论文arXiv 2611.217714 天前
开源达芬奇手术器械模块适配UR5e实现电外科精准控制与数据记录
本文由 AI 根据公开内容整理,可能有误,请以原文为准:An Open-Source da Vinci X/Xi Instrument Module for Laparoscopic Surgery Research(arXiv 2611.21771)
核心内容
针对腹腔镜手术研究中机器人运动与电外科能量激活难以同步记录的痛点,该研究推出适配Universal Robots UR5/UR5e机械臂的开源da Vinci X/Xi器械驱动模块。该系统通过五电机皮带传动驱动弹簧加载盘,并设计专用电外科信号拦截器,在保留医生脚踏板优先权的同时,完整记录所有激活请求来源与时序。台架测试验证了12次激活/去激活事件的零丢失记录能力,并在离体脾脏凝固与胆囊切除实验中完成单/双极电外科操作验证。
硬件架构采用五电机经同步带驱动弹簧加载盘的机械接口,配合光学追踪系统对Fenestrated Bipolar Forceps进行标定,将俯仰和偏航增益从0.904/1.14精确校正至1.00/1.02。软件层面通过interposer实现电外科指令的软件下发与硬件踏板信号仲裁,确保研究级机器人能同步采集器械位姿、视频流及能量触发源标签。该模块化设计解决了传统手术机器人研究平台缺乏标准化电外科交互接口的问题,为具身智能手术算法提供了高保真多模态数据集构建基础。
关键看点
- 机电驱动架构:五电机经同步带驱动弹簧加载盘,物理复现da Vinci X/Xi器械末端运动学特性
- 信号同步记录:电外科拦截器实现软件指令与脚踏板信号仲裁,台架测试12次事件记录零丢失
- 运动学标定精度:光学追踪校准使双极钳俯仰/偏航增益由0.904/1.14收敛至1.00/1.02
- 离体实验验证:在脾脏凝血与胆囊解剖场景中成功执行单极切割与双极凝固等真实电外科任务
工程与产业观察
该开源模块填补了通用协作机器人与专业手术器械间的控制鸿沟,其核心价值在于构建了包含运动、视觉与能量触发时序的多模态对齐数据集。对于具身智能手术研发,这种硬件级信号同步机制是训练端到端策略模型、验证安全约束算法的必要基础设施,显著降低了自建高精度手术实验平台的工程门槛。
英文摘要 (Abstract)
Studying electrosurgical tasks on a research robot requires control of both instrument motion and energy activation, along with a record of when each action occurs. This paper presents an open-source module for da Vinci X/Xi instruments on a UR5/UR5e robotic arm. Five motors transmit torque through timing belts to spring-loaded drive discs. An electrosurgical interposer accepts software commands, gives the surgeon's foot pedals priority, and records the source of each activation request. In bench testing, the interposer recorded all 12 activation and deactivation events from six pedal presses. Ex vivo demonstrations included monopolar and bipolar coagulation of splenic tissue and monopolar cutting during gallbladder dissection. Optical tracking of the Fenestrated Bipolar Forceps showed that calibration brought pitch and yaw gains from 0.904 and 1.14 to 1.00 and 1.02, respectively. The module enables researchers to record instrument motion, video, and the timing and source of electrosurgical commands during laparoscopic tasks.
作者:Douglas McDonough, Justin Liao, Jiawei Ge, Antony Goldenberg, Yvonne Zhang, Mackenzie A Eagleson, Ravi Prakash, Axel Krieger, Chunwoo Kim
外部来源
本页事实对应的公开页面,以原文为准。(点击将离开本站)