{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T06:27:30Z","timestamp":1787984850629,"version":"build-2784847793"},"reference-count":54,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Yunnan Provincial Science and Technology Department Program","award":["Ref. 202301AY070001-121"],"award-info":[{"award-number":["Ref. 202301AY070001-121"]}]},{"name":"Yunnan Provincial Science and Technology Department programme","award":["Ref. 202301AT070268"],"award-info":[{"award-number":["Ref. 202301AT070268"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>With the intensification of population aging and the increasing incidence of neurological diseases, the demand for precise and intelligent control technology in hand rehabilitation robots has become more urgent. Traditional control methods struggle to effectively capture the dynamic temporal features of hand movements, especially in scenarios where there are modal differences between hand function data of healthy individuals and stroke patients, leading to insufficient control accuracy and poor generalization. This paper focuses on hand rehabilitation robot control technology and proposes the C-GAP model. By designing a cross-modal attention mechanism, the model realizes feature collaboration of multi-source data such as electromyography (EMG), force, and joint angles. It relies on Stacked Gated Recurrent Units to accurately extract the temporal dynamic patterns of typical hand functional movements, such as grasping, pinching, and wrist rotation. In combination with an adaptive PID controller, the model optimizes force-controlled trajectories in rehabilitation training, forming a complete control scheme tailored to hand rehabilitation scenarios. Experimental validation shows that the model performs stably in classifying typical hand functional movements and dynamic control on the Ninapro DB5 (healthy hand function multimodal data) and MUSED-I (stroke patient hand function unimodal data) datasets, effectively adapting to rehabilitation training needs under different hand function states. The research provides technical support for the precise perception and control of sequential movements in hand rehabilitation robots, contributing to enhancing the specificity and safety of rehabilitation training. It has practical significance for promoting the application of recurrent neural networks in the field of rehabilitation robot control.<\/jats:p>","DOI":"10.1371\/journal.pone.0342802","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:38:09Z","timestamp":1772822289000},"page":"e0342802","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Integrating contrastive cross-modal attention and stacked GRU for hand function rehabilitation robot control"],"prefix":"10.1371","volume":"21","author":[{"given":"Wei","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huidong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi-Fu","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6506-5740","authenticated-orcid":true,"given":"Chang-Liang","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,3,6]]},"reference":[{"key":"pone.0342802.ref001","article-title":"A home-based upper limb rehabilitation system via cloud-based teleoperation and sEMG-driven bilateral control","author":"L H","year":"2025","journal-title":"IEEE Internet of Things Journal."},{"key":"pone.0342802.ref002","article-title":"A home-based dual-mode upper limb rehabilitation system: Teleoperation mode and bilateral mode with sEMG and IMU","author":"L H","year":"2025","journal-title":"IEEE J Biomed Health Inform."},{"key":"pone.0342802.ref003","doi-asserted-by":"crossref","unstructured":"H L, S G, H W, et al. Development of a sEMG-controlled portable exoskeleton system for home-based upper limb rehabilitation. In: Proc 2024 IEEE Int Conf Mechatronics Autom (ICMA). 2024. p. 952\u20137.","DOI":"10.1109\/ICMA61710.2024.10633043"},{"key":"pone.0342802.ref004","doi-asserted-by":"crossref","first-page":"102985","DOI":"10.1016\/j.jelekin.2025.102985","article-title":"Assessing stroke-induced abnormal muscle coactivation in the upper limb using the surface EMG co-contraction Index: a systematic review","volume":"81","author":"Y Wang","year":"2025","journal-title":"J Electromyogr Kinesiol."},{"key":"pone.0342802.ref005","article-title":"LADRC-SMC-based disturbance rejection motion control of a desktop upper limb rehabilitation robot","author":"Y C","year":"2025","journal-title":"Ind Robot."},{"key":"pone.0342802.ref006","unstructured":"X Y. Speed torque control method of upper limb rehabilitation robot based on PID controller. Int J High Speed Electron Syst. 2025;2540688."},{"issue":"3","key":"pone.0342802.ref007","article-title":"Advances in control techniques for rehabilitation exoskeleton robots: a systematic review","volume":"14","author":"M G","year":"2025","journal-title":"Actuators."