并提高了多样性。
  • 自动化标注流程:针对海量视频数据,利用另一个AI模型自动为每个运动片段生成文本描述,仅用两周时间完成了全数据集的标注,解决了传统人工标注不切实际的问题。
  • 缩放规律验证:研究发现,与视觉数据类似,机器人模型的预测误差降低主要依赖于训练数据的增加,而非单纯扩大模型规模。随着预训练数据量的增加,模型在陌生环境中的成功率从25%提升至75%,且尚未触及性能天花板。
  • 少样本学习能力:通过结合自有公寓录制数据、开源数据集和标注后的UMI数据进行后训练,模型能够以少于10小时的新任务数据快速适应新指令,在打包手机、洗衣机装载等复杂操作中表现优异。

行业启示

  • 数据成为核心资产:机器人AI的竞争焦点正从算法架构转向高质量、大规模、多样化的数据集构建。企业应优先投资数据基础设施和采集工具,而非仅仅追求模型参数的堆叠。
  • 低成本采集范式的普及:手持设备辅助数据采集可能成为行业标准做法,因为它打破了物理限制,允许在非结构化环境中高效获取丰富数据,加速了从仿真到现实(Sim-to-Real)的迁移。
  • 开源生态的重要性:小米计划开源模型及代码,这将促进社区协作和基准测试的统一,有助于行业快速迭代并解决通用机器人泛化难题,同时也加剧了围绕数据质量和规模的竞争。

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Robotics 机器人 Training 训练 Dataset 数据集 Research 科学研究