Gait phase (GP) estimation is a critical component in control of exoskeletons and prostheses, enabling seamless user interaction in various controllers. In recent years, methods based on machine learning and sensor fusion have offered advances in GP estimation, but their high computational costs and reliance on training and numerous sensors present practical challenges. Estimation methods using phase variables, such as phase-portrait-based methods, can circumvent these drawbacks. However, their lower accuracy has limited their application. To address this limitation, we introduce a novel human-in-the-loop (HIL) optimization approach for improving the accuracy of GP estimation in phase-portrait-based methods. The approach is based on geometric manipulation of the phase portraits with linear transformations, which are adapted online by employing Covariance Matrix Adaptation Evolution Strategy (CMA-ES). The performance of this adaptive method (termed AM) is compared against using a fixed transformation (FM) at different walking speeds on level and inclined treadmill. The results demonstrate the superior performance of AM in all tested conditions in terms of accuracy and linearity, with an average RMS error of $1.97 pm 0.20%$ . Convergence times for one round of optimization on a low-end single-board computer were less than 11 s on average. This study confirms the potential of leveraging HIL optimization for enhancing the performance of phase-portrait-based methods to reach accuracy levels comparable to more complex state-of-the-art methods.
{"title":"Human-in-the-Loop Optimization for Terrain- and User-Adaptive Gait Phase Estimation in Phase-Portrait-Based Methods","authors":"Tian Ye;Ali Reza Manzoori;Auke Ijspeert;Mohamed Bouri","doi":"10.1109/TMRB.2024.3517136","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3517136","url":null,"abstract":"Gait phase (GP) estimation is a critical component in control of exoskeletons and prostheses, enabling seamless user interaction in various controllers. In recent years, methods based on machine learning and sensor fusion have offered advances in GP estimation, but their high computational costs and reliance on training and numerous sensors present practical challenges. Estimation methods using phase variables, such as phase-portrait-based methods, can circumvent these drawbacks. However, their lower accuracy has limited their application. To address this limitation, we introduce a novel human-in-the-loop (HIL) optimization approach for improving the accuracy of GP estimation in phase-portrait-based methods. The approach is based on geometric manipulation of the phase portraits with linear transformations, which are adapted online by employing Covariance Matrix Adaptation Evolution Strategy (CMA-ES). The performance of this adaptive method (termed AM) is compared against using a fixed transformation (FM) at different walking speeds on level and inclined treadmill. The results demonstrate the superior performance of AM in all tested conditions in terms of accuracy and linearity, with an average RMS error of <inline-formula> <tex-math>$1.97 pm 0.20%$ </tex-math></inline-formula>. Convergence times for one round of optimization on a low-end single-board computer were less than 11 s on average. This study confirms the potential of leveraging HIL optimization for enhancing the performance of phase-portrait-based methods to reach accuracy levels comparable to more complex state-of-the-art methods.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 1","pages":"94-99"},"PeriodicalIF":3.4,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143529875","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 : 2024-11-26DOI: 10.1109/TMRB.2024.3503898
Eugenia De Remigis;Fehmi M. Dikbaş;Michele Ibrahimi;Francesco Bianciardi;Elisa L. Petrocelli;Elisa Roberti;Veronica Iacovacci;Stefano Palagi
Microscale robotics represents a promising future for minimally invasive medicine. However, one of the biggest challenges of microrobots moving through the human body is represented by the complex 3D structure of biological lumina and tissues, which obstructs the navigation of micron-sized devices. Here, we fabricate ultra-deformable magnetic microrobots, consisting of ferrofluid-loaded lipid vesicles, and we magnetically pull them through chambers that exert upon them a gradually more forceful confinement. We thus analyze their capability to face interstices comparable to or smaller than their characteristic size and their consequent behavior in terms of stability, velocity, and deformation. The results show that the inherent compliance of these vesicle-based magnetic microrobots allows them to infiltrate successfully in interstices slightly smaller than their size. Further enhancement of their compliance and the development of specific control strategies may lead to microrobots able to move through interstices and traverse complex biological environments.
