THE APPLICATION OF VISUAL-BASED ACUPOINT POSITIONING TECHNOLOGY IN ACUPOINT ROBOTS

作者：MengDi Wang, Dianhao Wu, Yi Wang, Qiao Fang, ZhenBiao Chen, KunLin Xie · 发表于：Eurasia Journal of Science and Technology · 年份：2026 · DOI：10.61784/ejst3150 · 研究领域：Acupuncture Treatment Research Studies、Gaze Tracking and Assistive Technology、Traditional Chinese Medicine Studies

Acupuncture efficacy depends on the precision of acupoint localization. Based on prior research, this paper proposes a technical framework for automatic facial acupoint positioning and robotic acupuncture: facial information is captured using RGB-D vision, and an improved YOLOv8 model detects 27 index acupoints across 15 categories, enabling precise three-dimensional coordinate mapping for localization. A specialized end-effector integrating needle exchange, holding, and rotation functions converts lifting, thrusting, twisting, retention, and withdrawal into linear and rotational motions. An enhanced APF-RRT* algorithm is proposed to achieve obstacle-avoidance path planning during continuous multi-acupoint needling. Experiments conducted with UR5e, Kinect V2, and a simulated human head demonstrate that the system achieves average errors of 0.54 mm, 0.50 mm, and 0.66 mm in the three dimensions, achieving millimeter-level accuracy in acupoint localization.