CN-122022340-A - Unmanned aerial vehicle disaster relief task allocation method and system based on quantum black oligopolistic mechanism

CN122022340ACN 122022340 ACN122022340 ACN 122022340ACN-122022340-A

Abstract

The invention discloses an unmanned aerial vehicle disaster relief task allocation method and system based on a quantum black oligopolistic mechanism, relates to the technical field of unmanned aerial vehicle resource allocation, and aims to solve the problems that the constraint considered by the existing method is not comprehensive enough, the solving time is long, and local optimization is easy to fall into. The method comprises the following steps of establishing a multi-unmanned aerial vehicle task allocation model and an objective function of the unmanned aerial vehicle task allocation model, selecting tasks and initializing quantum black oligopolistic populations, constructing an adaptability function based on the objective function, calculating the adaptability of the black oligopolistic populations and determining a global optimal position, updating quantum rotation angles of all quantum black oligopolistic populations, calculating the adaptability of the updated black oligopolistic populations and updating the global optimal position, iteratively completing, outputting a task allocation matrix of the global optimal position, completing all task allocation, and outputting an allocation scheme of the unmanned aerial vehicle for executing disaster monitoring, material putting and rescue effect evaluation tasks.

Inventors

LI SHIRUI
GAO HONGYUAN
LUAN FENGHU
ZHU QINGLIN
JIAO DANDAN
WANG YUFENG
GU XIAOYUAN
WANG JIAYI

Assignees

哈尔滨工程大学

Dates

Publication Date: 20260512
Application Date: 20260130

Claims (7)