},{"key":"pone.0342802.ref008","first-page":"1","article-title":"Designing an EEG signal-driven dual-path fuzzy neural network-controlled pneumatic exoskeleton for upper limb rehabilitation","author":"HH H","year":"2025","journal-title":"Int J Fuzzy Syst."},{"issue":"1","key":"pone.0342802.ref009","article-title":"Optimization of fuzzy-PD control for a 3-DOF robotics manipulator using a back-propagation neural network","volume":"11","author":"S F","year":"2024","journal-title":"Math Model Eng Problems."},{"issue":"3","key":"pone.0342802.ref010","doi-asserted-by":"crossref","first-page":"14287","DOI":"10.48084\/etasr.7146","article-title":"An SEMG signal-based robotic arm for rehabilitation applying fuzzy logic","volume":"14","author":"N NK","year":"2024","journal-title":"Eng Technol Appl Sci Res."},{"issue":"6","key":"pone.0342802.ref011","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1007\/s10489-025-06317-4","article-title":"Dynamically modulated robot compliance via online fuzzy neural networks for individualized ankle rehabilitation","volume":"55","author":"L J","year":"2025","journal-title":"Applied Intelligence."},{"issue":"5","key":"pone.0342802.ref012","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0302707","article-title":"Combining enhanced spectral resolution of EMG and a deep learning approach for knee pathology diagnosis","volume":"19","author":"A Khader","year":"2024","journal-title":"PLoS One."},{"issue":"1","key":"pone.0342802.ref013","article-title":"Parallel convolutional neural network and empirical mode decomposition for high accuracy in motor imagery EEG signal classification","volume":"20","author":"J D","year":"2025","journal-title":"PLoS One."},{"issue":"13","key":"pone.0342802.ref014","doi-asserted-by":"crossref","first-page":"4378","DOI":"10.3390\/s24134378","article-title":"Glove-Net: enhancing grasp classification with multisensory data and deep learning approach","volume":"24","author":"S Pratap","year":"2024","journal-title":"Sensors (Basel)."},{"key":"pone.0342802.ref015","article-title":"A discrete-time neural network control method based on deterministic learning for upper-limb rehabilitation robot","author":"Z N","year":"2024","journal-title":"IEEE Trans Autom Sci Eng."},{"issue":"12","key":"pone.0342802.ref016","doi-asserted-by":"crossref","first-page":"10439","DOI":"10.1080\/15397734.2024.2356066","article-title":"Inverse kinematics analysis of a wrist rehabilitation robot using artificial neural network and adaptive neuro-fuzzy inference system","volume":"52","author":"S B","year":"2024","journal-title":"Mech Based Des Struct Machines."},{"key":"pone.0342802.ref017","doi-asserted-by":"crossref","unstructured":"P L, J X, A W, et al. RBF network-based adaptive control for humanoid gait data. In: Proc 2025 IEEE Int Conf Real-time Comput Robotics (RCAR), 2025. 890\u20135.","DOI":"10.1109\/RCAR65431.2025.11139698"},{"key":"pone.0342802.ref018","doi-asserted-by":"crossref","first-page":"1828","DOI":"10.1109\/TNSRE.2024.3396065","article-title":"Effectiveness of Intelligent Control Strategies in Robot-Assisted Rehabilitation-A Systematic Review","volume":"32","author":"D Felix Brown","year":"2024","journal-title":"IEEE Trans Neural Syst Rehabil Eng."},{"issue":"11","key":"pone.0342802.ref019","doi-asserted-by":"crossref","first-page":"6053","DOI":"10.3390\/app15116053","article-title":"Research on iterative learning method for lower limb exoskeleton rehabilitation robot based on RBF neural network","volume":"15","author":"L J","year":"2025","journal-title":"Appl Sci."},{"issue":"5","key":"pone.0342802.ref020","doi-asserted-by":"crossref","first-page":"20230146","DOI":"10.1002\/EXP.20230146","article-title":"Neural interfaces: bridging the brain to the world beyond healthcare","volume":"4","author":"S Xu","year":"2024","journal-title":"Exploration (Beijing)."},{"issue":"1","key":"pone.0342802.ref021","first-page":"14","article-title":"Recent applications of EEG-based brain-computer-interface in the medical field","volume":"12","author":"X-Y Liu","year":"2025","journal-title":"Mil Med Res."},{"key":"pone.0342802.ref022","doi-asserted-by":"crossref","first-page":"106551","DOI":"10.1016\/j.bspc.2024.106551","article-title":"Exploration of deep learning-driven multimodal information fusion frameworks and their application in lower limb motion recognition","volume":"96","author":"Z C","year":"2024","journal-title":"Biomed Signal Process Control."},{"key":"pone.0342802.ref023","doi-asserted-by":"crossref","first-page":"1310247","DOI":"10.3389\/fbioe.2023.1310247","article-title":"Multimodal fusion and human-robot interaction control of an intelligent robot","volume":"11","author":"T Gong","year":"2024","journal-title":"Front Bioeng Biotechnol."