{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:51:53Z","timestamp":1773154313695,"version":"3.50.1"},"reference-count":59,"publisher":"SAGE Publications","issue":"10-11","license":[{"start":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T00:00:00Z","timestamp":1736467200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"Spanish Ministry of Science, Innovation, and Universities MCIU"},{"name":"The State Research Agency"},{"name":"European Regional Development Fund ERDF"},{"name":"European Union, NextGenerationEU"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of Robotics Research"],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>\n            We present a comprehensive framework for studying and leveraging morphological symmetries in robotic systems. These are intrinsic properties of the robot\u2019s morphology, frequently observed in animal biology and robotics, which stem from the replication of kinematic structures and the symmetrical distribution of mass. We illustrate how these symmetries extend to the robot\u2019s state space and both proprioceptive and exteroceptive sensor measurements, resulting in the equivariance of the robot\u2019s equations of motion and optimal control policies. Thus, we recognize morphological symmetries as a relevant and previously unexplored physics-informed geometric prior, with significant implications for both data-driven and analytical methods used in modeling, control, estimation and design in robotics. For data-driven methods, we demonstrate that morphological symmetries can enhance the sample efficiency and generalization of machine learning models through data augmentation, or by applying equivariant\/invariant constraints on the model\u2019s architecture. In the context of analytical methods, we employ abstract harmonic analysis to decompose the robot\u2019s dynamics into a superposition of lower-dimensional, independent dynamics. We substantiate our claims with both synthetic and real-world experiments conducted on bipedal and quadrupedal robots. Lastly, we introduce the repository\n            <jats:sc>MorphoSymm<\/jats:sc>\n            to facilitate the practical use of the theory and applications outlined in this work.\n          <\/jats:p>","DOI":"10.1177\/02783649241282422","type":"journal-article","created":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T11:04:45Z","timestamp":1736507085000},"page":"1743-1766","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":4,"title":["Morphological symmetries in robotics"],"prefix":"10.1177","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9793-2482","authenticated-orcid":false,"given":"Daniel Ordo\u00f1ez","family":"Apraez","sequence":"first","affiliation":[{"name":"Istituto Italiano di Tecnologia (IIT)"},{"name":"IIT"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3007-3553","authenticated-orcid":false,"given":"Giulio","family":"Turrisi","sequence":"additional","affiliation":[{"name":"Istituto Italiano di Tecnologia (IIT)"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8341-1400","authenticated-orcid":false,"given":"Vladimir","family":"Kostic","sequence":"additional","affiliation":[{"name":"IIT"}]},{"given":"Mario","family":"Martin","sequence":"additional","affiliation":[{"name":"Institut de Rob\u00f2tica i Inform\u00e0tica Industrial, CSIC-UPC"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6845-4998","authenticated-orcid":false,"given":"Antonio","family":"Agudo","sequence":"additional","affiliation":[{"name":"Institut de Rob\u00f2tica i Inform\u00e0tica Industrial, CSIC-UPC"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8640-684X","authenticated-orcid":false,"given":"Francesc","family":"Moreno-Noguer","sequence":"additional","affiliation":[{"name":"Institut de Rob\u00f2tica i Inform\u00e0tica Industrial, CSIC-UPC"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9415-098X","authenticated-orcid":false,"given":"Massimiliano","family":"Pontil","sequence":"additional","affiliation":[{"name":"IIT"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3034-4686","authenticated-orcid":false,"given":"Claudio","family":"Semini","sequence":"additional","affiliation":[{"name":"Istituto Italiano di Tecnologia (IIT)"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0725-4279","authenticated-orcid":false,"given":"Carlos","family":"Mastalli","sequence":"additional","affiliation":[{"name":"Heriot-Watt