1. An unmanned aerial vehicle disaster relief task allocation method based on a quantum black oligopolistic mechanism is characterized by comprising the following steps: Step one, establishing a multi-unmanned aerial vehicle task allocation model and an objective function of the unmanned aerial vehicle task allocation model; Selecting tasks and initializing quantum black oligopolistic populations; constructing an adaptability function based on an objective function of the unmanned aerial vehicle task allocation model, calculating the adaptability of all black oligopolists and determining a global optimal position; updating quantum rotation angles of all quantum black oligopolishes; step five, calculating the fitness of the updated black oligopolistic and updating the global optimal position; judging whether the maximum iteration times are reached, if yes, terminating iteration, outputting a task allocation matrix of the global optimal position, otherwise, returning to the fourth step to continue iteration; And step seven, judging whether all tasks are distributed and completed, returning to the step two to execute the next task if the tasks are not distributed and outputting an allocation scheme for the unmanned aerial vehicle to execute disaster monitoring, material delivery and rescue effect evaluation tasks if the tasks are distributed and completed.
2. The method of claim 1, wherein step one includes the process of: Assuming that there is Unmanned aerial vehicle is put up on ground Sequentially executing disaster monitoring O, material throwing A and rescue effect evaluation task E at disaster points, wherein the first task is that The material carrying capacity of the unmanned aerial vehicle is , ; The unmanned aerial vehicle task allocation matrix is represented as one Matrix of binary decision variables If unmanned aerial vehicle Executing disaster points Is to (1) Otherwise ; Set the first The initial coordinates of the unmanned aerial vehicle are First, the The coordinates of the disaster points are Unmanned aerial vehicle Disaster-stricken point Is the distance of (2) Wherein Unmanned aerial vehicle The assigned task set is ; Setting the unmanned aerial vehicle to finish tasks on disaster points in three stages, firstly executing disaster monitoring tasks, then executing material throwing tasks, and finally executing rescue effect evaluation tasks Is as follows Unmanned aerial vehicle The probability of successfully completing the disaster monitoring task is that Unmanned aerial vehicle The probability of successfully completing the material delivery task is that Unmanned aerial vehicle The probability of successfully completing the rescue effect evaluation task is as follows , As disaster points Is to reduce the environmental risk coefficient of the disaster point to the following condition if the materials are successfully put in ; The objective function of the unmanned aerial vehicle task allocation model is , To perform tasks Is used to determine the benefit of (1), To perform tasks At the cost of the effort to be made, Performing tasks for unmanned aerial vehicles A penalty term that does not satisfy the constraint condition at the time, The objective functions of the three tasks are respectively: (1) Disaster monitoring task: The unmanned aerial vehicle executes disaster monitoring tasks with the benefit of The unmanned aerial vehicle performs disaster monitoring tasks at the cost of , Is that Constraint punishment of the disaster monitoring task is as follows Wherein As penalty factors, the penalty function of each unmanned aerial vehicle for executing at least one disaster point task is that The penalty function that each disaster point task can only be executed by one unmanned plane is that Wherein Indicating that when two values in brackets are equal to 0 and are not equal to 1, the objective function of the disaster monitoring task is ; (2) Material delivery tasks: The unmanned aerial vehicle executes the income of material input task as The voyage cost is At the cost of , Is a collection In the number of tasks in the (c) process, , Is a collection Middle (f) Environmental risk factors for the individual disaster points, Is a scaling factor at the total cost of Wherein And As the weight coefficient of the light-emitting diode, And is also provided with Constraint punishment of the material delivery task is that Wherein As penalty factors, the penalty function of each unmanned aerial vehicle for executing at least one disaster point task is that The penalty function that each disaster point task can only be executed by one unmanned plane is that The material amount thrown in the unmanned aerial vehicle cannot exceed the material carrying capacity Is given by (1) The objective function of the material delivery task is ; (3) Rescue effect evaluation task: The benefit of the unmanned aerial vehicle for executing the rescue effect evaluation task is that The voyage cost is At the cost of , Is unmanned plane Successful completion of aggregate Middle (f) Probability of material delivery tasks at disaster points is as follows Wherein In order for the scaling factor to be a factor, And As the weight coefficient of the light-emitting diode, And is also provided with Constraint punishment of rescue effect evaluation task is as follows Wherein As penalty factors, the penalty function of each unmanned aerial vehicle for executing at least one disaster point task is that The penalty function that each disaster point task can only be executed by one unmanned plane is that The objective function of the rescue effect evaluation task is 。
3. The method of claim 2, wherein step two comprises the following process: setting the population scale as The maximum iteration number is Search space dimension is Dimension, group I of black oligopolistic Generation 1 Quantum black oligopolistic record only Measuring the quantum black oligopolistic to obtain corresponding black oligopolistic record The measuring method is that Wherein , , Is that Is a random number of (a) in the memory.
4. A method according to claim 3, characterized in that step three comprises the following procedure: calculating the fitness of each black oligopolistic according to the fitness function Confirm to the first The global optimum position is 。
5. The method of claim 4, wherein step four comprises the following process: Will be the first Generation 1 Quantum black oligopolistic No The rotation angle of each quantum is recorded as The movement pattern of black oligopolides on the spider web is divided into linear and spiral, so the evolution pattern of quantum rotation angle is , And In order for the scaling factor to be a factor, Is that Is the first of (2) The dimensions of the dimensions, Is that Is the first of (2) The dimensions of the dimensions, As a result of the linear motion factor, In the form of a spiral-shaped motion factor, Is that Is a random number of (a) and (b), Is the probability of a linear motion and, The corresponding quantum turnstile is defined as First, the Quantum black oligopolistic No Quantum rotation gate for quantum bit Updating: , Is that Is the first of (2) The dimensions of the dimensions, To take an absolute function.
6. An unmanned aerial vehicle disaster relief task allocation system based on a quantum black oligopolistic mechanism, which is characterized by comprising program modules corresponding to the steps of the method according to any one of claims 1-5, wherein the steps in the unmanned aerial vehicle disaster relief task allocation method based on the quantum black oligopolistic mechanism are executed during operation.
7. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program configured to implement the steps in the unmanned aerial vehicle disaster relief task allocation method based on the quantum black oligopolistic mechanism according to any one of claims 1 to 5 when called by a processor.

