Pub Date : 2024-08-08DOI: 10.1109/TMRB.2024.3434228
{"title":"IEEE Transactions on Medical Robotics and Bionics Society Information","authors":"","doi":"10.1109/TMRB.2024.3434228","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3434228","url":null,"abstract":"","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"C3-C3"},"PeriodicalIF":3.4,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10631874","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141966301","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 : 2024-08-08DOI: 10.1109/TMRB.2024.3434206
{"title":"IEEE Transactions on Medical Robotics and Bionics Publication Information","authors":"","doi":"10.1109/TMRB.2024.3434206","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3434206","url":null,"abstract":"","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"C2-C2"},"PeriodicalIF":3.4,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10631865","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965835","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 : 2024-08-08DOI: 10.1109/TMRB.2024.3426732
Emmanuel Vander Poorten;Leonardo S. Mattos;Guillaume Morel;Paolo Fiorini;Alicia Casals;Arianna Menciassi
The IEEE Transactions on Medical Robotics and Bionics (T-MRB) is an initiative shared by the two IEEE Societies of Robotics and Automation – RAS – and Engineering in Medicine and Biology – EMBS.
{"title":"Guest Editorial Joining Efforts Moving Faster in Surgical Robotics","authors":"Emmanuel Vander Poorten;Leonardo S. Mattos;Guillaume Morel;Paolo Fiorini;Alicia Casals;Arianna Menciassi","doi":"10.1109/TMRB.2024.3426732","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3426732","url":null,"abstract":"The IEEE Transactions on Medical Robotics and Bionics (T-MRB) is an initiative shared by the two IEEE Societies of Robotics and Automation – RAS – and Engineering in Medicine and Biology – EMBS.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"784-786"},"PeriodicalIF":3.4,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10631867","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965836","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 : 2024-08-08DOI: 10.1109/TMRB.2024.3434230
{"title":"IEEE Transactions on Medical Robotics and Bionics Information for Authors","authors":"","doi":"10.1109/TMRB.2024.3434230","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3434230","url":null,"abstract":"","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"C4-C4"},"PeriodicalIF":3.4,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10631866","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141966302","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 : 2024-07-11DOI: 10.1109/TMRB.2024.3421543
E. Saghbiny;L. Leblanc;A. Harlé;C. Bobbio;R. Vialle;G. Morel;B. Tamadazte
The accurate placement of pedicle screws is crucial for various spinal interventions, demanding precise geometric alignment while carrying inherent risks. Studies show that the rate of complications can reach up to 18% in case of imprecise placement of pedicle screws. To enhance the precision and safety of pedicle screw placement, we have developed a robotic system equipped with several sensors and paired with a breach detection algorithm capable of identifying potential breaches in the spinal canal. The breach detection algorithm was conceptualized through an analysis of the cutting torque of the drill system. An ex-vivo experiment was conducted to assess the effectiveness of the developed robotic solution and breach detection algorithm. The data (e.g., cutting torque, position, velocity, etc.) used during the validation were collected by drilling 80 pedicles in fresh porcine vertebrae. The results demonstrated that the proposed algorithm could predict breaches in 96.42% of cases, i.e., the distance between the detected point (drilling stop) and the point of the breach is within 2 mm. In a single instance, the detection occurred earlier than anticipated due to the trajectory being oriented significantly medially, resulting in an initial interaction with the cortical bone at an earlier point.
{"title":"Breach Detection in Spine Surgery Based on Cutting Torque","authors":"E. Saghbiny;L. Leblanc;A. Harlé;C. Bobbio;R. Vialle;G. Morel;B. Tamadazte","doi":"10.1109/TMRB.2024.3421543","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3421543","url":null,"abstract":"The accurate placement of pedicle screws is crucial for various spinal interventions, demanding precise geometric alignment while carrying inherent risks. Studies show that the rate of complications can reach up to 18% in case of imprecise placement of pedicle screws. To enhance the precision and safety of pedicle screw placement, we have developed a robotic system equipped with several sensors and paired with a breach detection algorithm capable of identifying potential breaches in the spinal canal. The breach detection algorithm was conceptualized through an analysis of the cutting torque of the drill system. An ex-vivo experiment was conducted to assess the effectiveness of the developed robotic solution and breach detection algorithm. The data (e.g., cutting torque, position, velocity, etc.) used during the validation were collected by drilling 80 pedicles in fresh porcine vertebrae. The results demonstrated that the proposed algorithm could predict breaches in 96.42% of cases, i.e., the distance between the detected point (drilling stop) and the point of the breach is within 2 mm. In a single instance, the detection occurred earlier than anticipated due to the trajectory being oriented significantly medially, resulting in an initial interaction with the cortical bone at an earlier point.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"1084-1092"},"PeriodicalIF":3.4,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141966300","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 : 2024-07-05DOI: 10.1109/TMRB.2024.3421513
Peter Walker Ferguson;Jianwei Sun;Ji Ma;Joel Perry;Jacob Rosen
This study aims to document the design of the OTHER Hand: a novel bilateral, reconfigurable, hand exoskeleton with opposable thumbs for use with upper limb exoskeletons. Intended for grasp research and rehabilitation with an emphasis on stroke, the OTHER Hand is designed as a one-size-fits-all system that can enable most of the common prehensile grasps and hand postures performed in activities of daily living. The capacity of the system to perform such grasps and postures is experimentally demonstrated by an average 94% normalized Grasping Ability Score across thirteen subjects using the Anthropomorphic Hand Assessment Protocol. This score demonstrates near-unhindered grasping performance for individuals without hand impairments wearing the OTHER Hand.