University"},{"name":"IHMC Robotics \u2013 Florida Institute for Human & Machine Cognition"}]}],"member":"179","published-online":{"date-parts":[[2025,1,10]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.809155"},{"key":"e_1_3_4_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801676"},{"key":"e_1_3_4_4_1","isbn-type":"print","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems, NIPS \u201921","author":"Bietti A","year":"2024","unstructured":"Bietti A, Venturi L, Bruna J (2024) On the sample complexity of learning under invariance and geometric stability. In: Proceedings of the 35th International Conference on Neural Information Processing Systems, NIPS \u201921. Red Hook, NY, USA: Curran Associates Inc. ISBN 9781713845393.","ISBN":"https:\/\/id.crossref.org\/isbn\/9781713845393"},{"key":"e_1_3_4_5_1","first-page":"1","article-title":"Geometric algebra transformer","volume":"37","author":"Brehmer J","year":"2023","unstructured":"Brehmer J, de Haan P, Behrends S, et al. (2023) Geometric algebra transformer. Advances in Neural Information Processing Systems 37: 1\u201310. https:\/\/arxiv.org\/abs\/2305.18415.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_6_1","first-page":"1","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS \u201923\u2019","author":"Brehmer J","year":"2024","unstructured":"Brehmer J, Bose J, de Haan P, et al. (2024) Edgi: equivariant diffusion for planning with embodied agents. In: Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS \u201923\u2019, pp. 1\u201317. ACM."},{"key":"e_1_3_4_7_1","unstructured":"Bronstein MM Bruna J Cohen T et al. (2021) Geometric deep learning: grids groups graphs geodesics and gauges. arXiv preprint arXiv:2104.13478."},{"key":"e_1_3_4_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793878"},{"key":"e_1_3_4_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2652491"},{"key":"e_1_3_4_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/SII.2019.8700380"},{"key":"e_1_3_4_11_1","volume-title":"International Conference on Learning Representations","author":"Cesa G","year":"2021","unstructured":"Cesa G, Lang L, Weiler M (2021) A program to build e (n)-equivariant steerable cnns International Conference on Learning Representations."},{"key":"e_1_3_4_12_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781420041767"},{"key":"e_1_3_4_13_1","doi-asserted-by":"crossref","unstructured":"Corb\u00e8res T Mastalli C Merkt W et al. (2024) Perceptive locomotion through whole-body mpc and optimal region selection.","DOI":"10.1109\/ACCESS.2025.3558093"},{"key":"e_1_3_4_14_1","volume-title":"Group Theory in Physics: An Introduction","author":"Cornwell JF","year":"1997","unstructured":"Cornwell JF (1997) Group Theory in Physics: An Introduction. Academic Press."},{"key":"e_1_3_4_15_1","first-page":"3088","volume-title":"Proceedings of the 27th International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research","author":"de Haan P","year":"2024","unstructured":"de Haan P, Cohen T, Brehmer J (2024) Euclidean, projective, conformal: choosing a geometric algebra for equivariant transformers. In: Dasgupta S, Mandt S, Li Y (eds) Proceedings of the 27th International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research. PMLR, Vol. 238, 3088\u20133096. https:\/\/proceedings.mlr.press\/v238\/haan24a.html."},{"key":"e_1_3_4_16_1","volume-title":"Group Theory: Application to the Physics of Condensed Matter","author":"Dresselhaus MS","year":"2007","unstructured":"Dresselhaus MS, Dresselhaus G, Jorio A (2007) Group Theory: Application to the Physics of Condensed Matter. Springer Science & Business Media."},{"key":"e_1_3_4_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-77064-2_38"},{"key":"e_1_3_4_18_1","volume-title":"Singularities and Groups in Bifurcation Theory: Volume II","author":"Golubitsky M","year":"2012","unstructured":"Golubitsky M, Stewart I, Schaeffer DG (2012) Singularities and Groups in Bifurcation Theory: Volume II. Springer Science & Business Media, Vol. 69."},{"key":"e_1_3_4_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2976639"},{"key":"e_1_3_4_20_1","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2022.836498"},{"key":"e_1_3_4_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.03.014"},{"key":"e_1_3_4_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793865"},{"key":"e_1_3_4_24_1","unstructured":"Klein L Kr\u00e4mer A No\u00e9 F (2023) Equivariant flow matching. arXiv preprint arXiv:2306.15030."