{"title":"Infiltration of Cell-Inspired Ultra-Deformable Magnetic Microrobots in Restrictive Environments","authors":"Eugenia De Remigis;Fehmi M. Dikbaş;Michele Ibrahimi;Francesco Bianciardi;Elisa L. Petrocelli;Elisa Roberti;Veronica Iacovacci;Stefano Palagi","doi":"10.1109/TMRB.2024.3503898","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3503898","url":null,"abstract":"Microscale robotics represents a promising future for minimally invasive medicine. However, one of the biggest challenges of microrobots moving through the human body is represented by the complex 3D structure of biological lumina and tissues, which obstructs the navigation of micron-sized devices. Here, we fabricate ultra-deformable magnetic microrobots, consisting of ferrofluid-loaded lipid vesicles, and we magnetically pull them through chambers that exert upon them a gradually more forceful confinement. We thus analyze their capability to face interstices comparable to or smaller than their characteristic size and their consequent behavior in terms of stability, velocity, and deformation. The results show that the inherent compliance of these vesicle-based magnetic microrobots allows them to infiltrate successfully in interstices slightly smaller than their size. Further enhancement of their compliance and the development of specific control strategies may lead to microrobots able to move through interstices and traverse complex biological environments.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 1","pages":"123-129"},"PeriodicalIF":3.4,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10768195","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143529873","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 : 2024-11-25DOI: 10.1109/TMRB.2024.3504972
{"title":"2024 Index IEEE Transactions on Medical Robotics and Bionics Vol. 6","authors":"","doi":"10.1109/TMRB.2024.3504972","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3504972","url":null,"abstract":"","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 4","pages":"1781-1815"},"PeriodicalIF":3.4,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10766877","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713844","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 : 2024-11-25DOI: 10.1109/TMRB.2024.3506163
Carlo Tiseo;Quentin Rouxel;Martin Asenov;Keyhan Kouhkiloui Babarahmati;Subramanian Ramamoorthy;Zhibin Li;Michael Mistry
Medical robotics can help improve the reach of healthcare services. A challenge for medical robots is their complex physical interaction. This work evaluates a recently introduced control architecture based on Fractal Impedance Control (FIC) in medical applications. The deployed FIC architecture is robust to delay between the master and the replica robots and can switch online between an admittance and impedance behavior. Our experiments analyze three scenarios: teleoperated surgery, rehabilitation, and remote ultrasound scan. The experiments did not require any adjustment of the robot tuning, which is essential in medical applications where the operators do not have an engineering background. Our results show that it is possible to teleoperate the robot to perform remote occupational therapy, operate a scalpel, and use an ultrasound scan. However, our experiments also highlighted the need for a better robot embodiment to control the system precisely in 3D dynamic tasks.
{"title":"Achieving Dexterous Bidirectional Interaction in Uncertain Conditions for Medical Robotics","authors":"Carlo Tiseo;Quentin Rouxel;Martin Asenov;Keyhan Kouhkiloui Babarahmati;Subramanian Ramamoorthy;Zhibin Li;Michael Mistry","doi":"10.1109/TMRB.2024.3506163","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3506163","url":null,"abstract":"Medical robotics can help improve the reach of healthcare services. A challenge for medical robots is their complex physical interaction. This work evaluates a recently introduced control architecture based on Fractal Impedance Control (FIC) in medical applications. The deployed FIC architecture is robust to delay between the master and the replica robots and can switch online between an admittance and impedance behavior. Our experiments analyze three scenarios: teleoperated surgery, rehabilitation, and remote ultrasound scan. The experiments did not require any adjustment of the robot tuning, which is essential in medical applications where the operators do not have an engineering background. Our results show that it is possible to teleoperate the robot to perform remote occupational therapy, operate a scalpel, and use an ultrasound scan. However, our experiments also highlighted the need for a better robot embodiment to control the system precisely in 3D dynamic tasks.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 1","pages":"43-50"},"PeriodicalIF":3.4,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143529878","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 : 2024-11-25DOI: 10.1109/TMRB.2024.3505304
Emily A. Bywater;Nikko Van Crey;Elliott J. Rouse
In ankle-foot orthosis development, it is challenging to both specify the appropriate ankle mechanics and design systems that can physically render them. Recently, a new ankle-foot orthosis-the Variable Stiffness Orthosis (VSO)–was introduced to allow customization of the shape of the joint’s torque-angle relationship via a cam-based transmission. A module in the VSO permits switching between two coupled torque-angle relationships at desired kinematic transitions. This module decouples energy storage and return (DESR), enabling new functionality, including varying the ankle’s equilibrium position and exchanging energy between gait phases. However, the torque-angle relationships are defined by many parameters and subject to substantial constraints. We developed an optimization framework to design two versions of the DESR module to address foot drop. The angle module was designed to maximize swing ankle angle, and the energy module was designed to maximize energy recycled from early stance phase to augment push off. We validated the results of the optimization with brute-force searching and empirically tested the DESR mechanics in a rotary dynamometer. The angle module facilitated swing angles of up to 0.63° dorsiflexion, while simultaneously permitting a plantarflexed standing angle, and the energy module recycled up to 1.84 J.