本研究旨在记录 "OTHER 手 "的设计：一种新型的可重新配置的双侧手部外骨骼，具有可对置的拇指，可与上肢外骨骼一起使用。OTHER手 "设计用于抓握研究和康复（重点是中风），是一个 "一刀切 "的系统，可以实现日常生活中大多数常见的前伸抓握和手部姿势。实验证明，该系统有能力完成此类抓握和姿势，13 名受试者使用拟人手评估协议获得了平均 94% 的正常化抓握能力分数。这一分数表明，佩戴 OTHER Hand 的无手部障碍者几乎可以无障碍地完成抓握动作。
{"title":"On the OTHER Hand: A Bilateral, Reconfigurable Hand Exoskeleton With Opposable Thumbs for Use With Upper Limb Exoskeletons","authors":"Peter Walker Ferguson;Jianwei Sun;Ji Ma;Joel Perry;Jacob Rosen","doi":"10.1109/TMRB.2024.3421513","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3421513","url":null,"abstract":"This study aims to document the design of the OTHER Hand: a novel bilateral, reconfigurable, hand exoskeleton with opposable thumbs for use with upper limb exoskeletons. Intended for grasp research and rehabilitation with an emphasis on stroke, the OTHER Hand is designed as a one-size-fits-all system that can enable most of the common prehensile grasps and hand postures performed in activities of daily living. The capacity of the system to perform such grasps and postures is experimentally demonstrated by an average 94% normalized Grasping Ability Score across thirteen subjects using the Anthropomorphic Hand Assessment Protocol. This score demonstrates near-unhindered grasping performance for individuals without hand impairments wearing the OTHER Hand.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"1158-1169"},"PeriodicalIF":3.4,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965572","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 : 2024-07-05DOI: 10.1109/TMRB.2024.3421256
Tudor Jianu;Baoru Huang;Minh Nhat Vu;Mohamed E. M. K. Abdelaziz;Sebastiano Fichera;Chun-Yi Lee;Pierre Berthet-Rayne;Ferdinando Rodriguez y Baena;Anh Nguyen
Autonomous robots in endovascular operations have the potential to navigate circulatory systems safely and reliably while decreasing the susceptibility to human errors. However, there are numerous challenges involved with the process of training such robots, such as long training duration and safety issues arising from the interaction between the catheter and the aorta. Recently, endovascular simulators have been employed for medical training but generally do not conform to autonomous catheterization due to the lack of standardization and RL framework compliance. Furthermore, most current simulators are closed-source, which hinders the collaborative development of safe and reliable autonomous systems through shared learning and community-driven enhancements. In this work, we introduce CathSim, an open-source simulation environment that accelerates the development of machine learning algorithms for autonomous endovascular navigation. We first simulate the high-fidelity catheter and aorta with a state-of-the-art endovascular robot. We then provide the capability of real-time force sensing between the catheter and the aorta in simulation. Furthermore, we validate our simulator by conducting two different catheterization tasks using two popular reinforcement learning algorithms, namely SAC and PPO. The experimental results show that our open-source simulator can mimic the behavior of real-world endovascular robots and facilitate the development of different autonomous catheterization tasks. Our simulator is publicly available at https://github.com/airvlab/cathsim .
