{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T05:02:54Z","timestamp":1784869374572,"version":"3.55.0"},"reference-count":41,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Evaluating wearable assistive robots in real-world caregiving is challenging because temporally aligned and repeatable A\/B comparisons are rarely available. Conventional evaluations assume that assist-on and assist-off trials are comparable in task content, posture, and movement timing. However, caregivers adjust their posture and timing across human\u2013human interactions and task sequences. This study proposes a causally inspired diagnostic framework based on DBN\/SCM-inspired time-series modeling and movement-fixed counterfactual estimation. We represented the multimodal observations using intervention, robot state, movement context, EMG, and context variables. Node-specific relationships were approximated using Attention-based Sparse Variational Gaussian Process regressors. We evaluated the framework at three levels of environmental complexity. These levels comprised controlled trunk flexion, partially controlled bed-to-wheelchair transfer, and real-world caregiving. The proposed framework is intended as a diagnostic counterfactual evaluation tool rather than as a method for strict causal identification. Across experiments, one-step EMG prediction accuracy alone was insufficient to identify intervention-sensitive models. In controlled validation, the selected movement-decoupled robot-only model reproduced an EMG-reducing response consistent with the controlled A\/B reference. When fitted to the partially controlled transfer data, the selected structural specification identified an EMG-increasing response in supported contexts. In the real-world caregiving case study, the global assist-mediated response (AMR) was near zero despite a positive pooled A\/B difference. However, the stratified analysis identified localized supported responses. The near-zero AMR indicates that the pooled difference was not reproduced through the modeled assist intervention\u2013robot state\u2013EMG pathway under fixed movement context. This result should not be interpreted as evidence of overall device ineffectiveness. These findings suggest that context-fixed counterfactual diagnosis can help interpret assistive responses under increasing environmental complexity.<\/jats:p>","DOI":"10.3390\/s26144646","type":"journal-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T13:25:46Z","timestamp":1784726746000},"page":"4646","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Causally Inspired Counterfactual Evaluation Framework for Wearable Assistive Robots"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7201-1592","authenticated-orcid":false,"given":"Wataru","family":"Fujita","sequence":"first","affiliation":[{"name":"Department of Life Science and Systems Engineering, Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Kitakyushu 808-0196, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryoma","family":"Tokunaga","sequence":"additional","affiliation":[{"name":"Department of Life Science and Systems Engineering, Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Kitakyushu 808-0196, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4882-5514","authenticated-orcid":false,"given":"Ai","family":"Higuchi","sequence":"additional","affiliation":[{"name":"JTEKT Corporation, Kariya 448-8652, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8766-4250","authenticated-orcid":false,"given":"Tomohiro","family":"Shibata","sequence":"additional","affiliation":[{"name":"Department of Life Science and Systems Engineering, Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Kitakyushu 808-0196, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1489","DOI":"10.3233\/BMR-230319","article-title":"Occupational Low Back Pain among Japanese Caregivers: A Large-Scale Cross-Sectional Study","volume":"37","author":"Abiko","year":"2024","journal-title":"J. Back. Musculoskelet. Rehabil."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"427","DOI":"10.7210\/jrsj.41.427","article-title":"The Creation of Nursing-Care Robotology","volume":"41","author":"Shibata","year":"2023","journal-title":"J. Robot. Soc. Jpn."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Martinez-Hernandez, U., Metcalfe, B., Assaf, T., Jabban, L., Male, J., and Zhang, D. (2021). Wearable Assistive Robotics: A Perspective on Current Challenges and Future Trends. Sensors, 21.","DOI":"10.3390\/s21206751"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Lefint, J., and Moniz, A.B. (2024). Assessment of Exoskeletons for Work Activities: The Dilemma behind the Product. Appl. Sci., 14.","DOI":"10.3390\/app14167108"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"29839","DOI":"10.1038\/s41598-025-14500-3","article-title":"Effects on muscular activity and usability of soft active versus rigid passive back exoskeleton during symmetric lifting tasks","volume":"15","author":"Lei","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_6","unstructured":"Fujita, W., Tokunaga, R., Higuchi, A., and Shibata, T. (2026). Causally-informed Evaluation of Wearable Assistive Robots in Real-World Caregiving, 2026. IEEE RO-MAN 2026, IEEE."