IDEAS home Printed from https://ideas.repec.org/a/nat/natcom/v13y2022i1d10.1038_s41467-022-31795-2.html
   My bibliography  Save this article

Mechanical intelligence for learning embodied sensor-object relationships

Author

Listed:
  • Ahalya Prabhakar

    (École Polytechnique Fédérale de Lausanne (EPFL))

  • Todd Murphey

    (Northwestern University)

Abstract

Intelligence involves processing sensory experiences into representations useful for prediction. Understanding sensory experiences and building these contextual representations without prior knowledge of sensor models and environment is a challenging unsupervised learning problem. Current machine learning methods process new sensory data using prior knowledge defined by either domain knowledge or datasets. When datasets are not available, data acquisition is needed, though automating exploration in support of learning is still an unsolved problem. Here we develop a method that enables agents to efficiently collect data for learning a predictive sensor model—without requiring domain knowledge, human input, or previously existing data—using ergodicity to specify the data acquisition process. This approach is based entirely on data-driven sensor characteristics rather than predefined knowledge of the sensor model and its physical characteristics. We learn higher quality models with lower energy expenditure during exploration for data acquisition compared to competing approaches, including both random sampling and information maximization. In addition to applications in autonomy, our approach provides a potential model of how animals use their motor control to develop high quality models of their sensors (sight, sound, touch) before having knowledge of their sensor capabilities or their surrounding environment.

Suggested Citation

  • Ahalya Prabhakar & Todd Murphey, 2022. "Mechanical intelligence for learning embodied sensor-object relationships," Nature Communications, Nature, vol. 13(1), pages 1-8, December.
  • Handle: RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-31795-2
    DOI: 10.1038/s41467-022-31795-2
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41467-022-31795-2
    File Function: Abstract
    Download Restriction: no

