{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T09:26:54Z","timestamp":1758274014100,"version":"3.40.5"},"reference-count":55,"publisher":"Cambridge University Press (CUP)","issue":"10","license":[{"start":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T00:00:00Z","timestamp":1688947200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotica"],"published-print":{"date-parts":[[2023,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The assist-as-needed (AAN) controller is effective in robot-assisted rehabilitation. However, variations of the engagement of subjects with fixed controller often lead to unsatisfying results. Therefore, adaptive AAN that adjusts control parameters based on individualized engagement is essential to enhance the training effect further. Nevertheless, current approaches mainly focus on the within-trial real-time engagement estimation, and the presence of measurement noise may cause improper evaluation of engagement. In addition, most studies on human-in-loop optimization strategies modulate the controller by greedy strategies, which are prone to fall into local optima. These shortcomings in previous studies could significantly limit the efficacy of AAN. This paper proposes an adaptive AAN to promote engagement by providing subjects with a subject-adaptive assistance level based on trial-wise engagement estimation and performance. Firstly, the engagement is estimated from energy information, which assesses the work done by the subject during a full trial to reduce the influence of measurement outliers. Secondly, the AAN controller is adapted by Bayesian optimization (BO) to maximize the subject\u2019s performance according to historical trial-wise performance. The BO algorithm is good at dealing with noisy signals within limited steps. Experiments with ten healthy subjects resulted in a decrease of 34.59<jats:inline-formula><jats:alternatives><jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"png\" xlink:href=\"S0263574723000899_inline1.png\"\/><jats:tex-math>$\\%$<\/jats:tex-math><\/jats:alternatives><\/jats:inline-formula>in their average trajectory error, accompanied by a reduction of 9.71<jats:inline-formula><jats:alternatives><jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"png\" xlink:href=\"S0263574723000899_inline2.png\"\/><jats:tex-math>$\\%$<\/jats:tex-math><\/jats:alternatives><\/jats:inline-formula>in their energy consumption, thus verifying the superiority of the proposed method to prior work. These results suggest that the proposed method could potentially improve the effect of upper limb rehabilitation.<\/jats:p>","DOI":"10.1017\/s0263574723000899","type":"journal-article","created":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T09:43:47Z","timestamp":1688982227000},"page":"3101-3115","source":"Crossref","is-referenced-by-count":3,"title":["Bayesian optimization for assist-as-needed controller in robot-assisted upper limb training based on energy information"],"prefix":"10.1017","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7052-9215","authenticated-orcid":false,"given":"Jianxi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guozheng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aiguo","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"56","published-online":{"date-parts":[[2023,7,10]]},"reference":[{"key":"S0263574723000899_ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TOH.2018.2878232"},{"key":"S0263574723000899_ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2021.3082198"},{"key":"S0263574723000899_ref45","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574720001459"},{"key":"S0263574723000899_ref48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ACCESS.2020.2995591","article-title":"An improved grasshopper optimization algorithm for optimizing hybrid active power filters\u2019 parameters","volume":"99","author":"Huang","year":"2020","journal-title":"IEEE Access"},{"key":"S0263574723000899_ref54","doi-asserted-by":"publisher","DOI":"10.1108\/AA-11-2020-0178"},{"key":"S0263574723000899_ref39","article-title":"Convergence rates of efficient global optimization algorithms","volume":"12","author":"Bull","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"S0263574723000899_ref50","unstructured":"[50] Toscano-Palmerin, S. and Frazier, P. I. , \u201cBayesian optimization with expensive integrands,\u201d arXiv preprint arXiv. 08661, (2018)."},{"key":"S0263574723000899_ref36","first-page":"97","article-title":"A new method of locating the maximum point of an arbitrary multipeak curve in the presence of noise","volume":"64","author":"Kushner","year":"1964","journal-title":"J. Fluids Eng."},{"key":"S0263574723000899_ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3210592"},{"key":"S0263574723000899_ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2008.918389"},{"key":"S0263574723000899_ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2503726"},{"key":"S0263574723000899_ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2892157"},{"key":"S0263574723000899_ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.apmr.2003.06.001"},{"key":"S0263574723000899_ref52","article-title":"Practical Bayesian optimization of machine learning algorithms","volume":"4","author":"Snoek","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0263574723000899_ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TDMR.2020.2965205"},{"key":"S0263574723000899_ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2885165"},{"key":"S0263574723000899_ref4","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574721000357"},{"key":"S0263574723000899_ref24","doi-asserted-by":"crossref","unstructured":"[24] Hocine, N. , Goua\u00efch, A. , Di Loreto, I. and Joab, M. . Motivation Based Difficulty Adaptation for Therapeutic Games. In: 2011 IEEE 1st International Conference on Serious Games and Applications for Health (SeGAH), IEEE, (2011).","DOI":"10.1109\/SeGAH.2011.6165459"},{"key":"S0263574723000899_ref12","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2020.596019"},{"key":"S0263574723000899_ref25","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574722001709"},{"key":"S0263574723000899_ref28","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2016.00518"},{"key":"S0263574723000899_ref30","doi-asserted-by":"crossref","unstructured":"[30] Stroppa, F. , Marcheschi, S. , Mastronicola, N. , Loconsole, C. and