Abstract:
In the first part of the article, it is shown that autonomous flying robots formed by unmanned aerial vehicles, as a rule, have an automatic control system with limited computing resources not allowing to implement well-known labor-intensive logical models of knowledge representation and processing for planning purposeful behavior. In this regard, there is a need to develop such a model for the representation and processing of knowledge, which makes it possible with polynomial complexity to form plans for purposeful behavior in a priori underdetermined and various conditions of a problematic environment. To solve this problem, a model of knowledge representation was developed in the form of a set of typical basic, intermediate and terminal growth elements, which allow automatic planning of purposeful behavior in the space of sub-tasks in the form of a growing reduction network model for solving complex problems in underdetermined operating conditions. Procedures for automatic goal-setting have been developed that allow an autonomous flying robot to secure its activities in various conditions of an unstable a priori underdetermined problematic environment.
Keywords:autonomous flying robot, purposeful behavior, problematic environment, knowledge representation model, reduction of tasks into subtasks, space of subtasks.