{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T06:13:37Z","timestamp":1788416017756,"version":"build-2803163510"},"reference-count":18,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T00:00:00Z","timestamp":1788393600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Wearable lower-limb exoskeletons have the potential to support intention-driven control of lower-limb exoskeletons, but existing control strategies often rely on mechanical or manual triggers that fail to capture user intent.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>Subjects were recruited from 23\/9\/2024 to 10\/2\/2025. A BiLSTM detector was pretrained on a dataset collected from 50 healthy volunteers (45 for training, 5 for independent testing) using bilateral surface EMG recordings from six lower-limb muscles (12 EMG channels), 16-channel EEG, and hip\u2013knee kinematics. Seven naive participants then completed ten 20-m outward-and-return walking trials (10\u202fm outward and 10\u202fm return) under each of three control modes (EMG, EEG, hybrid). Primary outcomes were triggering latency and classification accuracy. Triggering latency was defined as the time interval between the onset of the gait-transition event and the activation of the exoskeleton assistance command. This latency included the observation delay introduced by the sliding window, feature extraction time, BiLSTM inference time, and communication delay between the decoder and the exoskeleton controller. Usability was assessed with donning\/doffing times and QUEST 2.0.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The hybrid BiLSTM detector achieved higher classification accuracy (left: 91.3%; right: 86.6%) and shorter mean per-step triggering latency (left: 0.29\u202fs; right: 0.28\u202fs) than either EMG-only (mean 0.33\u202fs) or EEG-only approaches (mean 0.30\u202fs). Hybrid EEG\u2013EMG fusion therefore improved decoding performance while reducing triggering latency compared with unimodal decoding strategies. The latency reduction relative to EMG-only control corresponded to a large effect size (Cohen\u2019s d\u202f\u2248\u202f0.88). Hybrid sessions also yielded shorter total session time (mean 32.1\u202fmin). Usability metrics demonstrated acceptable donning\/doffing times and favorable QUEST 2.0 scores (mean 32.0\/40).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>These proof-of-concept results demonstrate that BiLSTM-based fusion of EEG and EMG improves responsiveness and classification reliability for exoskeleton assistance. These findings underscore the contribution of EEG-derived sensorimotor features and EMG information for intention-related gait transition detection within a multimodal real-time exoskeleton control framework. We discuss limitations related to sample size, artifact validation, and generalizability and identify next steps for patient studies and ergonomic optimization.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnbot.2026.1914651","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T05:23:10Z","timestamp":1788412990000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid EEG\u2013EMG intention decoding for real-time triggering of a lower-limb exoskeleton"],"prefix":"10.3389","volume":"20","author":[{"given":"Ke","family":"Wang","sequence":"first","affiliation":[{"name":"The Third People\u2019s Hospital of Jincheng, Jincheng","place":["Shanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenshan","family":"Li","sequence":"additional","affiliation":[{"name":"Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danyang","family":"Ding","sequence":"additional","affiliation":[{"name":"Beijing Rehabilitation Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"RoboCT Technology Development Co., Ltd","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Sun","sequence":"additional","affiliation":[{"name":"RoboCT Technology Development Co., Ltd","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbo","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing Rehabilitation Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijun","family":"Gong","sequence":"additional","affiliation":[{"name":"Beijing Rehabilitation Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,3]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/j.neuroimage.2017.07.013","article-title":"Unidirectional brain to muscle connectivity reveals motor cortex control of leg muscles during stereotyped walking","volume":"159","author":"Artoni","year":"2017","journal-title":"NeuroImage"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"460","DOI":"10.23736\/S1973-9087.21.06887-8","article-title":"Robotic-assisted gait rehabilitation following stroke: a systematic review of current guidelines and practical clinical recommendations","volume":"57","author":"Calabr\u00f2","year":"2021","journal-title":"Eur. J. Phys. Rehabil. Med."