Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Skills for physical artificial intelligence

Nature Machine Intelligence volume 2, pages 658–660 (2020)Cite this article

Subjects

Synthesizing robots via physical artificial intelligence is a multidisciplinary challenge for future robotics research. An education methodology is needed for researchers to develop a combination of skills in physical artificial intelligence.

Akin to biological organisms, the next generations of robots are expected to act autonomously in the unstructured environment of the real world and be self-sustained in controller adaptation and learning1, physical resilience to damages2 and integration with collective systems3. These future robots will decide and adapt in real time on navigation, locomotion and manipulation by processing combinations of signals, simultaneously sent from multiple sensors in their ‘body’ to their ‘brain’. In addition, they will need to self-predict their capabilities4, self-heal5 and self-grow6 upon need, as well as maintain homeostasis7 in every situation to ensure harmonic balance between the task performance and self-preservation. Such intelligent behaviour will result from a close interaction between the structure of the brain, body morphology and interaction with the environment. The developments in data-based, digital artificial intelligence and learning capabilities in computation, algorithms and cognition have tremendously grown in the past decades, while the development of robots’ bodies, morphology and materials has lagged behind8,9,10. In this Comment, we introduce the physical counterpart of digital artificial intelligence, namely physical artificial intelligence (PAI), and propose a methodology of educating the future generations of researchers to gain skills for the creation of PAI.

This is a preview of subscription content, access via your institution

Relevant articles

Open Access articles citing this article.

Access options

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Learn more

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: PAI is the theory and practice of synthesizing nature-like intelligent robotic systems.
Fig. 2: The five main disciplines of PAI.

References

  1. Cully, A., Clune, J., Tarapore, D. & Mouret, J.-B. Nature 521, 503–507 (2015).

    Article  Google Scholar 

  2. Bilodeau, R. A. & Kramer, R. K. Front. Robot. AI 4, 48 (2017).

    Article  Google Scholar 

  3. Petersen, K. H., Napp, N., Stuart-Smith, R., Rus, D. & Kovac, M. Sci. Robot. 4, eaau8479 (2019).

    Article  Google Scholar 

  4. Xia, B. et al. Actuators 9, 62 (2020).

    Article  Google Scholar 

  5. Pena-Francesch, A., Jung, H., Demirel, M. C. & Sitti, M. Nat. Mater. 19, 1230–1235 (2020).

    Article  Google Scholar 

  6. Sadeghi, A., Mondini, A. & Mazzolai, B. Soft Robot. 4, 211–223 (2017).

    Article  Google Scholar 

  7. Man, K. & Damasio, A. Nat. Mach. Intell. 1, 446–452 (2019).

    Article  Google Scholar 

  8. Sol, J. A. H. P. et al. Chem. Commun. 55, 1726–1729 (2019).

    Article  Google Scholar 

  9. Pfeifer, R., Bongard, J. & Grand, S. How the Body Shapes the Way We Think: A New View of Intelligence (MIT Press, 2007).

  10. Mengüç, Y., Correll, N., Kramer, R. & Paik, J. Sci. Robot. 2, eaar4527 (2017).

    Article  Google Scholar 

  11. Lipson, H. & Pollack, J. B. Nature 406, 974–978 (2000).

    Article  Google Scholar 

  12. Yang, G.-Z. et al. Sci. Robot. 3, eaar7650 (2018).

    Article  Google Scholar 

  13. Kovac, M. Science 352, 895–896 (2016).

    Article  Google Scholar 

  14. Hauser, H. Nat. Mach. Intell. 1, 338–339 (2019).

    Article  Google Scholar 

  15. Howard, D. et al. Nat. Mach. Intell. 1, 12–19 (2019).

    Article  Google Scholar 

  16. Chrisley, R. & Ziemke, T. In Encyclopedia of Cognitive Science (Wiley, 2006).

  17. Miriyev, A., Stack, K. & Lipson, H. Nat. Commun. 8, 596 (2017).

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Materials and Technology Center of Robotics, Empa — Swiss Federal Laboratories for Materials Science and Technology, Dübendorf, Switzerland

    Aslan Miriyev & Mirko Kovač

  2. Aerial Robotics Lab, Department of Aeronautics, Imperial College London, London, United Kingdom

    Aslan Miriyev & Mirko Kovač

Authors
  1. Aslan Miriyev
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mirko Kovač
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Aslan Miriyev or Mirko Kovač.

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Miriyev, A., Kovač, M. Skills for physical artificial intelligence. Nat Mach Intell 2, 658–660 (2020). https://doi.org/10.1038/s42256-020-00258-y

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-020-00258-y

This article is cited by

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing