CN117348424A - Unmanned aerial vehicle group collaborative mapping method and system based on self-adaptive algorithm - Google Patents
Unmanned aerial vehicle group collaborative mapping method and system based on self-adaptive algorithm Download PDFInfo
- Publication number
- CN117348424A CN117348424A CN202311623442.7A CN202311623442A CN117348424A CN 117348424 A CN117348424 A CN 117348424A CN 202311623442 A CN202311623442 A CN 202311623442A CN 117348424 A CN117348424 A CN 117348424A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- task
- mapping
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013507 mapping Methods 0.000 title claims abstract description 156
- 238000000034 method Methods 0.000 title claims abstract description 99
- 230000008569 process Effects 0.000 claims abstract description 53
- 230000011218 segmentation Effects 0.000 claims abstract description 21
- 241000251468 Actinopterygii Species 0.000 claims description 70
- 230000003044 adaptive effect Effects 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 18
- 238000009826 distribution Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 12
- 230000005540 biological transmission Effects 0.000 claims description 10
- 238000007405 data analysis Methods 0.000 claims description 9
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 8
- 230000002265 prevention Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 230000005856 abnormality Effects 0.000 claims description 3
- 239000000969 carrier Substances 0.000 claims description 3
- 230000006870 function Effects 0.000 description 21
- 230000004044 response Effects 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 238000012876 topography Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000019637 foraging behavior Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an unmanned aerial vehicle group collaborative mapping method and system based on a self-adaptive algorithm, which are used in the mapping field, and the method comprises the following steps: performing task segmentation on the mapping task; acquiring parameter information data of the unmanned aerial vehicle, and distributing the most suitable unmanned aerial vehicle and load for each subtask; converting the planning scheme of the optimal flight path into an executed instruction sequence; the unmanned aerial vehicle flies according to the distributed tasks and flight paths, and mapping data are transmitted back to the control center through the wireless mesh network; if the unmanned aerial vehicle encounters an emergency, the standby unmanned aerial vehicle is mobilized through a self-adaptive algorithm, and a task and a flight path are planned again; the control center acquires mapping data transmitted back by all unmanned aerial vehicles, analyzes the mapping data and generates a final mapping result. According to the invention, faults are predicted by two modes of an isolated forest model and a Bayesian network, the precision of fault prediction is improved, and in the task execution process, the task scheduling and the flight path planning are performed dynamically.
Description
Technical Field
The invention relates to the field of mapping, in particular to an unmanned aerial vehicle group collaborative mapping method and system based on a self-adaptive algorithm.
Background
Mapping is an activity based on geography and engineering techniques to measure and represent natural and artificial features of the earth to facilitate the production of maps and other types of products. Its purpose is to obtain an accurate understanding of the geographical environment information. Traditional mapping methods typically collect data manually and then process and sort the data to create detailed maps or models. This approach, while accurate, takes very high time and cost.
In contrast, unmanned mapping is a modern way of obtaining geographic information. Unmanned aerial vehicles can fly over large areas in a short time, acquire information of the ground through a carried camera or other sensors, and then convert the information into a useful map or model through data analysis software. This results in a greatly improved efficiency of the overall mapping process, while also reducing costs.
Current unmanned aerial vehicle operations rely primarily on manual labor, or use preset flight routes. Such modes of operation present significant challenges when faced with complex terrain or large-scale tasks. Unmanned aerial vehicle's communication can meet signal interference and environmental impact problem under the field environment, leads to unable normal operating. Meanwhile, due to hardware limitations of the unmanned aerial vehicle, the single unmanned aerial vehicle may not be able to complete when performing complex tasks. The current trend is therefore to use multiple unmanned aerial vehicles for collaborative work to improve the stability and efficiency of task completion.
In general, unmanned aerial vehicle surveying is a result of the integration of modern technology into traditional surveying methods, which successfully solves many of the problems of traditional surveying methods and has broad application prospects.
However, in the prior art, when the unmanned aerial vehicle fails, manual intervention is generally required to perform fault processing and task rescheduling, which consumes a great amount of time and resources and may cause task delay, various emergencies, such as unstable airflow and abnormal local airflow, may be encountered when the unmanned aerial vehicle performs mapping tasks, the existing scheme often has difficulty in responding to the changes in real time, lacks the capability of dynamically adjusting the flight path and task scheduling, and the existing scheme often lacks accuracy in the aspect of fault prediction of the unmanned aerial vehicle, so that effective response cannot be made in advance when the unmanned aerial vehicle fails.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
In order to overcome the problems, the invention aims to provide an unmanned aerial vehicle group collaborative mapping method and system based on a self-adaptive algorithm, and aims to solve the problems that in the prior art, when an unmanned aerial vehicle breaks down, manual intervention is generally needed to perform fault processing and task re-planning, a large amount of time and resources are consumed undoubtedly, and task delay is possibly caused.
For this purpose, the invention adopts the following specific technical scheme:
according to one aspect of the invention, there is provided an unmanned aerial vehicle group collaborative mapping method based on an adaptive algorithm, the unmanned aerial vehicle group collaborative mapping method comprising the steps of:
s1, performing task segmentation on a mapping task to obtain subtasks with definite input and output requirements;
s2, acquiring parameter information data of the unmanned aerial vehicle, and inputting the parameter information data into a self-adaptive algorithm by combining attribute characteristics and clustering center similarity of the unmanned aerial vehicle and a load scheme set according to task scheduling parameters, so as to allocate the most suitable unmanned aerial vehicle and load for each subtask;
s3, converting the planning scheme of the optimal flight path into an executed instruction sequence, and inputting the instruction sequence into a flight control system of the unmanned aerial vehicle;
s4, the unmanned aerial vehicle flies according to the distributed tasks and flight paths, and in the flight process, the unmanned aerial vehicle collects mapping data by using the loaded mapping equipment according to a set load scheme, and then the mapping data are transmitted back to the control center through a wireless mesh network;
s5, in the task execution process, if the unmanned aerial vehicle encounters an emergency, according to the attribute characteristics of the unmanned aerial vehicle and the similarity of the clustering center, the standby unmanned aerial vehicle is mobilized through a self-adaptive algorithm, and the task and the flight path are re-planned;
S6, the control center acquires mapping data transmitted back by all unmanned aerial vehicles, analyzes the mapping data and generates a final mapping result;
and S7, feeding back according to the mapping result and the execution condition of the unmanned aerial vehicle, adaptively adjusting parameters of the adaptive algorithm, and evaluating the whole process by using a preset index after the mapping task is completed.
Optionally, task segmentation of the mapping task to obtain subtasks with explicit input and output requirements includes the steps of:
s11, analyzing the overall content and the target of the mapping task, and determining the setting requirement of the mapping task;
s12, dividing the whole mapping task into a plurality of subtasks for mapping each small area respectively;
s13, for each subtask, well-defined input and output are defined, wherein the input at least comprises the position and the size of the small area in the mapping task, and the output comprises mapping data of the small area in the mapping task.
Optionally, acquiring parameter information data of the unmanned aerial vehicle, and combining attribute characteristics and cluster center similarity of the unmanned aerial vehicle and a load scheme set according to task scheduling parameters, and inputting the parameter information data into an adaptive algorithm, so that the most suitable unmanned aerial vehicle and load are allocated to each subtask, and the method comprises the following steps:
S21, acquiring parameter information data of each unmanned aerial vehicle, wherein the parameter information data at least comprises flight speed, flight height and endurance time;
s22, dividing the unmanned aerial vehicles into different types by using a clustering algorithm according to the attribute characteristics of the unmanned aerial vehicles, and calculating the similarity between each unmanned aerial vehicle and a clustering center;
s23, setting a load scheme according to task parameters, and constructing an adaptability function of a shoal of fish algorithm;
s24, regarding each subtask as a fish, and determining the initial assignable unmanned aerial vehicle number of each subtask through a shoal of fish algorithm according to the subtask requirements and the fitness function;
s25, according to the similarity between each unmanned aerial vehicle and the subtasks, preferentially distributing the unmanned aerial vehicle to the subtasks which are most matched with the unmanned aerial vehicle;
s26, obtaining an allocation result, and iteratively searching for optimal load scheme allocation by using a shoal of fish algorithm according to the fitness function.
Optionally, regarding each subtask as a fish, determining the initial assignable unmanned aerial vehicle number of each subtask by a shoal of fish algorithm according to the subtask requirements and the fitness function comprises the following steps:
s241, generating an initial fish swarm, wherein each fish represents an initial mapping scheme of a subtask and the unmanned aerial vehicle;
S242, calculating the fitness value of each fish;
s243, iteratively updating the fish shoal through the shoal gathering and rear-end collision of the fish shoal algorithm to continuously optimize the fitness value of the fish shoal;
s244, outputting fish with the highest final fitness value when the iteration number reaches a set condition, acquiring an initial mapping scheme of the optimal task and the unmanned aerial vehicle, and determining the number of unmanned aerial vehicles which can be initially allocated to each subtask;
the formula for calculating the fitness value of each fish is:
；
wherein,
in the method, in the process of the invention,a value representing an fitness function;
representing the number of subtasks;
representing the rate requirements of the subtasks;
indicate->Proportional fairness coefficient for subtasks;
representing the total power constraint in the subtask;
representing subtasks;
indicate->The power sum of the sub-carriers to which the sub-tasks are allocated;
indicate->Subtasks in->Power values on subcarriers;
indicate->Subtasks in->Channel gain on subcarriers.
Optionally, obtaining an allocation result, and iteratively searching for an optimal load scheme allocation by using a fish swarm algorithm according to the fitness function, including the following steps:
s261, acquiring the number of unmanned aerial vehicles which can be initially allocated to each subtask;
s262, constructing an adaptability function of the load scheme, and simultaneously considering the efficiency and fairness of load distribution;
S263, initializing load fish groups, wherein each load fish represents a load scheme;
s264, calculating the fitness value of each load fish, and evaluating the advantages and disadvantages of the load scheme according to the fitness function;
s265, iteratively updating the load fish swarm through the swarm and rear-end collision operation of the fish swarm algorithm, so that the fitness value of the load fish swarm is continuously optimized, and outputting the load fish with the highest fitness value when the iteration termination condition is reached, so as to obtain the optimal load scheme distribution.
Optionally, in the task execution process, if the unmanned aerial vehicle encounters an emergency, according to the attribute characteristics of the unmanned aerial vehicle and the similarity of the clustering center, the standby unmanned aerial vehicle is mobilized through the adaptive algorithm, and the task and the flight path are re-planned, including the following steps:
s51, monitoring the state of the unmanned aerial vehicle in real time in the task execution process, and inputting the condition parameters of the unmanned aerial vehicle into an isolated forest model for fault prediction;
s52, combining the real-time state and the historical fault data of the unmanned aerial vehicle, and predicting the probability of fault occurrence by utilizing a Bayesian network;
s53, detecting the occurrence of an emergency through a sensor and a radar, and analyzing the fault type of the current unmanned aerial vehicle by utilizing an isolated forest model;
S54, comparing the fault type result analyzed by the isolated forest model with the predicted result of the Bayesian network, if the predicted result is consistent, determining the final fault type, otherwise, returning to the step S51;
s55, when the final fault type is achieved, selecting alternative unmanned aerial vehicles by referring to the attribute characteristics of the unmanned aerial vehicles and the similarity of the clustering centers trained in advance, and simultaneously selecting the best standby unmanned aerial vehicle to replace the failed unmanned aerial vehicle by considering the current battery quantity of each alternative unmanned aerial vehicle and the distance between each alternative unmanned aerial vehicle and the failed unmanned aerial vehicle;
s56, after the standby unmanned aerial vehicle is started, reestablishing task configuration by utilizing original task planning and flight path information;
and S57, in the process of continuously executing the task, operating an isolated forest model and a Bayesian network on the unmanned aerial vehicle by utilizing edge calculation, and optimizing task allocation and flight path planning in real time according to the task scheduling parameters of the unmanned aerial vehicle and the attribute characteristics of the unmanned aerial vehicle, thereby realizing dynamic scheduling and fault prevention.
Optionally, in combination with the real-time status and the historical fault data of the unmanned aerial vehicle, the probability prediction of the occurrence of the fault by using the bayesian network comprises the following steps:
S521, collecting real-time state information of the current unmanned aerial vehicle;
s522, collecting historical fault data;
s523, combining the real-time state information and the historical fault data to serve as input data of the Bayesian network;
s524, initializing a Bayesian network, and presetting prior probability in each node in the network;
s525, when the unmanned aerial vehicle executes a task, the collected real-time state data is used as an observation value to be input into a network, and the state of the network is updated;
s526, running a Bayesian inference algorithm, and updating probability distribution of each node in the network according to the provided observation data;
s527, checking the probability value of the node related to the fault, and predicting the occurrence probability of the fault.
Optionally, detecting occurrence of an emergency event by a sensor and a radar, and analyzing the fault type of the current unmanned aerial vehicle by using an isolated forest model includes the following steps:
s531, setting a sensor and a radar of the unmanned aerial vehicle, and monitoring the flight state and the surrounding environment in real time;
s532, when the sensor and the radar detect abnormal signals or sudden changes, determining that an emergency occurs;
s533, collecting navigation data of the unmanned aerial vehicle, environment data acquired by a sensor and associated data of the type of the emergent event;
S534, extracting feature data of the associated data, and inputting the feature data into the isolated forest model to obtain an anomaly score;
s535, judging the fault type of the unmanned aerial vehicle according to the magnitude of the abnormality score.
Optionally, in the process of continuously executing the task, the edge calculation is utilized to operate an isolated forest model and a Bayesian network on the unmanned aerial vehicle, and the task allocation and the flight path planning are optimized in real time according to the task scheduling parameters of the unmanned aerial vehicle and the attribute characteristics of the unmanned aerial vehicle, so that the dynamic scheduling and the fault prevention are realized, and the method comprises the following steps:
s571, an edge calculation function on the unmanned aerial vehicle is used, and an isolated forest model and a Bayesian network are operated on the unmanned aerial vehicle at the same time, so that network delay is reduced;
s572, collecting task scheduling parameters and attribute characteristic data of the unmanned aerial vehicle in real time in the process of executing tasks by the unmanned aerial vehicle;
s573, analyzing the collected parameters and characteristic data in real time through an isolated forest model and a Bayesian network to obtain the current state and the occurrence risk of the unmanned aerial vehicle;
s574, performing dynamic scheduling of tasks according to the data analysis result, and if the model predicts faults which occur in the future, adjusting the scheduling in advance to avoid the influence of the faults on the tasks;
And S575, optimizing the flight path of the unmanned aerial vehicle in real time according to the data analysis result, and planning the flight path in advance to avoid a small area if the model predicts that a fault or risk occurs in a small area.
According to another aspect of the present invention, there is also provided an adaptive algorithm-based unmanned aerial vehicle group collaborative mapping system, the system comprising: the system comprises a task segmentation module, a task allocation module, an instruction sequence generation module, a mapping data transmission module, a fault processing and standby unmanned aerial vehicle scheduling module, a mapping result generation module and an evaluation module;
the task segmentation module is connected with the instruction sequence generation module through the task distribution module, the instruction sequence generation module is connected with the fault processing and standby unmanned aerial vehicle dispatching module through the mapping data transmission module, and the fault processing and standby unmanned aerial vehicle dispatching module is connected with the evaluation module through the mapping result generation module;
the task segmentation module is used for carrying out task segmentation on the mapping task to obtain subtasks with definite input and output requirements;
the task allocation module is used for acquiring parameter information data of the unmanned aerial vehicle, combining attribute characteristics and clustering center similarity of the unmanned aerial vehicle and a load scheme set according to task scheduling parameters, and inputting the parameter information data into the self-adaptive algorithm so as to allocate the most suitable unmanned aerial vehicle and load for each subtask;
The instruction sequence generation module is used for converting the planning scheme of the optimal flight path into an executable instruction sequence and inputting the executable instruction sequence into a flight control system of the unmanned aerial vehicle;
the unmanned aerial vehicle is used for acquiring mapping data by using the loaded mapping equipment in the flight process according to the assigned task and the flight path, and then transmitting the mapping data back to the control center through the wireless mesh network;
the fault processing and standby unmanned aerial vehicle scheduling module is used for scheduling a standby unmanned aerial vehicle through a self-adaptive algorithm according to the attribute characteristics of the unmanned aerial vehicle and the similarity of a clustering center if the unmanned aerial vehicle encounters an emergency in the task execution process, and re-planning the task and the flight path;
the mapping result generation module is used for acquiring mapping data transmitted back by all unmanned aerial vehicles by the control center, analyzing the mapping data and generating a final mapping result;
the evaluation module is used for feeding back according to the mapping result and the execution condition of the unmanned aerial vehicle, adaptively adjusting the parameters of the adaptive algorithm, and evaluating the whole process by using a preset index after the mapping task is completed.
Compared with the prior art, the application has the following beneficial effects:
1. the whole implementation method is self-adaptive, which means that the method can be flexibly adjusted according to actual task demands and performance characteristics of the unmanned aerial vehicle, the use efficiency and task completion quality of the unmanned aerial vehicle are greatly improved, secondly, the method introduces concepts of fitness functions and data schemes, so that the system can comprehensively evaluate pairing schemes of each unmanned aerial vehicle and tasks according to various factors, the optimal scheme is selected, the overall utilization rate of resources is improved, furthermore, iterative search is performed by using a fish swarm algorithm, so that the satisfactory solution can be quickly found in a complex search space, finally, the method not only considers the execution efficiency, but also considers fairness, and has important significance in the aspects of guaranteeing the working pressure distribution balance of each unmanned aerial vehicle, improving the sustainability of the unmanned aerial vehicle for long-term use, and the like.
2. In the process of executing the task, the unmanned aerial vehicle monitors the state of the unmanned aerial vehicle in real time, if the unmanned aerial vehicle fails, the unmanned aerial vehicle can immediately process and re-plan the task, when the unmanned aerial vehicle fails, the most suitable standby unmanned aerial vehicle can be quickly selected according to the attribute characteristics and the similarity of the pre-trained clustering center, one-by-one comparison is not needed, and the comprehensive evaluation can be carried out according to the current battery quantity and the distance, so that the failure processing efficiency is improved.
3. According to the invention, the fault is predicted by two modes of an isolated forest model and a Bayesian network, the precision of fault prediction can be improved, and in the task execution process, dynamic task scheduling and flight path planning are performed according to real-time task scheduling parameters and flight path information, so that the method is suitable for different flight environments.
4. According to the invention, through edge calculation, the unmanned aerial vehicle can locally operate an isolated forest model and a Bayesian network, so that network delay is reduced, the rapid response capability to faults is improved, the unmanned aerial vehicle can dynamically adjust the flight path according to the current flight environment and the real-time unmanned aerial vehicle state, and the anti-interference capability and adaptability to various emergencies are enhanced.
Drawings
The above features, features and advantages of the present invention, as well as the manner of attaining them and method of attaining them, will become more apparent and the invention will be better understood by reference to the following description of embodiments, taken in conjunction with the accompanying drawings. Here shown in schematic diagram:
fig. 1 is a flow chart of an unmanned aerial vehicle group collaborative mapping method based on an adaptive algorithm according to an embodiment of the present invention;
fig. 2 is a functional block diagram of a unmanned aerial vehicle crowd collaborative mapping system based on an adaptive algorithm in accordance with an embodiment of the present invention.
In the figure:
1. a task segmentation module; 2. a task allocation module; 3. an instruction sequence generation module; 4. a mapping data transmission module; 5. a fault processing and standby unmanned aerial vehicle scheduling module; 6. a mapping result generation module; 7. and an evaluation module.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will clearly and completely describe the technical solution in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
According to the embodiment of the invention, an unmanned aerial vehicle group collaborative mapping method and system based on an adaptive algorithm are provided.
The invention will be further described with reference to the accompanying drawings and detailed description, as shown in fig. 1, according to an embodiment of the invention, there is provided an unmanned aerial vehicle group collaborative mapping method based on an adaptive algorithm, the unmanned aerial vehicle group collaborative mapping method including the following steps:
S1, performing task segmentation on a mapping task to obtain subtasks with clear input and output requirements.
Preferably, the task segmentation of the mapping task, resulting in subtasks with explicit input and output requirements, comprises the steps of:
s11, analyzing the overall content and the target of the mapping task, and determining the setting requirement of the mapping task;
s12, dividing the whole mapping task into a plurality of subtasks for mapping each small area respectively;
s13, for each subtask, well-defined input and output are defined, wherein the input at least comprises the position and the size of the small area in the mapping task, and the output comprises mapping data of the small area in the mapping task.
It should be explained that in the task design of the unmanned aerial vehicle mapping system, not only the inherent factors such as topography and topography are considered, but also various variables such as weather, illumination and unmanned aerial vehicle performance are concerned. Therefore, the task segmentation and definition process needs to make intelligent and flexible mapping strategies by using a geographic information system technology, including task priority, unmanned aerial vehicle performance selection, emergency response and other settings. Therefore, the surveying efficiency can be effectively improved, the possibility of errors is reduced, and the surveying efficiency is a key step for constructing a stable and high-quality unmanned aerial vehicle surveying system.
S2, acquiring parameter information data of the unmanned aerial vehicle, and inputting the parameter information data into a self-adaptive algorithm by combining attribute characteristics and clustering center similarity of the unmanned aerial vehicle and a load scheme set according to task scheduling parameters, so that the most suitable unmanned aerial vehicle and load are distributed for each subtask.
Preferably, the method comprises the steps of acquiring parameter information data of the unmanned aerial vehicle, combining attribute characteristics and cluster center similarity of the unmanned aerial vehicle and a load scheme set according to task scheduling parameters, and inputting the parameter information data into a self-adaptive algorithm, so that the most suitable unmanned aerial vehicle and load are distributed for each subtask, and the method comprises the following steps:
s21, acquiring parameter information data of each unmanned aerial vehicle, wherein the parameter information data at least comprises flight speed, flight height and endurance time;
s22, dividing the unmanned aerial vehicles into different types by using a clustering algorithm according to the attribute characteristics of the unmanned aerial vehicles, and calculating the similarity between each unmanned aerial vehicle and a clustering center;
s23, setting a load scheme according to task parameters, and constructing an adaptability function of a shoal of fish algorithm;
s24, regarding each subtask as a fish, and determining the initial assignable unmanned aerial vehicle number of each subtask through a shoal of fish algorithm according to the subtask requirements and the fitness function;
S25, according to the similarity between each unmanned aerial vehicle and the subtasks, preferentially distributing the unmanned aerial vehicle to the subtasks which are most matched with the unmanned aerial vehicle;
s26, obtaining an allocation result, and iteratively searching for optimal load scheme allocation by using a shoal of fish algorithm according to the fitness function.
Preferably, regarding each subtask as a fish, determining the initial assignable unmanned aerial vehicle number of each subtask by a shoal of fish algorithm according to the subtask requirements and fitness function comprises the following steps:
s241, generating an initial fish swarm, wherein each fish represents an initial mapping scheme of a subtask and the unmanned aerial vehicle;
s242, calculating the fitness value of each fish;
s243, iteratively updating the fish shoal through the shoal gathering and rear-end collision of the fish shoal algorithm to continuously optimize the fitness value of the fish shoal;
s244, outputting fish with the highest final fitness value when the iteration number reaches a set condition, acquiring an initial mapping scheme of the optimal task and the unmanned aerial vehicle, and determining the number of unmanned aerial vehicles which can be initially allocated to each subtask;
the formula for calculating the fitness value of each fish is:
；
wherein,
in the method, in the process of the invention,a value representing an fitness function;
representing the number of subtasks;
representing the rate requirements of the subtasks;
indicate- >Proportional fairness coefficient for subtasks;
representing the total power constraint in the subtask;
representing subtasks;
indicate->The power sum of the sub-carriers to which the sub-tasks are allocated;
indicate->Subtasks in->Power values on subcarriers;
indicate->Subtasks in->Channel gain on subcarriers.
Preferably, obtaining an allocation result, and iteratively searching for an optimal load scheme allocation by using a shoal of fish algorithm according to a fitness function, wherein the allocation method comprises the following steps:
s261, acquiring the number of unmanned aerial vehicles which can be initially allocated to each subtask;
s262, constructing an adaptability function of the load scheme, and simultaneously considering the efficiency and fairness of load distribution;
s263, initializing load fish groups, wherein each load fish represents a load scheme;
s264, calculating the fitness value of each load fish, and evaluating the advantages and disadvantages of the load scheme according to the fitness function;
s265, iteratively updating the load fish swarm through the swarm and rear-end collision operation of the fish swarm algorithm, so that the fitness value of the load fish swarm is continuously optimized, and outputting the load fish with the highest fitness value when the iteration termination condition is reached, so as to obtain the optimal load scheme distribution.
It should be explained that, in the mapping task using the unmanned aerial vehicle, the sub-task allocation and the unmanned aerial vehicle matching adopt an adaptive algorithm, such as a shoal of fish algorithm used herein, the shoal of fish algorithm is a heuristic optimization algorithm, and solves the problem by simulating the fish foraging behavior, the clustering behavior, the rear-end collision behavior and the like according to a certain fitness function.
S3, converting the planning scheme of the optimal flight path into an executed instruction sequence, and inputting the instruction sequence into a flight control system of the unmanned aerial vehicle.
It should be explained that in the flight control of the unmanned aerial vehicle, the optimal flight path planning is a critical ring, which not only relates to how fast and accurately the unmanned aerial vehicle reaches the target position, but also relates to how effectively to avoid obstacles in the flight process, such as buildings, wires, trees, etc., the optimal flight path planning scheme generally needs to consider various factors, including performance parameters, flight environment, flight tasks, etc. of the unmanned aerial vehicle, the planned flight path needs to be converted into a series of flight instructions, and the instructions can be sent into the flight control system of the unmanned aerial vehicle to control the unmanned aerial vehicle to fly according to the predetermined path, and the accuracy of the step directly relates to the completion quality of the mapping task and the safety of the unmanned aerial vehicle.
S4, the unmanned aerial vehicle flies according to the distributed tasks and flight paths, and in the flight process, according to a set load scheme, the unmanned aerial vehicle collects mapping data by using the loaded mapping equipment, and then the mapping data are transmitted back to the control center through the wireless mesh network.
It should be explained that, in the unmanned aerial vehicle mapping system, unmanned aerial vehicle can fly according to the preset flight path, in the flight process, unmanned aerial vehicle utilizes the mapping equipment that it loaded to gather required mapping data, for example, the camera captures geographic information, radar equipment acquires topography data etc., the collection of these data can be usually carried out according to the preset loading scheme, in order to guarantee the degree of accuracy and the integrality of data, afterwards, the mapping data that obtains can be transmitted back to control center through wireless mesh network, it is worth noting that mesh network provides good network coverage for heterogeneous unmanned aerial vehicle, guaranteed data transmission's stability and instantaneity, it is significant to unmanned aerial vehicle control and the completion of mapping data analysis work.
S5, in the task execution process, if the unmanned aerial vehicle encounters an emergency, the standby unmanned aerial vehicle is mobilized through the self-adaptive algorithm according to the attribute characteristics of the unmanned aerial vehicle and the similarity of the clustering center, and the task and the flight path are planned again.
Preferably, in the task execution process, if the unmanned aerial vehicle encounters an emergency, according to the attribute characteristics of the unmanned aerial vehicle and the similarity of the clustering center, the standby unmanned aerial vehicle is mobilized through the adaptive algorithm, and the task and the flight path are re-planned, including the following steps:
S51, monitoring the state of the unmanned aerial vehicle in real time in the task execution process, and inputting the condition parameters of the unmanned aerial vehicle into an isolated forest model for fault prediction;
s52, combining the real-time state and the historical fault data of the unmanned aerial vehicle, and predicting the probability of fault occurrence by utilizing a Bayesian network;
s53, detecting the occurrence of an emergency through a sensor and a radar, and analyzing the fault type of the current unmanned aerial vehicle by utilizing an isolated forest model;
s54, comparing the fault type result analyzed by the isolated forest model with the predicted result of the Bayesian network, if the predicted result is consistent, determining the final fault type, otherwise, returning to the step S51;
s55, when the final fault type is achieved, selecting alternative unmanned aerial vehicles by referring to the attribute characteristics of the unmanned aerial vehicles and the similarity of the clustering centers trained in advance, and simultaneously selecting the best standby unmanned aerial vehicle to replace the failed unmanned aerial vehicle by considering the current battery quantity of each alternative unmanned aerial vehicle and the distance between each alternative unmanned aerial vehicle and the failed unmanned aerial vehicle;
s56, after the standby unmanned aerial vehicle is started, reestablishing task configuration by utilizing original task planning and flight path information;
and S57, in the process of continuously executing the task, operating an isolated forest model and a Bayesian network on the unmanned aerial vehicle by utilizing edge calculation, and optimizing task allocation and flight path planning in real time according to the task scheduling parameters of the unmanned aerial vehicle and the attribute characteristics of the unmanned aerial vehicle, thereby realizing dynamic scheduling and fault prevention.
Preferably, the probability prediction of the occurrence of a fault by using a bayesian network in combination with real-time status and historical fault data of the unmanned aerial vehicle comprises the steps of:
s521, collecting real-time state information of the current unmanned aerial vehicle;
s522, collecting historical fault data;
s523, combining the real-time state information and the historical fault data to serve as input data of the Bayesian network;
s524, initializing a Bayesian network, and presetting prior probability in each node in the network;
s525, when the unmanned aerial vehicle executes a task, the collected real-time state data is used as an observation value to be input into a network, and the state of the network is updated;
s526, running a Bayesian inference algorithm, and updating probability distribution of each node in the network according to the provided observation data;
s527, checking the probability value of the node related to the fault, and predicting the occurrence probability of the fault.
Specifically, various emergency conditions, such as equipment failure, weather changes, flight obstacles, etc., may be encountered during the flight task execution of the unmanned aerial vehicle, which requires that we monitor the unmanned aerial vehicle's state in real time and make corresponding adjustments quickly, and in this process, two important models are used: the method comprises the steps of combining results of an isolated forest model and a Bayesian network, wherein the isolated forest model is used for rapidly detecting possible fault states of the unmanned aerial vehicle, the Bayesian network is used for predicting the possibility of occurrence of faults, and by means of the results of the two models, faults of the unmanned aerial vehicle can be found and confirmed as early as possible, then, the standby unmanned aerial vehicle which is most suitable for replacement is rapidly selected according to the attribute characteristics of the unmanned aerial vehicle and the similarity of a clustering center, and task allocation and flight path planning are rapidly carried out again by utilizing original task planning and flight path information.
Preferably, detecting occurrence of an emergency event by a sensor and a radar, and analyzing the fault type of the current unmanned aerial vehicle by using an isolated forest model comprises the following steps:
s531, setting a sensor and a radar of the unmanned aerial vehicle, and monitoring the flight state and the surrounding environment in real time;
s532, when the sensor and the radar detect abnormal signals or sudden changes, determining that an emergency occurs;
s533, collecting navigation data of the unmanned aerial vehicle, environment data acquired by a sensor and associated data of the type of the emergent event;
s534, extracting feature data of the associated data, and inputting the feature data into the isolated forest model to obtain an anomaly score;
s535, judging the fault type of the unmanned aerial vehicle according to the magnitude of the abnormality score.