    File URL: https://libkey.io/10.1038/s41467-022-31795-2?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. R. Quian Quiroga & L. Reddy & G. Kreiman & C. Koch & I. Fried, 2005. "Invariant visual representation by single neurons in the human brain," Nature, Nature, vol. 435(7045), pages 1102-1107, June.
    2. Manoj Srinivasan & Andy Ruina, 2006. "Computer optimization of a minimal biped model discovers walking and running," Nature, Nature, vol. 439(7072), pages 72-75, January.
    3. Massimo Vergassola & Emmanuel Villermaux & Boris I. Shraiman, 2007. "‘Infotaxis’ as a strategy for searching without gradients," Nature, Nature, vol. 445(7126), pages 406-409, January.
    4. Hiromi Yasuda & Philip R. Buskohl & Andrew Gillman & Todd D. Murphey & Susan Stepney & Richard A. Vaia & Jordan R. Raney, 2021. "Mechanical computing," Nature, Nature, vol. 598(7879), pages 39-48, October.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Xin Zhou & Xingjing Ren & Dingbang Xiao & Jianqi Zhang & Ran Huang & Zhipeng Li & Xiaopeng Sun & Xuezhong Wu & Cheng-Wei Qiu & Franco Nori & Hui Jing, 2023. "Higher-order singularities in phase-tracked electromechanical oscillators," Nature Communications, Nature, vol. 14(1), pages 1-9, December.
    2. Grzegorz Suchanek & Jerzy Wołoszyn & Andrzej Gołaś, 2022. "Evaluation of Selected Algorithms for Air Pollution Source Localisation Using Drones," Sustainability, MDPI, vol. 14(5), pages 1-19, March.
    3. Rodrigo Quian Quiroga & Marta Boscaglia & Jacques Jonas & Hernan G. Rey & Xiaoqian Yan & Louis Maillard & Sophie Colnat-Coulbois & Laurent Koessler & Bruno Rossion, 2023. "Single neuron responses underlying face recognition in the human midfusiform face-selective cortex," Nature Communications, Nature, vol. 14(1), pages 1-11, December.
    4. Runnan Cao & Peter Brunner & Puneeth N. Chakravarthula & Krista L. Wahlstrom & Cory Inman & Elliot H. Smith & Xin Li & Adam N. Mamelak & Nicholas J. Brandmeir & Ueli Rutishauser & Jon T. Willie & Shuo, 2025. "A neuronal code for object representation and memory in the human amygdala and hippocampus," Nature Communications, Nature, vol. 16(1), pages 1-16, December.
    5. Leonhard Waschke & Fabian Kamp & Evi Elzen & Suresh Krishna & Ulman Lindenberger & Ueli Rutishauser & Douglas D. Garrett, 2025. "Single-neuron spiking variability in hippocampus dynamically tracks sensory content during memory formation in humans," Nature Communications, Nature, vol. 16(1), pages 1-9, December.
    6. Alan Godoy & Pedro Tabacof & Fernando J Von Zuben, 2017. "The role of the interaction network in the emergence of diversity of behavior," PLOS ONE, Public Library of Science, vol. 12(2), pages 1-32, February.
    7. Luca D. Kolibius & Frederic Roux & George Parish & Marije Wal & Mircea Plas & Ramesh Chelvarajah & Vijay Sawlani & David T. Rollings & Johannes D. Lang & Stephanie Gollwitzer & Katrin Walther & Rüdige, 2023. "Hippocampal neurons code individual episodic memories in humans," Nature Human Behaviour, Nature, vol. 7(11), pages 1968-1979, November.
    8. Jakub Kopal & Kuldeep Kumar & Kimia Shafighi & Karin Saltoun & Claudia Modenato & Clara A. Moreau & Guillaume Huguet & Martineau Jean-Louis & Charles-Olivier Martin & Zohra Saci & Nadine Younis & Elis, 2024. "Using rare genetic mutations to revisit structural brain asymmetry," Nature Communications, Nature, vol. 15(1), pages 1-19, December.
    9. Wenzhong Yan & Shuguang Li & Mauricio Deguchi & Zhaoliang Zheng & Daniela Rus & Ankur Mehta, 2023. "Origami-based integration of robots that sense, decide, and respond," Nature Communications, Nature, vol. 14(1), pages 1-11, December.
    10. Jonathan B Dingwell & Joseph P Cusumano, 2019. "Humans use multi-objective control to regulate lateral foot placement when walking," PLOS Computational Biology, Public Library of Science, vol. 15(3), pages 1-28, March.
    11. Rybalova, E. & Averyanov, V. & Lozi, R. & Strelkova, G., 2024. "Peculiarities of the spatio-temporal dynamics of a Hénon–Lozi map network in the presence of Lévy noise," Chaos, Solitons & Fractals, Elsevier, vol. 184(C).
    12. Louis Kang & Taro Toyoizumi, 2024. "Distinguishing examples while building concepts in hippocampal and artificial networks," Nature Communications, Nature, vol. 15(1), pages 1-19, December.
    13. Tie Mei & Chang Qing Chen, 2023. "In-memory mechanical computing," Nature Communications, Nature, vol. 14(1), pages 1-11, December.
    14. Junghwan Byun & Aniket Pal & Jongkuk Ko & Metin Sitti, 2024. "Integrated mechanical computing for autonomous soft machines," Nature Communications, Nature, vol. 15(1), pages 1-13, December.
    15. Thomas P. Reber & Sina Mackay & Marcel Bausch & Marcel S. Kehl & Valeri Borger & Rainer Surges & Florian Mormann, 2023. "Single-neuron mechanisms of neural adaptation in the human temporal lobe," Nature Communications, Nature, vol. 14(1), pages 1-9, December.
    16. Henning Sprekeler & Christian Michaelis & Laurenz Wiskott, 2007. "Slowness: An Objective for Spike-Timing–Dependent Plasticity?," PLOS Computational Biology, Public Library of Science, vol. 3(6), pages 1-13, June.
    17. Lyons, Benjamin Frederick & Levin, Michael, 2024. "Cognitive Glues Are Shared Models of Relative Scarcities: The Economics of Collective Intelligence," OSF Preprints 3fdya_v1, Center for Open Science.
    18. Jonathan B Dingwell & Joby John & Joseph P Cusumano, 2010. "Do Humans Optimally Exploit Redundancy to Control Step Variability in Walking?," PLOS Computational Biology, Public Library of Science, vol. 6(7), pages 1-15, July.
    19. Brigitta Dúzs & Oliver Skarsetz & Giorgio Fusi & Claudius Lupfer & Andreas Walther, 2024. "Mechano-adaptive meta-gels through synergistic chemical and physical information-processing," Nature Communications, Nature, vol. 15(1), pages 1-10, December.
    20. Sina Mackay & Thomas P. Reber & Marcel Bausch & Jan Boström & Christian E. Elger & Florian Mormann, 2024. "Concept and location neurons in the human brain provide the ‘what’ and ‘where’ in memory formation," Nature Communications, Nature, vol. 15(1), pages 1-9, December.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-31795-2. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.