-- Reconfigurable robots that can change their physical configuration post-fabrication have demonstrate their potential in adapting to different environments or tasks. However, it is challenging to determine how to optimally adjust reconfigurable parameters for a given task, especially when the controller depends on the robot's configuration. In this paper, we address this problem using a tendon-driven reconfigurable manipulator composed of multiple serially connected origami-inspired modules as an example. Under tendon actuation, these modules can achieve different shapes and motions, governed by joint stiffnesses (reconfiguration parameters) and the tendon displacements (control inputs). We leverage recent advances in co-optimization of design and control for robotic system to treat reconfiguration parameters as design variables and optimize them using reinforcement learning techniques. We first establish a forward model based on the minimum potential energy method to predict the shape of the manipulator under tendon actuations. Through co-optimization, we obtain optimized joint stiffness and the corresponding optimal control policy to enable the manipulator to accomplish the task that would be infeasible with fixed reconfiguration parameters (i.e., fixed joint stiffness). We envision the co-optimization framework can be extended to other reconfigurable robotic systems, enabling them to optimally adapt their configuration and behavior for diverse tasks and environments. Traditionally, the design and control of robotic systems have been treated as separate processes: a robot's physical structure is first designed, and then a controller is developed to operate it.

HVS outperforms DLBVS in iteration time, error reduction, and con - trol smoothness. Experimental validation confirms HVS effectiveness under occlusion s and noise. Abstract This paper introduces a novel Hybrid Visual Servoing (HVS) approa ch for controlling tendon-driven continuum robots (TDCRs). The HVS sys tem combines Image-Based Visual Servoing (IBVS) with Deep Learning-Based Visual Servoing (DLBVS) to overcome the limitations of each method and improve overall performance. IBVS offers higher accuracy and fa ster convergence in feature-rich environments, while DLBVS enhances rob ustness against disturbances and offers a larger workspace. By enabling sm ooth transitions between IBVS and DLBVS, the proposed HVS ensures e ffective control in dynamic, unstructured environments. The effectivene ss of this approach is validated through simulations and real-world experiments, demonstrating that HVS achieves reduced iteration time, faster conver gence, lower final error, and smoother performance compared to DLBVS alone, while maintaining DLBVS's robustness in challenging conditions such as occlu - sions, lighting changes, actuator noise, and physical impacts.

This paper presents a study on the backstepping control of tendon-driven continuum robots for large deflections using the Cosserat rod model. Continuum robots are known for their flexibility and adaptability, making them suitable for various applications. However, modeling and controlling them pose challenges due to their nonlinear dynamics. To model their dynamics, the Cosserat rod method is employed to account for significant deflections, and a numerical solution method is developed to solve the resulting partial differential equations. Previous studies on controlling tendon-driven continuum robots using Cosserat rod theory focused on sliding mode control and were not tested for large deflections, lacking experimental validation. In this paper, backstepping control is proposed as an alternative to sliding mode control for achieving a significant bending. The numerical results are validated through experiments in this study, demonstrating that the proposed backstepping control approach is a promising solution for achieving large deflections with smoother trajectories, reduced settling time, and lower overshoot. Furthermore, two scenarios involving external forces and disturbances were introduced to further highlight the robustness of the backstepping control approach.

This paper presents the first kinematic modeling of tendon-driven rolling-contact joint mechanisms with general contact surfaces subject to external loads. We derived the kinematics as a set of recursive equations and developed efficient iterative algorithms to solve for both tendon force actuation and tendon displacement actuation. The configuration predictions of the kinematics were experimentally validated using a prototype mechanism. Our MATLAB implementation of the proposed kinematic is available at https://github.com/hjhdog1/RollingJoint.

Abstract-- The ability to accurately model mechanical hysteretic behavior in tendon-actuated continuum robots using deep learning approaches is a growing area of interest. In this paper, we investigate the hysteretic response of two types of tendon-actuated continuum robots and, ultimately, compare three types of neural network modeling approaches with both forward and inverse kinematic mappings: feedforward neural network (FNN), FNN with a history input buffer, and long short-term memory (LSTM) network. We seek to determine which model best captures temporal dependent behavior. We find that, depending on the robot's design, choosing different In contrast, the modeling of hysteretic effects has received much I. INTRODUCTION While hysteresis models such as the Preisach Since continuum robots produce a workspace through flexure and Bouc-Wen models [10] have been developed explicitly of their components, modeling their kinematics is substantially to reproduce hysteretic effects, it remains challenging to more complex than for robots comprised of rigid links estimate model parameters based on data sets [11]. Furthermore, since the flexure depends With the explosion of interest in deep learning, neural on the robot design, the modeling equations vary with robot networks are being applied as an alternative technique to type, e.g., concentric tube robots [1] versus tendon-actuated mechanics-based modeling of continuum robot kinematics robots (Figure 1) [2].