Search

Search Results

• THE METHOD OF ESTIMATION POSITIONS OF THE UAVS BY MEASURING THE DISTANCES BETWEEN ELEMENTS OF THE GROUP

  V.A. Kostjukov, M.Y. Medvedev, V.K. Pshikhopov, E.Y. Kosenko

  2021-04-04

  Abstract ▼

  Currently, the active use of groups of robots has begun to solve a number of tasks for civil
  and military purposes. In this regard, problems arise associated with group management, the organization
  of reliable communication channels and ensuring the effective functioning of the group
  with limited energy resources. When solving the problem of optimizing energy consumption, the
  problem of increasing the efficiency of interaction of the elements of the group with stationary
  charging stations arises. This problem can only be solved by considering an integrated system,
  which includes robots and charging stations. Centralized management of such a system is justified
  in the case of a small number of its elements. However, with an increase in the number of elements
  in a group, the complexity of management increases, so a combination of centralized and decentralized
  management methods becomes a higher priority solution. The complex of problems of
  decentralized management of such a group includes the task of organizing the optimal interaction
  of its elements in order to achieve the goal of its functioning. When organizing energy exchange
  between robots and charging stations, solving this problem plays a key role in optimizing energy
  consumption. In this article, the concept of the interaction of mobile and stationary objects is developed,
  which implies the possibility of each agent choosing an appropriate companion for interaction.
  This choice is made taking into account the current state of the system and the assessment
  of the history of interaction results. The developed concept is detailed for a system that includes
  UAVs and their recharging stations. An algorithm is proposed for the decentralized selection of
  pairs of interacting elements "UAV - charging station" based on two indicators - the energy efficiency
  of the charging process, and the time spent by the UAV to reach the target point. Both indicators
  are taken into account when choosing the weights assigned to each charging station as its
  degrees of efficiency. Also, these indicators are included in the optimized quality criterion. An
  optimization procedure has been developed, the result of which is the number of the charging station
  that is most suitable for a given mobile object for interaction.

• BIOINSPIRED METHOD FOR CLASSIFICATION OF DISTRIBUTED RESOURCES FOR DISPATCHING IN GRID-COMPUTING

  D.Y. Kravchenko , Y.A. Kravchenko, V.V. Markov , A. E. Saak

  2021-11-14

  Abstract ▼

  The article is devoted to solving the problem of scheduling distributed computing resources
  based on their classification by the bioinspired search method to improve the efficiency of gridcomputing
  functioning. The relevance of the problem is justified by a significant increase in the
  demand for the paradigm of distributed computing in conditions of information overflow and uncertainty.
  The article deals with the problems of scheduling heterogeneous computing resources
  when solving complex professional and scientific problems arriving at different points in time,
  based on the classification according to significant signs of resource compliance and readiness. A
  comparative review of existing analogues is carried out. The formulation of the problem to be
  solved in the context of the selected research topic is formulated. The strategy of choosing
  bioinspired modeling for solving the problem has been substantiated. The aspects of various decentralized
  bioinspired methods effectiveness of the use are analyzed. It is proposed to solve the
  problem of scheduling computational resources based on determining the correspondence of the
  resource to the required class. The classification is carried out on the basis of the bioinspired
  optimization method application, built on the basis of the Fish School Search algorithm. The use of
  the population bioinspired method allows us to provide unprecedented parallelism in obtaining
  alternative solutions and to optimize the distribution of available computing resources depending
  on the sets of significant features. The object of the research is the processes of data classification,
  which include ordered sequences of actions aimed at the distribution of computing resources by
  classes of problems to be solved. The subject of the research is bioinspired methods for solving the
  problem of data classification in grid-computing. To evaluate the effectiveness of the proposed
  method, a software application was developed and a computational experiment was carried outwith a different number of computing resources generated classes. Each computing resource has a
  certain set of attributes, which is a vector of its features. The cosine measure of the similarity between
  a resource attributes vector and a certain class attributes vector is a classification criterion.
  To improve the quality of the dispatching process, the task of classifying computing resources is
  solved for a variety of options for organizing the flows of complex tasks to be solved in gridcomputing.
  The obtained quantitative estimates demonstrate the time savings in solving the problems
  of scheduling distributed computing resources based on their classification by the bioinspired
  search method at least 7 %. The time complexity in the considered examples was . The described
  studies have a high level of theoretical and practical significance and are directly related
  to the solution of artificial intelligence classical problems.