{"title":"CathSim: An Open-Source Simulator for Endovascular Intervention","authors":"Tudor Jianu;Baoru Huang;Minh Nhat Vu;Mohamed E. M. K. Abdelaziz;Sebastiano Fichera;Chun-Yi Lee;Pierre Berthet-Rayne;Ferdinando Rodriguez y Baena;Anh Nguyen","doi":"10.1109/TMRB.2024.3421256","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3421256","url":null,"abstract":"Autonomous robots in endovascular operations have the potential to navigate circulatory systems safely and reliably while decreasing the susceptibility to human errors. However, there are numerous challenges involved with the process of training such robots, such as long training duration and safety issues arising from the interaction between the catheter and the aorta. Recently, endovascular simulators have been employed for medical training but generally do not conform to autonomous catheterization due to the lack of standardization and RL framework compliance. Furthermore, most current simulators are closed-source, which hinders the collaborative development of safe and reliable autonomous systems through shared learning and community-driven enhancements. In this work, we introduce CathSim, an open-source simulation environment that accelerates the development of machine learning algorithms for autonomous endovascular navigation. We first simulate the high-fidelity catheter and aorta with a state-of-the-art endovascular robot. We then provide the capability of real-time force sensing between the catheter and the aorta in simulation. Furthermore, we validate our simulator by conducting two different catheterization tasks using two popular reinforcement learning algorithms, namely SAC and PPO. The experimental results show that our open-source simulator can mimic the behavior of real-world endovascular robots and facilitate the development of different autonomous catheterization tasks. Our simulator is publicly available at \u0000<uri>https://github.com/airvlab/cathsim</uri>\u0000.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"971-979"},"PeriodicalIF":3.4,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965165","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 : 2024-07-03DOI: 10.1109/TMRB.2024.3422608
Guochen Ning;Jie Wang;Hongen Liao
Robotic ultrasound imaging systems (RUSs) have captured significant interest owing to their potential to facilitate autonomous ultrasound imaging. However, existing RUSs built upon robotic systems oriented towards conventional manufacturing struggle to navigate the variable and dynamic clinical environments. We introduce a portable and lightweight RUS designed to enhance adaptability for ultrasound imaging tasks. The proposed system features multiple parallel rings and bearings, affording it four degrees-of-freedom for precise posture control. Further enhancing its adaptability, the actuators are isolated from the mechanism and connected by a cable-sheath mechanism, resulting in a mere 519g lightweight structure that attaches to the body. Quantitative assessments indicate that within a vast workspace of 981 cm3, the posture control precision of the probe is measured at $1.32pm 0.1$ mm and [ $1.8pm 1.1^{circ }$ , $1.9pm 2.2^{circ }$ , $0.8~pm 0.8^{circ }$ ]. The maximum compression force measured for the probe is 14.5 N. The quantitative evaluation results show that the system can attach to various parts of the human body for image acquisition. In addition, the proposed system excels in performing stable scanning procedures even in rapidly changing dynamic environments. Our system can realize imaging tasks with a much lighter structure and has the potential to be applied to more complex scenarios.
{"title":"Cable-Driven Light-Weighting and Portable System for Robotic Medical Ultrasound Imaging","authors":"Guochen Ning;Jie Wang;Hongen Liao","doi":"10.1109/TMRB.2024.3422608","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3422608","url":null,"abstract":"Robotic ultrasound imaging systems (RUSs) have captured significant interest owing to their potential to facilitate autonomous ultrasound imaging. However, existing RUSs built upon robotic systems oriented towards conventional manufacturing struggle to navigate the variable and dynamic clinical environments. We introduce a portable and lightweight RUS designed to enhance adaptability for ultrasound imaging tasks. The proposed system features multiple parallel rings and bearings, affording it four degrees-of-freedom for precise posture control. Further enhancing its adaptability, the actuators are isolated from the mechanism and connected by a cable-sheath mechanism, resulting in a mere 519g lightweight structure that attaches to the body. Quantitative assessments indicate that within a vast workspace of 981 cm3, the posture control precision of the probe is measured at \u0000<inline-formula> <tex-math>$1.32pm 0.1$ </tex-math></inline-formula>\u0000mm and [\u0000<inline-formula> <tex-math>$1.8pm 1.1^{circ }$ </tex-math></inline-formula>\u0000, \u0000<inline-formula> <tex-math>$1.9pm 2.2^{circ }$ </tex-math></inline-formula>\u0000, \u0000<inline-formula> <tex-math>$0.8~pm 0.8^{circ }$ </tex-math></inline-formula>\u0000]. The maximum compression force measured for the probe is 14.5 N. The quantitative evaluation results show that the system can attach to various parts of the human body for image acquisition. In addition, the proposed system excels in performing stable scanning procedures even in rapidly changing dynamic environments. Our system can realize imaging tasks with a much lighter structure and has the potential to be applied to more complex scenarios.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"1220-1231"},"PeriodicalIF":3.4,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965683","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}
Although the da Vinci surgical system enhances manipulation dexterity and restores 3D vision in robotic surgery, it requires surgeons to asynchronously control surgical instruments and the endoscope, which hinders a smooth operation. Surgeons frequently position the endoscope to maintain a good field of view during operation, potentially increasing surgical time and workload. In this paper, a Human-Out-Of-The-Loop (HOOTL) endoscope navigation control with the assistance of context awareness is proposed to enhance surgical autonomy. A comprehensive comparison study using 8 state-of-the-art networks was conducted to find out the best model for surgical phase recognition. Ten human subjects were invited to participate in a classic ring transferring task based on three different endoscope navigation pipelines on a da Vinci research kit platform, including standard endoscope navigation, semi-autonomous endoscope navigation with manual pedal control, and HOOTL endoscope navigation supported by vision-based phase recognition. The experimental results showed that the proposed endoscope navigation approach releases the operation need of controlling the pedals, and it significantly reduces the execution time compared to the other two navigation pipelines. The result of the NASA Task Load Index (NASA-TLX) questionnaire indicates that the proposed endoscope navigation can reduce the physical and mental load for the users.
