Pub Date : 2025-02-25DOI: 10.1109/THMS.2025.3539187
Zhengyang Lou;Zitong Zhan;Huan Xu;Yin Li;Yu Hen Hu;Ming-Lun Lu;Dwight M. Werren;Robert G. Radwin
A computer vision (CV) method to automatically measure the revised NIOSH lifting equation asymmetry angle (A) from a single camera is described and tested. A laboratory study involving ten participants performing various lifts was used to estimate A in comparison to ground truth joint coordinates obtained using 3-D motion capture (MoCap). To address challenges, such as obstructed views and limitations in camera placement in real-world scenarios, the CV method utilized video-derived coordinates from a selected set of landmarks. A 2-D pose estimator (HR-Net) detected landmark coordinates in each video frame, and a 3-D algorithm (VideoPose3D) estimated the depth of each 2-D landmark by analyzing its trajectories. The mean absolute precision error for the CV method, compared to MoCap measurements using the same subset of landmarks for estimating A, was 6.25° (SD = 10.19°, N = 360). The mean absolute accuracy error of the CV method, compared against conventional MoCap landmark markers was 9.45° (SD = 14.01°, N = 360).
{"title":"A Single-Camera Method for Estimating Lift Asymmetry Angles Using Deep Learning Computer Vision Algorithms","authors":"Zhengyang Lou;Zitong Zhan;Huan Xu;Yin Li;Yu Hen Hu;Ming-Lun Lu;Dwight M. Werren;Robert G. Radwin","doi":"10.1109/THMS.2025.3539187","DOIUrl":"https://doi.org/10.1109/THMS.2025.3539187","url":null,"abstract":"A computer vision (CV) method to automatically measure the revised NIOSH lifting equation asymmetry angle (<italic>A</i>) from a single camera is described and tested. A laboratory study involving ten participants performing various lifts was used to estimate <italic>A</i> in comparison to ground truth joint coordinates obtained using 3-D motion capture (MoCap). To address challenges, such as obstructed views and limitations in camera placement in real-world scenarios, the CV method utilized video-derived coordinates from a selected set of landmarks. A 2-D pose estimator (HR-Net) detected landmark coordinates in each video frame, and a 3-D algorithm (VideoPose3D) estimated the depth of each 2-D landmark by analyzing its trajectories. The mean absolute precision error for the CV method, compared to MoCap measurements using the same subset of landmarks for estimating <italic>A</i>, was 6.25° (SD = 10.19°, N = 360). The mean absolute accuracy error of the CV method, compared against conventional MoCap landmark markers was 9.45° (SD = 14.01°, <italic>N</i> = 360).","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"55 2","pages":"309-314"},"PeriodicalIF":3.5,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-24DOI: 10.1109/THMS.2025.3538162
Hongguang Pan;Shiyu Tong;Haoqian Song;Xin Chu
It has been proven that electroencephalography (EEG) is an effective method for evaluating an individual's mental state. However, when it comes to the evaluation of miners' mental state, there are still some issues with missing EEG dataset and unsatisfactory evaluation accuracy. Therefore, this article proposes a miner mental state evaluation scheme with decision-level fusion based on multidomain EEG information. First, in the comprehensive lab for coal-related programs of Xi'an University of Science and Technology, the coal mine environment is simulated, and a realistic EEG dataset is constructed. Second, the multidomain features are extracted to represent abundant information in time, frequency, time-frequency, and space domain. These features with low dimension are classified adopting support vector machine (SVM), k-nearest neighbor (kNN), and back propagation (BP) network to obtain the optimal evaluation submodel (four domains corresponding to four submodels). Finally, based on the state probabilities provided by the optimal evaluation submodel, we adopt stack fusion and an improved Yager rule to fuse four submodels in order to find the most suitable fusion algorithm. The experimental results demonstrate that the average accuracy can reach 93.19% on the self-built dataset when utilizing the improved Yager rule with weight, and it realizes a better evaluation accuracy.
