Pub Date : 2024-10-31DOI: 10.1109/TMRB.2024.3488840
C. F. Blanco-Diaz;G. Degl'Innocenti;E. Vendrame;M. Uliano;M. Controzzi;L. Cappello
In telemanipulation, supplementary feedback can enhance operator perception and control precision. This study introduces a haptic interface designed to convey temporally discrete tactile cues when remotely controlling a robot. Low-profile piezoelectric sensors were integrated in the thumb of a robotic hand to capture the key events of the manipulation task (i.e., object contact and release). Synchronously with such events, pressure bursts were delivered to the operator’s fingertip through a soft textile thimble equipped with inflatable pockets. Both this haptic display and the sensing module were individually evaluated. The pneumatic system responsible for pockets inflation was characterized in terms of reaction time, proving suitable for the application with a latency of less than 70 ms. Regarding the sensing module, the behavior of the sensorized thumb was first evaluated under static conditions, identifying contact and release events when grasping with the robotic hand differently shaped objects fixed on a table. Then, the accuracy of the touch event detection was assessed while performing a more complex manipulation task (i.e., a pick and lift task). This evaluation was conducted first with the robot programmed to grasp and lift an object following pre-defined trajectories, where we measured accuracy of 100% for contact and 90% for release event detection. Then, we performed a telemanipulation pilot study involving eight participants, where the system proved capable of correctly detecting object contact and release events with an accuracy of 100% and 86.4%. Despite preliminary, these results confirmed proper functioning of the system and paved the way for the exploration of a new haptic feedback policy in telemanipulation based on temporally discrete tactile events.
{"title":"Design and Characterization of a Low-Profile Haptic System for Telemanipulation","authors":"C. F. Blanco-Diaz;G. Degl'Innocenti;E. Vendrame;M. Uliano;M. Controzzi;L. Cappello","doi":"10.1109/TMRB.2024.3488840","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3488840","url":null,"abstract":"In telemanipulation, supplementary feedback can enhance operator perception and control precision. This study introduces a haptic interface designed to convey temporally discrete tactile cues when remotely controlling a robot. Low-profile piezoelectric sensors were integrated in the thumb of a robotic hand to capture the key events of the manipulation task (i.e., object contact and release). Synchronously with such events, pressure bursts were delivered to the operator’s fingertip through a soft textile thimble equipped with inflatable pockets. Both this haptic display and the sensing module were individually evaluated. The pneumatic system responsible for pockets inflation was characterized in terms of reaction time, proving suitable for the application with a latency of less than 70 ms. Regarding the sensing module, the behavior of the sensorized thumb was first evaluated under static conditions, identifying contact and release events when grasping with the robotic hand differently shaped objects fixed on a table. Then, the accuracy of the touch event detection was assessed while performing a more complex manipulation task (i.e., a pick and lift task). This evaluation was conducted first with the robot programmed to grasp and lift an object following pre-defined trajectories, where we measured accuracy of 100% for contact and 90% for release event detection. Then, we performed a telemanipulation pilot study involving eight participants, where the system proved capable of correctly detecting object contact and release events with an accuracy of 100% and 86.4%. Despite preliminary, these results confirmed proper functioning of the system and paved the way for the exploration of a new haptic feedback policy in telemanipulation based on temporally discrete tactile events.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 1","pages":"100-107"},"PeriodicalIF":3.4,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10740009","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143529893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-14DOI: 10.1109/TMRB.2024.3479878
Navid Masoumi;Andrés C. Ramos;Tannaz Torkaman;Liane S. Feldman;Jake Barralet;Javad Dargahi;Amir Hooshiar
A novel soft sensor calibration method is proposed for minimally invasive surgery, based on our developed gelatin-graphite sensor with high compliance and adaptability. This approach uses convolutional deep learning that accounts for a sensor’s non-linear behavior and reduces noise amplification. This technique offers a smaller minimum detectable force than other approaches and is particularly useful in sensitive surgical scenarios. The sensor’s performance is characterized by its fine resolution ( $leq 1$ mN) and accurate force estimation, especially for forces below 400 mN of amplitude. The best calibration (Morse) scheme provides high performance, with a Mean Absolute Error of $leq 7.9$ mN. This work was validated through comparison among other representative studies and offered a path toward future directions for optimizing and implementing soft robotic sensors in minimally invasive surgeries. The application of this sensor can revolutionize surgical procedures and capitalize on the benefits of soft robotics, potentially enhancing precision and reducing trauma in surgeries.
