This paper presents a learning-based approach for centralized position control of Tendon Driven Continuum Robots (TDCRs) using Deep Reinforcement Learning (DRL), with a particular focus on the Sim-to-Real transfer of control policies. The proposed control method employs the Modified Transpose Jacobian (MTJ) control strategy, with its parameters optimally tuned using the Deep Deterministic Policy Gradient (DDPG) algorithm. Classical model-based controllers encounter significant challenges due to the inherent uncertainties and nonlinear dynamics of continuum robots. In contrast, model-free control strategies require efficient gain-tuning to handle diverse operational scenarios. This research aims to develop a model-free controller with performance comparable to model-based strategies by integrating an optimal adaptive gain-tuning system. Both simulations and real-world implementations demonstrate that the proposed method significantly enhances the trajectory-tracking performance of continuum robots independent of initial conditions and paths within the operational task-space, effectively establishing a task-free controller.

翻译：本文提出了一种基于深度强化学习（DRL）的集中式位置控制方法，用于肌腱驱动连续体机器人（TDCRs），特别关注控制策略的从仿真到现实（Sim-to-Real）迁移。所提出的控制方法采用改进的转置雅可比（MTJ）控制策略，其参数通过深度确定性策略梯度（DDPG）算法进行优化整定。经典的基于模型的控制器由于连续体机器人固有的不确定性和非线性动力学而面临重大挑战。相比之下，无模型控制策略需要高效的增益整定以应对多样化的操作场景。本研究旨在通过集成一个最优自适应增益整定系统，开发一种性能与基于模型策略相当的无模型控制器。仿真和实际实验均表明，所提出的方法显著提升了连续体机器人在操作任务空间内独立于初始条件和路径的轨迹跟踪性能，从而有效地建立了一个任务无关的控制器。