{"title":"A Miner Mental State Evaluation Scheme With Decision Level Fusion Based on Multidomain EEG Information","authors":"Hongguang Pan;Shiyu Tong;Haoqian Song;Xin Chu","doi":"10.1109/THMS.2025.3538162","DOIUrl":"https://doi.org/10.1109/THMS.2025.3538162","url":null,"abstract":"It has been proven that electroencephalography (EEG) is an effective method for evaluating an individual's mental state. However, when it comes to the evaluation of miners' mental state, there are still some issues with missing EEG dataset and unsatisfactory evaluation accuracy. Therefore, this article proposes a miner mental state evaluation scheme with decision-level fusion based on multidomain EEG information. First, in the comprehensive lab for coal-related programs of Xi'an University of Science and Technology, the coal mine environment is simulated, and a realistic EEG dataset is constructed. Second, the multidomain features are extracted to represent abundant information in time, frequency, time-frequency, and space domain. These features with low dimension are classified adopting support vector machine (SVM), k-nearest neighbor (kNN), and back propagation (BP) network to obtain the optimal evaluation submodel (four domains corresponding to four submodels). Finally, based on the state probabilities provided by the optimal evaluation submodel, we adopt stack fusion and an improved Yager rule to fuse four submodels in order to find the most suitable fusion algorithm. The experimental results demonstrate that the average accuracy can reach 93.19% on the self-built dataset when utilizing the improved Yager rule with weight, and it realizes a better evaluation accuracy.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"55 2","pages":"289-299"},"PeriodicalIF":3.5,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-21DOI: 10.1109/THMS.2025.3532910
Xiang Zhang;Jinyang Huang;Huan Yan;Yuanhao Feng;Peng Zhao;Guohang Zhuang;Zhi Liu;Bin Liu
Recent years have witnessed a growing interest in Wi-Fi-based gesture recognition. However, existing works have predominantly focused on closed-set paradigms, where all testing gestures are predefined during training. This poses a significant challenge in real-world applications, as unseen gestures might be misclassified as known class during testing. To address this issue, we propose WiOpen, a robust Wi-Fi-based open-set gesture recognition (OSGR) framework. Implementing OSGR requires addressing challenges caused by the unique uncertainty in Wi-Fi sensing. This uncertainty, resulting from noise and domains, leads to widely scattered and irregular data distributions in collected Wi-Fi sensing data. Consequently, data ambiguity between classes and challenges in defining appropriate decision boundaries to identify unknowns arise. To tackle these challenges, WiOpen adopts a twofold approach to eliminate uncertainty and define precise decision boundaries. Initially, it addresses uncertainty induced by noise during data preprocessing by utilizing the channel state information (CSI) ratio. Next, it designs the OSGR network based on an uncertainty quantification method. Throughout the learning process, this network effectively mitigates uncertainty stemming from domains. Ultimately, the network leverages relationships among samples' neighbors to dynamically define open-set decision boundaries, successfully realizing OSGR. Comprehensive experiments on publicly accessible datasets confirm WiOpen's effectiveness.
{"title":"WiOpen: A Robust Wi-Fi-Based Open-Set Gesture Recognition Framework","authors":"Xiang Zhang;Jinyang Huang;Huan Yan;Yuanhao Feng;Peng Zhao;Guohang Zhuang;Zhi Liu;Bin Liu","doi":"10.1109/THMS.2025.3532910","DOIUrl":"https://doi.org/10.1109/THMS.2025.3532910","url":null,"abstract":"Recent years have witnessed a growing interest in Wi-Fi-based gesture recognition. However, existing works have predominantly focused on closed-set paradigms, where all testing gestures are predefined during training. This poses a significant challenge in real-world applications, as unseen gestures might be misclassified as known class during testing. To address this issue, we propose WiOpen, a robust Wi-Fi-based open-set gesture recognition (OSGR) framework. Implementing OSGR requires addressing challenges caused by the unique uncertainty in Wi-Fi sensing. This uncertainty, resulting from noise and domains, leads to widely scattered and irregular data distributions in collected Wi-Fi sensing data. Consequently, data ambiguity between classes and challenges in defining appropriate decision boundaries to identify unknowns arise. To tackle these challenges, WiOpen adopts a twofold approach to eliminate uncertainty and define precise decision boundaries. Initially, it addresses uncertainty induced by noise during data preprocessing by utilizing the channel state information (CSI) ratio. Next, it designs the OSGR network based on an uncertainty quantification method. Throughout the learning process, this network effectively mitigates uncertainty stemming from domains. Ultimately, the network leverages relationships among samples' neighbors to dynamically define open-set decision boundaries, successfully realizing OSGR. Comprehensive experiments on publicly accessible datasets confirm WiOpen's effectiveness.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"55 2","pages":"234-245"},"PeriodicalIF":3.5,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-14DOI: 10.1109/THMS.2025.3532358