{"title":"Optimizing the Mechanics of a Variable-Stiffness Orthosis With Energy Recycling to Mitigate Foot Drop","authors":"Emily A. Bywater;Nikko Van Crey;Elliott J. Rouse","doi":"10.1109/TMRB.2024.3505304","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3505304","url":null,"abstract":"In ankle-foot orthosis development, it is challenging to both specify the appropriate ankle mechanics and design systems that can physically render them. Recently, a new ankle-foot orthosis-the Variable Stiffness Orthosis (VSO)–was introduced to allow customization of the shape of the joint’s torque-angle relationship via a cam-based transmission. A module in the VSO permits switching between two coupled torque-angle relationships at desired kinematic transitions. This module decouples energy storage and return (DESR), enabling new functionality, including varying the ankle’s equilibrium position and exchanging energy between gait phases. However, the torque-angle relationships are defined by many parameters and subject to substantial constraints. We developed an optimization framework to design two versions of the DESR module to address foot drop. The angle module was designed to maximize swing ankle angle, and the energy module was designed to maximize energy recycled from early stance phase to augment push off. We validated the results of the optimization with brute-force searching and empirically tested the DESR mechanics in a rotary dynamometer. The angle module facilitated swing angles of up to 0.63° dorsiflexion, while simultaneously permitting a plantarflexed standing angle, and the energy module recycled up to 1.84 J.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 1","pages":"130-140"},"PeriodicalIF":3.4,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143529877","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}
Myoelectric control models enabling accurate hand gesture recognition via electromyography (EMG) have attracted increasing attentions in rehabilitation robotics. Adapting pre-trained models to new users is a main challenge in real world applications due to the inter-user different EMG characteristics. Most previous transfer learning approaches employed a rigid model calibration process, usually in a supervised manner with ground truth labels, or in an unsupervised manner but still requiring users to perform pre-defined hand gestures to update model parameters. We argue that such a rigid model calibration process lacks flexibility and limit the translation of myoelectric control into real world practice. In this work, we gradually “flexibilize” the standard model calibration process toward a highly flexible version, which does not require the labels of calibration data, and can be performed on only a subset of pre-defined hand gestures or even unknown user-defined hand gestures. We identify those key components contributing to the performance difference along the way. Compared with the supervised method, the unsupervised model calibration even contributed to a 10% improvement (${p}lt 0.05$ ) in case where only a subset of gesture categories were available for model calibration. Moreover, the unsupervised model calibration achieved a highest recognition accuracy of 86.57% using unknown user-defined gestures, with no significant difference compared to the accuracy with pre-defined gestures (${p}gt 0.05$ ).
