It is advisable to use heuristic methods for the task of planning the flight routes of unmanned aerial vehicles (UAVs) at the planning stage of monitoring and reconnaissance. With their help they look for solutions within some subspace of possible acceptable solutions. They are the best in terms of taking into account the practice, experience, intuition, knowledge of the decision maker. The values of individual predicted factors should be represented using the mathematical apparatus of fuzzy sets. A method of formalizing knowledge about UAV flight route planning has been developed. It is based on interval fuzzy sets. In conditions of uncertainty, they allow to formalize the factors that take into account the conditions of monitoring, search, detection and destruction of objects, the impact of the external environment on the range of UAVs. This effect is manifested in the form of linguistic and interval-estimated parameters for each option, which allow to take into account the uncertainty. The developed method allows to form the area of definition of linguistic variables. These variables are used to describe the conditions for monitoring, reconnaissance and the impact of the environment on the range of UAVs. Such variables are also used to form from the set of the most important objects of monitoring, exploration of the most significant ground objects on the basis of an assessment of the degree of non-dominance of elements. The proposed approach provides a formalization of UAV flight route options for each possible scenario of the location of objects, the impact of the external environment. The result of formalization is fuzzy production rules, where fuzzy linguistic utterances are used as the antecedent and consequent.
The most important task of the Armed Forces (AF) of Ukraine in the defense nature of military doctrine is the constant monitoring of the enemy. Monitoring should ensure a timely and organized transition of troops from peacetime to martial law. The main role is played by monitoring and intelligence. Their tasks are to provide the leadership and headquarters in a timely manner with complete and reliable information about the enemy. Among the available technical means capable of quickly and efficiently collecting the necessary information, one can single out unmanned aerial vehicles (UAVs). When monitoring the area, UAVs fly over the area of interest and collect the necessary data.
Thus, UAVs can be used to monitor forests, fields, borders, for environmental and meteorological monitoring, search and rescue missions, for military purposes, etc. The presence of large potential capabilities of UAVs does not guarantee the achievement of the specified efficiency of reconnaissance and monitoring. Its increase can be achieved by intelligently predicting the behavior of UAVs. This takes into account the influence of environmental factors, the behavioral nature of the objects of monitoring, knowledge and experience of UAV operators.
The experience of practical application of
UAVs [
At present, the combination of stochastic and non-stochastic uncertainty factors influencing this process is insufficiently taken into account when selecting appropriate options for the UAV flight route. Factors of non-stochastic uncertainty have the nature of behavioral uncertainty. Therefore, it is necessary to adapt pre-designed decisionmaking models to change many possible situations.
Tasks of this class require increasing the level
of automation of their solution. The reason for this
is the dynamism, ephemerality and high degree of
uncertainty of the air and ground conditions, time
constraints. But the task of automating the
planning of UAV flight routes is complicated by
the need to take into account the experience of
decision makers (DM). This requires formalizing
one's own knowledge and experience in ATS. To
work with knowledge, including its formalization,
it is necessary to improve mathematical support
and software (MSS). Trends in the development
of MSS show the need for the introduction of
modern information technology (IT), including
intelligent IT. They are aimed at creating and
using the knowledge bases (KB) of the UAV
control system (CS) [
The knowledge base is a set of rules, facts,
derivation mechanisms and software that describe
a subject area and are designed to represent the
accumulated knowledge in it [
Global trends in research in the field of control theory are concentrated in two areas – artificial intelligence and machine learning, robotics and decision theory. Artificial intelligence technologies are actively used in the military sphere. Work is being actively carried out to increase the autonomy of the functioning of combat systems.
The article [
In [
In the article [
The article [
The article [
The article [
The work [
In [
In [
The result of the literature analysis indicates the relevance and prospects of research in the direction of developing intelligent UAV control systems. search, detection and destruction of objects.
Thus, a change in approaches to planning UAV flight routes will make it possible to better solve the problems of observation, search, detection and destruction of objects.