Sungwoo Park;Moon Ki Jung;Kyujung Kim;HyunSeop Lim;JuYoung Yoon;Dong Jin Hyun
This article proposes a novel evaluation approach on wearing passive upper-limb exoskeletons for overhead tasks in real-world automotive manufacturing lines. We determined that wearing exoskeletons reduced the biomechanical efforts of workers measured by joint kinematics and electromyography as well as the estimated shoulder joint reaction forces and torques derived from simulation. These quantitatively measured variables were statistically associated with subjective measures collected through satisfaction questionnaires. We specifically found that participants increased the shoulder flexion and abduction angles as well as the shoulder range of motion while wearing exoskeletons. Participants also reduced muscle activities, joint torques for shoulder flexion, and reaction forces exerted on the shoulder joints while wearing exoskeletons. Interestingly, our analysis also found that the increased shoulder movement while wearing the device was negatively associated with the satisfaction level. This indicates that although the assistance provided by the device allows users to perform a wider range of arm lifting movements, the deviation from their original movement with the device may lead to decreases in satisfaction levels. This integrative approach using biomechanics and ergonomics suggests that we can potentially predict the subjective scale of satisfaction based on biomechanical variables and preliminarily evaluate the usability and comfort while wearing exoskeletons in real-world settings.
{"title":"Correlations Between Biomechanical Variables and Subjective Measures of Satisfaction While Using a Passive Upper-Limb Exoskeleton for Overhead Tasks in the Field","authors":"Sungwoo Park;Moon Ki Jung;Kyujung Kim;HyunSeop Lim;JuYoung Yoon;Dong Jin Hyun","doi":"10.1109/THMS.2025.3532358","DOIUrl":"https://doi.org/10.1109/THMS.2025.3532358","url":null,"abstract":"This article proposes a novel evaluation approach on wearing passive upper-limb exoskeletons for overhead tasks in real-world automotive manufacturing lines. We determined that wearing exoskeletons reduced the biomechanical efforts of workers measured by joint kinematics and electromyography as well as the estimated shoulder joint reaction forces and torques derived from simulation. These quantitatively measured variables were statistically associated with subjective measures collected through satisfaction questionnaires. We specifically found that participants increased the shoulder flexion and abduction angles as well as the shoulder range of motion while wearing exoskeletons. Participants also reduced muscle activities, joint torques for shoulder flexion, and reaction forces exerted on the shoulder joints while wearing exoskeletons. Interestingly, our analysis also found that the increased shoulder movement while wearing the device was negatively associated with the satisfaction level. This indicates that although the assistance provided by the device allows users to perform a wider range of arm lifting movements, the deviation from their original movement with the device may lead to decreases in satisfaction levels. This integrative approach using biomechanics and ergonomics suggests that we can potentially predict the subjective scale of satisfaction based on biomechanical variables and preliminarily evaluate the usability and comfort while wearing exoskeletons in real-world settings.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"55 2","pages":"176-184"},"PeriodicalIF":3.5,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Occupational exoskeletons have the potential to prevent work-related musculoskeletal disorders. Their widespread adoption should be promoted by investigating their long-term innocuity, sustained effectiveness, and practicability. This article presents a six-months longitudinal study exploring effects of an arm support exoskeleton (ASE) on six male workers, examining potential side effects, ASE's effectiveness, and its integration into daily work practices. Monthly clinical visits were scheduled to monitor workers’ health. Effectiveness, usability and acceptance metrics were collected at the beginning of the study and after six months. No side effects were found in clinical metrics during the study. Significant reductions, consistent overtime, were observed in shoulder muscle activity (up to 30%) and in effort perception-related metrics (up to 2.4 out of 10 points). Usage time settled around 10% of the monthly work-shift and gradually decreased possibly due to external factors (e.g., social, motivational, and seasonal factors) beyond researchers' control. Results encourage the continuation of similar investigations to strengthen these findings and promote the use of occupational exoskeletons.