Description

Unmanned aerial vehicle disaster relief task allocation method and system based on quantum black oligopolistic mechanism Technical Field The invention relates to the technical field of unmanned aerial vehicle resource allocation, in particular to an unmanned aerial vehicle disaster relief task allocation method and system based on a quantum black oligopolistic mechanism. Background The unmanned aerial vehicle as an aircraft has unique value in disaster emergency response by virtue of the remarkable characteristics of light weight structure, low manufacturing cost, zero casualties and the like. The unmanned aerial vehicle can execute tasks such as disaster monitoring, material throwing, rescue effect evaluation and the like, and greatly improves rescue efficiency and multi-department cooperative capacity. The unmanned aerial vehicle system can improve the efficiency of completing tasks through information exchange among unmanned aerial vehicles, and has better fault tolerance and robustness compared with a single unmanned aerial vehicle. The multi-unmanned aerial vehicle task allocation technology is an important technology in an unmanned aerial vehicle system, tasks are allocated reasonably to members in the unmanned aerial vehicle system through an optimization algorithm under limited resource constraint, and accurate trade-off between benefits and losses is achieved. According to the prior art, pang Hailong et al published in "a heterogeneous multi-unmanned aerial vehicle multi-target task allocation method" by the fourth China Command control Congress (2016: 267-270), find that the task allocation model is solved by integer programming, but the algorithm has high computational complexity, and is difficult to cope with the high-dimensional nonlinear problem. Along with the development of intelligent computation, the application of various intelligent optimization algorithms provides a new research thought for unmanned aerial vehicle task allocation. Nuri Ozalp et al, in "Cooperative multi-TASK ASSIGNMENT for heterogonous UAVs" published on ICAR 2015 (2015 International Conference on Advanced Robotics), applied intelligent multi-structure genetic algorithm to unmanned aerial vehicle task allocation problem, designed two novel genetic operators, significantly improved the quality of understanding, but the real-time performance is poor, and the applicable scene is single. Ma et al, in "multiple unmanned aerial vehicle task Allocation based on adaptive Firework algorithm" published in electro-optic and control (2018, 25 (01): 37-43, applied the improved adaptive Firework algorithm to unmanned aerial vehicle task Allocation problem, although the algorithm has a faster convergence speed, it is easy to fall into local optimum. The unmanned aerial vehicle task allocation method achieves good effects, but the constraint considered is not comprehensive enough, the solving time is long, and the unmanned aerial vehicle task allocation method is easy to sink into local optimum. Therefore, a new task allocation model and a solution method with high convergence speed, high precision and wide applicability are required to be designed for unmanned aerial vehicle task allocation. Disclosure of Invention The invention aims to solve the technical problems that: the existing unmanned aerial vehicle task allocation method is not comprehensive in constraint consideration, long in solving time and easy to sink into a locally optimal problem. The invention adopts the technical scheme for solving the technical problems: The invention provides an unmanned aerial vehicle disaster relief task allocation method based on a quantum black oligopolistic mechanism, which comprises the following steps: Step one, establishing a multi-unmanned aerial vehicle task allocation model and an objective function of the unmanned aerial vehicle task allocation model; Selecting tasks and initializing quantum black oligopolistic populations; constructing an adaptability function based on an objective function of the unmanned aerial vehicle task allocation model, calculating the adaptability of all black oligopolists and determining a global optimal position; updating quantum rotation angles of all quantum black oligopolishes; step five, calculating the fitness of the updated black oligopolistic and updating the global optimal position; judging whether the maximum iteration times are reached, if yes, terminating iteration, outputting a task allocation matrix of the global optimal position, otherwise, returning to the fourth step to continue iteration; And step seven, judging whether all tasks are distributed and completed, returning to the step two to execute the next task if the tasks are not distributed and outputting an allocation scheme for the unmanned aerial vehicle to execute disaster monitoring, material delivery and rescue effect evaluation tasks if the tasks are distributed and completed. Further, the first step comprises the following steps: A