Flexible endoscopic surgical robots provide enhanced access and maneuverability in complex anatomical environments, addressing limitations encountered by conventional rigid robotic systems. However, achieving precise control of these robots remains challenging due to inherent nonlinear hysteresis originating from friction and tendon slack in tendon-driven mechanisms, significantly impacting surgical accuracy and increasing the cognitive workload on surgeons. To overcome these challenges, this study introduces MonoEndoCal, a deep learning-based autonomous calibration framework designed to estimate bending angles and compensate for nonlinear hysteresis using only monocular endoscopic images, without the need for additional sensors or markers. Leveraging advanced vision models-Depth Anything V2 for dense depth estimation and Segment Anything Model 2 for zero-shot segmentation-MonoEndoCal accurately estimates robot bending angles in real-time. These angle estimations, along with corresponding actuation commands, are employed to derive a precise hysteresis model using differential equations capturing the robot's nonlinear dynamics. By integrating this hysteresis model with robot kinematics, MonoEndoCal implements an effective feedforward control strategy that enables precise hysteresis compensation and enhanced control accuracy. Experimental validations further demonstrate its robustness across varying robot geometries, input characteristics (both periodic and aperiodic), and blood contamination, highlighting its strong potential for improving control precision. Note to Practitioners-Flexible endoscopic surgical robots are increasingly used to enhance precision and reduce patient trauma in minimally invasive procedures. However, accurate control remains challenging due to nonlinear hysteresis in tendon-driven mechanisms, which can significantly affect surgical performance. This work presents MonoEndoCal, a deep learning-based autonomous calibration framework that uses only monocular endoscopic images-without external sensors or markers to estimate bending angles and compensate for hysteresis in real time. From a practical perspective, the proposed method can be integrated into existing endoscopic robotic platforms with minimal hardware modification, making it well-suited for clinical environments with strict space constraints. Practitioners adopting this framework should ensure that real-time computational resources are available and validate the hysteresis model with system-specific calibration data to achieve optimal performance. This approach offers a cost-effective, sensorless calibration solution that can improve control fidelity and reduce surgeon workload in tendon-driven surgical robots.

In situbioprinting has been identified as a promising tissue engineering technique for treating volumetric muscle loss (VML) injuries. However, the success of this procedure significantly depends on the uniform and precise deposition of cells contributing to the regeneration of muscles. To address this critical need, in this work, we present design and quantitative evaluation of a novel autonomousin situbioprinting surgical robotic framework that can be used with a generic bioprinting material. The proposed framework consists of three main components: (i) a bioprinting tool integrated with a seven-degree-of-freedom robotic manipulator to perform a precise autonomous bioprinting procedure; (ii) a unique 3D visual measurement framework comprised of a high-accuracy structured light camera with complementary 2D/3D computer vision algorithms-to enable online and accurate measurement and reconstruction of the bioprinted constructs; and (iii) a quantitative evaluation module with novel assessment metrics-to characterize and evaluate the performance of the bioprinting process toward finding optimal bioprinting parameters. To ensure the biological functionality of a printed construct using our robotic system, we performed 90 experiments and identified optimal bioprinting parameters using the proposed novel assessment metrics.Note to Practitioners—This paper was motivated by the problem of volumetric muscle loss treatment using anin situbioprinting procedure but it also can be applied for treatment of skin and cartilage injuries. Existing approaches to performin situbioprinting is limited to either manual handheld bioprinting devices– that suffer from poor manual control and inaccurate printing constructs– or robotic systems– that have been developed without (i) considering a realistic surgical workflow and (ii) quantitatively evaluating the quality of printed constructs. To collectively address these issues, in this paper, we propose a novel autonomousin siturobotic bioprinting framework. We also introduce unique and complementary quantitative assessment metrics to characterize and evaluate the performance of the bioprinting process. Experiments suggest that the proposed framework can robustly identify optimal bioprinting parameters to ensure the biological functionality of a printed construct using our robotic system.

In this paper, a novel mathematical framework is introduced for modeling deformation behavior of Tendon-Driven Continuum Manipulators (TD-CMs) featuring discontinuous cross-sectional geometries (i.e., having flexural patterns). Leveraging this framework, we also introduce the concept of design space by which the deformation-behavior space of a TD-CM can intuitively be analyzed via its geometrical design parameters. To thoroughly evaluate the performance of the proposed modeling framework, we have conducted various simulation studies and experiments.

In this paper, with the goal of addressing the high early-detection miss rate of colorectal cancer (CRC) polyps during a colonoscopy procedure, we propose the design and fabrication of a unique inflatable vision-based tactile sensing balloon (VTSB). The proposed soft VTSB can readily be integrated with the existing colonoscopes and provide a radiation-free, safe, and high-resolution textural mapping and morphology characterization of CRC polyps. The performance of the proposed VTSB has been thoroughly characterized and evaluated on four different types of additively manufactured CRC polyp phantoms with three different stiffness levels. Additionally, we integrated the VTSB with a colonoscope and successfully performed a simulated colonoscopic procedure inside a tube with a few CRC polyp phantoms attached to its internal surface.

Endoscopes are widely used for not only intraluminal diagnosis but also therapeutic procedures in the gastrointestinal area. However, conventional endoscopes present a few challenges such as nonintuitive manipulation, physical burden on the operator, and lack of dexterity. These challenges limit endoscope usage in complex surgical procedures. Moreover, endoscope operators undergo extensive and lengthy training to attain an adequate skill level. In this paper, we introduce a flexible surgery robot platform K-FLEX that facilitates teleoperation via an intuitive master interface and bimanual manipulation by means of two dexterous surgical robot arms. Its effects on endoscopic procedures, especially in terms of task performance, learning properties, and physical burden on the operator, are validated by conducting a user test. The experimental results demonstrate that the developed robotic assistant increases operation speed, especially for novices; simplifies the learning process; and reduces the workload on the operator compared to conventional endoscopes.