{"title":"Introducing a Passive Shoulder Exoskeleton in a Production Plant: A Longitudinal Observation of Its Effects on Workers","authors":"Andrea Parri;Ilaria Pacifico;Eleonora Guanziroli;Federica Aprigliano;Silverio Taglione;Francesco Giovacchini;Francesco Saverio Violante;Franco Molteni;Nicola Vitiello;Simona Crea","doi":"10.1109/THMS.2025.3536199","DOIUrl":"https://doi.org/10.1109/THMS.2025.3536199","url":null,"abstract":"Occupational exoskeletons have the potential to prevent work-related musculoskeletal disorders. Their widespread adoption should be promoted by investigating their long-term innocuity, sustained effectiveness, and practicability. This article presents a six-months longitudinal study exploring effects of an arm support exoskeleton (ASE) on six male workers, examining potential side effects, ASE's effectiveness, and its integration into daily work practices. Monthly clinical visits were scheduled to monitor workers’ health. Effectiveness, usability and acceptance metrics were collected at the beginning of the study and after six months. No side effects were found in clinical metrics during the study. Significant reductions, consistent overtime, were observed in shoulder muscle activity (up to 30%) and in effort perception-related metrics (up to 2.4 out of 10 points). Usage time settled around 10% of the monthly work-shift and gradually decreased possibly due to external factors (e.g., social, motivational, and seasonal factors) beyond researchers' control. Results encourage the continuation of similar investigations to strengthen these findings and promote the use of occupational exoskeletons.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"55 2","pages":"185-196"},"PeriodicalIF":3.5,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-10DOI: 10.1109/THMS.2025.3532598
Syed Muhammad Amrr;Mohamed Zaery;S. M. Suhail Hussain;Mohammad A. Abido
This article introduces a novel prescribed time-based method for analyzing the convergence of evolutionary game dynamics in an information lossy network. Traditional game theory limits players to two choices, i.e., either cooperation or defection. However, player behavior in real-world scenarios is often multidimensional and complex; therefore, this work employs a continuous action iterated dilemma that allows players to choose a wider range of strategies. Moreover, traditional convergence analysis often relies on Jacobian matrices, which entail complex derivations. In contrast, the proposed strategy employs a time generator-based protocol that achieves agreement between all the players at a prescribed time, explicitly set by the user through a time parameter within the protocol. A comprehensive Lyapunov analysis affirms the prescribed time convergence even when the network is exposed to information loss during data transfer. Numerical simulations illustrate that the proposed scheme leads to a faster agreement at the preassigned time and with a better resilience performance compared to existing methods.
{"title":"Time-Based Protocol for Continuous Action Iterated Dilemma in Information Lossy Networks","authors":"Syed Muhammad Amrr;Mohamed Zaery;S. M. Suhail Hussain;Mohammad A. Abido","doi":"10.1109/THMS.2025.3532598","DOIUrl":"https://doi.org/10.1109/THMS.2025.3532598","url":null,"abstract":"This article introduces a novel prescribed time-based method for analyzing the convergence of evolutionary game dynamics in an information lossy network. Traditional game theory limits players to two choices, i.e., either cooperation or defection. However, player behavior in real-world scenarios is often multidimensional and complex; therefore, this work employs a continuous action iterated dilemma that allows players to choose a wider range of strategies. Moreover, traditional convergence analysis often relies on Jacobian matrices, which entail complex derivations. In contrast, the proposed strategy employs a time generator-based protocol that achieves agreement between all the players at a prescribed time, explicitly set by the user through a time parameter within the protocol. A comprehensive Lyapunov analysis affirms the prescribed time convergence even when the network is exposed to information loss during data transfer. Numerical simulations illustrate that the proposed scheme leads to a faster agreement at the preassigned time and with a better resilience performance compared to existing methods.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"55 2","pages":"315-321"},"PeriodicalIF":3.5,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ecological environment and natural resource issues are becoming more and more prominent, which promotes the recycling of waste products for green economy. Disassembly plays a key role in the remanufacturing and reuse of waste products. However, with the rapid development of production automation, designers tend to ignore the fact that manual operation is more flexible. It is of great importance to consider human factors in a disassembly process. This work considers two human disassembly postures, namely standing and sitting. The multiobjective disassembly line balancing problem considering human posture changes is studied. A mathematical model with the objective functions of maximizing profit, minimizing the number of posture changes at a workstation, and minimizing the difference of maximum posture changes between any two workstations is established. The model is solved through a newly proposed Pareto-based discrete harmony search algorithm. Three neighborhood structures are designed to enlarge the search space for better solutions. Furthermore, an elite reserve strategy is used to improve the global optimization ability of the proposed algorithm. Finally, the proposed model and algorithm are applied to cases of different scales of complexities, and the effectiveness of the proposed model and algorithm is verified in comparison with four competitive algorithms.
