Robotique

Voir détails dans le fichier pdf joint

Sujet : Conception et mise en oeuvre d'une architecture décisionnelle pour drone autonome.

Plateforme : drone DJI matrice 600
Mots-clés : autonomie ajustable, drone, planification
Localisation : Bondy - Institut de Recherche pour le Développement (IRD) et Campus Jussieu – LIP6.
Durée : 6 mois - 589 euros net mensuel
Envoyer  (CV, LM) à : cedric.herpson@lip6.fr

Détail du sujet en pièce jointe.

An important challenge in collective systems is to understand how they are able to adapt in a decentralized manner to novel environmental conditions. Individuals in these systems must be able to acquire new behaviors autonomously (through natural evolution or learning), and they must be able to do so in an open-ended manner, to deal with potentially entirely novel environments.

voir fichier .pdf

Contexte :

Voir description détaillée dans le fichier pdf joint.

Established in 2005, Aldebaran is a SoftBank Group company. Aldebaran has 450 employees and is headquartered in France with offices in China, Japan and the United States. For almost 10 years, Aldebaran has been driving technology into a new world by designing humanoid robots and has become the worldwide leader in humanoid robotics.

Our robots (NAO, Pepper, Romeo) are used in more than 70 countries in various fields, such as research, education, retail, care, tourism or entertainment.

In our recent work (Cully et al., Nature, 2015 / see the video below), we demonstrated how a 6-legged robot can recover from an unforeseen damage conditions in less than 2 minutes. This novel machine learning algorithm opens many new possibilities to make robots more reliable and, overall, more adaptive.

Embodied evolutionary robotics (EER) designates a set of methods and algorithms to design adaptive collective robotic systems, where each robot can communicate only with close-by robots (Watson et al., 2002)(Bredeche et al., 2012). Lately, it has become apparent that the algorithms used in EER are related to classical models of population genetics. A very interesting aspect of evolutionary robotics is that it can be used to simulate interactions between individual during the evolutionary process.

Swarm robotics designates large groups of robots with limited communication and capability, that coordinates on a local basis to achieve tasks that can be evaluated on a larger scale. Typical examples are: collective construction (Werfel et al. 2014), self-assembly into specific patterns (Rubenstein et al., 2014), collective transport and exploration (Bayindir, Sahin, 2007).