The purpose of the study is to develop a method of formalizing knowledge about the planning of UAV flight routes on the basis of interval fuzzy sets in the monitoring, search, detection and destruction of objects in conditions of uncertainty.
To formalize the knowledge of UAV flight route planning, it is advisable to use interval fuzzy sets of type 2 (IFST2). For IFST2, the values of the membership functions of the second order are constant. That is, the membership function is unified (homogeneous) in contrast to the general fuzzy sets of type 2 (FST2).
Іnterval fuzzy sets of type 2 allow you to use
all the tools of interval calculations and are
expressed
by the
degree
of truth
̃ ( , ) ≤ 1,which is expressed
and ∈ ⊆ [
If ( ) = 1, ∀ ∈ [ , ̅] ⊆ [
≡ ̃ ( ) and, accordingly, the
upper membership function of the first type ̅ ≡
̅̃ ( ). Then IFST2 can be represented as
̃ =
⊆ [
The article proposes the use of triangular fuzzy numbers (TFN) and trapezoidal fuzzy intervals (TFI). The expediency of their use is due to the simplicity of operations on them and visual graphical interpretation.
In the general case, the fuzzy interval is called
A
with convex upper and lower membership functions, limiting the area of uncertainty of this IFST2. The fuzzy number of
A unimodal upper and lower membership functions, which limit the area of uncertainty of this IFST2.
Features of the representation of TFN or TFI in terms of IFST2 are as follows:
– the left and right boundaries of fuzzy quantities in terms of IFST2 are not points but uncertainty intervals; ¯ – the extreme
values of the uncertainty intervals, in turn, are the boundaries of the two FST1. They are defined by the upper membership function ̅̃ and the lower membership function ̃ . These functions limit the occupied area of uncertainty (FOU) TFNIFST2 or TFIIFST2 above and below, respectively;
– the upper ̅̃ and lower ̃ membership functions determine the normal convex FST1 on a non-empty carrier. Moreover, in the case of TFN IFST2 it will be unimodal normal convex FST1.
Thus, it is proposed to formally present the
¯
parameters [
– center (modal value) ̅̃ ∆; а – center (modal value) ̃ ∆ ̅ – right fuzzy coefficient ̅̃ ∆; – right fuzzy coefficient ̃ ∆.
In this case, the triangular upper membership function ̅̃ ∆; unimodal convex FST1 on a nonempty carrier – an open interval [ ̅ − ̅ , ̅ + ̅ ], and the ( ̃ ) generates a normal triangular function ̃ ∆ normal unimodal convex FST1 on a nonempty carrier – open interval [ − , + ].
It is also proposed to formally represent FOU TFI IFST2 in the form of a tuple with the ¯ ¯ ¯ ¯ following parameters: ( ̃ ) generates a where ̅ – left fuzzy coefficient ̅̃п; – left fuzzy coefficient ̃п; ̅ – lower modal value ̅̃п; – lower modal value ̃п; ̅ – upper modal value ̅̃п;
– upper modal value ̃п; ̅ – right fuzzy coefficient ̅̃п; – right fuzzy coefficient ̃п. (5)
In this case, the trapezoidal upper membership function ̅̃п ( ̃ ) generates a normal convex FST1 on a nonempty carrier – an open interval [ ̅ − ̅ , ̅ + ̅ ], and the trapezoidal lower function ̃п
( ̃ ) generates a normal unimodal convex FST1 on a non-empty carrier – open interval.
In this case, the set of fuzzy production rules will be called the base of rules (BR). It is intended for • by the structure of fuzzy production rules: SISO – a structure that implements one input and one output; MISO – a structure that implements many inputs and one output; MIMO is a structure that implements many inputs and many outputs.
When formalizing knowledge about the process of planning the route of the UAV flight in the form of a fuzzy production rule that describes a predetermined version of the UAV routes, we will use the rules with MISO-structure.
