Contact

pierre-yves dot# oudeyer at inria.fr

Popular science highlights

Fondation Cartier
L'expérience Ergo-Robots, expostion "Mathématiques un Dépaysement Soudain", Fondation Cartier, Paris
France Culture
France Culture (jan. 2012), "La robotique pour mieux comprendre l'homme", Emission Continent Sciences de Stéphane Deligeorges. A propos du contexte scientifique dans lequel s'inscrit le projet Ergo-Robots.
France Inter
France Inter, (Nov. 2011) "En direct de la Fondation Cartier: Les mystères des mathématiques, et les robots et la curiosité", 3D Le Journal (émission de Stéphane Paoli), France Inter. Podcast
France Inter
France Inter (Juil. 2011) "Robots, Invasion Imminente ?", On verra ça demain (émission de Daniel Fiévet), France Inter. Podcast
France Culture
France Culture (Juin 2011) Interview "L'apprentissage des robots", Podcast
Le Monde.fr
Le Monde.Fr (avr. 2011) Reportage sur les interfaces homme-robot et l'utilisation de l'humanoide Nao dans les laboratoires de recherche
France Info
France Info (mars 2011)
Interview à propos du robot Acroban
(Communiqué de presse Acroban)
Euronews
Euronews (aug. 2010)
on Acroban in SIGGRAPH'2010, Los Angeles, USA).
)
Science et Vie (2009)
Interview

La Recherche (2008) Interview
Metro (2008)
Interview
France Culture (2006) Interview
Pour la Science (2006) Article "Un robot curieux"
Le Monde (2005)
Des robots remontent aux sources du langage (2005)
Business Week (2005) How This Dog Teaches Itself New Tricks

more press ...

I am research director at Inria, heading the Flowers team, in developmental and social robotics. I study mechanisms for life-long autonomous learning and development in machines and humans, i.e. the developmental processes which lead to the progressive formation of behavioural, cognitive and social structures. I am particularly interested in the formation of repertoires of sensorimotor and interaction skills as well as in the acquisition and morphogenesis of language.

This research is articulated along two mutually reinforcing strands:

  • Understanding and building developmental machines inspired by the living, and their application to personal robotics: This consists in taking functional inspiration from developmental learning in animals, and humans in particular, and study how aspects of these capabilities can be transposed in autonomous embodied machines. This raises fundamental questions about the nature of machines: Can a robot learn like a child? Can machines acquire novel skills autonomously and in an open-ended manner? This also applies to the emerging field of personal robotics, where robots need to interact and adapt continuously to the particularities of non-expert human users.

  • Elaborating computer and robotic models as tools for understanding developmental processes in humans and other animals: The formation of behavioural, cognitive and social structures in animals, and humans in particular, is the result of complex dynamical interactions between the brain, the body and the physical and social environment, spanning several spatiotemporal scales. Computer and robotic models can be highly useful technical and conceptual tools to study those complex dynamics.

A central hypothesis of this work is that open-ended learning in the real-world, as well as evolutionary formation of structures, can only happen when strong developmental processes constrain and structure exploration in extremely large and high-dimensional spaces. My approach is thus to study various families of such constraints through computational and robotic modeling, and in particular: self-organization, constraints on curiosity-driven exploration and intrinsic motivation, morphology and embodiment, maturation, perceptual and motor primitives, social cues and interaction dynamics allowing for fluid and robust peer-to-peer interaction and social learning.

I am also strongly involved in creating interactions between science and society at large through popular science (vulgarisation scientifique, médiation scientifique), involving regular writing of popular science articles, participation to wide audience radio and tv programs and intervention in the press to address scientific issues, participation to science festivales and museum exhibitions.

Selected recent publications
Selected all times publications
Selected publications by topic
All publications

Recent articles highlights:

Active learning of inverse models, goal babbling
Baranes, A., Oudeyer, P-Y. (2013) Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots, Robotics and Autonomous Systems, 61(1), pp. 49-73. http://dx.doi.org/10.1016/j.robot.2012.05.008. Bibtex

Human-robot interfaces for robot teaching, Large-scale real-world user study
Rouanet, P., Oudeyer, P-Y., Danieau, F., Filliat, D. (2013) The Impact of Human-Robot Interfaces on the Learning of Visual Object, IEEE Transactions on Robotics, 29(2), pp. 525-541. Bibtex

Exploration in model-based reinforcement learning
Lopes M., Lang T., Toussaint M. and Oudeyer P-Y. (2012) Exploration in Model-based Reinforcement Learning by Empirically Estimating Learning Progress, Neural Information Processing Systems (NIPS 2012), Tahoe, USA. Bibtex

Strategic learning, life-long learning
Lopes M., Oudeyer P-Y. (2012) The Strategic Student Approach for Life-Long Exploration and Learning, in Proceedings of IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-Epirob), San Diego, USA. Bibtex

Nguyen, M., Oudeyer, P-Y. (2013) Active Choice of Teachers, Learning Strategies and Goals for a Socially Guided Intrinsic Motivation Learner, Paladyn Journal of Behavioural Robotics (in press).

