Cable-Driven Continuum Manipulators (CDCMs) enable scar-free procedures via natural orifices and improve target lesion accessibility through curved paths. However, CDCMs face limitations in workspace and control accuracy due to non-linear cable effects causing hysteresis. This paper introduces an extensible CDCM with a Semi-active Mechanism (SAM) to expand the workspace via translational motion without additional mechanical elements or actuation. We collect a hysteresis dataset using 8 fiducial markers and RGBD sensing. Based on this dataset, we develop a real-time hysteresis compensation control algorithm using the trained Temporal Convolutional Network (TCN) with a 1ms time latency, effectively estimating the manipulator's hysteresis behavior. Performance validation through random trajectory tracking tests and box pointing tasks shows the proposed controller significantly reduces hysteresis by up to 69.5% in joint space and approximately 26% in the box pointing task.

翻译：缆驱连续体机械臂（CDCMs）能够通过自然腔道实现无疤痕手术，并借助弯曲路径提升对目标病灶的可达性。然而，由于非线性缆绳效应引起的迟滞现象，CDCMs在工作空间与控制精度方面存在局限。本文提出一种采用半主动机构（SAM）的可扩展CDCM，该机构无需额外机械元件或驱动装置，即可通过平移运动扩展工作空间。我们利用8个基准标记点与RGBD传感技术采集了迟滞数据集。基于该数据集，我们开发了一种实时迟滞补偿控制算法，采用训练后的时序卷积网络（TCN）实现1ms时间延迟，有效估计了机械臂的迟滞行为。通过随机轨迹跟踪测试与方框指向任务的性能验证表明，所提出的控制器在关节空间中将迟滞降低了高达69.5%，在方框指向任务中降低了约26%。