“…The purpose is to make better use of low-level control capabilities in performing real-time operations. A number of different architectures for autonomous robot navigation have been proposed in the last twenty years (Latombe, 1991;Fugimura, 1991;Tzafestas, 1999). These include hierarchical architectures that partition the robot's functionalities into high-level (model and plan) and low-level (sense and execute) layers; behaviour -based architectures that achieve complex behaviour by combining several simple behaviourproducing units; and hybrid architectures that combine a layered organization with a behaviour-based decomposition of the execution layer (see e.g., (Izumi & Watanabe, 2000;Watanabe et al, 1996;Topalov & Tzafestas, 2001;Watanabe et al, 2005;Lozano-Perez, 1983;Khatib, 1986;Ratering & Gini, 1995;Erdmann & Lozano-Perez, 1987;Griswold & Elan, 1990;Gil de Lamadrid & Gini, 1990;Fibry, 1987;Gat, 1991;Sugeno & Nishida, 1985;Yen & Pflunger, 1992)).…”