{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T14:23:43Z","timestamp":1743690223847,"version":"3.37.3"},"reference-count":20,"publisher":"Walter de Gruyter GmbH","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Highly compliant Pneumatic Soft Actuators (PSAs) have the potential to perform challenging tasks in a broad range of applications that require shape-adaptive capabilities. Achieving accurate tracking control for such actuators with complex geometries and material compositions typically involves many time-consuming and laborious engineering steps. In this work, we propose a data-driven learning-based control approach to address reference tracking tasks, incorporating self-adaptation <jats:italic>in situ<\/jats:italic>. We utilize a short interaction maneuver, recorded <jats:italic>a priori<\/jats:italic>, to collect the quasi-static data affected by severe hysteresis. Besides a linear feedback controller, we use two Gaussian process models to predict the feedforward control input to compensate for the nonlinearity in a one-shot learning setting. The proposed control approach demonstrates accurate tracking performance even under realistic varying configurations, such as alterations in mass and orientation, without any parameter tuning. Notably, training was achieved with only 25\u201350\u202fs of experimental interaction, which emphasizes the plug-and-play capabilities in diverse real-world applications.<\/jats:p>","DOI":"10.1515\/auto-2023-0237","type":"journal-article","created":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T09:13:32Z","timestamp":1715073212000},"page":"440-448","source":"Crossref","is-referenced-by-count":1,"title":["Gaussian process-based nonlinearity compensation for pneumatic soft actuators"],"prefix":"10.1515","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0076-5239","authenticated-orcid":false,"given":"Alexander","family":"Pawluchin","sequence":"first","affiliation":[{"name":"Department VII \u2013 Humanoid Robotics , Berlin University of Applied Sciences , Luxemburger Stra\u00dfe 10, 13353 Berlin , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3937-6350","authenticated-orcid":false,"given":"Michael","family":"Meindl","sequence":"additional","affiliation":[{"name":"Institute of Mechatronic Systems (imes) , Leibniz University Hannover (LUH), An der Universit\u00e4t 1, 30823 Hannover , Garbsen , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9858-1293","authenticated-orcid":false,"given":"Ive","family":"Weygers","sequence":"additional","affiliation":[{"name":"Department Artificial Intelligence in Biomedical Engineering , FAU Erlangen-N\u00fcrnberg , Werner-von-Siemens-Stra\u00dfe 61, 91052 Erlangen , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6920-1690","authenticated-orcid":false,"given":"Thomas","family":"Seel","sequence":"additional","affiliation":[{"name":"Institute of Mechatronic Systems (imes) , Leibniz University Hannover (LUH), An der Universit\u00e4t 1, 30823 Hannover , Garbsen , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5568-8795","authenticated-orcid":false,"given":"Ivo","family":"Boblan","sequence":"additional","affiliation":[{"name":"Department VII \u2013 Humanoid Robotics , Berlin University of Applied Sciences , Luxemburger Stra\u00dfe 10, 13353 Berlin , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"374","published-online":{"date-parts":[[2024,5,7]]},"reference":[{"key":"2025022009450623525_j_auto-2023-0237_ref_001","doi-asserted-by":"crossref","unstructured":"P. Polygerinos, et al., \u201cSoft robotics: review of fluid\u2010driven intrinsically soft devices; manufacturing, sensing, control, and applications in human\u2010robot Interaction,\u201d Adv. Eng. Mater., vol. 19, no. 1700016, 2017.","DOI":"10.1002\/adem.201700016"},{"key":"2025022009450623525_j_auto-2023-0237_ref_002","doi-asserted-by":"crossref","unstructured":"H. Masashi, M. Takamitsu, N. Tomoyuki, T. Tatsuya, and M. Jun, \u201cUser-robot collaborative excitation for pam model identification in exoskeleton robots,\u201d in 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017, pp.