The Flowers project-team, at Inria and Ensta ParisTech, studies mechanisms that can allow robots and humans to acquire autonomously and cumulatively repertoires of novel skills over extended periods of time.
This includes mechanisms for learning by self-exploration, as well as learning through interaction with peers, for the acquisition of both sensorimotor and social skills. Sensorimotor skills include locomotion, affordance learning, active manipulation. Interactive skills include grounded language use and understanding, adaptive interaction protocols, and human-robot collaboration.
Our approach is organized along two strands of research:
Our project-team, headed by Pierre-Yves Oudeyer (Inria) and co-started with David Filliat (Ensta ParisTech Cognitive Robotics Group), focuses in particular on the study of developmental mechanisms that guide efficient open-ended learning of novel skills in large real world environments. In particular, we study:
In this project, in collaboration with cognitive neuroscientist J. Gottlieb (Univ. Columbia, NY, US) and developmental psychologist C. Kidd (Univ. Rochester, US), we target to construct a comprehensive theory that defines curiosity in the context of quantitative models of learning and decision making and probes its neural mechanisms. We are looking for outstanding postdoc applications.
Together with J. Gottlieb and T. Gliga, we have co-organized the Second Interdisciplinary Symposium on Information Seeking, Curiosity and Attention in London, in september 2016. This great event has gathered researchers from neuroscience, psychology and computer science/machine learning: J. Nelson, D. Markant, R. Ligneul, S. Kouider, M. Gruber, K. Murayama, J. O’Reilly, G. Baldassarre, P. Dayan, P-Y. Oudeyer, K. Doya, W. Shultz, A. Bell, L. Hunt, J. Gottlieb, D. Bell, K. Begus, L. Goupil, L. Feigenson, D. Bavelier, T. Gliga.
Most videos and slides of the symposium are available on the Neurocuriosity 2016 symposium web site.
Link to information about the Poppy humanoid robot : Poppy Project web site. Poppy is an open-source 3D printed robotic platform designed by the Flowers team. Poppy Humanoid robot was initially built to study the impact of the body on sensorimotor development and cognition: it makes it possible to really consider the body as an experimental variable. See article at Humanoids 2013 conference. It then evolved into an open platform for interdisciplinary invention, building and programming of robots, used in science, art and education.
Our work on calibration-free interaction applied to Brain-Computer Interaction has been published in PlosOne. Title: Exploiting task constraints for self-calibrated brain-machine interface control using error-related potentials. Authors: I. Iturrate, J.
Jonathan Grizou defended his thesis entitled Learning From Unlabeled Interaction Frames on October 24, 2014. The video, slides, and thesis manuscript can be found at this link: http://jgrizou.com/projects/thesis_defense/ Keywords: Learning from
The video of the PhD defense of Olivier Mangin is finally out ! The full dissertation can be found here (olivier.mangin.com/publi). Olivier’s work focused on learning recurring patterns in multimodal perception. For that purpose he developed
We have a new paper accepted to the 2014 Conference on Uncertainty in Artificial Intelligence (UAI) to be held in July 2014 in Quebec, Canada. It is a joint work with Iñaki Iturrate (EPFL) and Luis Montesano (Univ. Zaragoza). [webpage] [pdf] [bib]
We have a new paper accepted to the 2014 AAAI Conference on Artificial Intelligence to be held in July 2014 in Quebec, Canada. We present a method allowing a user to instruct a new task to an agent by mentally assessing the agent’s actions and