{"title":"Toward Human-Out-of-the-Loop Endoscope Navigation Based on Context Awareness for Enhanced Autonomy in Robotic Surgery","authors":"Ziyang Chen;Ke Fan;Laura Cruciani;Matteo Fontana;Lorenzo Muraglia;Francesco Ceci;Laura Travaini;Giancarlo Ferrigno;Elena De Momi","doi":"10.1109/TMRB.2024.3422618","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3422618","url":null,"abstract":"Although the da Vinci surgical system enhances manipulation dexterity and restores 3D vision in robotic surgery, it requires surgeons to asynchronously control surgical instruments and the endoscope, which hinders a smooth operation. Surgeons frequently position the endoscope to maintain a good field of view during operation, potentially increasing surgical time and workload. In this paper, a Human-Out-Of-The-Loop (HOOTL) endoscope navigation control with the assistance of context awareness is proposed to enhance surgical autonomy. A comprehensive comparison study using 8 state-of-the-art networks was conducted to find out the best model for surgical phase recognition. Ten human subjects were invited to participate in a classic ring transferring task based on three different endoscope navigation pipelines on a da Vinci research kit platform, including standard endoscope navigation, semi-autonomous endoscope navigation with manual pedal control, and HOOTL endoscope navigation supported by vision-based phase recognition. The experimental results showed that the proposed endoscope navigation approach releases the operation need of controlling the pedals, and it significantly reduces the execution time compared to the other two navigation pipelines. The result of the NASA Task Load Index (NASA-TLX) questionnaire indicates that the proposed endoscope navigation can reduce the physical and mental load for the users.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"1116-1124"},"PeriodicalIF":3.4,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10584115","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965579","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 : 2024-07-03DOI: 10.1109/TMRB.2024.3422652
Yi Hu;Zahra Samadikhoshkho;Jun Jin;Mahdi Tavakoli
Autonomous robotic surgery represents one of the most groundbreaking advancements in medical technology. Learning from human demonstrations is promising in this domain, which facilitates the transfer of skills from humans to robots. However, the practical application of this method is challenged by the difficulty of acquiring high-quality demonstrations. Surgical tasks often involve complex manipulations and stringent precision requirements, leading to frequent errors in the demonstrations. These imperfect demonstrations adversely affect the performance of controller policies learned from the data. Unlike existing methods that rely on extensive human labeling of demonstrated trajectories, we present a novel label-free adaptive Gaussian sample consensus framework to progressively refine the control policy. We demonstrate the efficacy and practicality of our approach through two experimental studies: a handwriting classification task, providing reproducible ground-truth labels for evaluation, and an endoscopy scanning task, demonstrating the feasibility of our method in a real-world clinical context. Both experiments highlight our method’s capacity to efficiently adapt to and learn from an ongoing stream of imperfect demonstrations.
{"title":"Label-Free Adaptive Gaussian Sample Consensus Framework for Learning From Perfect and Imperfect Demonstrations","authors":"Yi Hu;Zahra Samadikhoshkho;Jun Jin;Mahdi Tavakoli","doi":"10.1109/TMRB.2024.3422652","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3422652","url":null,"abstract":"Autonomous robotic surgery represents one of the most groundbreaking advancements in medical technology. Learning from human demonstrations is promising in this domain, which facilitates the transfer of skills from humans to robots. However, the practical application of this method is challenged by the difficulty of acquiring high-quality demonstrations. Surgical tasks often involve complex manipulations and stringent precision requirements, leading to frequent errors in the demonstrations. These imperfect demonstrations adversely affect the performance of controller policies learned from the data. Unlike existing methods that rely on extensive human labeling of demonstrated trajectories, we present a novel label-free adaptive Gaussian sample consensus framework to progressively refine the control policy. We demonstrate the efficacy and practicality of our approach through two experimental studies: a handwriting classification task, providing reproducible ground-truth labels for evaluation, and an endoscopy scanning task, demonstrating the feasibility of our method in a real-world clinical context. Both experiments highlight our method’s capacity to efficiently adapt to and learn from an ongoing stream of imperfect demonstrations.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"1093-1103"},"PeriodicalIF":3.4,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141966291","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}
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：