\u00a03063\u20133068.","DOI":"10.1109\/IROS.2017.8206145"},{"key":"2025022009450623525_j_auto-2023-0237_ref_003","doi-asserted-by":"crossref","unstructured":"J. Burgner-Kahrs, D. C. Rucker, and H. Choset, \u201cContinuum robots for medical applications: a survey,\u201d IEEE Trans. Robot., vol.\u00a031, no.\u00a06, pp.\u00a01261\u20131280, 2015. https:\/\/doi.org\/10.1109\/tro.2015.2489500.","DOI":"10.1109\/TRO.2015.2489500"},{"key":"2025022009450623525_j_auto-2023-0237_ref_004","doi-asserted-by":"crossref","unstructured":"J. Walker, et al.., \u201cSoft robotics: a review of recent developments of pneumatic soft actuators,\u201d Actuators, vol.\u00a09, no.\u00a01, p.\u00a03, 2020. https:\/\/doi.org\/10.3390\/act9010003.","DOI":"10.3390\/act9010003"},{"key":"2025022009450623525_j_auto-2023-0237_ref_005","doi-asserted-by":"crossref","unstructured":"T. George Thuruthel, Y. Ansari, E. Falotico, and C. Laschi, \u201cControl strategies for soft robotic manipulators: a survey,\u201d Soft Robot., vol.\u00a05, no.\u00a02, pp.\u00a0149\u2013163, 2018. https:\/\/doi.org\/10.1089\/soro.2017.0007.","DOI":"10.1089\/soro.2017.0007"},{"key":"2025022009450623525_j_auto-2023-0237_ref_006","doi-asserted-by":"crossref","unstructured":"C. Della Santina, C. Duriez, and D. Rus, \u201cModel-based control of soft robots: a survey of the state of the art and open challenges,\u201d IEEE Control Syst., vol.\u00a043, no.\u00a03, pp.\u00a030\u201365, 2023. https:\/\/doi.org\/10.1109\/mcs.2023.3253419.","DOI":"10.1109\/MCS.2023.3253419"},{"key":"2025022009450623525_j_auto-2023-0237_ref_007","doi-asserted-by":"crossref","unstructured":"V. Falkenhahn, T. Mahl, A. Hildebrandt, R. Neumann, and O. Sawodny, \u201cDynamic modeling of bellows-actuated continuum robots using the euler\u2013Lagrange formalism,\u201d IEEE Trans. Robot., vol.\u00a031, no.\u00a06, pp.\u00a01483\u20131496, 2015. https:\/\/doi.org\/10.1109\/tro.2015.2496826.","DOI":"10.1109\/TRO.2015.2496826"},{"key":"2025022009450623525_j_auto-2023-0237_ref_008","doi-asserted-by":"crossref","unstructured":"D. Mueller, A. Raisch, A. Hildebrandt, and O. Sawodny, \u201cNonlinear model based dynamic control of pneumatic driven quasi continuum manipulators,\u201d in 2020 IEEE\/SICE International Symposium on System Integration (SII), 2020, pp.\u00a0277\u2013282.","DOI":"10.1109\/SII46433.2020.9026206"},{"key":"2025022009450623525_j_auto-2023-0237_ref_009","doi-asserted-by":"crossref","unstructured":"F. Schreiber, et al.., \u201cTracking control with hysteresis compensation for manipulator segments driven by pneumatic artificial muscles,\u201d in 2011 IEEE International Conference on Robotics and Biomimetics, 2011, pp.\u00a02750\u20132755.","DOI":"10.1109\/ROBIO.2011.6181721"},{"key":"2025022009450623525_j_auto-2023-0237_ref_010","doi-asserted-by":"crossref","unstructured":"X. Luo, M. Xiao, Y. Ding, and H. Ding, \u201cHysteresis modeling and compensation of a pneumatic end-effector based on Gaussian process regression,\u201d Sens. Actuators, A, vol.\u00a0315, 2020, Art. no. 112227. https:\/\/doi.org\/10.1016\/j.sna.2020.112227.","DOI":"10.1016\/j.sna.2020.112227"},{"key":"2025022009450623525_j_auto-2023-0237_ref_011","doi-asserted-by":"crossref","unstructured":"D. Nguyen-Tuong and J. Peters, \u201cModel learning for robot control: a survey,\u201d Cogn. Process., vol.\u00a012, no.\u00a04, pp.\u00a0319\u2013340, 2011. https:\/\/doi.org\/10.1007\/s10339-011-0404-1.","DOI":"10.1007\/s10339-011-0404-1"},{"key":"2025022009450623525_j_auto-2023-0237_ref_012","doi-asserted-by":"crossref","unstructured":"M. T. Gillespie, C. M. Best, E. C. Townsend, D. Wingate, and M. D. Killpack, \u201cLearning nonlinear dynamic models of soft robots for model predictive control with neural networks,\u201d in 2018 IEEE International Conference on Soft Robotics (RoboSoft), 2018, pp.