{"title":"Toward Highly Flexible Inter-User Calibration of Myoelectric Control Models With User-Defined Hand Gestures","authors":"Yangyang Yuan;Zihao Chen;Jionghui Liu;ChihHong Chou;Chenyun Dai;Xinyu Jiang","doi":"10.1109/TMRB.2024.3504737","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3504737","url":null,"abstract":"Myoelectric control models enabling accurate hand gesture recognition via electromyography (EMG) have attracted increasing attentions in rehabilitation robotics. Adapting pre-trained models to new users is a main challenge in real world applications due to the inter-user different EMG characteristics. Most previous transfer learning approaches employed a rigid model calibration process, usually in a supervised manner with ground truth labels, or in an unsupervised manner but still requiring users to perform pre-defined hand gestures to update model parameters. We argue that such a rigid model calibration process lacks flexibility and limit the translation of myoelectric control into real world practice. In this work, we gradually “flexibilize” the standard model calibration process toward a highly flexible version, which does not require the labels of calibration data, and can be performed on only a subset of pre-defined hand gestures or even unknown user-defined hand gestures. We identify those key components contributing to the performance difference along the way. Compared with the supervised method, the unsupervised model calibration even contributed to a 10% improvement (<inline-formula> <tex-math>${p}lt 0.05$ </tex-math></inline-formula>) in case where only a subset of gesture categories were available for model calibration. Moreover, the unsupervised model calibration achieved a highest recognition accuracy of 86.57% using unknown user-defined gestures, with no significant difference compared to the accuracy with pre-defined gestures (<inline-formula> <tex-math>${p}gt 0.05$ </tex-math></inline-formula>).","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 1","pages":"359-367"},"PeriodicalIF":3.4,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143521345","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}
Extraction of the correct and efficient descriptors of muscular activity plays a vital role in tackling the challenging problem of myoelectric control of powered prostheses. This work presents a feature extraction framework that aims to enhance the representation of muscular activities by increasing the amount of information that can be extracted from individual and combined electromyogram (EMG) channels. The proposed method for feature selection is based on Shapley Additive explanations (SHAP). The SHAP value is used to reduce the feature dimension. The proposed approach has been evaluated on two datasets obtained at a sampling rate of 1 kHz through a band consisting of seven EMG channels. The Standard deviation (SD) and Integrated EMG (IEMG) of electrodes 3, 5, 6, and 7 recognized four motions with a classification accuracy of 98.42%±1.16% and six gestures with a classification accuracy of 96.6%±0.91%, respectively. In the present work, an ensemble technique called bagging in the random forest algorithm has been used to obtain the optimum results.
{"title":"Explainable AI-Guided Optimization of EMG Channels and Features for Precise Hand Gesture Classification: A SHAP-Based Study","authors":"Parul Rani;Sidharth Pancholi;Vikash Shaw;Suraj Pandey;Manfredo Atzori;Sanjeev Kumar","doi":"10.1109/TMRB.2024.3504007","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3504007","url":null,"abstract":"Extraction of the correct and efficient descriptors of muscular activity plays a vital role in tackling the challenging problem of myoelectric control of powered prostheses. This work presents a feature extraction framework that aims to enhance the representation of muscular activities by increasing the amount of information that can be extracted from individual and combined electromyogram (EMG) channels. The proposed method for feature selection is based on Shapley Additive explanations (SHAP). The SHAP value is used to reduce the feature dimension. The proposed approach has been evaluated on two datasets obtained at a sampling rate of 1 kHz through a band consisting of seven EMG channels. The Standard deviation (SD) and Integrated EMG (IEMG) of electrodes 3, 5, 6, and 7 recognized four motions with a classification accuracy of 98.42%±1.16% and six gestures with a classification accuracy of 96.6%±0.91%, respectively. In the present work, an ensemble technique called bagging in the random forest algorithm has been used to obtain the optimum results.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 1","pages":"368-376"},"PeriodicalIF":3.4,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143521429","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 : 2024-11-21DOI: 10.1109/TMRB.2024.3503911
Naman Gupta;Dhruva Khanzode;Ranjan Jha
Cardiovascular diseases, driven by pollution and unhealthy lifestyle factors, are commonly treated with cardiac catheterization. However, this exposes medical staff to harmful X-ray radiation, leading to the development of robot-assisted catheterization systems for safer procedures. Despite their advantages, existing robotic systems are frequently complex and struggle with catheter maneuverability without a guidewire. This paper introduces a novel two-degree-of-freedom robot-assisted cardiac catheterization system, detailing its development, evaluation, and mathematical modeling. The system is designed for precise control of catheter motion through both translational and rotational movements, enhancing procedural efficiency and safety. We provide an in-depth analysis of deformation forces, stress, and strain characteristics based on catheter materials, supported by comprehensive mathematical modeling of applied forces and torques. Simulation results show that the system requires a torque of 1.870 Nm, a displacement of 0.089 m, and a velocity of 1.450 m/s for translational motion. For rotational motion, the system demands 0.915 Nm of torque, an angle of 5.102 rad, and an angular velocity of 88.735 rad/s. These results are validated against pre-existing models to confirm the system’s performance. The study concludes by presenting a three-dimensional (3D) model of the system, demonstrating its ability to improve the safety and precision of cardiac catheterization.
