Home » Teams » ASIMOV » Stéphane Doncieux
  • Stéphane Doncieux

  • Professeur des Universités
  • Équipe: ASIMOV
  • Bureau: 65-66 306
  • Email: stephane -dot- doncieux -at- sorbonne-universite -dot- fr
  • Telephone:+33(0)1 44 27 87 45
  • Addresse: ISIR, Campus Pierre et Marie Curie, 4 place Jussieu, BC173, 75005 Paris
  • Site web: https://pages2.isir.upmc.fr/sdoncieux/
  • Bio: Stéphane Doncieux est professeur d'informatique à l'ISIR (Institut des systèmes intelligents et de la robotique), Sorbonne Université, CNRS. Depuis janvier 2019, il est directeur adjoint de l'ISIR. Jusqu'à cette date, il était responsable de l'équipe de recherche multidisciplinaire AMAC (Architectures et Modèles d'Adaptation et de Cognition). Il a été coordinateur du projet DREAM FET H2020 de 2015 à 2018 (https://dream.isir.upmc.fr/). Ses recherches portent sur la robotique cognitive et en particulier sur l'apprentissage et l'adaptation avec une approche développementale.

Publications

  • Giuseppe Paolo, Miranda Coninx, Alban Laflaquière, Stéphane Doncieux. Discovering and Exploiting Sparse Rewards in a Learned Behavior Space. Evolutionary Computation, In press, pp.1-28. ⟨hal-04239313⟩
  • Stephane Doncieux, Raja Chatila, Sirko Straube, Frank Kirchner. Human-centered AI and robotics. AI Perspectives, 2022, 4 (1), pp.14. ⟨10.1186/s42467-021-00014-x⟩. ⟨hal-03992545⟩
  • Aurélien Morel, Yakumo Kunimoto, Alex Coninx, Stéphane Doncieux. Automatic Acquisition of a Repertoire of Diverse Grasping Trajectories through Behavior Shaping and Novelty Search. IEEE International Conference on Robotics and Automation 2022, IEEE, May 2022, Philadelphia, United States. ⟨hal-03625864⟩
  • Léni Le Goff, Oussama Yaakoubi, Alexandre Coninx, Stéphane Doncieux. Building an Affordances Map With Interactive Perception. Frontiers in Neurorobotics, 2022, 16, pp.17. ⟨10.3389/fnbot.2022.504459⟩. ⟨hal-03992611⟩
  • Achkan Salehi, Alexandre Coninx, Stephane Doncieux. Few-shot Quality-Diversity Optimization. IEEE Robotics and Automation Letters, In press, 7 (2), pp.1-10. ⟨10.1109/LRA.2022.3148438⟩. ⟨hal-03569179⟩
  • Achkan Salehi, Alexandre Coninx, Stephane Doncieux. Geodesics, Non-linearities and the Archive of Novelty Search. GECCO '22: Genetic and Evolutionary Computation Conference, Jul 2022, Boston Massachusetts, United States. pp.156-159, ⟨10.1145/3520304.3528944⟩. ⟨hal-03661188⟩
  • Marija Jegorova, Stephane Doncieux, Timothy Hospedales. Behavioral Repertoire via Generative Adversarial Policy Networks. IEEE Transactions on Cognitive and Developmental Systems, 2022, 14 (4), pp.1344-1355. ⟨10.1109/TCDS.2020.3008574⟩. ⟨hal-03992639⟩
  • Freek Stulp, Michael Spranger, Kim Listmann, Stephane Doncieux, Moritz Tenorth, et al.. Innovation Paths for Machine Learning in Robotics [Industry Activities]. IEEE Robotics and Automation Magazine, 2022, 29 (4), pp.141-144. ⟨10.1109/MRA.2022.3213205⟩. ⟨hal-03992530⟩
  • Alexandre Chenu, Nicolas Perrin-Gilbert, Stéphane Doncieux, Olivier Sigaud. Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms. 30th International Conference on Artificial Neural Networks - ICANN 2021, Sep 2021, Bratislava, Slovakia. pp.568-579, ⟨10.1007/978-3-030-86380-7_46⟩. ⟨hal-03404366⟩
  • Giuseppe Paolo, Alexandre Coninx, Stéphane Doncieux, Alban Laflaquière. Sparse Reward Exploration via Novelty Search and Emitters. The Genetic and Evolutionary Computation Conference 2021 (GECCO 2021), Jul 2021, Lille, France. ⟨10.1145/3449639.3459314⟩. ⟨hal-03200022⟩
