Behavior planning is known to be one of the basic cognitive functions, whichis essential for any cognitive architecture of any control system used inrobotics. At the same time most of the widespread planning algorithms employedin those systems are developed using only approaches and models of ArtificialIntelligence and don't take into account numerous results of cognitiveexperiments. As a result, there is a strong need for novel methods of behaviorplanning suitable for modern cognitive architectures aimed at robot control.One such method is presented in this work and is studied within a special classof navigation task called smart relocation task. The method is based on thehierarchical two-level model of abstraction and knowledge representation, e.g.symbolic and subsymbolic. On the symbolic level sign world model is used forknowledge representation and hierarchical planning algorithm, PMA, is utilizedfor planning. On the subsymbolic level the task of path planning is consideredand solved as a graph search problem. Interaction between both planners isexamined and inter-level interfaces and feedback loops are described.Preliminary experimental results are presented.
展开▼