{"title":"Embedded Force Sensor for Soft Robots With Deep Transformation Calibration","authors":"Navid Masoumi;Andrés C. Ramos;Tannaz Torkaman;Liane S. Feldman;Jake Barralet;Javad Dargahi;Amir Hooshiar","doi":"10.1109/TMRB.2024.3479878","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3479878","url":null,"abstract":"A novel soft sensor calibration method is proposed for minimally invasive surgery, based on our developed gelatin-graphite sensor with high compliance and adaptability. This approach uses convolutional deep learning that accounts for a sensor’s non-linear behavior and reduces noise amplification. This technique offers a smaller minimum detectable force than other approaches and is particularly useful in sensitive surgical scenarios. The sensor’s performance is characterized by its fine resolution (\u0000<inline-formula> <tex-math>$leq 1$ </tex-math></inline-formula>\u0000mN) and accurate force estimation, especially for forces below 400 mN of amplitude. The best calibration (Morse) scheme provides high performance, with a Mean Absolute Error of \u0000<inline-formula> <tex-math>$leq 7.9$ </tex-math></inline-formula>\u0000 mN. This work was validated through comparison among other representative studies and offered a path toward future directions for optimizing and implementing soft robotic sensors in minimally invasive surgeries. The application of this sensor can revolutionize surgical procedures and capitalize on the benefits of soft robotics, potentially enhancing precision and reducing trauma in surgeries.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 4","pages":"1363-1374"},"PeriodicalIF":3.4,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Image-guided robotic interventions represent a transformative frontier in surgery, blending advanced imaging and robotics for improved precision and outcomes. This paper addresses the critical need for integrating open-source platforms to enhance situational awareness in image-guided robotic research. We present an open-source toolkit, named ENTRI, that seamlessly combines a physics-based constraint formulation framework, AMBF, with a state-of-the-art imaging platform application, 3D Slicer. ENTRI facilitates the creation of highly customizable interactive digital twins, that incorporate processing and visualization of medical imaging, robot kinematics, and scene dynamics for real-time robot control. Through a feasibility study, we showcase real-time synchronization of a physical robotic interventional environment in both 3D Slicer and AMBF, highlighting low-latency updates and improved visualization. The source code and supplementary materials for this study are available at https://github.com/LCSR-CIIS/ENTRI .
图像引导机器人介入是外科手术的变革前沿，它将先进的成像技术和机器人技术相结合，提高了手术的精确度和效果。本文探讨了在图像引导机器人研究中整合开源平台以提高态势感知能力的关键需求。我们提出了一个名为 ENTRI 的开源工具包，它将基于物理的约束制定框架 AMBF 与最先进的成像平台应用程序 3D Slicer 无缝地结合在一起。ENTRI 可帮助创建高度定制化的交互式数字双胞胎，将医学成像、机器人运动学和场景动力学的处理和可视化结合起来，实现实时机器人控制。通过可行性研究，我们在 3D Slicer 和 AMBF 中展示了物理机器人介入环境的实时同步，突出了低延迟更新和改进的可视化。本研究的源代码和补充材料可在 https://github.com/LCSR-CIIS/ENTRI 上获取。
{"title":"ENTRI: Enhanced Navigational Toolkit for Robotic Interventions","authors":"Manish Sahu;Hisashi Ishida;Laura Connolly;Hongyi Fan;Anton Deguet;Peter Kazanzides;Francis X. Creighton;Russell H. Taylor;Adnan Munawar","doi":"10.1109/TMRB.2024.3475827","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3475827","url":null,"abstract":"Image-guided robotic interventions represent a transformative frontier in surgery, blending advanced imaging and robotics for improved precision and outcomes. This paper addresses the critical need for integrating open-source platforms to enhance situational awareness in image-guided robotic research. We present an open-source toolkit, named ENTRI, that seamlessly combines a physics-based constraint formulation framework, AMBF, with a state-of-the-art imaging platform application, 3D Slicer. ENTRI facilitates the creation of highly customizable interactive digital twins, that incorporate processing and visualization of medical imaging, robot kinematics, and scene dynamics for real-time robot control. Through a feasibility study, we showcase real-time synchronization of a physical robotic interventional environment in both 3D Slicer and AMBF, highlighting low-latency updates and improved visualization. The source code and supplementary materials for this study are available at \u0000<uri>https://github.com/LCSR-CIIS/ENTRI</uri>\u0000.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 4","pages":"1405-1408"},"PeriodicalIF":3.4,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Soft crawling robots demonstrated high compliance and effectiveness in performing complex tasks in unstructured and harsh environments. They can navigate inside constrained spaces and provide superior adaptability. This paper presents a soft crawling robot with a modified Yoshimura origami-based central chamber (elongation/contraction actuator) and four electrostatic adhesion feet (anchoring elements). It was designed to perform linear and steering locomotion under specific actuation sequences to avoid obstacles autonomously; it features a height-adjustable ability to squeeze under low gaps. A dual-morphing mechanism, enabling the origami-based chamber to operate with two locomotion modalities, was investigated to provide a simple but effective actuation method. Tests were carried out to validate the dual-morphing mechanism and to characterise the crawling robot’s performance. Experimental tests successfully demonstrated the robot’s capabilities, e.g., locomotion under low gaps (i.e., 20 mm, 66% of the height of the robot), obstacle avoidance, climbing on a sloped surface (i.e., 15 deg), and lifting and carrying objects (i.e., 80 g, ten times its weight).
