Task-Based LSTM Kinematic Modeling for a Tendon-Driven Flexible Surgical Robot
Task-Based LSTM Kinematic Modeling for a Tendon-Driven Flexible Surgical Robot
复制标题
DOI：
10.1109/tmrb.2021.3127366
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
Weibang Bai;Francesco Cursi;Xiaotong Guo;Baoru Huang;Benny P. L. Lo;Guang-Zhong Yang;E. Yeatman
中科院分区：
文献类型：
--
作者：
Weibang Bai;Francesco Cursi;Xiaotong Guo;Baoru Huang;Benny P. L. Lo;Guang-Zhong Yang;E. Yeatman
肌腱驱动的柔性手术机器人由于肌腱传输的非线性，通常存在建模不准确和运动控制不精确的问题。基于学习的方法是实验数据驱动的，具有经验性建模的不确定性，可以用来改进不可避免的问题。为了提高柔性肌腱驱动手术机器人的控制精度，提出了一种基于LSTM的基于任务数据的运动学建模方法。实验证明了该学习模型在完成路径跟踪任务时的有效性和优越性，尤其是与传统的建模方法相比。
Tendon-driven flexible surgical robots are normally suffering from the inaccurate modeling and imprecise motion control problems due to the nonlinearities of tendon transmission. Learning-based approaches are experimental data-driven with uncertainties modeled empirically, which can be adopted to improve the inevitable issues. This work proposes a LSTM-based kinematic modeling approach with task-based data for a flexible tendon-driven surgical robot to improve the control accuracy. Real experiments demonstrated the effectiveness and superiority of the proposed learned model when completing path following tasks, especially compared to the traditional modeling.