},{"key":"pone.0342802.ref024","doi-asserted-by":"crossref","first-page":"4189","DOI":"10.1109\/TNSRE.2023.3325215","article-title":"A systematic review of gait analysis in the context of multimodal sensing fusion and AI","volume":"31","author":"R Katmah","year":"2023","journal-title":"IEEE Trans Neural Syst Rehabil Eng."},{"issue":"9","key":"pone.0342802.ref025","doi-asserted-by":"crossref","first-page":"2200055","DOI":"10.1002\/adsr.202200055","article-title":"Multimodal sensing in stroke motor rehabilitation","volume":"2","author":"Z Z","year":"2023","journal-title":"Adv Sens Res."},{"issue":"9","key":"pone.0342802.ref026","doi-asserted-by":"crossref","first-page":"13773","DOI":"10.1109\/JSEN.2024.3374344","article-title":"The human-machine interaction methods and strategies for upper and lower extremity rehabilitation robots: a review","volume":"24","author":"Z L","year":"2024","journal-title":"IEEE Sensors Journal."},{"key":"pone.0342802.ref027","doi-asserted-by":"crossref","DOI":"10.1017\/wtc.2024.25","article-title":"Synergistic grasp analysis: a cross-sectional exploration using a multi-sensory data glove","volume":"6","author":"S Pratap","year":"2025","journal-title":"Wearable Technol."},{"issue":"4","key":"pone.0342802.ref028","doi-asserted-by":"crossref","first-page":"6133","DOI":"10.1109\/JSEN.2024.3523512","article-title":"Understanding grasp synergies during reach-to-grasp using an instrumented data glove","volume":"25","author":"S Pratap","year":"2025","journal-title":"IEEE Sensors J."},{"key":"pone.0342802.ref029","article-title":"A sEMG-based active-passive fusion rehabilitation method for ankle fracture rehabilitation robot after surgery","author":"N M","year":"2025","journal-title":"IEEE Robot Autom Lett."},{"key":"pone.0342802.ref030","first-page":"5425","article-title":"Robust sensor fusion and biomimetic control of a lower-limb exoskeleton with multimodal sensors","volume":"22","author":"JC A","year":"2024","journal-title":"IEEE Trans Autom Sci Eng."},{"key":"pone.0342802.ref031","article-title":"Control method of lower limb rehabilitation robot based on nonlinear time series prediction model and sensor technology","author":"X Y","year":"2024","journal-title":"IEEE Access."},{"issue":"8","key":"pone.0342802.ref032","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0328969","article-title":"Robust skeletal motion tracking using temporal and spatial synchronization of two video streams","volume":"20","author":"V Abromavi\u010dius","year":"2025","journal-title":"PLoS One."},{"issue":"12","key":"pone.0342802.ref033","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0310192","article-title":"The effect of gravity on hand spatio-temporal kinematic features during functional movements","volume":"19","author":"A Bucchieri","year":"2024","journal-title":"PLoS One."},{"issue":"4","key":"pone.0342802.ref034","doi-asserted-by":"crossref","first-page":"1307","DOI":"10.1080\/17483107.2023.2170477","article-title":"Research of intent recognition in rehabilitation robots: a systematic review","volume":"19","author":"S Luo","year":"2024","journal-title":"Disabil Rehabil Assist Technol."},{"issue":"9","key":"pone.0342802.ref035","doi-asserted-by":"crossref","first-page":"9871","DOI":"10.1109\/JSEN.2023.3258980","article-title":"A motor recovery training and evaluation method for the upper limb rehabilitation robotic system","volume":"23","author":"C H","year":"2023","journal-title":"IEEE Sens J."},{"key":"pone.0342802.ref036","doi-asserted-by":"crossref","unstructured":"Z AJ, T S, R F. Reinforcement learning-based control for an upper limb rehabilitation robot. In: Proc 2023 Adv Sci Eng Technol Int Conf (ASET), 2023. p. 1\u20136.","DOI":"10.1109\/ASET56582.2023.10180597"},{"issue":"11","key":"pone.0342802.ref037","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0314611","article-title":"Application of a sEMG hand motion recognition method based on variational mode decomposition and ReliefF algorithm in rehabilitation medicine","volume":"19","author":"Y Yuan","year":"2024","journal-title":"PLoS One."},{"issue":"7","key":"pone.0342802.ref038","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1007\/s42452-025-07424-0","article-title":"Optimal PID controller with evolutionary optimization algorithms for rehabilitation robots","volume":"7","author":"J K","year":"2025","journal-title":"Discover Appl Sci."},{"issue":"22","key":"pone.0342802.ref039","doi-asserted-by":"crossref","first-page":"16021","DOI":"10.1007\/s00521-021-06785-y","article-title":"AI-driven rehabilitation and assistive robotic system with intelligent PID controller based on RBF neural networks","volume":"35","author":"X W","year":"2023","journal-title":"Neural Comput Appl."