Home » Teams » ACIDE » Leo Cazenille

  • Leo Cazenille

  • Post-Doc
  • Équipe: ACIDE
  • Bureau: Corridor 65-66, bureau 312
  • Addresse: ISIR, Campus Pierre et Marie Curie, 4 place Jussieu, BC173, 75005 Paris
  • Site web: https://scholar.google.com/citations?user=TZ5YZSoAAAAJ
  • Bio: Mes recherches se situent à la croisée de l'intelligence artificielle, de la robotique des essaims et des systèmes complexes. J'étudie comment les interactions locales entre des agents autonomes donnent naissance à des comportements collectifs, et comment ces comportements peuvent être compris, contrôlés et mis à profit pour le calcul distribué et la coordination. Mon travail combine le calcul évolutif, les algorithmes de qualité-diversité, l'apprentissage automatique et l'expérimentation incarnée, couvrant aussi bien les sociétés biohybrides animal-robot, les essaims robotiques auto-organisés que les systèmes multi-agents. Plus récemment, je me suis concentré sur les représentations collectives distribuées, l'apprentissage social et la communication émergente, en explorant comment des populations de robots et d'agents d'IA peuvent acquérir collectivement des connaissances, s'adapter et développer des formes d'auto-organisation de plus en plus sophistiquées.

    À l'ISIR, je travaille avec le Pr Nicolas Bredeche sur le projet ANR Spectral-swarm-robotics (grant ANR-24-CE33-7791).

    Mots clés : Machine Learning, Optimization, Complex systems, Collective Intelligence, Swarm Robotics.

    Google scholar : https://scholar.google.com/citations?user=TZ5YZSoAAAAJ
    Github : https://github.com/leo-cazenille
    ResearchGate : https://www.researchgate.net/profile/Leo-Cazenille-2

Publications

  • Leo Cazenille, Nicolas Lobato-Dauzier, Alessia Loi, Mika Ito, Olivier Marchal, et al.. Hearing the shape of an arena with spectral swarm robotics. Science Robotics, 2026, 11 (119), https://www.science.org/doi/10.1126/scirobotics.adr9578. ⟨10.1126/scirobotics.adr9578⟩. ⟨hal-04526436v2⟩
    [ HTTP | PDF ]
  • Leo Cazenille, Nicolas Bredeche, José Halloy. Automated optimization of multilevel models of collective behaviour: application to mixed society of animals and robots. Bioinspiration and Biomimetics, 2022, 17 (5), pp.055002. ⟨10.1088/1748-3190/ac7fd1⟩. ⟨hal-03842222⟩
    [ HTTP | PDF ]
  • Leo Cazenille, Nicolas Bredeche, Nathanael Aubert-Kato. Using MAP-Elites to Optimize Self-Assembling Behaviors in a Swarm of Bio-micro-robots. Swarm Conference, 2019, Okinawa, Japan. ⟨hal-03175252⟩
    [ HTTP | PDF ]
  • Leo Cazenille, Nicolas Bredeche, José Halloy. Automatic Calibration of Artificial Neural Networks for Zebrafish Collective Behaviours using a Quality Diversity Algorithm. Living Machines Conference, 2019, Nara, Japan. ⟨hal-03175254⟩
    [ HTTP | PDF ]
  • Leo Cazenille, Nicolas Bredeche, Nathanael Aubert-Kato. Exploring Self-Assembling Behaviors in a Swarm of Bio-micro-robots using Surrogate-Assisted MAP-Elites. IEEE Symposium Series on Computational Intelligence, 2019, Xiamen, China. ⟨hal-03175249⟩
    [ HTTP | PDF ]
  • Leo Cazenille, Nicolas Bredeche, José Halloy. Evolutionary optimisation of neural network models for fish collective behaviours in mixed groups of robots and zebrafish. 7th International Conference on Biomimetic and Biohybrid System (Living Machines 2018), Jul 2018, Paris, France. pp.85-96, ⟨10.1007/978-3-319-95972-6_10⟩. ⟨hal-03313855⟩
    [ HTTP | PDF ]
  • Leo Cazenille, Bertrand Collignon, Yohann Chemtob, Frank Bonnet, Alexey Gribovskiy, et al.. How mimetic should a robotic fish be to socially integrate into zebrafish groups?. Bioinspiration and Biomimetics, 2018, 13 (2), pp.025001. ⟨10.1088/1748-3190/aa8f6a⟩. ⟨hal-03313840⟩
    [ HTTP | PDF ]
  • Leo Cazenille, Nicolas Bredeche, José Halloy. Modelling zebrafish collective behaviours with multilayer perceptrons optimised by evolutionary algorithms. 2021. ⟨hal-03314684⟩
    [ HTTP | PDF ]
  • Leo Cazenille, Yohann Chemtob, Frank Bonnet, Alexey Gribovskiy, Francesco Mondada, et al.. Automated calibration of a biomimetic space-dependent model for zebrafish and robot collective behaviour in a structured environment. International Conference on Biomimetic and Biohybrid Systems, 2017, Stanford, CA, United States. ⟨10.1007/978-3-319-63537-8_10⟩. ⟨hal-03314574⟩
    [ HTTP | PDF ]
  • Nathanael Aubert-Kato, Charles Fosseprez, Guillaume Gines, Ibuki Kawamata, Huy Dinh, et al.. Evolutionary optimization of self-assembly in a swarm of bio-micro-robots. Genetic and Evolutionary Computation Conference (GECCO '17), Jul 2017, Berlin, Germany. ⟨10.1145/3071178.3071289⟩. ⟨hal-03313837⟩
    [ HTTP | PDF ]
  • Leo Cazenille, Nicolas Bredeche, José Halloy. Automated optimisation of multi-level models of collective behaviour in a mixed society of animals and robots. 2021. ⟨hal-03314683⟩
    [ HTTP | PDF ]
  • Leo Cazenille, Nicolas Bredeche, José Halloy. Multi-objective optimization of multi-level models for controlling animal collective behavior with robots. 4th International Conference Living Machines 2015, 2015, Barcelona, Spain. pp.379-390, ⟨10.1007/978-3-319-22979-9_38⟩. ⟨hal-03175192⟩
    [ HTTP | PDF ]