  • Salehi Achkan, Alexandre Coninx, Stephane Doncieux. BR-NS: an Archive-less Approach to Novelty Search. The Genetic and Evolutionary Computation Conference, Jul 2021, Lille, France. pp.172-179, ⟨10.1145/3449639.3459303⟩. ⟨hal-03344296⟩
  • Alexandre Chenu, Nicolas Perrin-Gilbert, Stephane Doncieux, Olivier Sigaud. Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms. 2021. ⟨hal-03196479⟩
  • Seungsu Kim, Alexandre Coninx, Stephane Doncieux. From exploration to control: Learning object manipulation skills through novelty search and local adaptation. Robotics and Autonomous Systems, 2021, 136, pp.103710. ⟨10.1016/j.robot.2020.103710⟩. ⟨hal-03432702⟩
  • Astrid Merckling, Alexandre Coninx, Loic Cressot, Stephane Doncieux, Nicolas Perrin. State Representation Learning from Demonstration. 6th International Conference on Machine Learning, Optimization, and Data Science, LOD 2020, Jul 2020, Siena, Italy. ⟨hal-03083156⟩
  • Stephane Doncieux, Giuseppe Paolo, Alban Laflaquière, Alexandre Coninx. Novelty Search makes Evolvability Inevitable. GECCO '20, Jul 2020, Cancun, Mexico. ⟨10.1145/3377930.3389840⟩. ⟨hal-02561763⟩
  • Joel Lehman, Jeff Clune, Dusan Misevic, Christoph Adami, Julie Beaulieu, et al.. The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities. Artificial Life, 2020, 26 (2), pp.274-306. ⟨10.1162/artl_a_00319⟩. ⟨hal-01735473⟩
  • Stephane Doncieux, Nicolas Bredeche, Léni Kenneth Le Goff, Benoît Girard, Alexandre Coninx, et al.. DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics. 2020. ⟨hal-02562103⟩
  • Giuseppe Paolo, Alban Laflaquière, Alexandre Coninx, Stephane Doncieux. Unsupervised Learning and Exploration of Reachable Outcome Space. IEEE International Conference on Robotics and Automation (ICRA), 2020, Paris, France. ⟨10.1109/icra40945.2020.9196819⟩. ⟨hal-02951255⟩
  • Léni K. Le Goff, Emma Hart, Alexandre Coninx, Stéphane Doncieux. On pros and cons of evolving topologies with novelty search. Artificial Life Conference Proceedings, 2020, Montréal, Canada. pp.423-431. ⟨hal-02987420⟩
  • Stephane Doncieux. Des robots capables de faire face à des environnements ouverts. Interstices, 2019. ⟨hal-02339132⟩
  • Stephane Doncieux, Alban Laflaquière, Alexandre Coninx. Novelty search: a Theoretical Perspective. GECCO '19: Genetic and Evolutionary Computation Conference, Jul 2019, Prague Czech Republic, France. pp.99-106, ⟨10.1145/3321707.3321752⟩. ⟨hal-02561846⟩
  • Carlos Maestre, Ghanim Mukhtar, Christophe Gonzales, Stéphane Doncieux. Action Generation Adapted to Low-Level and High-Level Robot-Object Interaction States. Frontiers in Neurorobotics, 2019, 13, pp.56. ⟨10.3389/fnbot.2019.00056⟩. ⟨hal-02277550⟩
  • Stéphane Doncieux, David Filliat, Natalia Díaz-Rodríguez, Timothy Hospedales, Richard Duro, et al.. Open-Ended Learning: A Conceptual Framework Based on Representational Redescription. Frontiers in Neurorobotics, 2018, 12, pp.59. ⟨10.3389/fnbot.2018.00059⟩. ⟨hal-01889947⟩
  • Carlos Maestre, Ghanim Mukhtar, Christophe Gonzales, Stephane Doncieux. Iterative affordance learning with adaptive action generation. International Conference on Development and Learning (ICDL) and the International Conference on Epigenetic Robotics (EpiRob), Sep 2017, Lisbon, Portugal. ⟨hal-01617793⟩
