Statut |
Confirmé |
Série |
LPTMS |
Domaines |
cond-mat.stat-mech |
Date |
Mardi 14 Mai 2024 |
Heure |
11:00 |
Institut |
LPTMS |
Salle |
Salle des séminaires du FAST et du LPTMS, bâtiment Pascal n°530 |
Nom de l'orateur |
Sire |
Prenom de l'orateur |
Clément |
Addresse email de l'orateur |
|
Institution de l'orateur |
LPT Toulouse |
Titre |
When poor little fish are confronted with AI, robot-fish, virtual reality, and drones |
Résumé |
After introducing the collective behaviors observed in fish schools, I will outline a methodology for
quantitatively measuring social interactions (attraction/repulsion; alignment) within animal groups. The
reconstructed interactions can then be directly implemented in analytical models which quantitatively
reproduce the collective motion of fish. I will also briefly address an alternative machine learning approach
designed to produce realistic fish trajectories.
In the latter part of the presentation, I will explore various applications of such analytical or machine learning
behavioral models in the context of robotic and drone platforms, and a virtual reality setup
for fish! In
particular, our robot-fish and VR setups constitute original and powerful tools to study the social dynamics of
fish and their response to controlled perturbations. |
Numéro de preprint arXiv |
|
Commentaires |
|
Fichiers attachés |
|