{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T15:06:26Z","timestamp":1774451186881,"version":"3.50.1"},"reference-count":75,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T00:00:00Z","timestamp":1753833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"Centre for Advanced Robotics Technology Innovation (CARTIN), National Research Foundation, Singapore"},{"name":"Soft and Hybrid Robot Phase 2a project, National Robotics Program, Singapore","award":["W2125d0243"],"award-info":[{"award-number":["W2125d0243"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of Robotics Research"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:p>Safe and efficient robot\u2013environment interaction is a critical yet challenging problem, particularly in the presence of uncertainty and unforeseen changes. Soft robotics, known for its inherent compliance, enables safe interactions with the environment but often suffers from inefficient control performance. Meta-learning, which leverages a robot\u2019s prior experiences in different environments, offers the potential for rapid adaptation to similar conditions with minimal observations. Building on this principle, this work develops a learning-based control approach to enhance the control efficiency of soft robotics. Specifically, a flexible meta-learning model structure is designed to address robot\u2013environment interactions across different situations. An uncertainty-aware optimal control policy, equipped with stability guarantees, is carefully crafted to achieve desired performance. The proposed approach is validated on two soft robotic systems: a pneumatic cable-driven soft manipulator and a rod-driven soft robot. Experimental results demonstrate that these robots can rapidly adapt to varying environmental situations and effectively achieve control objectives, even in the presence of random and unforeseen disturbances. Furthermore, comparisons with other learning-based and physics-based control methods highlight the superiority of our approach in terms of faster adaptation, improved stability, and higher accuracy. This work provides a feasible control approach for soft robots to handle uncertainty and adapt to unforeseen changes in robot\u2013environment interactions.<\/jats:p>","DOI":"10.1177\/02783649251360254","type":"journal-article","created":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T10:04:23Z","timestamp":1753869863000},"page":"452-476","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":2,"title":["Learning to control a soft robotic manipulator under uncertainty and unforeseen changes in robot\u2013environment interaction"],"prefix":"10.1177","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6555-9938","authenticated-orcid":false,"given":"Zhiqiang","family":"Tang","sequence":"first","affiliation":[{"name":"National University of Singapore"},{"name":"Singapore-MIT Alliance for Research and Technology (SMART) Centre"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6010-6427","authenticated-orcid":false,"given":"Peiyi","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2582-8037","authenticated-orcid":false,"given":"Wenci","family":"Xin","sequence":"additional","affiliation":[{"name":"National University of Singapore"}]},{"given":"Cecilia","family":"Laschi","sequence":"additional","affiliation":[{"name":"National University of Singapore"}]}],"member":"179","published-online":{"date-parts":[[2025,7,30]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635840"},{"key":"e_1_3_4_3_1","doi-asserted-by":"publisher","DOI":"10.1177\/1729881416687132"},{"key":"e_1_3_4_4_1","unstructured":"Arcari E Carron A Zeilinger MN (2020) Meta learning mpc using finite-dimensional Gaussian process approximations. arXiv preprint arXiv:2008.05984."},{"key":"e_1_3_4_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05188-w"},{"key":"e_1_3_4_6_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915584806"},{"key":"e_1_3_4_7_1","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop CM","year":"2006","unstructured":"Bishop CM, Nasrabadi NM (2006) Pattern Recognition and Machine Learning. Springer, Vol. 4."},{"key":"e_1_3_4_8_1","doi-asserted-by":"publisher","DOI":"10.22260\/ISARC2012\/0073"},{"key":"e_1_3_4_9_1","first-page":"153","volume-title":"Advances in Neural Information Processing Systems","author":"Bonilla EV","year":"2007","unstructured":"Bonilla EV, Chai KM, Williams C (2007) Multi-task Gaussian process prediction. In: Advances in Neural Information Processing Systems, 153\u2013160."},{"key":"e_1_3_4_10_1","unstructured":"Brochu E Cora VM De Freitas N (2010) A tutorial on bayesian optimization of expensive cost functions with application to active user modeling and hierarchical reinforcement learning. arXiv preprint arXiv:1012.2599."