EndoNav：语言引导机器人内窥检查的语义-几何接地
Original title: EndoNav: Semantic-to-Geometric Grounding for Language-Guided Robotic Endoscopic Examination
Source: arXiv cs.ROPublish time unverified
EndoNav 将外科医生口令经视角智能体转为结构化可视化目标，再经几何约束运动规划自主调整内窥镜；在尸检标本鼻窦检查中可视化 IoU 达 87%，接近两位外科医生之间的一致水平（87.44%）。
AI summary · AI generated
arXiv:2608.22093v1 Announce Type: new Abstract: Minimally invasive procedures performed within confined anatomical spaces depend on continuous endoscopic visualization. Current robotic endoscope systems can stabilize or reposition an endoscope, but they do not possess relevant context to provide effective visualization assistance.