  • Leni Le Goff, Ghanim Mukhtar, Pierre-Henri Le Fur, Stephane Doncieux. Segmenting Objects through an Autonomous Agnostic Exploration Conducted by a Robot. 2017 First IEEE International Conference on Robotic Computing (IRC), Apr 2017, Taichung, Taiwan. ⟨10.1109/IRC.2017.22⟩. ⟨hal-01879084⟩
  • Matthieu Zimmer, Stephane Doncieux. Bootstrapping Q-Learning for Robotics from Neuro-Evolution Results. IEEE Transactions on Cognitive and Developmental Systems, 2017, ⟨10.1109/TCDS.2016.2628817⟩. ⟨hal-01494744⟩
  • Camilla Freitas Salgueiredo, Olivier Orfila, Guillaume Saint Pierre, Philippe Doublet, Sébastien Glaser, et al.. Experimental testing and simulations of speed variations impact on fuel consumption of conventional gasoline passenger cars. Transportation Research : Part D, Transport and Environment, 2017, 57, pp.336-349. ⟨10.1016/j.trd.2017.09.029⟩. ⟨hal-01671388⟩
  • Leonid L. Rubchinsky, Sungwoo Ahn, Wouter Klijn, Ben Cumming, Stuart Yates, et al.. 26th Annual Computational Neuroscience Meeting (CNS*2017): Part 2. BMC Neuroscience, 2017, 18 (Suppl 1), pp.59. ⟨10.1186/s12868-017-0371-2⟩. ⟨hal-01580190⟩
  • Seungsu Kim, Stéphane Doncieux. Learning highly diverse robot throwing movements through quality diversity search. 2nd Evolution in Cognition Workshop, Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2017, Berlin, Germany. pp.1177-1178. ⟨hal-02987421⟩
  • Mehdi Khamassi, Stéphane Doncieux. Nouvelles approches en Robotique Cognitive. Intellectica - La revue de l’Association pour la Recherche sur les sciences de la Cognition (ARCo), 2016, 2016/1 (65), pp.7-25. ⟨10.3406/intel.2016.1788⟩. ⟨hal-01375651⟩
  • José Pontes, Stephane Doncieux, Cristina Peixoto Santos, Vincent Padois. AN ADAPTIVE APPROACH TO HUMANOID LOCOMOTION. Advances in Cooperative Robotics -- Proceedings of the 19th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, World Scientific Publishing, pp.437-444, 2016, 978-981-3149-12-0. ⟨10.1142/9789813149137_0052⟩. ⟨hal-01398513⟩
  • Carlos Maestre, Christophe Gonzales, Stéphane Doncieux. Bootstraping manipulation skills to learn affordances in open-ended environments. Workshop Autonomous Perception: Applying Sensorimotor Contingencies and Predictive Processing to Developmental Robotics (ICDL-Epirob), 2016, Cergy-Pontoise, France. pp.1-2. ⟨hal-02987422⟩
  • Carlos Maestre, Antoine Cully, Christophe Gonzales, Stephane Doncieux. Bootstrapping interactions with objects from raw sensorimotor data: a Novelty Search based approach. IEEE International Conference on Development and Learning and on Epigenetic Robotics, Aug 2015, Providence, United States. pp.7-12, ⟨10.1109/DEVLRN.2015.7346098⟩. ⟨hal-01164789⟩
  • Stephane Doncieux, Nicolas Bredeche, Jean-Baptiste Mouret, Gusz Ae Eiben. Evolutionary robotics: what, why, and where to. Frontiers in Robotics and AI, 2015, pp.10.3389/frobt.2015.00004. ⟨10.3389/frobt.2015.00004⟩. ⟨hal-01131267⟩
  • Pierre Ecarlat, Antoine Cully, Carlos Maestre, Stéphane Doncieux. Learning a high diversity of object manipulations though an evolutionary-based babbling. Proceedings of the workshop Learning Object Affordances, IROS 2015, 2015, Hambourg, Unknown Region. pp.1-2. ⟨hal-02987423⟩
  • Leni Le Goff, Carlos Maestre, Stéphane Doncieux. Visual saliency-based babbling of unknown dynamic environments. Proceedings of the workshop Learning Object Affordances, IROS 2015, 2015, Hambourg, Unknown Region. pp.1-2. ⟨hal-02987424⟩