\u00a039\u201345.","DOI":"10.1109\/ROBOSOFT.2018.8404894"},{"key":"2025022009450623525_j_auto-2023-0237_ref_013","doi-asserted-by":"crossref","unstructured":"P. Hyatt, D. Wingate, and M. D. Killpack, \u201cModel-based control of soft actuators using learned non-linear discrete-time models,\u201d Front. Robot. AI, vol.\u00a06, 2019, Art. no. 22. https:\/\/doi.org\/10.3389\/frobt.2019.00022.","DOI":"10.3389\/frobt.2019.00022"},{"key":"2025022009450623525_j_auto-2023-0237_ref_014","doi-asserted-by":"crossref","unstructured":"A. P. Sabelhaus and C. Majidi, \u201cGaussian process dynamics models for soft robots with shape memory actuators,\u201d in 2021 IEEE 4th International Conference on Soft Robotics (RoboSoft), 2021, pp.\u00a0191\u2013198.","DOI":"10.1109\/RoboSoft51838.2021.9479294"},{"key":"2025022009450623525_j_auto-2023-0237_ref_015","doi-asserted-by":"crossref","unstructured":"C. Rela\u00f1o, J. Mu\u00f1oz, and C. A. Monje, \u201cGaussian process regression for forward and inverse kinematics of a soft robotic arm,\u201d Eng. Appl. Artif. Intell., vol.\u00a0126, 2023, Art. no. 107174. https:\/\/doi.org\/10.1016\/j.engappai.2023.107174.","DOI":"10.1016\/j.engappai.2023.107174"},{"key":"2025022009450623525_j_auto-2023-0237_ref_016","doi-asserted-by":"crossref","unstructured":"T.-L. Habich, S. Kleinjohann, and M. Schappler, \u201cLearning-based position and stiffness feedforward control of antagonistic soft pneumatic actuators using Gaussian processes,\u201d in 2023 IEEE International Conference on Soft Robotics (RoboSoft), 2023, pp.\u00a01\u20137.","DOI":"10.1109\/RoboSoft55895.2023.10122057"},{"key":"2025022009450623525_j_auto-2023-0237_ref_017","doi-asserted-by":"crossref","unstructured":"C. Della Santina, et al.., \u201cControlling soft robots: balancing feedback and feedforward elements,\u201d IEEE Robot. Autom. Mag., vol.\u00a024, no.\u00a03, pp.\u00a075\u201383, 2017. https:\/\/doi.org\/10.1109\/mra.2016.2636360.","DOI":"10.1109\/MRA.2016.2636360"},{"key":"2025022009450623525_j_auto-2023-0237_ref_018","doi-asserted-by":"crossref","unstructured":"M. Meindl, D. Lehmann, and T. Seel, \u201cBridging reinforcement learning and iterative learning control: autonomous motion learning for unknown, nonlinear dynamics,\u201d Front. Robot. AI, vol.\u00a09, 2022, Art. no. 793512. https:\/\/doi.org\/10.3389\/frobt.2022.793512.","DOI":"10.3389\/frobt.2022.793512"},{"key":"2025022009450623525_j_auto-2023-0237_ref_019","doi-asserted-by":"crossref","unstructured":"C. E. Rasmussen and C. K. I. Williams, Gaussian Process for Machine Learning (Adaptive computation and Machine learning), 3. Print, London, England, The MIT Press, 2006.","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"2025022009450623525_j_auto-2023-0237_ref_020","unstructured":"A. Pawluchin, M. Michael, T. Seel, and I. Boblan, \u201cAccurate and agile control of a pneumatic robotic actuator by gp-based feedforward learning,\u201d in Proceedings on Automation in Medical Engineering, 2023."}],"container-title":["at - Automatisierungstechnik"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2023-0237\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2023-0237\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T09:47:53Z","timestamp":1740044873000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2023-0237\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,1]]},"references-count":20,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,5,7]]},"published-print":{"date-parts":[[2024,5,27]]}},"alternative-id":["10.1515\/auto-2023-0237"],"URL":"https:\/\/doi.org\/10.1515\/auto-2023-0237","relation":{},"ISSN":["0178-2312","2196-677X"],"issn-type":[{"type":"print","value":"0178-2312"},{"type":"electronic","value":"2196-677X"}],"subject":[],"published":{"date-parts":[[2024,5,1]]}}}