Task-Based LSTM Kinematic Modelling for a Tendon-Driven Flexible Surgical Robot

Tendon-driven flexible surgical robots are normally suffering from the inaccurate modelling and imprecise motion control problems due to the nonlinearities of tendon transmission. Learning-based approaches are experimental data-driven with uncertainties modelled empirically, which can be adopted to improve the inevitable issues. This work proposes a LSTM-based kinematic modelling 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 modelling.