• THEORETICAL FOUNDATIONS OF CREATING SELF-ORGANIZING DISPATCHERS OF DISTRIBUTED SYSTEMS BASED ON A MULTI-AGENT SOCIO-INSPIRATIONAL APPROACH

  A.I. Kalyaev

  2021-11-14

  Abstract ▼

  This article describes new principles of organization, methods and algorithms for the functioning
  of the Distributed System (DS) dispatcher, which allow allocating and reallocating resources
  with dynamically changing parameters between incoming tasks in order to minimize their
  execution time. The main problem that does not allow today to effectively estimate the execution
  time of tasks in a heterogeneous DS directly follows from the distribution of the system: each of its
  elements has partial independence and may differ significantly from others, moreover, in the process
  of operation, its capabilities may change, and all this is essential. affects the efficiency of
  distribution of tasks between DS nodes and the time it takes to complete tasks. The article proposes
  a new approach to organizing a DS dispatcher, based on the application of the theory of multiagent
  systems and socio-inspirational (based on accepted in human society) methods: DS users
  place their tasks on special nodes – bulletin boards, a proactive software agent is placed on each
  DS node, which implements constant monitoring of the parameters of your site and search on message
  boards suitable for solving problems. At the same time, the agents participating in the solution
  of the common task form communities in which they plan the process of solving the task and
  the distribution of parts of the tasks to minimize the delay time for their solution. As a criterion for
  the effectiveness of the DS, it was decided to take the value of the average delay in the execution of
  functional tasks relative to the required points in time, respectively, the agents distribute tasks in
  such a way as to minimize the value of the specified criterion. This article includes an introduction,
  a formal statement of the task of scheduling DS resources, a review of existing approaches to
  organizing a DS dispatcher, a description of the proposed multi-agent solution to the task of
  scheduling DS resources using a socio-inspirational approach, an algorithm for the operation of a
  distributed system and its elements, a description of the application of a socio-inspirational approach
  in relation to the task scheduling process. and conclusion. The main advantages of the
  proposed approach include: the ability to use reliable and up-to-date information about the specialization
  and current performance of resources in dispatching; high fault tolerance due to the
  absence of DS elements, failure of which leads to a complete loss of DS performance; the possibility
  of flexible scaling of the DS (increasing the number of resources), achieved by decentralizing
  the dispatching process.

• COMPARATIVE ANALYSIS OF CENTRALIZED AND DECENTRALIZED ALGORITHMS FOR THE MOVEMENT OF MULTICOPTER-TYPE UAVS

  М.Y. Medvedev, V.K. Pshikhopov

  2022-04-21

  Abstract ▼

  The development of robotics makes their group application relevant for solving various
  tasks. The effectiveness of performing the tasks of detecting and determining the coordinates of
  objects by a group of robots significantly depends on the accuracy of maintaining a given formation.
  In this regard, the task of determining motion planning algorithms that ensure the greatest
  accuracy of maintaining a given formation is of practical interest. This article is devoted to the
  study of the accuracy of maintaining the formation of a multicopter-type UAV group using a centralized
  motion planning algorithm and a decentralized algorithm. The centralized algorithm uses
  a master UAV, which transmits its coordinates to the slave UAVs. Based on the coordinates obtained
  and the given framework of the formation, the guided UAVs plan their movement. In a decentralized
  system, neighboring UAV groups transmit their coordinates to each other, on the basis
  of which the movement of a separate UAV is planned. The accuracy of the control system is investigated
  depending on the errors of the navigation system and the frequency of updating data on the
  position of the leading or neighboring UAVs. It is assumed that the group's UAVs determine their coordinates in discrete moments of time using an external navigation system. Centralized and
  decentralized algorithms are worked out by the same motion control system. The algorithms are
  investigated in this article by numerical modeling methods. In the process of simulation, models of
  kinematics, dynamics and actuators are taken into account, as well as models for the formation of
  errors in the navigation system. It is shown that the de-centralized algorithm of group motion
  planning provides higher accuracy compared to the centralized algorithm. However, the technical
  implementation of a decentralized algorithm is more complicated from the point of view of organizing
  a group communication system. In a centralized system, data transmission from the master
  UAV to the slave should be implemented. In a decentralized system, it is required to implement
  network communication.