These conditions are factors that take into account the conditions of monitoring, the impact of the external environment, and the conclusions – recommendations on the appropriate route of the
When developing a method of formalizing knowledge about the planning of UAV flight routes on the basis of interval fuzzy sets, the following limitations and assumptions are taken into account:
- issues related to the assessment of the adequacy and informativeness of the parameters used to describe the projected situation are considered resolved and are not considered in this study;
- construction of membership functions for conditions and conclusions of fuzzy production rules begins with the use of the simplest forms of membership functions – piecewise linear functions. Subsequently, their nature can be clarified and taken into account during the adjustment of the rules (for example, at the stage of learning a fuzzy logical system);
- issues of ensuring the completeness and consistency of a set of fuzzy production rules in this study are not considered.
The method of formalizing knowledge about the process of planning a reconnaissance flight of a UAV based on IFST2 includes the following main stages:
- presentation of factors that take into account the conditions of monitoring, exploration, environmental impact in the form of linguistic variables for each projected option; - formation objects of monitoring, intelligence based on the assessment of the degree of non-dominance of the elements;
- presentation of options for the location of ground objects, the impact of the external environment, the appropriate variant of the UAV flight route in the form of fuzzy production rules, where as an antecedent, a follower use fuzzy linguistic statements.
Thus, it is investigated that for the task of UAV flight route planning at the planning and reconnaissance planning stage it is expedient to use heuristic methods. They are looking for solutions within some subspace of possible acceptable solutions. They are the best in terms of taking into account the practice, experience, intuition, knowledge of ATS. The values of individual predicted factors should be represented using the mathematical apparatus of fuzzy sets. A method for formalizing knowledge about UAV flight route planning based on interval fuzzy sets in conditions of uncertainty has been developed. With its help it is possible to formalize the factors that take into account the conditions of monitoring, search, detection and destruction of objects, the impact of the external environment on the range of UAVs.
They are presented in the form of linguistic and interval-estimated parameters for each option. This approach allows: - take into account uncertainty; - to form the area of definition of linguistic variables that are used to describe the conditions of monitoring, reconnaissance and the impact of the external environment on the range of UAVs; - to form from a set of the most important objects of monitoring, reconnaissance of the most significant ground objects on the basis of an estimation of a degree of non-dominance of elements;
- to formalize the flight options of the UAV for each possible variant of the location of objects, the influence of the external environment in the form of fuzzy production rules, where fuzzy linguistic statements are used as an antecedent, a consequent.
The calculation of the mathematical expectation of the time to perform individual operations in the construction of UAV flight routes at the planning stage is carried out.
In the traditional approach, the time for
information preparation and direct planning of
UAV routes is up to 66% of the total time for
making a decision [
The mathematical expectation of the total time for making a decision is ∗[ ̅ ]=211,59 s; the time spent on entering the initial data – ∗[ ̅ ]=67 s (up to 31% from ∗[ ̅ ]) the waiting time for the result of solving the problem – ∗[ ̅ ]=73,63 s (up to 35% from ∗[ ̅ ]). Efficiency of decision-making by a decisionmaker at the stage of planning UAV flight routes may turn out to be unacceptably low (P=0.47 ... 0.9). To increase the efficiency of decisionmaking, it is necessary to reduce the time for preparation and the direct solution of the problem.
In the proposed approach to planning the routes of the UAV reconnaissance flight, the mathematical expectation of the total time for making a decision was ∗[ ̅ ]=103,59 s, the time spent by the decision-maker for entering the initial data was – ∗[ ̅ ]=13,74 s (up to 13% from ∗[ ̅ ]), the waiting time for the decision result was – ∗[ ̅ ]=33,71 s (up to 32% from ∗[ ̅ ]).
The proposed approach to planning UAV flight routes under conditions of uncertainty makes it possible to reduce the total decisionmaking time by up to 2 times.