{"title":"Design and Mathematical Modeling of a Novel Two-Degree-of-Freedom Robot-Assisted Cardiac Catheterization System","authors":"Naman Gupta;Dhruva Khanzode;Ranjan Jha","doi":"10.1109/TMRB.2024.3503911","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3503911","url":null,"abstract":"Cardiovascular diseases, driven by pollution and unhealthy lifestyle factors, are commonly treated with cardiac catheterization. However, this exposes medical staff to harmful X-ray radiation, leading to the development of robot-assisted catheterization systems for safer procedures. Despite their advantages, existing robotic systems are frequently complex and struggle with catheter maneuverability without a guidewire. This paper introduces a novel two-degree-of-freedom robot-assisted cardiac catheterization system, detailing its development, evaluation, and mathematical modeling. The system is designed for precise control of catheter motion through both translational and rotational movements, enhancing procedural efficiency and safety. We provide an in-depth analysis of deformation forces, stress, and strain characteristics based on catheter materials, supported by comprehensive mathematical modeling of applied forces and torques. Simulation results show that the system requires a torque of 1.870 Nm, a displacement of 0.089 m, and a velocity of 1.450 m/s for translational motion. For rotational motion, the system demands 0.915 Nm of torque, an angle of 5.102 rad, and an angular velocity of 88.735 rad/s. These results are validated against pre-existing models to confirm the system’s performance. The study concludes by presenting a three-dimensional (3D) model of the system, demonstrating its ability to improve the safety and precision of cardiac catheterization.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 1","pages":"230-241"},"PeriodicalIF":3.4,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143521354","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 : 2024-11-21DOI: 10.1109/TMRB.2024.3503925
Francesco Missiroli;Francesco Ferrazzi;Enrica Tricomi;Maura Casadio;Lorenzo Masia
Wearable robotic devices like exosuits address mobility challenges in musculoskeletal disorders. While exoskeletons mainly aid in rehabilitation routines, lightweight exosuits provide a cost-effective solution, empowering individuals with motor disabilities in performing daily activities. Characterized by discreet, flexible designs, exosuits seamlessly integrate into daily routines, offering unobtrusive support and enhancing functional independence for those with mobility impairments. This research proposes a novel exoglove controlled via force-myography to restore grasping motor ability in individuals with partial loss of hand-motor function but retaining residual wrist movement. The exosuit aims to provide a tailored solution, offering cost-effective advantages over traditional exoskeletons. The proposed exoglove uses force myography to translate the user’s wrist movements into a motor command to assist grasping. Such an approach could ensure reliable and consistent control for people with partial or total loss of finger motion. With more than 89% accuracy in wrist movement classification, it can operate with minimal effort, moreover, the exoglove preserves natural finger motion, demonstrated by negligible muscle activity variations.