  • Stephane Doncieux, Jean-Baptiste Mouret. Beyond black-box optimization: a review of selective pressures for evolutionary robotics. Evolutionary Intelligence, 2014, 7 (2), pp.71-93. ⟨10.1007/s12065-014-0110-x⟩. ⟨hal-01150254⟩
  • Camila Freitas Salgeiredo, Olivier Orfila, Guillaume Saint Pierre, Alex Coiret, Pierre-Olivier Vandanjon, et al.. Overview of strategies for reducing co2 emissions during the use phase of passenger cars. Transport Research Arena 2014 proceedings, 2014, Paris, France. pp.1-10. ⟨hal-02987426⟩
  • Stéphane Doncieux. Knowledge extraction from learning traces in continuous domains. AAAI 2014 fall Symposium ''Knowledge, Skill, and Behavior Transfer in Autonomous Robots''., 2014, Arlington, United States. pp.1-8. ⟨hal-02987425⟩
  • Stéphane Doncieux, Jean-Baptiste Mouret. Behavioral Diversity with Multiple Behavioral Distances. IEEE Congress on Evolutionary Computation, 2013 (CEC 2013), 2013, Cancun, Mexico. pp.1-8. ⟨hal-01300703⟩
  • Stéphane Doncieux. Transfer learning for direct policy search: a reward shaping approach. Proceedings of ICDL-EpiRob conference, 2013, Osaka, Japan. pp.1-6. ⟨hal-02987427⟩
  • Miguel Alexandre Oliveira, Stéphane Doncieux, Jean-Baptiste Mouret, Cristina Peixoto Santos. Optimization of Humanoid Walking Controller: Crossing the Reality Gap. IEEE RAS International Conference on Humanoid Robots (Humanoids 2013), Oct 2013, Atlanta, GA, United States. pp.106-111, ⟨10.1109/HUMANOIDS.2013.7029963⟩. ⟨hal-01300704⟩
  • Charles Ollion, Tony Pinville, Stéphane Doncieux. With a little help from selection pressures: evolution of memory in robot controllers. Thirteenth International Conference on the Synthesis and Simulation of Living Systems (ALIFE 2012), Jul 2012, East Lansing, MI, United States. pp.407-414, ⟨10.7551/978-0-262-31050-5-ch054?mobileUi=0&⟩. ⟨hal-02987429⟩
  • Jean-Baptiste Mouret, Stéphane Doncieux. Encouraging Behavioral Diversity in Evolutionary Robotics: an Empirical Study. Evolutionary Computation, 2012, 20 (1), pp.91-133. ⟨10.1162/EVCO_a_00048⟩. ⟨hal-00687609⟩
  • Charles Ollion, Stéphane Doncieux. Towards behavioral consistency in neuroevolution. From Animals to Animats: Proceedings of the 12th International Conference on Adaptive Behaviour (SAB 2012), Springer, publisher, 2012, Odense, Denmark. pp.1-10. ⟨hal-02987428⟩
  • Sylvain Koos, Jean-Baptiste Mouret, Stéphane Doncieux. The Transferability Approach: Crossing the Reality Gap in Evolutionary Robotics. IEEE Transactions on Evolutionary Computation, 2012, pp.1-25. ⟨10.1109/TEVC.2012.2185849⟩. ⟨hal-00687617⟩
  • Jean-Baptiste Mouret, Sylvain Koos, Stéphane Doncieux. Crossing the Reality Gap: a Short Introduction to the Transferability Approach. 2012. ⟨hal-01300706⟩
  • Tony Pinville, Sylvain Koos, Jean-Baptiste Mouret, Stéphane Doncieux. How to Promote Generalisation in Evolutionary Robotics: the ProGAb Approach. Conference on Genetic and Evolutionary Computation, Jul 2010, Ireland. pp.259-266, ⟨10.1145/2001576.2001612⟩. ⟨hal-00633928⟩
  • Stéphane Doncieux, Nicolas Bredeche, Jean-Baptiste Mouret (Dir.). New Horizons in Evolutionary Robotics: Extended Contributions from the 2009 EvoDeRob Workshop. Springer, 341, 2011, Studies in Computational Intelligence, 978-3-642-18271-6. ⟨10.1007/978-3-642-18272-3⟩. ⟨hal-01300712⟩
  • Charles Ollion, Stéphane Doncieux. Why and how to measure exploration in behavioral space. GECCO'11: Proceedings of the 13th annual conference on Genetic and evolutionary computation ACM, publisher, 2011, Dublin, Ireland. pp.267-294. ⟨hal-02987430⟩