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"102815","DOI":"10.1016\/j.jelekin.2023.102815","article-title":"The effect of back muscle fatigue on EMG and kinematics based estimation of low-back loads and active moments during manual lifting tasks","volume":"73","author":"Tabasi","year":"2023","journal-title":"J. Electromyogr. Kinesiol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2111","DOI":"10.1109\/TNSRE.2023.3268657","article-title":"Development and Evaluation of a Lumbar Assisted Exoskeleton with Mixed Lifting Tasks by Various Postures","volume":"31","author":"Li","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Cardoso, A., Ribeiro, A., Carneiro, P., and Colim, A. (2024). Evaluating Exoskeletons for WMSD Prevention: A Systematic Review of Applications and Ergonomic Approach in Occupational Settings. Int. J. Environ. Res. Public Health, 21.","DOI":"10.3390\/ijerph21121695"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Vall\u00e9e, A. (2024). Exoskeleton Technology in Nursing Practice: Assessing Effectiveness, Usability, and Impact on Nurses\u2019 Quality of Work Life, a Narrative Review. BMC Nurs., 23.","DOI":"10.1186\/s12912-024-01821-3"},{"key":"ref_11","first-page":"703","article-title":"Development of Power Assisting Suit for Assisting Nurse Labor","volume":"45","author":"Yamamoto","year":"2002","journal-title":"JSME Int. J. Ser. C Mech. Syst. Mach. Elem. Manuf."},{"key":"ref_12","first-page":"eaar5438","article-title":"Human-in-the-loop optimization of wearable assistive devices","volume":"3","author":"Lamers","year":"2018","journal-title":"Sci. Robot."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e12","DOI":"10.1017\/wtc.2023.5","article-title":"Effects of Back-Support Exoskeletons with Different Functional Mechanisms on Trunk Muscle Activity and Kinematics","volume":"4","author":"Reimeir","year":"2023","journal-title":"Wearable Technol."},{"key":"ref_14","first-page":"103197","article-title":"Evaluation of back-support exoskeletons in lifting tasks using EMG and kinematics","volume":"89","author":"Ruppert","year":"2020","journal-title":"Appl. Ergon."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Fanti, V., Leggieri, S., Poliero, T., Sposito, M., Caldwell, D.G., and Di Natali, C. (2024). Multi-Exoskeleton Performance Evaluation: Integrated Muscle Energy Indices to Determine the Quality and Quantity of Assistance. Bioengineering, 11.","DOI":"10.3390\/bioengineering11121231"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Li-Baboud, Y.S., Virts, A., Bostelman, R., Yoon, S., Rahman, A., Rhode, L., Ahmed, N., and Shah, M. (2023). Evaluation Methods and Measurement Challenges for Industrial Exoskeletons. Sensors, 23.","DOI":"10.3390\/s23125604"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"104582","DOI":"10.1016\/j.apergo.2025.104582","article-title":"Technical field-evaluation of exoskeleton-assisted overhead work among carpenters","volume":"129","author":"Brandt","year":"2025","journal-title":"Appl. Ergon."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.ergon.2010.01.007","article-title":"Effects of Training and Experience on Patient Transfer Biomechanics","volume":"40","author":"Hodder","year":"2010","journal-title":"Int. J. Ind. Ergon."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e41328","DOI":"10.7554\/eLife.41328","article-title":"Individuals Physically Interacting in a Group Rapidly Coordinate Their Movement by Estimating the Collective Goal","volume":"8","author":"Takagi","year":"2019","journal-title":"eLife"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"954","DOI":"10.7210\/jrsj.43.954","article-title":"Evaluation of J-PAS fleairy in Care Facilities: Analysis of Learning and Effectiveness during Long-Term and Multi-Unit Deployment","volume":"43","author":"Higuchi","year":"2025","journal-title":"J. Robot. Soc. Jpn."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Kogami, T., Higuchi, A., and Shibata, T. (2022). Fatigue Assessment Using Surface EMG on Lifting Motions. Proceedings of the 2022 IEEE 4th Global Conference on Life Sciences and Technologies (LifeTech), IEEE.","DOI":"10.1109\/LifeTech53646.2022.9754833"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e53","DOI":"10.1017\/wtc.2025.10033","article-title":"Mapping the Evidence on Occupational Exoskeleton Use for the Workforce in Healthcare, Social Care, and Industry: A Systematic Scoping Review","volume":"6","author":"Bhat","year":"2025","journal-title":"Wearable Technol."