{"title":"Assistive Force Myography Controlled Exoglove","authors":"Francesco Missiroli;Francesco Ferrazzi;Enrica Tricomi;Maura Casadio;Lorenzo Masia","doi":"10.1109/TMRB.2024.3503925","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3503925","url":null,"abstract":"Wearable robotic devices like exosuits address mobility challenges in musculoskeletal disorders. While exoskeletons mainly aid in rehabilitation routines, lightweight exosuits provide a cost-effective solution, empowering individuals with motor disabilities in performing daily activities. Characterized by discreet, flexible designs, exosuits seamlessly integrate into daily routines, offering unobtrusive support and enhancing functional independence for those with mobility impairments. This research proposes a novel exoglove controlled via force-myography to restore grasping motor ability in individuals with partial loss of hand-motor function but retaining residual wrist movement. The exosuit aims to provide a tailored solution, offering cost-effective advantages over traditional exoskeletons. The proposed exoglove uses force myography to translate the user’s wrist movements into a motor command to assist grasping. Such an approach could ensure reliable and consistent control for people with partial or total loss of finger motion. With more than 89% accuracy in wrist movement classification, it can operate with minimal effort, moreover, the exoglove preserves natural finger motion, demonstrated by negligible muscle activity variations.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 1","pages":"27-32"},"PeriodicalIF":3.4,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143529881","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 : 2024-11-21DOI: 10.1109/TMRB.2024.3504001
Jake Kanetis;Michael A. Gonzalez;Alex K. Vaskov;Paul S. Cederna;Cynthia A. Chestek;Deanna H. Gates
Individuals who use upper limb prostheses receive limited feedback from their devices. Researchers have attempted to elicit sensation through direct stimulation of peripheral nerves or through stimulation of reinnervated skin or muscle. Previous research found that electrical stimulation of Regenerative Peripheral Nerve Interfaces (RPNIs) elicited sensations that were referred to the phantom hand. The purpose of this study was to determine if this sensation could be used to improve performance of a functional task. Two participants with upper limb loss completed the Box and Blocks Test in a virtual environment under four feedback conditions on a single day of testing. These conditions included no feedback, vibration triggered by object contact, and two conditions where RPNIs were electrically stimulated upon object contact. For the RPNI conditions, one was somatotopic, meaning the referred sensation and virtual sensor were collocated and the other was non-somatotopic, where the referred sensation and virtual sensor locations differed. Participants moved the most blocks when somatotopic feedback was provided. Both participants expressed a preference for the somatotopic sensation, noting that it made their movements feel more natural. Overall, this study demonstrates that RPNI-elicited sensation has the potential to improve functional performance.
{"title":"Assessing the Utility of Regenerative Peripheral Nerve Interfaces (RPNIs) in Providing Referred Sensations in a Functional Task in a Virtual Environment","authors":"Jake Kanetis;Michael A. Gonzalez;Alex K. Vaskov;Paul S. Cederna;Cynthia A. Chestek;Deanna H. Gates","doi":"10.1109/TMRB.2024.3504001","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3504001","url":null,"abstract":"Individuals who use upper limb prostheses receive limited feedback from their devices. Researchers have attempted to elicit sensation through direct stimulation of peripheral nerves or through stimulation of reinnervated skin or muscle. Previous research found that electrical stimulation of Regenerative Peripheral Nerve Interfaces (RPNIs) elicited sensations that were referred to the phantom hand. The purpose of this study was to determine if this sensation could be used to improve performance of a functional task. Two participants with upper limb loss completed the Box and Blocks Test in a virtual environment under four feedback conditions on a single day of testing. These conditions included no feedback, vibration triggered by object contact, and two conditions where RPNIs were electrically stimulated upon object contact. For the RPNI conditions, one was somatotopic, meaning the referred sensation and virtual sensor were collocated and the other was non-somatotopic, where the referred sensation and virtual sensor locations differed. Participants moved the most blocks when somatotopic feedback was provided. Both participants expressed a preference for the somatotopic sensation, noting that it made their movements feel more natural. Overall, this study demonstrates that RPNI-elicited sensation has the potential to improve functional performance.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 1","pages":"141-148"},"PeriodicalIF":3.4,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143529897","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：