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1016\/j.tics.2014.04.012","article-title":"Frontal theta as a mechanism for cognitive control","volume":"18","author":"Cavanagh","year":"2014","journal-title":"Trends Cogn. Sci."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"e2038","DOI":"10.1002\/pri.2038","article-title":"Safety and usability of the MAK exoskeleton in patients with stroke","volume":"29","author":"Cumplido-Trasmonte","year":"2024","journal-title":"Physiotherapy Res Intl"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1569148","DOI":"10.3389\/fnins.2025.1569148","article-title":"Multimodal closed-loop strategies for gait recovery after spinal cord injury and stroke via the integration of robotics and neuromodulation","volume":"19","author":"De Seta","year":"2025","journal-title":"Front. Neurosci."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.conb.2010.02.015","article-title":"Beta-band oscillations \u2014 signalling the status quo?","volume":"20","author":"Engel","year":"2010","journal-title":"Curr. Opin. Neurobiol."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"742163","DOI":"10.3389\/fnbot.2021.742163","article-title":"Neuromechanical biomarkers for robotic Neurorehabilitation","volume":"15","author":"Garro","year":"2021","journal-title":"Front. Neurorobot."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Netw."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"12653","DOI":"10.1523\/JNEUROSCI.1554-09.2009","article-title":"Long-term modifications in motor cortical dynamics induced by intensive practice","volume":"29","author":"Kilavik","year":"2009","journal-title":"J. Neurosci."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"025011","DOI":"10.1088\/1741-2560\/8\/2\/025011","article-title":"A hybrid brain\u2013computer interface based on the fusion of electroencephalographic and electromyographic activities","volume":"8","author":"Leeb","year":"2011","journal-title":"J. Neural Eng."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"359","DOI":"10.3389\/fnins.2016.00359","article-title":"Control of an ambulatory exoskeleton with a brain\u2013machine interface for spinal cord injury gait rehabilitation","volume":"10","author":"L\u00f3pez-Larraz","year":"2016","journal-title":"Front. Neurosci."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1186\/s12984-021-00942-z","article-title":"Efficacy of an exoskeleton-based physical therapy program for non-ambulatory patients during subacute stroke rehabilitation: a randomized controlled trial","volume":"18","author":"Louie","year":"2021","journal-title":"J NeuroEng Rehabil"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1097\/00004691-199911000-00002","article-title":"Corticomuscular coherence: a review","volume":"16","author":"Mima","year":"1999","journal-title":"J. Clin. Neurophysiol."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"104523","DOI":"10.1016\/j.knee.2026.104523","article-title":"GNN-based deep surrogate modeling of knee contact mechanics: generalizing neuromuscular control patterns across subjects","volume":"62","author":"Pan","year":"2026","journal-title":"Knee"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"2443","DOI":"10.1113\/jphysiol.2012.227397","article-title":"The motor cortex drives the muscles during walking in human subjects","volume":"590","author":"Petersen","year":"2012","journal-title":"J. Physiol."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1842","DOI":"10.1016\/S1388-2457(99)00141-8","article-title":"Event-related EEG\/MEG synchronization and desynchronization: basic principles","volume":"110","author":"Pfurtscheller","year":"1999","journal-title":"Clin. Neurophysiol."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.nbd.2014.11.025","article-title":"Brain\u2013machine interfaces in neurorehabilitation of stroke","volume":"83","author":"Soekadar","year":"2015","journal-title":"Neurobiol. Dis."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"2212","DOI":"10.1523\/JNEUROSCI.3543-15.2016","article-title":"Distinct \u03b2 band oscillatory networks subserving motor and cognitive control during gait adaptation","volume":"36","author":"Wagner","year":"2016","journal-title":"J. Neurosci."}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2026.1914651\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T05:23:10Z","timestamp":1788412990000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2026.1914651\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,3]]},"references-count":18,"alternative-id":["10.3389\/fnbot.2026.1914651"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2026.1914651","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,3]]},"article-number":"1914651"}}