Hybrid Visual Servoing of Tendon-driven Continuum Robots

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.