Joint action and language learning with Non-Negative Matrix Factorization
Mangin O., Oudeyer P.Y. (2012) Learning to recognize parallel combinations of human motion primitives with linguistic descriptions using non-negative matrix factorization, in IEEE/RSJ International Conference on Intelligent Robots and Systems, Vilamoura, Algarve (Portugal). [data] [slides of presentation at IROS 2012][video of presentation] Bibtex

Factorial Inverse Feedback Learning
Mangin O., Oudeyer P.Y. (2012) Learning the combinatorial structure of demonstrated behaviors with inverse feedback control, in Proceedings of 3rd International Workshop on Human Behavior Unterstanding (HBU 2012), pp. 134-147, Springer, LNCS 7559. (This article is about Factorial Inverse Feedback Learning). [slides] Bibtex

Adaptive Maturation for Motor Learning
Stulp, F. and Oudeyer, P-Y. (in press) Adaptive Exploration through Covariance Matrix Adaptation Enables Developmental Motor Learning, Paladyn Journal of Behavioural Robotics. [Bibtex] [Details] [slides]

Modeling Speech Development with Curiosity-driven Learning
Moulin-Frier, C. and Oudeyer, P-Y. (2012) Curiosity Driven Phonetic Learning, in Proceedings of IEEE International Conference on Development and Learning and Epigenetic Robot (ICDL-Epirob), San Diego, USA. Bibtex (Best Paper Award, category "Models of Cognitive Development").

Selected all times publications

Baranes, A., Oudeyer, P-Y. (2013) Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots, Robotics and Autonomous Systems, 61(1), pp. 49-73. http://dx.doi.org/10.1016/j.robot.2012.05.008. Bibtex

Oudeyer, P-Y. (2013) Self-Organization and Complex Dynamical Systems in the Evolution of Speech, in Smith, K. and Binder, P. eds., The Language Phenomenon, Springer. Bibtex

Lopes M., Oudeyer P-Y. (2012) The Strategic Student Approach for Life-Long Exploration and Learning, in Proceedings of IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-Epirob), San Diego, USA. Bibtex

Nguyen, M., Oudeyer, P-Y. (2013) Active Choice of Teachers, Learning Strategies and Goals for a Socially Guided Intrinsic Motivation Learner, Paladyn Journal of Behavioural Robotics (in press).

Lopes M., Lang T., Toussaint M. and Oudeyer P-Y. (2012) Exploration in Model-based Reinforcement Learning by Empirically Estimating Learning Progress, Neural Information Processing Systems (NIPS 2012), Tahoe, USA. Bibtex

Oudeyer, P-Y. (2010) On the impact of robotics in behavioral and cognitive sciences: from insect navigation to human cognitive development, IEEE Transactions on Autonomous Mental Development, 2(1), pp. 2--16. DOI: 10.1109/TAMD.2009.2039057. Bibtex

Kaplan, F., Oudeyer, P-Y., Bergen B. (2008) Computational Models in the Debate over Language Learnability, Infant and Child Development, 17(1), pp. 55--80. Bibtex

Oudeyer P-Y, Kaplan , F. and Hafner, V. (2007) Intrinsic Motivation Systems for Autonomous Mental Development, IEEE Transactions on Evolutionary Computation, 11(2), pp. 265--286. DOI: 10.1109/TEVC.2006.890271. Bibtex

Kaplan F. and Oudeyer P-Y. (2007a) In search of the neural circuits of intrinsic motivation, Frontiers in Neuroscience, 1(1), pp.225--236. Bibtex

Oudeyer P-Y., Kaplan F. (2006) Discovering Communication, Connection Science, 18(2), pp. 189--206. Bibtex 

Oudeyer, P-Y. (2006) Self-Organization in the Evolution of Speech, Studies in the Evolution of Language, Oxford University Press. Bibtex

Oudeyer, P-Y. (2005) The Self-Organization of Speech Sounds, Journal of Theoretical Biology, 233(3), pp. 435--449. Bibtex

Oudeyer P-Y. (2003) The production and recognition of emotions in speech: features and algorithms, International Journal in Human-Computer Studies , 59(1-2), pp. 157--183, special issue on Affective Computing. Bibtex

Kaplan, F., Oudeyer, P-Y., Kubinyi, E. and Miklosi, A. (2002) Robotic clicker training. Robotics and Autonomous Systems, 38(3-4), pp. 197--206. Bibtex

ERC I was awarded an ERC Starting Grant (project EXPLORERS) from the European Research Council, which will fund a large-scale research project called EXPLORERS over the next 5 years (2010-2014). This project will focus on advanced life-long motor learning in robots as well as on the re-use of learnt motor skills to acquire language. Topics range from intrinsically motivated exploration and learning of motor skills, artificial curiosity, socially-guided robot learning, learning and discovery of body maps, language acquisition. Interested applicants can send me their CV.

Ergo-Robots, Fondation Cartier pour l'Art Contemporain News, october 2011:"The Ergo-Robots Experiment: Artificial Curiosity and Language" is an installation presented in the exhibition "Mathematics: A Beautiful Elsewhere", from 21st october 2011 to 18th march 2012, in Fondation Cartier pour l'Art Contemporain, Paris, France.
See the dedicated web page here.

It experiments models curiosity-driven learning and its interaction with language formation in humans and robots. It features robots that explore and learn about their environment through artificial curiosity, and at the same time invent their own language, to talk about their environment. Based on recent advanced models of autonomous learning inspired by human infant development, they progressively acquire new skills, discover ways to communicate with humans, and self-organize their own culture.

At the frontiers of sciences and art, exploring fundamental questions about the nature of humans and machines, "Ergo-Robots" is a project which benefited from a collaboration with filmaker David Lynch (who designed the head and the environment of the robots) from an encounter with mathematician Mikhail Gromov (and his theory of ergo-systems).

Its software and hardware development was realized by the INRIA Flowers team in collaboration with University of Bordeaux/Labri.

Photos of the Ergo-Robots installation are available here.
More information on the dedicated web page on Ergo-Robots
Contact: pierre-yves.oudeyer _ @ _ inria.fr

 

Project
highlights

Developmental Robotics
Active life-long learning, intrinsic motivation,
artificial curiosity
Social learning, human-robot interaction
Language acquisition in robots and humans
Modeling the evolution of language
Emotional Speech Synthesis and recognition