},{"issue":"3","key":"pone.0342802.ref040","doi-asserted-by":"crossref","first-page":"388","DOI":"10.18196\/jrc.v4i3.18411","article-title":"A robust fuzzy fractional order PID design based on multi-objective optimization for rehabilitation device control","volume":"4","author":"Z I","year":"2023","journal-title":"J Robot Control."},{"key":"pone.0342802.ref041","doi-asserted-by":"crossref","first-page":"105460","DOI":"10.1016\/j.mechmachtheory.2023.105460","article-title":"Implementation of cable-driven waist rehabilitation robotic system using fractional-order controller","volume":"190","author":"L Y","year":"2023","journal-title":"Mech Mach Theory."},{"issue":"2","key":"pone.0342802.ref042","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1080\/03772063.2020.1838346","article-title":"Towards neuro-fuzzy compensated PID control of lower extremity exoskeleton system for passive gait rehabilitation","volume":"69","author":"N J","year":"2023","journal-title":"IETE J Res."},{"key":"pone.0342802.ref043","unstructured":"E K, G A, G E. In: Proc SoutheastCon 2024, 2024. p. 681\u20135."},{"key":"pone.0342802.ref044","article-title":"Reinforcement learning methods for assistive and rehabilitation robotic systems: a survey","author":"S M","year":"2025","journal-title":"IEEE Trans Syst Man Cybern Syst."},{"key":"pone.0342802.ref045","doi-asserted-by":"crossref","unstructured":"R M, C T, A P, et al. AI-CARE: artificial intelligence for customized adaptive robot-aided rehabilitation. In: Proceedings of the International Workshop on Human-Friendly Robotics. 2024. p. 168\u201381.","DOI":"10.1007\/978-3-031-81688-8_13"},{"issue":"4","key":"pone.0342802.ref046","first-page":"7004","article-title":"Uncertainty compensated high-order adaptive iteration learning control for robot-assisted upper limb rehabilitation","volume":"21","author":"A Q","year":"2023","journal-title":"IEEE Transactions on Automation Science and Engineering."},{"key":"pone.0342802.ref047","doi-asserted-by":"crossref","first-page":"82730","DOI":"10.1109\/ACCESS.2024.3413576","article-title":"LLMT: A transformer-based multi-modal lower limb human motion prediction model for assistive robotics applications","volume":"12","author":"H SHS","year":"2024","journal-title":"IEEE Access."},{"key":"pone.0342802.ref048","doi-asserted-by":"crossref","unstructured":"Q G, J G. A data-driven adaptive control algorithm for lower limb rehabilitation exoskeletons based on transformer. In: Proc 2025 5th Int Conf Control Intell Robotics; 2025. p. 113\u20138.","DOI":"10.1145\/3757940.3757958"},{"issue":"4","key":"pone.0342802.ref049","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.3390\/s24041047","article-title":"An optimized stimulation control system for upper limb exoskeleton robot-assisted rehabilitation using a fuzzy logic-based pain detection approach","volume":"24","author":"IB Abdallah","year":"2024","journal-title":"Sensors (Basel)."},{"issue":"1","key":"pone.0342802.ref050","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1108\/IR-07-2023-0146","article-title":"Research on fuzzy impedance control of upper-limb rehabilitation robot based on membership functions online optimization learning strategy","volume":"51","author":"W P","year":"2024","journal-title":"Ind Robot: Int J Robotics Res Appl."},{"key":"pone.0342802.ref051","doi-asserted-by":"crossref","first-page":"102320","DOI":"10.1016\/j.inffus.2024.102320","article-title":"Multi-sensor fusion federated learning method of human posture recognition for dual-arm nursing robots","volume":"107","author":"W J","year":"2024","journal-title":"Inf Fusion."},{"key":"pone.0342802.ref052","article-title":"Federated learning-enhanced edge deep learning model for EMG-based gesture recognition in real-time human-robot interaction","author":"MH Z","year":"2025","journal-title":"IEEE Sensors Journal."},{"key":"pone.0342802.ref053","article-title":"Human-machine co-adaptation for robot-assisted rehabilitation via dual-agent multiple model reinforcement learning (DAMMRL)","author":"A Y","year":"2024","journal-title":"arXiv preprint"},{"key":"pone.0342802.ref054","article-title":"Research on lower limb movement rehabilitation assessment based on graph convolutional network","author":"X Z","year":"2024","journal-title":"IEEE Access."}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0342802","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:38:19Z","timestamp":1772822299000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0342802"}},"subtitle":[],"editor":[{"given":"Jyotindra","family":"Narayan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":54,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,6]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0342802","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,6]]}}}