},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793766"},{"key":"e_1_3_4_12_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adf9001"},{"key":"e_1_3_4_13_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"e_1_3_4_14_1","first-page":"25878","article-title":"Generalization bounds for meta-learning: an information-theoretic analysis","volume":"34","author":"Chen Q","year":"2021","unstructured":"Chen Q, Shui C, Marchand M (2021) Generalization bounds for meta-learning: an information-theoretic analysis. Advances in Neural Information Processing Systems 34: 25878\u201325890.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160425"},{"key":"e_1_3_4_16_1","volume-title":"Efficient Reinforcement Learning Using Gaussian Processes","author":"Deisenroth MP","year":"2010","unstructured":"Deisenroth MP (2010) Efficient Reinforcement Learning Using Gaussian Processes. KIT Scientific Publishing, Vol. 9."},{"key":"e_1_3_4_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"e_1_3_4_18_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919897292"},{"key":"e_1_3_4_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2023.3253419"},{"key":"e_1_3_4_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/admt.202100018"},{"key":"e_1_3_4_21_1","first-page":"1082","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Fallah A","year":"2020","unstructured":"Fallah A, Mokhtari A, Ozdaglar A (2020) On the convergence theory of gradient-based model-agnostic meta-learning algorithms. In: International Conference on Artificial Intelligence and Statistics. PMLR, 1082\u20131092."},{"key":"e_1_3_4_22_1","first-page":"1126","volume-title":"International Conference on Machine Learning","author":"Finn C","year":"2017","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning. PMLR, 1126\u20131135."},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029449"},{"key":"e_1_3_4_24_1","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2017.0007"},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.3182\/20120823-5-NL-3013.00030"},{"key":"e_1_3_4_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46024-6_3"},{"key":"e_1_3_4_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2019.2949757"},{"key":"e_1_3_4_28_1","first-page":"29","article-title":"Theoretical convergence of multi-step model-agnostic meta-learning","volume":"23","author":"Ji K","year":"2022","unstructured":"Ji K, Yang J, Liang Y (2022) Theoretical convergence of multi-step model-agnostic meta-learning. Journal of Machine Learning Research 23: 29.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_4_29_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.654398"},{"key":"e_1_3_4_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2005.861458"},{"key":"e_1_3_4_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341462"},{"key":"e_1_3_4_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"key":"e_1_3_4_33_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"e_1_3_4_34_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aah3690"},{"key":"e_1_3_4_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2023.3253421"},{"key":"e_1_3_4_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.004"},{"key":"e_1_3_4_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmva.2016.04.008"},{"key":"e_1_3_4_38_1","first-page":"2","article-title":"Radial basis function network for multi-task learning","volume":"18","author":"Liao X","year":"2005","unstructured":"Liao X, Carin L (2005) Radial basis function network for multi-task learning. Advances in Neural Information Processing Systems 18: 2.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIOROB.2016.7523731"},{"key":"e_1_3_4_40_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915587925"},{"key":"e_1_3_4_41_1","volume-title":"International Conference on Learning Representations","author":"Nagabandi A","year":"2019","unstructured":"Nagabandi A, Clavera I, Liu S, et al. (2019) Learning to adapt in dynamic, real-world environments through meta-reinforcement learning. In: International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HyztsoC5Y7"},{"key":"e_1_3_4_42_1","unstructured":"Nichol A Achiam J Schulman J (2018) On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999."},{"key":"e_1_3_4_43_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm6597"},{"key":"e_1_3_4_44_1","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202100140"},{"key":"e_1_3_4_45_1","unstructured":"Peng H (2020) A comprehensive overview and survey of recent advances in meta-learning. arXiv preprint arXiv:2004.11149."