Frisoli, A. . Online Adaptive Assistance Control in Robot-Based Neurorehabilitation Therapy. In: 2017 International Conference on Rehabilitation Robotics (ICORR), IEEE, (2017).","DOI":"10.1109\/ICORR.2017.8009318"},{"key":"S0263574723000899_ref40","doi-asserted-by":"crossref","unstructured":"[40] Abdelhameed, E. H. , Sato, N. and Morita, Y. . Design of a Variable Resistance Training System Using Rotary Magneto-Rheological Brake. In: 2017 3rd International Conference on Control, Automation and Robotics (ICCAR), IEEE, (2017).","DOI":"10.1109\/ICCAR.2017.7942706"},{"key":"S0263574723000899_ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2185843"},{"key":"S0263574723000899_ref46","doi-asserted-by":"publisher","DOI":"10.1016\/S0947-3580(98)70113-X"},{"key":"S0263574723000899_ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2871196"},{"key":"S0263574723000899_ref31","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr.2018.5241"},{"key":"S0263574723000899_ref32","doi-asserted-by":"crossref","unstructured":"[32] Shirzad, N. and Van der Loos, H. F. M. . Adaptation of Task Difficulty in Rehabilitation Exercises Based on the User\u2019s Motor Performance and Physiological Responses. In: 2013 IEEE 13th International Conference on Rehabilitation Robotics (ICORR), IEEE, (2013).","DOI":"10.1109\/ICORR.2013.6650429"},{"key":"S0263574723000899_ref10","doi-asserted-by":"publisher","DOI":"10.1186\/1743-0003-4-8"},{"key":"S0263574723000899_ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3144537"},{"key":"S0263574723000899_ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107481"},{"key":"S0263574723000899_ref21","doi-asserted-by":"crossref","unstructured":"[21] Pehlivan, A. U. , Losey, D. P. , Rose, C. G. and O\u2019Malley, M. K. . Maintaining Subject Engagement During Robotic Rehabilitation with a Minimal Assist-as-Needed (mAAN) Controller. In: 2017 International Conference on Rehabilitation Robotics (ICORR), IEEE, (2017).","DOI":"10.1109\/ICORR.2017.8009222"},{"key":"S0263574723000899_ref9","first-page":"S208","article-title":"Neural plasticity: The biological substrate for neurorehabilitation","volume":"2","author":"Warraich","year":"2010","journal-title":"PMandR"},{"key":"S0263574723000899_ref34","doi-asserted-by":"publisher","DOI":"10.1080\/10749357.2022.2058292"},{"key":"S0263574723000899_ref3","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574721001107"},{"key":"S0263574723000899_ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2021.3137971"},{"key":"S0263574723000899_ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2894908"},{"key":"S0263574723000899_ref5","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574722000388"},{"key":"S0263574723000899_ref7","doi-asserted-by":"publisher","DOI":"10.1682\/JRRD.2005.06.0103"},{"key":"S0263574723000899_ref53","first-page":"8","article-title":"Standards for surface electromyography: The European project Surface EMG for non-invasive assessment of muscles (SENIAM)","volume":"10","author":"Stegeman","year":"2007","journal-title":"Enschede: Roessingh Res. Dev."},{"key":"S0263574723000899_ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2020.2992090"},{"key":"S0263574723000899_ref41","doi-asserted-by":"crossref","unstructured":"[41] Agarwal, P. and Deshpande, A. D. . Impedance and Force-Field Control of the Index Finger Module of a Hand Exoskeleton for Rehabilitation. In: 2015 IEEE International Conference on Rehabilitation Robotics (ICORR), IEEE, (2015).","DOI":"10.1109\/ICORR.2015.7281180"},{"key":"S0263574723000899_ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2016.2591183"},{"key":"S0263574723000899_ref29","doi-asserted-by":"crossref","unstructured":"[29] Cen, Y. , Yuan, J. , Ma, S. , Luo, J. and Wang, H. . \u201cTrajectory Optimization Algorithm of Trajectory Rehabilitation Training Mode for Rehabilitation Robot,\u201d 2022 IEEE International Conference on Robotics and Biomimetics (ROBIO), Jinhong, China (2022) pp. 2153\u20132158.","DOI":"10.1109\/ROBIO55434.2022.10011648"},{"key":"S0263574723000899_ref51","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aar5438"},{"key":"S0263574723000899_ref55","doi-asserted-by":"publisher","DOI":"10.1038\/nn1309"},{"key":"S0263574723000899_ref35","unstructured":"[35] Brochu, E. , Cora, V. M. and De Freitas, N. , \u201cA tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning,\u201d arXiv preprint arXiv. 1012.2599 (2010)."},{"key":"S0263574723000899_ref6","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574721001533"},{"key":"S0263574723000899_ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3113709"},{"key":"S0263574723000899_ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s004220050532"},{"key":"S0263574723000899_ref19","doi-asserted-by":"crossref","unstructured":"[19] Guidali, M. , Schlink, P. , Duschau-Wicke, A. and Riener, R. . Online Learning and Adaptation of Patient Support During ADL Training. In: 2011 IEEE International Conference on Rehabilitation Robotics, IEEE, (2011).","DOI":"10.1109\/ICORR.2011.5975434"},{"key":"S0263574723000899_ref26","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574723000693"},{"key":"S0263574723000899_ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891431"},{"key":"S0263574723000899_ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(13)61953-4"},{"key":"S0263574723000899_ref17","doi-asserted-by":"publisher","DOI":"10.1109\/72.165588"}],"container-title":["Robotica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0263574723000899","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T22:14:20Z","timestamp":1729721660000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0263574723000899\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,10]]},"references-count":55,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["S0263574723000899"],"URL":"https:\/\/doi.org\/10.1017\/s0263574723000899","relation":{},"ISSN":["0263-5747","1469-8668"],"issn-type":[{"type":"print","value":"0263-5747"},{"type":"electronic","value":"1469-8668"}],"subject":[],"published":{"date-parts":[[2023,7,10]]}}}