The article proposes one of the principles of organizing cognitive tools of conceptual thinking intended for planning purposeful activities by an autonomous intelligent robot in a priori undescribed conditions of a problematic environment. This principle is based on tools that provide the robot with the ability to concretize abstract knowledge, given regardless of a specific subject area, in order to adapt to the current operating conditions, using a system of leading questions and answers to clarify the information required for the conclusion of solutions. In accordance with two methods for determining the goal of behavior (declarative and procedural form of its representation), schemes of leading questions have been developed, receiving an answer to which an autonomous intelligent robot, taking into account the current operating conditions, concretizes the standard constructions of the knowledge representation model given in a general form and, on this basis, automatically generates purposeful action plan. To obtain answers to questions formulated according to a given scheme, procedures for processing knowledge and deriving solutions have been developed that take into account the current capabilities of both the intelligent robot itself and the information coming from the problem environment. The proposed decision inference procedures allow an autonomous intelligent robot to adapt to the current operating conditions and, on this basis, organize its purposeful activities related to the performance of complex tasks under conditions of uncertainty.
DOI: 10.37220/MIT.2023.59.1.023
Download the Marine Intelligent Technologies journal PDF from the official website (in Russian): http://morintex.ru/wp-content/files_mf/1678450986MIT112023OPT.pdf
Download the article (PDF) from eLibrary (in Russian, registration required): https://www.elibrary.ru/item.asp?id=50365199
Melekhin V. B., Khachumov M. V. The principle of concretization of abstract knowledge by an autonomous intelligent robot in the process of planning behavior under uncertainty // Marine Intelligent Technologies. 2023. № 1 part 1, P. 181—190.