},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1515\/9781400883974"},{"key":"e_1_3_4_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139279"},{"key":"e_1_3_4_27_1","volume-title":"The Variational Principles of Mechanics","author":"Lanczos C","year":"2020","unstructured":"Lanczos C (2020) The Variational Principles of Mechanics. University of Toronto press."},{"key":"e_1_3_4_28_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"e_1_3_4_29_1","volume-title":"First International Conference on Informatics in Control, Automation and Robotics","author":"Li W","year":"2004","unstructured":"Li W, Todorov E (2004) Iterative linear quadratic regulator design for nonlinear biological movement systems. In: First International Conference on Informatics in Control, Automation and Robotics. SciTePress, Vol. 2."},{"key":"e_1_3_4_30_1","volume-title":"5th Annual Conference on Robot Learning","author":"Lin TY","year":"2021","unstructured":"Lin TY, Zhang R, Yu J, et al. (2021) Legged robot state estimation using invariant Kalman filtering and learned contact events. In: 5th Annual Conference on Robot Learning. London, UK. CoRL."},{"key":"e_1_3_4_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196673"},{"key":"e_1_3_4_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3003464"},{"key":"e_1_3_4_33_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207176608921369"},{"key":"e_1_3_4_34_1","doi-asserted-by":"crossref","unstructured":"Mittal M Rudin N Klemm V et al. (2024) Symmetry considerations for learning task symmetric robot policies. arXiv preprint arXiv:2403.04359.","DOI":"10.1109\/ICRA57147.2024.10611493"},{"key":"e_1_3_4_35_1","first-page":"15908","volume-title":"International Conference on Machine Learning","author":"Mondal AK","year":"2022","unstructured":"Mondal AK, Jain V, Siddiqi K, et al. (2022) Eqr: equivariant representations for data-efficient reinforcement learning. In: International Conference on Machine Learning, pp. 15908\u201315926. PMLR."},{"key":"e_1_3_4_36_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-physchem-042018-052331"},{"key":"e_1_3_4_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812441"},{"key":"e_1_3_4_38_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.053"},{"key":"e_1_3_4_39_1","first-page":"1318","volume-title":"6th Annual Learning for Dynamics & Control Conference","author":"Ordo\u00f1ez-Apraez D","year":"2024","unstructured":"Ordo\u00f1ez-Apraez D, Kostic V, Turrisi G, et al. (2024) Dynamics harmonic analysis of robotic systems: application in data-driven koopman modelling. In: 6th Annual Learning for Dynamics & Control Conference, pp. 1318\u20131329. PMLR."},{"key":"e_1_3_4_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-013-9341-4"},{"key":"e_1_3_4_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-1021-7_60"},{"key":"e_1_3_4_42_1","doi-asserted-by":"publisher","DOI":"10.1119\/1.1987245"},{"key":"e_1_3_4_43_1","first-page":"20189","article-title":"Continuous mdp homomorphisms and homomorphic policy gradient","volume":"35","author":"Rezaei-Shoshtari S","year":"2022","unstructured":"Rezaei-Shoshtari S, Zhao R, Panangaden P, et al. (2022) Continuous mdp homomorphisms and homomorphic policy gradient. Advances in Neural Information Processing Systems 35: 20189\u201320204.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_44_1","first-page":"1","volume-title":"Workshop on Bilateral Paradigms on Humans and Humanoids: IEEE International Conference on Intelligent Robots and Systems (IROS 2003)","author":"Schaal S","year":"2003","unstructured":"Schaal S, Peters J, Nakanishi J, et al. (2003) Control, planning, learning, and imitation with dynamic movement primitives. In: Workshop on Bilateral Paradigms on Humans and Humanoids: IEEE International Conference on Intelligent Robots and Systems (IROS 2003), pp. 1\u201321. IEEE."},{"key":"e_1_3_4_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s002210050738"},{"key":"e_1_3_4_46_1","volume-title":"Geometric Fundamentals of Robotics","author":"Selig JM","year":"2005","unstructured":"Selig JM (2005) Geometric Fundamentals of Robotics. Springer, Vol. 128."},{"key":"e_1_3_4_47_1","doi-asserted-by":"crossref","unstructured":"Sol\u00e0 J Deray J Atchuthan D (2021) A micro Lie theory for state estimation in robotics.","DOI":"10.21105\/joss.01371"},{"key":"e_1_3_4_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802439"},{"key":"e_1_3_4_49_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton RS","year":"2018","unstructured":"Sutton RS, Barto AG (2018) Reinforcement Learning: An Introduction. MIT Press."