发表机构
University of California, Berkeley; KTH Royal Institute of Technology; Intuitive Surgical（加州大学伯克利分校; 瑞典皇家理工学院; 直觉外科公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出首个智能体机器人框架AGRO-SUVIDE，用于外科粘弹性清创，通过模块化技能构建与监控，在dVRK上实现85%的单碎片移除成功率，并泛化至五碎片场景。
AI 中文摘要
增强灵巧性有潜力减少外科医生在重复性手术任务中经历的疲劳。在本文中，我们提出了首个用于外科粘弹性清创（AGRO-SUVIDE）的智能体机器人框架，该任务涉及反复移除附着在粘弹性基质上的小碎片。利用智能体的自我改进和编码能力，AGRO-SUVIDE采用模块化框架。具体而言，演示分析模块利用视觉和运动信息，从单个专家演示中自动识别重复出现的技能。构建模块随后构建每个技能，要么作为基于模型的程序化技能（智能体根据脚手架库进行编码），要么作为基于无模型策略的技能。在运行时，监控模块将技能组合成一个循环式图，其大小根据观察到的碎片数量而定，然后验证每个技能的前置和后置条件，以决定是推进还是重试。我们通过da Vinci研究套件（dVRK）上的340次物理试验评估了AGRO-SUVIDE。AGRO-SUVIDE实现了平均单碎片移除成功率为85%，连续三个碎片移除成功率为60%，在一次人工干预下达到95%。它进一步泛化到未见过的五碎片场景，单碎片移除平均成功率为80%。项目页面：此https URL。
英文摘要
Augmented dexterity has the potential to reduce the fatigue experienced by surgeons during repetitive surgical tasks. In this paper, we propose the first AGentic RObotics framework for SUrgical VIscoelastic DEbridement (AGRO-SUVIDE), the repeated removal of small fragments attached to a viscoelastic substrate. Leveraging the self-improving and coding capability of agents, AGRO-SUVIDE adopts a modular framework. Specifically, the demonstration analysis module automatically identifies recurring skills from a single expert demonstration, using both visual and kinematic information. The construction module then builds each skill, either as a procedural model-based skill the agent codes against a scaffolded library or as a model-free policy-based skill. At runtime, the monitoring module composes the skills into a loop-style graph sized to the number of fragments it observes, then verifies pre- and post-conditions of each skill to decide whether to advance or retry. We evaluate AGRO-SUVIDE through 340 physical trials on the da Vinci Research Kit (dVRK). AGRO-SUVIDE achieves an average single-fragment removal success rate of 85%, completing consecutive three-fragment removal at 60% and at 95% with one human intervention. It further generalizes to unseen five-fragment scenarios with an average success rate of 80% for single-fragment removal. Project page: https://surgical-robotics.github.io/AGRO-SUVIDE/