},{"issue":"15","key":"e_1_3_4_46_1","first-page":"510","article-title":"The matrix cookbook","volume":"7","author":"Petersen KB","year":"2008","unstructured":"Petersen KB, Pedersen MS (2008) The matrix cookbook. Technical University of Denmark 7(15): 510.","journal-title":"Technical University of Denmark"},{"key":"e_1_3_4_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3157369"},{"key":"e_1_3_4_48_1","unstructured":"Quinonero-Candela J Girard A Rasmussen CE (2003) Prediction at an uncertain input for Gaussian processes and relevance vector machines-application to multiple-step ahead time-series forecasting."},{"key":"e_1_3_4_49_1","doi-asserted-by":"crossref","unstructured":"Raibert MH Craig JJ (1981) Hybrid position\/force control of manipulators.","DOI":"10.1115\/1.3139652"},{"key":"e_1_3_4_50_1","first-page":"63","volume-title":"Summer School on Machine Learning","author":"Rasmussen CE","year":"2003","unstructured":"Rasmussen CE (2003) Gaussian processes in machine learning. In: Summer School on Machine Learning. Springer, 63\u201371."},{"key":"e_1_3_4_51_1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231165085"},{"key":"e_1_3_4_52_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14543"},{"key":"e_1_3_4_53_1","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2019.0025"},{"key":"e_1_3_4_54_1","volume-title":"Evolutionary Principles in Self-Referential Learning","author":"Schmidhuber J","year":"1987","unstructured":"Schmidhuber J (1987) Evolutionary Principles in Self-Referential Learning. PhD Thesis. Technische Universit\u00e4t M\u00fcnchen."},{"key":"e_1_3_4_55_1","doi-asserted-by":"publisher","DOI":"10.1177\/0018720816644364"},{"key":"e_1_3_4_56_1","first-page":"10013","article-title":"Meta-adaptive nonlinear control: theory and algorithms","volume":"34","author":"Shi G","year":"2021","unstructured":"Shi G, Azizzadenesheli K, O\u2019Connell M, et al. (2021) Meta-adaptive nonlinear control: theory and algorithms. Advances in Neural Information Processing Systems 34: 10013\u201310025.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_57_1","first-page":"18","volume-title":"Proceedings of the 9th EAI International Conference on Simulation Tools and Techniques","author":"Son J","year":"2016","unstructured":"Son J, Gupta S, Tan G (2016) Bayesian optimization in high dimensional input space. In: Proceedings of the 9th EAI International Conference on Simulation Tools and Techniques, 18\u201327."},{"key":"e_1_3_4_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967293"},{"key":"e_1_3_4_59_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919873379"},{"key":"e_1_3_4_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3185786"},{"key":"e_1_3_4_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160513"},{"key":"e_1_3_4_62_1","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2023.0116"},{"key":"e_1_3_4_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1786-2"},{"key":"e_1_3_4_64_1","doi-asserted-by":"publisher","DOI":"10.1088\/1748-3190\/aa839f"},{"key":"e_1_3_4_65_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920903787"},{"key":"e_1_3_4_66_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1060.0175"},{"key":"e_1_3_4_67_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976605774320557"},{"key":"e_1_3_4_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2879335"},{"key":"e_1_3_4_69_1","doi-asserted-by":"publisher","DOI":"10.1142\/7017"},{"key":"e_1_3_4_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2019.2958015"},{"key":"e_1_3_4_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3189435"},{"key":"e_1_3_4_72_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-54327-6"},{"key":"e_1_3_4_73_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910368147"},{"key":"e_1_3_4_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635918"},{"key":"e_1_3_4_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2526062"},{"key":"e_1_3_4_76_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103451"}],"container-title":["The International Journal of Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649251360254","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/02783649251360254","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649251360254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T04:07:18Z","timestamp":1773893238000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/02783649251360254"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,30]]},"references-count":75,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1177\/02783649251360254"],"URL":"https:\/\/doi.org\/10.1177\/02783649251360254","relation":{},"ISSN":["0278-3649","1741-3176"],"issn-type":[{"value":"0278-3649","type":"print"},{"value":"1741-3176","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,30]]}}}