},{"key":"e_1_3_4_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907001"},{"key":"e_1_3_4_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759801"},{"key":"e_1_3_4_52_1","first-page":"4199","article-title":"Mdp homomorphic networks: group symmetries in reinforcement learning","volume":"33","author":"Van der Pol E","year":"2020","unstructured":"Van der Pol E, Worrall D, van Hoof H, et al. (2020) Mdp homomorphic networks: group symmetries in reinforcement learning. Advances in Neural Information Processing Systems 33: 4199\u20134210.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_53_1","volume-title":"International Conference on Learning Representations","author":"Wang D","year":"2022","unstructured":"Wang D, Walters R, Platt R (2022a) SO(2)-equivariant reinforcement learning. In: International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=7F9cOhdvfk_."},{"key":"e_1_3_4_54_1","first-page":"23078","volume-title":"Proceedings of the 39th International Conference on Machine Learning, Proceedings of Machine Learning Research","author":"Wang R","year":"2022","unstructured":"Wang R, Walters R, Yu R (2022b) Approximately equivariant networks for imperfectly symmetric dynamics. In: Chaudhuri K, Jegelka S, Song L, et al. (eds) Proceedings of the 39th International Conference on Machine Learning, Proceedings of Machine Learning Research, Vol. 162, 23078\u201323091. PMLR. https:\/\/proceedings.mlr.press\/v162\/wang22aa.html."},{"key":"e_1_3_4_55_1","first-page":"1345","volume-title":"Proceedings of the 6th Conference on Robot Learning, Proceedings of Machine Learning Research","author":"Wang D","year":"2023","unstructured":"Wang D, Jia M, Zhu X, et al. (2023) On-robot learning with equivariant models. In: Liu K, Kulic D, Ichnowski J (eds) Proceedings of the 6th Conference on Robot Learning, Proceedings of Machine Learning Research, Vol. 205, 1345\u20131354. PMLR. https:\/\/proceedings.mlr.press\/v205\/wang23c.html."},{"key":"e_1_3_4_56_1","doi-asserted-by":"crossref","unstructured":"Weiler M Forr\u00e9 P Verlinde E et al. (2023) Equivariant and coordinate independent convolutional networks. Open Access Book. https:\/\/maurice-weiler.gitlab.io\/cnn_book\/EquivariantAndCoordinateIndependentCNNs.pdf.","DOI":"10.1142\/14143"},{"key":"e_1_3_4_57_1","first-page":"23645","volume-title":"International Conference on Machine Learning","author":"Weissenbacher M","year":"2022","unstructured":"Weissenbacher M, Sinha S, Garg A, et al. (2022) Koopman q-learning: offline reinforcement learning via symmetries of dynamics. In: International Conference on Machine Learning, 23645\u201323667. PMLR."},{"key":"e_1_3_4_58_1","unstructured":"Wheeler JT (2014) General coordinate covariance of the Euler Lagrange equations. https:\/\/www.physics.usu.edu\/Wheeler\/ClassicalMechanics\/CMCoordinateinvarianceofEulerLagrange.pdf.ClassicalMechanicsclassnotes."},{"key":"e_1_3_4_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-36119-0_20"},{"key":"e_1_3_4_60_1","volume-title":"Proceedings of the 18th International Conference on Machine Learning","author":"Zinkevich M","year":"2001","unstructured":"Zinkevich M, Balch T (2001) Symmetry in Markov decision processes and its implications for single agent and multi agent learning. In: Proceedings of the 18th International Conference on Machine Learning. Citeseer."}],"container-title":["The International Journal of Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649241282422","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/02783649241282422","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649241282422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T08:10:52Z","timestamp":1760688652000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/02783649241282422"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,10]]},"references-count":59,"journal-issue":{"issue":"10-11","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["10.1177\/02783649241282422"],"URL":"https:\/\/doi.org\/10.1177\/02783649241282422","relation":{},"ISSN":["0278-3649","1741-3176"],"issn-type":[{"value":"0278-3649","type":"print"},{"value":"1741-3176","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,10]]}}}