HumynexSurg-1：一个精选的专家吸脂手术数据集
HumynexSurg-1: A Curated Expert Liposuction Dataset
浏览论文内容
中文总结 AI 辅助
该研究发布HumynexSurg-1，一个含同步力、视频和语音的专家吸脂手术数据集，用于训练手术机器人基础模型，并验证了GR00T N1.7的快速微调能力。
中文摘要 AI 辅助
机器人基础模型从大型演示语料库中学习操作技能，但手术操作在这些语料库中缺失：在780小时的Open-H手术数据集中，仅有一个数据集包含同步力信息，且没有数据集涵盖美容手术。吸脂手术是其中的难点，因为器械在皮肤下工作，外科医生依靠触觉和判断进行操作。Humynex Robotics为这类手术构建了精选的专家数据集。HumynexSurg-1是首个发布的数据集：由一位资深吸脂手术专家在猪腹部组织上进行操作，并对每个决策进行叙述，同时记录同步的抽吸压力、六轴手部力/力矩、俯视RGB-D视频、侧视视频和领夹式麦克风——共14个片段，42,738帧，35.6分钟，356条语音，其中95%可编译为吸脂专用标签模式。采集过程遵循一项专利申请中的感知方案，该方案围绕策略所需的数量进行组织，因此今天由模型捕获的通道可以在不改变数据格式的情况下，明天升级为传感器。本次发布将器械运动捕获为侧视视频中的工具-手轨迹，并提供力通道作为状态；已获资助的采集将增加测量得到的6自由度手柄位姿、经过验证的力通道、脂肪层超声成像和触诊感知。作为概念验证，NVIDIA Isaac GR00T N1.7在无需自定义代码的情况下，每次运行不到一小时即可在该数据集上微调并学习记录的会话；在同一片段上的扩展探针显示了进一步收益的来源：每个新会话都会降低未见会话上的误差。该数据集、其标签模式、质量保证报告和评估协议是本次发布的成果；下一次采集，即使用此处命名的传感器对脂肪区域进行多次短会话采集，是探针所指向的方向。
英文摘要
Robot foundation models learn manipulation from large demonstration corpora, but surgery is missing from those corpora: across the 780-hour Open-H surgical collection, one dataset carries synchronized force and none covers an aesthetic procedure. Liposuction is the hard case, because the instrument works under the skin and the surgeon operates by feel and by judgment. Humynex Robotics builds curated expert datasets for this kind of procedure. HumynexSurg-1 is the first release: a master liposuction surgeon performing on porcine abdominal tissue while narrating every decision, recorded with synchronized suction pressure, six-axis hand force/torque, top-down RGB-D video, side video and a lavalier microphone -- 14 episodes, 42,738 frames, 35.6 minutes, 356 utterances of which 95% compile into a liposuction-specific label schema. The capture follows a patent-pending sensing plan organized around the quantities a policy needs, so a channel captured today by a model can be upgraded to a sensor tomorrow without changing the data format. This release captures the instrument motion as a tool-hand track in the side video and provides the force channel as state; the funded capture adds a measured 6-DoF handle pose, a validated force channel, ultrasound imaging of the fat layer, and palpation sensing. As a proof of concept, NVIDIA Isaac GR00T N1.7 fine-tunes on the dataset with no custom code in under an hour per run and learns the recorded sessions; scaling probes on the same episodes show where further gains come from: every new session lowers the error on an unseen session. The dataset, its label schema, its quality-assurance reports and its evaluation protocol are the product; the next capture, many short sessions across fat regions with the sensors named here, is what the probes point to.
发表机构
- Humynex Robotics, Inc.（Humynex Robotics 公司）
机构由 AI 辅助整理，请以论文原文为准。
