Abstract
Natural beings undergo a morphological development process of their bodies while they are learning and adapting to the environments they face from infancy to adulthood. In fact, this is the period where the most important learning processes, those that will support learning as adults, will take place. However, in artificial systems, this interaction between morphological development and learning, and its possible advantages, have seldom been considered. In this line, this paper seeks to provide some insights into how morphological development can be harnessed in order to facilitate learning in embodied systems facing tasks or domains that are hard to learn. In particular, here we will concentrate on whether morphological development can really provide any advantage when learning complex tasks and whether its relevance towards learning increases as tasks become harder. To this end, we present the results of some initial experiments on the application of morphological development to learning to walk in three cases, that of a quadruped, a hexapod and that of an octopod. These results seem to confirm that as task learning difficulty increases the application of morphological development to learning becomes more advantageous.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Pfeifer, R., Bongard, J.: How the body shapes the way we think: a new view of intelligence. MIT press (2006)
Pfeifer, R.: Dynamics, morphology, and materials in the emergence of cognition. In: Burgard, W., Cremers, Armin B., Cristaller, T. (eds.) KI 1999. LNCS (LNAI), vol. 1701, pp. 27–44. Springer, Heidelberg (1999). https://doi.org/10.1007/3-540-48238-5_3
Chrisley, R.: Embodied artificial intelligence. Artif. Intell. 149(1), 131–150 (2003)
Pfeifer, R., Iida, F.: Embodied artificial intelligence: trends and challenges. In: Iida, F., Pfeifer, R., Steels, L., Kuniyoshi, Y. (eds.) Embodied Artificial Intelligence. LNCS (LNAI), vol. 3139, pp. 1–26. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-27833-7_1
Hoffmann, M., Pfeifer, R.: Robots as powerful allies for the study of embodied cognition from the bottom up, 1–22 (2018)
Doncieux, S., et al.: Open-ended learning: a conceptual framework based on representational redescription. Front. Neurorobot. 12, 59 (2018)
Asada, M., et al.: Cognitive developmental robotics: a survey. IEEE Trans. Auton. Ment. Dev. 1(1), 12–34 (2009)
Cangelosi, A., Schlesinger, M.: Developmental robotics: from babies to robots. MIT Press (2015)
Zlatev, J., Balkenius, C.: Introduction: why epigenetic robotics?. In: 1st International Workshop on Epigenetic Robotics (2001)
Weng, J., et al.: Autonomous mental development by robots and animals. Science 291(5504), 599–600 (2001)
Pfeifer, R., Iida, F.: Morphological computation: connecting body, brain and environment. Japanese Sci. Mon. 58, 48–54 (2005)
Matarić, M., Cliff, D.: Challenges in evolving controllers for physical robots. Rob. Auton. Syst. 19(1), 67–83 (1996)
Lipson, H., Pollack, J.B.: Automatic design and manufacture of robotic lifeforms. Nature 406(6799), 974–978 (2000)
Cheney, N., Bongard, J., Lipson, H.: Evolving soft robots in tight spaces. In: Proceedings of the 2015 annual conference on Genetic and Evolutionary Computation, pp. 935–942 (2015)
Trianni, V.: Evolutionary robotics: model or design? Front. Robot. AI 1, 13 (2014)
Clark, J.E., Whitall, J.: What is motor development? The lessons of history. Quest 41(3), 183–202 (1989)
Fischer, K.W.: A theory of cognitive development: the control and construction of hierarchies of skills. Psychol. Rev. 87(6), 477 (1980)
Roche, A.F.: Growth, Maturation, and Body Composition: The Fels Longitudinal Study, pp. 1929–1991. Cambridge University Press, Cambridge (1992)
Bongard, J.: Why morphology matters. Horizons Evol. Robot. 6, 125–152 (2014)
Vujovic, V., Rosendo, A., Brodbeck, L., Iida, F.: Evolutionary developmental robotics: improving morphology and control of physical robots. Artif. Life 23(2), 169–185 (2017)
Lungarella, M., Berthouze, L.: On the interplay between morphological, neural, and environmental dynamics: a robotic case study. Adapt. Behav. 10(3), 223–241 (2002)
Berthouze, L., Lungarella, M.: Motor skill acquisition under environmental perturbations: on the necessity of alternate freezing and freeing of degrees of freedom. Adapt. Behav. 12(1), 47–64 (2004)
Lungarella, M., Berthouze, L.: Adaptivity via alternate freeing and freezing of degrees of freedom. In: ICONIP 2002-Proceeding of 9th International Conference Neural Information Processing Computer Intelligence E-Age, vol. 1, pp. 482–487 (2002)
Bongard, J.: Morphological change in machines accelerates the evolution of robust behavior. Proc. Natl. Acad. Sci. 108(4), 1234–1239 (2011)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)
Chervenski, P., Ryan, S.: MultiNEAT, project website (2012). URL www.multineat.com/
Robotics, C.: VREP Simulator. http://www.coppeliarobotics.com/
Smith, R.L.: Open Dynamics Engine. https://www.ode.org/
CESGA. Centro de Supecomputacion de Galicia. http://www.cesga.es/. Accessed 14 Jan 2020
Acknowledgment
This work has been partially funded by the Ministerio de Ciencia, Innovación y Universidades of Spain/FEDER (grant RTI2018-101114-B-I00), Xunta de Galicia and FEDER (grant ED431C 2017/12) and M. Naya-Varela is very grateful for the support of the UDC-Inditex 2019 grant for international mobility. We also want to thank CESGA (Centro de Supercomputación de Galicia. https://www.cesga.es/) for the possibility of using its resources.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Naya-Varela, M., Faina, A., Duro, R.J. (2020). Some Experiments on the Influence of Problem Hardness in Morphological Development Based Learning of Neural Controllers. In: de la Cal, E.A., Villar Flecha, J.R., Quintián, H., Corchado, E. (eds) Hybrid Artificial Intelligent Systems. HAIS 2020. Lecture Notes in Computer Science(), vol 12344. Springer, Cham. https://doi.org/10.1007/978-3-030-61705-9_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-61705-9_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61704-2
Online ISBN: 978-3-030-61705-9
eBook Packages: Computer ScienceComputer Science (R0)