{"title":"Soft Crawling Robot With a Dual-Morphing Origami Configuration","authors":"Xuyang Ren;Yu Huan;Matteo Cianchetti;Shuxin Wang;Paolo Dario;Gastone Ciuti","doi":"10.1109/TMRB.2024.3472858","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3472858","url":null,"abstract":"Soft crawling robots demonstrated high compliance and effectiveness in performing complex tasks in unstructured and harsh environments. They can navigate inside constrained spaces and provide superior adaptability. This paper presents a soft crawling robot with a modified Yoshimura origami-based central chamber (elongation/contraction actuator) and four electrostatic adhesion feet (anchoring elements). It was designed to perform linear and steering locomotion under specific actuation sequences to avoid obstacles autonomously; it features a height-adjustable ability to squeeze under low gaps. A dual-morphing mechanism, enabling the origami-based chamber to operate with two locomotion modalities, was investigated to provide a simple but effective actuation method. Tests were carried out to validate the dual-morphing mechanism and to characterise the crawling robot’s performance. Experimental tests successfully demonstrated the robot’s capabilities, e.g., locomotion under low gaps (i.e., 20 mm, 66% of the height of the robot), obstacle avoidance, climbing on a sloped surface (i.e., 15 deg), and lifting and carrying objects (i.e., 80 g, ten times its weight).","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 4","pages":"1771-1780"},"PeriodicalIF":3.4,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-07DOI: 10.1109/TMRB.2024.3475509
Mustafa Haiderbhai;Lueder A. Kahrs
Traditional methods for autonomous cutting in surgical robotics have relied on trajectory-based planning algorithms. These methods fail to compensate for dynamic changes in soft materials such as deformation and topological change. To apply recent advances such as reinforcement learning (RL), a simulation is needed that models the cutting of soft materials. In this work, we develop a surgical robotics simulation environment for cutting deformable meshes with the da Vinci Research Kit (dVRK). Our environment is built using a particle-based physics simulation to simulate a rope grid structure to create realistic physics behavior and visual rendering. Cutting is implemented with the EndoWrist Round Tip Scissors (RTS) through a system of collision checking and callbacks to detect and update cuts. To showcase the deformable mesh cutting simulation, we design a cutting task of cutting along a desired path that can be solved through manual control. The grid structure can be adapted to render different materials, and we highlight how it can be made to resemble deformable tissue or fabric while being stable with no visible artifacts. This environment is a stepping stone towards training autonomous agents for cutting 2D deformable materials and building towards cutting more complex deformable shapes.
{"title":"Simulating Surgical Robot Cutting of Thin Deformable Materials Using a Rope Grid Structure","authors":"Mustafa Haiderbhai;Lueder A. Kahrs","doi":"10.1109/TMRB.2024.3475509","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3475509","url":null,"abstract":"Traditional methods for autonomous cutting in surgical robotics have relied on trajectory-based planning algorithms. These methods fail to compensate for dynamic changes in soft materials such as deformation and topological change. To apply recent advances such as reinforcement learning (RL), a simulation is needed that models the cutting of soft materials. In this work, we develop a surgical robotics simulation environment for cutting deformable meshes with the da Vinci Research Kit (dVRK). Our environment is built using a particle-based physics simulation to simulate a rope grid structure to create realistic physics behavior and visual rendering. Cutting is implemented with the EndoWrist Round Tip Scissors (RTS) through a system of collision checking and callbacks to detect and update cuts. To showcase the deformable mesh cutting simulation, we design a cutting task of cutting along a desired path that can be solved through manual control. The grid structure can be adapted to render different materials, and we highlight how it can be made to resemble deformable tissue or fabric while being stable with no visible artifacts. This environment is a stepping stone towards training autonomous agents for cutting 2D deformable materials and building towards cutting more complex deformable shapes.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 4","pages":"1401-1404"},"PeriodicalIF":3.4,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-04DOI: 10.1109/TMRB.2024.3474059
Korn Borvorntanajanya;Shen Treratanakulchai;Ferdinando Rodriguez y Rodriguez;Enrico Franco
This paper investigates the model based tracking control of soft growing robots with pneumatic actuation that extend according to the principle known as eversion. A model of the system which accounts for the pressure dynamics is presented. A new control law is constructed with a high-order sliding-mode approach and a nonlinear observer is employed to compensate for the effect of external forces. Numerical simulations and experiments demonstrate the effectiveness of the proposed controller compared to our former energy-shaping implementation and to a baseline sliding-mode controller. Experiments with a training phantom demonstrate that the new controller resulted in a reduced peak pressure, approximately 14.8% lower, a reduced tracking error, approximately 4.9% lower RMSE, and a reduced consumption of compressed air, approximately 3.9% lower, compared to a baseline sliding-mode algorithm.
{"title":"Model-Based Tracking Control of a Soft Growing Robot for Colonoscopy","authors":"Korn Borvorntanajanya;Shen Treratanakulchai;Ferdinando Rodriguez y Rodriguez;Enrico Franco","doi":"10.1109/TMRB.2024.3474059","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3474059","url":null,"abstract":"This paper investigates the model based tracking control of soft growing robots with pneumatic actuation that extend according to the principle known as eversion. A model of the system which accounts for the pressure dynamics is presented. A new control law is constructed with a high-order sliding-mode approach and a nonlinear observer is employed to compensate for the effect of external forces. Numerical simulations and experiments demonstrate the effectiveness of the proposed controller compared to our former energy-shaping implementation and to a baseline sliding-mode controller. Experiments with a training phantom demonstrate that the new controller resulted in a reduced peak pressure, approximately 14.8% lower, a reduced tracking error, approximately 4.9% lower RMSE, and a reduced consumption of compressed air, approximately 3.9% lower, compared to a baseline sliding-mode algorithm.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 4","pages":"1354-1362"},"PeriodicalIF":3.4,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-03DOI: 10.1109/TMRB.2024.3472844
Ang Zhang;Zhe Min;Zhengyan Zhang;Yingying Wang;Max Q.-H. Meng
This paper presents a novel augmented reality (AR)-assisted orthopedic surgical robotic system based on Head-Mounted Display (HMD) devices. The proposed system can overlay the preoperative plans over the patient’s anatomy and provide useful guidance for surgeons during interventions, with integrated calibration and registration components. A novel bi-directional generalised point set registration algorithm that utilises robust features is developed to accurately align the pre-operative CT and intra-operative patient spaces, which has been demonstrated to outperform existing registration methods. The efficacy of the system is both qualitatively and quantitatively assessed with an in vitro study representing a total knee arthroplasty (TKA) procedure. The experimental results showed that 1) the system can successfully align the preoperative and intraoperative spaces, with the mean target registration error (TRE) being $2.78 ; pm ; 2.51$ mm; 2) the models can be properly overlaid to the physical scenarios with the mean AR visualization accuracy being $6.97 ; pm ; 1.57$ mm.
