NIIAS

The increasing complexity of autonomous agents’ systems and the constant change of the environment require the development of decision-making algorithms that operate under conditions of incomplete data to achieve group goals. A multi-agent approach is used to describe a group of autonomous agents considering the system as a set of interacting intelligent agents. A model of the behavior of longhorn beetles is used to develop a method for collective analysis of the external environment by agents. A method based on continuous exchange of information between agents and aimed at minimizing resource costs when collecting information about the external environment is presented. During the empirical study of the developed method, an increase in the information received by the group and a decrease in the resources expended were obtained in comparison with the Model Predictive Control and Cooperative Decision-Making for Mixed Traffic algorithms. The proposed method allows reducing the resource costs of the agent group and increasing the system performance when achieving group goals under conditions of incomplete data.

Danil V. Fedorin, Semyon K. Nastenko, Dmitry S. Polyanichenko, Andrey V. Sukhanov, Sergey Y. Grishaev, and Maria A. Butakova. International Journal of Fuzzy Logic and Intelligent Systems 2025;25:97-111. https://doi.org/10.5391/IJFIS.2025.25.1.97

This Special Issue is devoted to probability, statistics, stochastic processes, and their different applications in systems and networks analysis [...]

Abstract The facilities of railway transport are operated in various environmental conditions (temperature, humidity, wind, pressure, amount of precipitation, snow, floods, etc.), under various operating conditions (track layout, track class, set speed, etc.) and in accordance with different management approaches. They are operated at different utilization rate. The facilities of the same functionality may have significant design differences. All these circumstances mean that facilities of the same functionality can fail with different frequency (intensity). Moreover, differences in failure rate can significantly vary depending on operating conditions. It follows that the dependability of a facility could not be evaluated by the total number of its failures at various sections of the railway network.

Active Logic is a conceptual system, the principles of which are satisfied with formalisms of reasoning, which allow correlating the results of reasoning with moments in time and ensuring tolerance to contradictions. At present, tolerance to contradictions (paraconsistency) as applied to Active Logic systems has received theoretical justification in the works of the authors of this report and refers to the so-called formalisms of step theories, combining the principles of Active Logic and logical programming. In particular, it was proved that the argumentative semantics of the formalism of extended step theories, which have two types of negation and have more developed expressive capabilities, are paranormal. The formalism introduced in this paper has even greater expressive capabilities. Keeping all the controls for the process of reasoning in time, this formalism allows one to more adequately represent facts about the subject area by using the language of first-order logic instead of the language of propositional logic. For the formalism of extended step theories of the first order, a declarative semantics is proposed, its paraneosistance is shown, and the expressive possibilities of this formalism in relation to the tasks of action planning are demonstrated using the example of the monkey and the banana.KeywordsActive logicTime reasoningExtended first-order step theoriesDeclarative semanticsParaconsistencyArgumentative semantics

The article provides a brief overview of the developed by the authors and approved methods of precision testing of various samples of NAP-V dynamic consumers and the main test results using these methods in various geographic, weather and operational conditions. One of the key advantages of the techniques is the use of technology for obtaining precision coordinates of control points by the method of long-baseline relative determinations and obtaining reference tracks of a dynamic consumer using the method of integer resolution of ambiguities of phase GNSS measurements.

The authors present the results of the dissertation research analysis on the issues of land monitoring and supervision (control), according to the following criteria

Recent advances in machine learning research could significantly alter the railroad industry by deploying fully autonomous trains. To achieve effective interaction between self-driving trains and the environment, an accurate long-range railway detection should be provided. In this paper, we propose a framework for the rail tracks segmentation on high-resolution images ($2168\times 4096$). The announced approach accelerates inference speed 6 times, by using two neural networks. The proposed architecture and its training approach provide a long-range railway segmentation within 150 meters, achieving 20 fps. Also, we propose an auxiliary algorithm detecting possible paths among all the found ones. To determine which data labeling approach has a higher impact, additional experiments were performed. The proposed framework provides a balanced tradeoff between computing efficiency and performance in the railroad segmentation problem.