• THE FORMALIZED APPROACH TO SYNTHESIS OF ARCHITECTURE IN THE SYSTEM OF ADAPTIVE GROUP CONTROL OF ROBOTIC COMPLEXES IN THE CONDITIONS OF THE NONDETERMINISTIC DYNAMIC ENVIRONMENT

  V.V. Sviridov

  2022-05-26

  Abstract ▼

  The rapid development of "multi-agent systems" as an independent and multifaceted section
  of artificial intelligence attracts many researchers in various fields of activity. The pace of progress
  in the development of information technologies, distributed information systems, and computer
  technology determines the possibilities of using robotics technologies in the Armed Forces of
  the Russian Federation. The factors presented in the article authorize the need to introduce new
  intelligent technologies into the troops - autonomous robotic complexes (systems). The development
  of artificial intelligence methods makes it possible to take a new step towards changing the
  style of interaction of complexes with each other as part of a robotic system. The idea of creating
  so-called "autonomous complexes" arose, which gave rise to a new style of adaptive group management.
  Instead of interaction initiated by the user-operator through commands and direct manipulations,
  complexes are independently involved in the joint process of solving a common problem
  in a non-deterministic dynamic environment. The article proposes a formalized approach to
  the design of architectures for group interaction of autonomous robotic complexes in a system
  based on the law of open control, i.e. induced and reliable preferences of each complex for action,
  satisfying the conditions of perfect coordination of their activities, by identifying parameters at
  which the objective function is maximized in various modes of functioning of the robotic system. A
  formalized formulation of the problem of synthesis of the adaptive group control system of autonomous
  robotic complexes under conditions of a priori uncertainty is presented. The architecture of
  group interaction of complexes is adaptively built based on the conditions of the external environment
  and the internal state of the system, in which each complex of the group functions to achieve
  a common goal (solving a system problem) at the time under consideration.

• DEVELOPMENT OF A CHATBOT FOR CLASSIFICATION AND ANALYSIS OF NATURAL LANGUAGE TEXTS USING LOCAL LARGE LANGUAGE MODELS

  Juman Hussain Mohammad , Juman Hussain Mohammad , Y.А. Kravchenko

  159-171

  2025-07-24

  Abstract ▼

  This paper explores local large language models (LLMs) and their application in text classification tasks, while also comparing their performance with traditional methods. The paper provides a comprehensive review of several key local LLMs, with particular focus on their architectural advantages, characteristics, and application domains. Specifically, we examine models with varying numbers of parameters, their ability to adapt to specialized domains, and their computational requirements when deployed on local hardware. Special emphasis is placed on the trade-offs between performance and resource efficiency. As a practical contribution, we developed a chatbot that utilizes local LLMs (such as DeepSeek, Gemma, and Llama2 via Ollama) to classify incoming texts into predefined categories, demonstrating the operation of these models without cloud computing. The system features a modular architecture that allows for easy integration of new models and comparison of their effectiveness. The computational experiment involves evaluating the accuracy and inference speed of local LLMs compared to simpler methods such as Sentence-BERT, TF-IDF and BoWC, highlighting scenarios in which local models outperform or underperform traditional approaches. Testing was conducted using the benchmark BBC dataset. The results show that language models (including 7-billion parameter models) demonstrate strong and logically consistent classification performance in natural language text processing. However, their results are not perfect for benchmark datasets. Notably, we identified cases where all tested models, including traditional methods, misclassified documents, suggesting potential issues with data labeling. These findings indicate the need to reconsider benchmark labels in standard datasets, particularly for domains with subjective categories where expert evaluations may vary significantly. On the other hand, while local LLMs lag behind cloud-based solutions in speed, their advantages in data privacy and offline operation make them suitable for specialized tasks. This is particularly valuable in medical and financial institutions where protection of sensitive information is critical, and where local models can be fine-tuned for specific business processes without the constraints of cloud APIs.