eprintid: 10204330 rev_number: 8 eprint_status: archive userid: 699 dir: disk0/10/20/43/30 datestamp: 2025-02-05 08:30:46 lastmod: 2025-02-05 08:33:18 status_changed: 2025-02-05 08:30:46 type: article metadata_visibility: show sword_depositor: 699 creators_name: Apraez, Daniel Ordoñez creators_name: Turrisi, Giulio creators_name: Kostic, Vladimir creators_name: Martin, Mario creators_name: Agudo, Antonio creators_name: Moreno-Noguer, Francesc creators_name: Pontil, Massimiliano creators_name: Semini, Claudio creators_name: Mastalli, Carlos title: Morphological symmetries in robotics ispublished: inpress divisions: UCL divisions: B04 divisions: F48 keywords: Symmetric dynamical systems; Morphological symmetries; Geometric Learning; Physics-Informed priors note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: We present a comprehensive framework for studying and leveraging morphological symmetries in robotic systems. These are intrinsic properties of the robot’s 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’s state space and both proprioceptive and exteroceptive sensor measurements, resulting in the equivariance of the robot’s 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’s architecture. In the context of analytical methods, we employ abstract harmonic analysis to decompose the robot’s 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 MorphoSymm to facilitate the practical use of the theory and applications outlined in this work. date: 2025-01-10 date_type: published publisher: SAGE Publications official_url: https://doi.org/10.1177/02783649241282422 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2266058 doi: 10.1177/02783649241282422 lyricists_name: Pontil, Massimiliano lyricists_id: MPONT27 actors_name: Flynn, Bernadette actors_id: BFFLY94 actors_role: owner funding_acknowledgements: PID2023-151184OB-I00 [Spanish Ministry of Science, Innovation, and Universities MCIU]; [State Research Agency AEI]; [European Regional Development Fund ERDF]; PE000013-CUP-J53C22003010006 [PNRR-MUR Project]; [European Union] full_text_status: public publication: The International Journal of Robotics Research pages: 24 issn: 0278-3649 citation: Apraez, Daniel Ordoñez; Turrisi, Giulio; Kostic, Vladimir; Martin, Mario; Agudo, Antonio; Moreno-Noguer, Francesc; Pontil, Massimiliano; ... Mastalli, Carlos; + view all <#> Apraez, Daniel Ordoñez; Turrisi, Giulio; Kostic, Vladimir; Martin, Mario; Agudo, Antonio; Moreno-Noguer, Francesc; Pontil, Massimiliano; Semini, Claudio; Mastalli, Carlos; - view fewer <#> (2025) Morphological symmetries in robotics. The International Journal of Robotics Research 10.1177/02783649241282422 <https://doi.org/10.1177/02783649241282422>. (In press). Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10204330/1/2402.15552v3.pdf