Retinal microsurgery is a high-precision surgery performed on an exceedingly delicate tissue. It now requires extensively trained and highly skilled surgeons. Given the restricted range of instrument motion in the confined intraocular space, and also potentially restricting instrument contact with the sclera, snake-like robots may prove to be a promising technology to provide surgeons with greater flexibility, dexterity, space access, and positioning accuracy during retinal procedures requiring high precision and advantageous tooltip approach angles, such as retinal vein cannulation and epiretinal membrane peeling. Kinematics modeling of these robots is an essential step toward accurate position control, however, as opposed to conventional manipulators, modeling of these robots does not follow a straightforward method due to their complex mechanical structure and actuation mechanisms. Especially, in wire-driven snake-like robots, the hysteresis problem due to the wire tension condition can have a significant impact on the positioning accuracy of these robots. In this paper, we proposed an experimental kinematics model with a hysteresis compensation algorithm using the probabilistic Gaussian mixture models (GMM) Gaussian mixture regression (GMR) approach. Experimental results on the two-degree-of-freedom (DOF) integrated robotic intraocular snake (I2RIS) show that the proposed model provides 0.4 deg accuracy, which is an overall 60% and 70% of improvement for yaw and pitch degrees of freedom, respectively, compared to a previous model of this robot.

翻译：视网膜显微手术是在极其脆弱的组织上进行的高精度外科手术，目前需要经过广泛训练且技术精湛的外科医生。鉴于眼内有限空间内器械运动范围受限，以及为避免器械与巩膜接触的潜在限制，蛇形机器人在需要高精度和有利工具尖端接近角度的视网膜手术（如视网膜静脉插管和视网膜前膜剥离）中，有望为外科医生提供更高的灵活性、灵巧度、空间可达性和定位精度。这些机器人的运动学建模是实现精确位置控制的关键步骤，然而与传统机械臂不同，由于其复杂的机械结构和驱动机制，这些机器人的建模难以遵循直接方法。特别是在线驱动蛇形机器人中，由线缆张力状态导致的迟滞问题会显著影响其定位精度。本文提出了一种基于概率高斯混合模型（GMM）和高斯混合回归（GMR）方法的迟滞补偿算法的实验运动学模型。在二自由度（DOF）集成式机器人眼内蛇形器械（I2RIS）上的实验结果表明，所提模型实现了0.4度的精度，与先前模型相比，在偏航和俯仰自由度上分别实现了60%和70%的整体改进。