{"title":"A Multiobjective Discrete Harmony Search Optimizer for Disassembly Line Balancing Problems Considering Human Factors","authors":"Tingting Wei;Xiwang Guo;Mengchu Zhou;Jiacun Wang;Shixin Liu;Shujin Qin;Ying Tang","doi":"10.1109/THMS.2025.3528629","DOIUrl":"https://doi.org/10.1109/THMS.2025.3528629","url":null,"abstract":"Ecological environment and natural resource issues are becoming more and more prominent, which promotes the recycling of waste products for green economy. Disassembly plays a key role in the remanufacturing and reuse of waste products. However, with the rapid development of production automation, designers tend to ignore the fact that manual operation is more flexible. It is of great importance to consider human factors in a disassembly process. This work considers two human disassembly postures, namely standing and sitting. The multiobjective disassembly line balancing problem considering human posture changes is studied. A mathematical model with the objective functions of maximizing profit, minimizing the number of posture changes at a workstation, and minimizing the difference of maximum posture changes between any two workstations is established. The model is solved through a newly proposed Pareto-based discrete harmony search algorithm. Three neighborhood structures are designed to enlarge the search space for better solutions. Furthermore, an elite reserve strategy is used to improve the global optimization ability of the proposed algorithm. Finally, the proposed model and algorithm are applied to cases of different scales of complexities, and the effectiveness of the proposed model and algorithm is verified in comparison with four competitive algorithms.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"55 2","pages":"124-133"},"PeriodicalIF":3.5,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-06DOI: 10.1109/THMS.2025.3530530
Celal Savur;Jamison Heard;Ferat Sahin
Effective human–robot collaboration (HRC) requires robots to understand and adapt to humans' psychological states. This research presents a novel approach to quantitatively measure human comfort levels during HRC through the development of two metrics: a comfortability index (CI) and an uncomfortability index (UnCI). We conducted HRC experiments where participants performed assembly tasks while the robot's behavior was systematically varied. Participants' subjective responses (including surprise, anxiety, boredom, calmness, and comfortability ratings) were collected alongside physiological signals, including electrocardiogram, galvanic skin response, and pupillometry data. We propose two novel approaches for estimating CI/UnCI: an adaptation of the emotion circumplex model that maps comfort levels to the arousal–valence space, and a kernel density estimation model trained on physiological data. Time-domain features were extracted from the physiological signals and used to train machine learning models for real-time comfort levels estimation. Our results demonstrate that the proposed approaches can effectively estimate human comfort levels from physiological signals alone, with the circumplex model showing particular promise in detecting high discomfort states. This work enables real-time measurement of human comfort during HRC, providing a foundation for developing more adaptive and human-aware collaborative robots.
