Résumé HDR Nicolas Bredecheón


This Habilitation Thesis manuscript presents some of my research activities as Assistant Researcher ("Maître de Conférences") at Université Paris-Sud XI since 2003. It contains a selected summary of my contributions to the field of Evolutionary Design of autonomous agents and developmental systems. Evolutionary Design is an automatic design method based on evolutionary operators, ie. combining selection pressure and partly blind variations, and has been shown to be particularly relevant to address problems for which a success value may be computed, without any hint on how to actually obtain the best design. The core motivation behind my research is to provide autonomous embodied agents with both efficient design and robust (self-)adaptation capabilities. In this scope, several aspects of my work are presented, starting with a focus on some important evolutionary mechanisms for automatic design of embodied agents (representation formalism and selection pressure), then addressing the problem of evolutionary design of structural design such as bridges and metallic truss structures, with a special focus on the relevance of developmental design with regards to robustness and scalability. Finally, on-line behavior learning for self-adaptation in the scope of a real-world autonomous robotic agent is described as well as perspectives towards self-adapting swarm of autonomous agents.