},{"key":"ref_23","first-page":"298","article-title":"Bayesian network modeling for discovering \u201cdependent synergies\u201d among muscles in reaching movements","volume":"55","author":"Li","year":"2007","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1063","DOI":"10.1038\/s41598-025-85316-4","article-title":"Real-time monitoring and prediction of remote operator fatigue in plateau deep mining based on dynamic Bayesian networks","volume":"15","author":"Chen","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_25","unstructured":"Fujita, W., Kogami, T., Higuchi, A., and Shibata, T. (2025, January 29\u201330). In-Situ Evaluation of Wearable Robotic Lumbar Support for Caregivers: A Bayesian Network Analysis Approach. Proceedings of the International Conference on Advancement in Healthcare Technology and Biomedical Engineering (AHTBE), Vancouver, BC, Canada."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Pearl, J. (2009). Causality: Models, Reasoning and Inference, Cambridge University Press.","DOI":"10.1017\/CBO9780511803161"},{"key":"ref_27","unstructured":"Murphy, K. (2002). Dynamic Bayesian Networks: Representation, Inference and Learning. [Ph.D. Thesis, University of California]."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Li, Y. (2023). Deep causal learning for robotic intelligence. Front. Neurorobot., 17.","DOI":"10.3389\/fnbot.2023.1128591"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","article-title":"Temporal Fusion Transformers for Interpretable Multi-Horizon Time Series Forecasting","volume":"37","author":"Lim","year":"2021","journal-title":"Int. J. Forecast."},{"key":"ref_30","unstructured":"Huang, J., Yao, Y., and Divakaran, A. (2025). Transforming Causality: Transformer-Based Temporal Causal Discovery with Prior Knowledge Integration. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Rasmussen, C.E., and Williams, C.K.I. (2006). Gaussian Processes for Machine Learning, MIT Press.","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"ref_32","first-page":"567","article-title":"Variational Learning of Inducing Variables in Sparse Gaussian Processes","volume":"Volume 5","author":"Titsias","year":"2009","journal-title":"Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics"},{"key":"ref_33","unstructured":"Hensman, J., Fusi, N., and Lawrence, N.D. (2013). Gaussian Processes for Big Data. Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence, AUAI Press."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Winter, D.A. (2009). Biomechanics and Motor Control of Human Movement, John Wiley & Sons. [4th ed.].","DOI":"10.1002\/9780470549148"},{"key":"ref_35","unstructured":"Jain, S., and Wallace, B.C. (2019). Attention Is Not Explanation. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wiegreffe, S., and Pinter, Y. (2019). Attention Is Not Not Explanation. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-1002"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/S1050-6411(00)00027-4","article-title":"Development of Recommendations for SEMG Sensors and Sensor Placement Procedures","volume":"10","author":"Hermens","year":"2000","journal-title":"J. Electromyogr. Kinesiol."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Kuber, P.M., and Rashedi, E. (2024). Investigating Spatiotemporal Effects of Back-Support Exoskeletons Using Unloaded Cyclic Trunk Flexion\u2013Extension Task Paradigm. Appl. Sci., 14.","DOI":"10.3390\/app14135564"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.apergo.2017.11.006","article-title":"Biomechanical Evaluation of Exoskeleton Use on Loading of the Lumbar Spine","volume":"68","author":"Weston","year":"2018","journal-title":"Appl. Ergon."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"110846","DOI":"10.1016\/j.jbiomech.2021.110846","article-title":"Changes in the distribution of muscle activity when using a passive trunk exoskeleton depend on the type of working task: A high-density surface EMG study","volume":"130","author":"Ghislieri","year":"2022","journal-title":"J. Biomech."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1016\/S0021-9290(01)00081-1","article-title":"Response of trunk muscle coactivation to changes in spinal stability","volume":"34","author":"Granata","year":"2001","journal-title":"J. Biomech."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4646\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T04:34:52Z","timestamp":1784867692000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4646"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":41,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26144646"],"URL":"https:\/\/doi.org\/10.3390\/s26144646","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,22]]}}}