{"title":"Human Comfort Index Estimation in Industrial Human–Robot Collaboration Task","authors":"Celal Savur;Jamison Heard;Ferat Sahin","doi":"10.1109/THMS.2025.3530530","DOIUrl":"https://doi.org/10.1109/THMS.2025.3530530","url":null,"abstract":"Effective human–robot collaboration (HRC) requires robots to understand and adapt to humans' psychological states. This research presents a novel approach to quantitatively measure human comfort levels during HRC through the development of two metrics: a comfortability index (CI) and an uncomfortability index (UnCI). We conducted HRC experiments where participants performed assembly tasks while the robot's behavior was systematically varied. Participants' subjective responses (including <italic>surprise</i>, <italic>anxiety</i>, <italic>boredom</i>, <italic>calmness</i>, and <italic>comfortability</i> ratings) were collected alongside physiological signals, including electrocardiogram, galvanic skin response, and pupillometry data. We propose two novel approaches for estimating CI/UnCI: an adaptation of the emotion circumplex model that maps comfort levels to the arousal–valence space, and a kernel density estimation model trained on physiological data. Time-domain features were extracted from the physiological signals and used to train machine learning models for real-time comfort levels estimation. Our results demonstrate that the proposed approaches can effectively estimate human comfort levels from physiological signals alone, with the circumplex model showing particular promise in detecting high discomfort states. This work enables real-time measurement of human comfort during HRC, providing a foundation for developing more adaptive and human-aware collaborative robots.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"55 2","pages":"246-255"},"PeriodicalIF":3.5,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-05DOI: 10.1109/THMS.2025.3532209
Long Meng;Luis Vargas;Derek G. Kamper;Xiaogang Hu
Neural or muscular injuries, such as due to amputation, spinal cord injury, and stroke, can affect hand functions, profoundly impacting independent living. This has motivated the advancement of cutting-edge assistive robotic hands. However, unintuitive myoelectric control of these devices remains challenging, which limits the clinical translation of these devices. Accordingly, we developed a robust motor-intent decoding approach to continuously predict the intended fingertip forces of single and multiple fingers in real time. We used population motor neuron discharge activities (i.e., neural drive from brain to spinal cord) decoded from a high-density surface electromyogram (HD-sEMG) signals as the control signals instead of the conventional global sEMG features. To enable real-time neural-drive prediction, we employed a convolutional neural network model to establish the mapping from global HD-sEMG features to finger-specific neural-drive signals, which were then employed for continuous and real-time control of three prosthetic fingers (index, middle, and ring). As a result, the neural-drive-based approach can decode the motor intent of single-finger and multifinger forces with significantly lower force estimation errors than that obtained using the global HD-sEMG-amplitude approach. Besides, the force prediction accuracy was consistent over time and demonstrated strong robustness to signal interference. Our network-based decoder can also achieve better finger isolation with minimal forces predicted in unintended fingers. Our work demonstrates that the accurate and robust finger force control could be achieved through this new decoding approach. The outcomes offer an efficient intent prediction approach that allows users to have intuitive control of prosthetic fingertip forces in a dexterous way.
{"title":"Real-Time Myoelectric-Based Neural-Drive Decoding for Concurrent and Continuous Control of Robotic Finger Forces","authors":"Long Meng;Luis Vargas;Derek G. Kamper;Xiaogang Hu","doi":"10.1109/THMS.2025.3532209","DOIUrl":"https://doi.org/10.1109/THMS.2025.3532209","url":null,"abstract":"Neural or muscular injuries, such as due to amputation, spinal cord injury, and stroke, can affect hand functions, profoundly impacting independent living. This has motivated the advancement of cutting-edge assistive robotic hands. However, unintuitive myoelectric control of these devices remains challenging, which limits the clinical translation of these devices. Accordingly, we developed a robust motor-intent decoding approach to continuously predict the intended fingertip forces of single and multiple fingers in real time. We used population motor neuron discharge activities (i.e., neural drive from brain to spinal cord) decoded from a high-density surface electromyogram (HD-sEMG) signals as the control signals instead of the conventional global sEMG features. To enable real-time neural-drive prediction, we employed a convolutional neural network model to establish the mapping from global HD-sEMG features to finger-specific neural-drive signals, which were then employed for continuous and real-time control of three prosthetic fingers (index, middle, and ring). As a result, the neural-drive-based approach can decode the motor intent of single-finger and multifinger forces with significantly lower force estimation errors than that obtained using the global HD-sEMG-amplitude approach. Besides, the force prediction accuracy was consistent over time and demonstrated strong robustness to signal interference. Our network-based decoder can also achieve better finger isolation with minimal forces predicted in unintended fingers. Our work demonstrates that the accurate and robust finger force control could be achieved through this new decoding approach. The outcomes offer an efficient intent prediction approach that allows users to have intuitive control of prosthetic fingertip forces in a dexterous way.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"55 2","pages":"256-265"},"PeriodicalIF":3.5,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-04DOI: 10.1109/THMS.2024.3523661
{"title":"IEEE Systems, Man, and Cybernetics Society Information","authors":"","doi":"10.1109/THMS.2024.3523661","DOIUrl":"https://doi.org/10.1109/THMS.2024.3523661","url":null,"abstract":"","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"55 1","pages":"C3-C3"},"PeriodicalIF":3.5,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10871172","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","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：