Evolving Symbolic Controllers

dc.creatorGodzik, Nicolas
dc.creatorSchoenauer, Marc
dc.creatorSebag, Michèle
dc.date2007-05-09
dc.date.accessioned2026-07-07T08:00:19Z
dc.date.available2026-07-07T08:00:19Z
dc.descriptionThe idea of symbolic controllers tries to bridge the gap between the top-down manual design of the controller architecture, as advocated in Brooks' subsumption architecture, and the bottom-up designer-free approach that is now standard within the Evolutionary Robotics community. The designer provides a set of elementary behavior, and evolution is given the goal of assembling them to solve complex tasks. Two experiments are presented, demonstrating the efficiency and showing the recursiveness of this approach. In particular, the sensitivity with respect to the proposed elementary behaviors, and the robustness w.r.t. generalization of the resulting controllers are studied in detail.
dc.identifierhttps://arxiv.org/abs/0705.1244
dc.identifierhttp://arxiv.org/abs/0705.1244
dc.identifierDans 4th European Workshop on Evolutionary Robotics, 2611 (2003) 638-650
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/128643
dc.subjectArtificial Intelligence
dc.titleEvolving Symbolic Controllers
dc.typetext

Files

Collections