{"title":"A Novel Augmented Reality Assisted Orthopedic Surgical Robotic System With Bidirectional Surface Registration Algorithms","authors":"Ang Zhang;Zhe Min;Zhengyan Zhang;Yingying Wang;Max Q.-H. Meng","doi":"10.1109/TMRB.2024.3472844","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3472844","url":null,"abstract":"This paper presents a novel augmented reality (AR)-assisted orthopedic surgical robotic system based on Head-Mounted Display (HMD) devices. The proposed system can overlay the preoperative plans over the patient’s anatomy and provide useful guidance for surgeons during interventions, with integrated calibration and registration components. A novel bi-directional generalised point set registration algorithm that utilises robust features is developed to accurately align the pre-operative CT and intra-operative patient spaces, which has been demonstrated to outperform existing registration methods. The efficacy of the system is both qualitatively and quantitatively assessed with an in vitro study representing a total knee arthroplasty (TKA) procedure. The experimental results showed that 1) the system can successfully align the preoperative and intraoperative spaces, with the mean target registration error (TRE) being \u0000<inline-formula> <tex-math>$2.78 ; pm ; 2.51$ </tex-math></inline-formula>\u0000 mm; 2) the models can be properly overlaid to the physical scenarios with the mean AR visualization accuracy being \u0000<inline-formula> <tex-math>$6.97 ; pm ; 1.57$ </tex-math></inline-formula>\u0000 mm.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 4","pages":"1555-1566"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-03DOI: 10.1109/TMRB.2024.3472833
Jixiu Li;Tao Zhang;Truman Cheng;Yehui Li;Calvin Sze Hang Ng;Philip Wai Yan Chiu;Zheng Li
Magnetic anchored and guided system(MAGS) is a promising solution for minimally invasive surgery, particularly in the realm of endoscope robotics. However, the inherent tight tissue contact in MAGS limits certain degrees of freedom, constraining the surgeon’s ability to adjust the field of view. To address this, we propose a novel solution by combining magnetic actuation with a cable-driven flexible link. Our study encompasses the design, analysis of magnetic force/torque, and kinematics of the flexible link. One prototype was fabricated, and experiments, including the evaluation of magnetic coupling performance and the motion of the flexible link, were conducted. These experiments validated both the theoretical modeling and the functionality of the magnetic endoscope system.
{"title":"Design, Analysis, and Preliminary Validation of Magnetic Anchored and Cable Driven Endoscope for Minimally Invasive Surgery","authors":"Jixiu Li;Tao Zhang;Truman Cheng;Yehui Li;Calvin Sze Hang Ng;Philip Wai Yan Chiu;Zheng Li","doi":"10.1109/TMRB.2024.3472833","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3472833","url":null,"abstract":"Magnetic anchored and guided system(MAGS) is a promising solution for minimally invasive surgery, particularly in the realm of endoscope robotics. However, the inherent tight tissue contact in MAGS limits certain degrees of freedom, constraining the surgeon’s ability to adjust the field of view. To address this, we propose a novel solution by combining magnetic actuation with a cable-driven flexible link. Our study encompasses the design, analysis of magnetic force/torque, and kinematics of the flexible link. One prototype was fabricated, and experiments, including the evaluation of magnetic coupling performance and the motion of the flexible link, were conducted. These experiments validated both the theoretical modeling and the functionality of the magnetic endoscope system.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 4","pages":"1397-1400"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Robot-assisted surgery (RAS) requires effective control strategies to ensure safety and accuracy while respecting the physical limits of the robot during tasks such as suturing and tissue manipulation. Model Predictive Control (MPC), with its inherent capability to handle complex dynamic systems, predict the future response and enforce constraints, is well-suited for these tasks. In this paper, MPC is employed to automate the suturing stitch task by mapping the operational space trajectory to the joint space while ensuring compliance with system kinematics constraints and safety requirements. To address varying requirements during suturing sub-tasks, two different objective functions and their corresponding constraint sets are used. The proposed framework is implemented using the ACADO toolkit to solve the Optimal Control Problem (OCP) and ROS to connect ACADO to CoppeliaSim/DVRK. Validation through simulations in CoppeliaSim and real-time experiments on the DVRK demonstrated that our approach achieved a positional/orientational accuracy of less than $1mm/4 ^{circ }$ in simulations, and an error norm of approximately $1.9mm$ in real world implementations, confirming its effectiveness in automating suturing task.
{"title":"MPC for Suturing Stitch Automation","authors":"Pasquale Marra;Sajjad Hussain;Marco Caianiello;Fanny Ficuciello","doi":"10.1109/TMRB.2024.3472796","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3472796","url":null,"abstract":"Robot-assisted surgery (RAS) requires effective control strategies to ensure safety and accuracy while respecting the physical limits of the robot during tasks such as suturing and tissue manipulation. Model Predictive Control (MPC), with its inherent capability to handle complex dynamic systems, predict the future response and enforce constraints, is well-suited for these tasks. In this paper, MPC is employed to automate the suturing stitch task by mapping the operational space trajectory to the joint space while ensuring compliance with system kinematics constraints and safety requirements. To address varying requirements during suturing sub-tasks, two different objective functions and their corresponding constraint sets are used. The proposed framework is implemented using the ACADO toolkit to solve the Optimal Control Problem (OCP) and ROS to connect ACADO to CoppeliaSim/DVRK. Validation through simulations in CoppeliaSim and real-time experiments on the DVRK demonstrated that our approach achieved a positional/orientational accuracy of less than \u0000<inline-formula> <tex-math>$1mm/4 ^{circ }$ </tex-math></inline-formula>\u0000 in simulations, and an error norm of approximately \u0000<inline-formula> <tex-math>$1.9mm$ </tex-math></inline-formula>\u0000 in real world implementations, confirming its effectiveness in automating suturing task.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 4","pages":"1468-1477"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-03DOI: 10.1109/TMRB.2024.3472856
Diego Dall’Alba;Lorenzo Busellato;Thiusius Rajeeth Savarimuthu;Zhuoqi Cheng;Iñigo Iturrate
Vascular diseases are commonly diagnosed using Ultrasound (US) imaging, which can be inconsistent due to its high dependence on the operator’s skill. Among these, Deep Vein Thrombosis (DVT) is a common yet potentially fatal condition, often leading to critical complications like pulmonary embolism. Robotic US Systems (RUSs) aim to improve diagnostic test consistency but face challenges with the complex scanning pattern requiring precise control over US probe pressure, such as the one needed for indirectly detecting occlusions during DVT assessment. This work introduces an imitation learning method based on Kernelized Movement Primitives (KMP) to standardize the contact force profile during US exams by training a robotic controller using sonographer demonstrations. A new recording device design enhances demonstration acquisition, integrating with US probes and enabling seamless force and position data recording. KMPs are used to link scan trajectory and interaction force, enabling generalization beyond the demonstrations. Our approach, evaluated on synthetic models and volunteers, shows that the KMP-based RUS can replicate an expert’s force control and US image quality, even under conditions requiring compression during scanning. It outperforms previous methods using manually defined force profiles, improving exam standardization and reducing reliance on specialized sonographers.
血管疾病通常使用超声波（US）成像进行诊断，但由于高度依赖操作员的技术，这种诊断方法并不稳定。其中，深静脉血栓（DVT）是一种常见但可能致命的疾病，往往会导致肺栓塞等严重并发症。机器人 US 系统（RUS）旨在提高诊断测试的一致性，但面临着复杂扫描模式的挑战，需要精确控制 US 探头的压力，例如在 DVT 评估过程中间接检测闭塞情况所需的压力。这项研究引入了一种基于核化运动原型（KMP）的模仿学习方法，通过超声波技师的演示来训练机器人控制器，从而使超声波检查过程中的接触力曲线标准化。新的记录设备设计增强了演示采集功能，可与超声探头集成，实现无缝力和位置数据记录。KMP 用于连接扫描轨迹和相互作用力，从而实现演示之外的推广。我们的方法在合成模型和志愿者身上进行了评估，结果表明，基于 KMP 的 RUS 可以复制专家的力控制和 US 图像质量，即使在扫描过程中需要压缩的条件下也是如此。它优于以前使用手动定义力曲线的方法，提高了检查的标准化程度，减少了对专业超声技师的依赖。
{"title":"Imitation Learning of Compression Pattern in Robotic-Assisted Ultrasound Examination Using Kernelized Movement Primitives","authors":"Diego Dall’Alba;Lorenzo Busellato;Thiusius Rajeeth Savarimuthu;Zhuoqi Cheng;Iñigo Iturrate","doi":"10.1109/TMRB.2024.3472856","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3472856","url":null,"abstract":"Vascular diseases are commonly diagnosed using Ultrasound (US) imaging, which can be inconsistent due to its high dependence on the operator’s skill. Among these, Deep Vein Thrombosis (DVT) is a common yet potentially fatal condition, often leading to critical complications like pulmonary embolism. Robotic US Systems (RUSs) aim to improve diagnostic test consistency but face challenges with the complex scanning pattern requiring precise control over US probe pressure, such as the one needed for indirectly detecting occlusions during DVT assessment. This work introduces an imitation learning method based on Kernelized Movement Primitives (KMP) to standardize the contact force profile during US exams by training a robotic controller using sonographer demonstrations. A new recording device design enhances demonstration acquisition, integrating with US probes and enabling seamless force and position data recording. KMPs are used to link scan trajectory and interaction force, enabling generalization beyond the demonstrations. Our approach, evaluated on synthetic models and volunteers, shows that the KMP-based RUS can replicate an expert’s force control and US image quality, even under conditions requiring compression during scanning. It outperforms previous methods using manually defined force profiles, improving exam standardization and reducing reliance on specialized sonographers.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 4","pages":"1567-1580"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10704653","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：