Preferably, in the process of continuously executing the task, the edge calculation is utilized to run an isolated forest model and a Bayesian network on the unmanned aerial vehicle, and the task allocation and the flight path planning are optimized in real time according to the task scheduling parameters of the unmanned aerial vehicle and the attribute characteristics of the unmanned aerial vehicle, so that the dynamic scheduling and the fault prevention are realized, and the method comprises the following steps:
s571, an edge calculation function on the unmanned aerial vehicle is used, and an isolated forest model and a Bayesian network are operated on the unmanned aerial vehicle at the same time, so that network delay is reduced;
S572, collecting task scheduling parameters and attribute characteristic data of the unmanned aerial vehicle in real time in the process of executing tasks by the unmanned aerial vehicle;
s573, analyzing the collected parameters and characteristic data in real time through an isolated forest model and a Bayesian network to obtain the current state and the occurrence risk of the unmanned aerial vehicle;
s574, performing dynamic scheduling of tasks according to the data analysis result, and if the model predicts faults which occur in the future, adjusting the scheduling in advance to avoid the influence of the faults on the tasks;
and S575, optimizing the flight path of the unmanned aerial vehicle in real time according to the data analysis result, and planning the flight path in advance to avoid a small area if the model predicts that a fault or risk occurs in a small area.
It should be explained that the state monitoring and emergency processing of the unmanned aerial vehicle in the flight process are a key ring, and the collection of real-time states, including the speed, the altitude, the position, the electric quantity and the like of the unmanned aerial vehicle, can help us to know the instant situation of the unmanned aerial vehicle, historical fault data, such as what type of faults occur in the past, the environmental conditions of the faults, can help us to predict the faults which may occur in the future, and these information are input into a bayesian network, so that the probability of the faults occurring in the future can be calculated.
Meanwhile, the unmanned aerial vehicle sensor and radar detect the information of the environment, promote the unmanned aerial vehicle to sense and make appropriate reaction, these data input to the isolated forest model when the incident appears, can analyze the current fault type of the unmanned aerial vehicle.
Finally, through edge calculation, the models can be operated on the unmanned aerial vehicle, data are analyzed in real time and react, so that transmission delay can be reduced, accuracy of real-time decision making is improved, the unmanned aerial vehicle can realize dynamic scheduling of tasks, faults are avoided, and the flight path is optimized in real time under the guidance of data analysis, and the operations are all for improving the working efficiency of the unmanned aerial vehicle and the capability of the unmanned aerial vehicle for coping with emergency events, so that the completion quality and safety of mapping tasks are improved.
And S6, the control center acquires mapping data transmitted back by all unmanned aerial vehicles, analyzes the mapping data and generates a final mapping result.
It should be explained that, in the unmanned aerial vehicle mapping task, the control center plays a vital role in acquiring and analyzing mapping data, all unmanned aerial vehicles transmit collected data such as photos, videos, humiture and other environmental information back to the control center in real time in the task execution process, the data are often large in quantity and high in accuracy, and can provide valuable information for map updating, land measurement, environmental monitoring and the like, the control center can process and analyze the mapping data by using special analysis software, and the process may comprise the steps of data cleaning, data fusion, data analysis, data visualization and the like so as to extract the most important information and generate final mapping results in a geographic information system, and the results have huge application value to the fields of urban planning, disaster response, scientific research and the like.
And S7, feeding back according to the mapping result and the execution condition of the unmanned aerial vehicle, adaptively adjusting parameters of the adaptive algorithm, and evaluating the whole process by using a preset index after the mapping task is completed.
It should be explained that this step embodies the adaptation and learning capabilities of the intelligent control system, which is of great importance in modern unmanned aerial vehicle mapping control. According to the mapping result and feedback of the unmanned aerial vehicle execution task condition, the control system can finely adjust the self-adaptive algorithm parameters so as to improve the performance and efficiency of the unmanned aerial vehicle in future tasks. For example, if the drone is performing poorly in a particular climate, the system may adjust parameters to improve its performance in a similar environment. In addition, the control system may also set a series of predetermined indicators, such as task execution time, data accuracy, equipment failure rate, etc., to evaluate the performance of the entire mapping process. This can further help the system understand the performance status of the drone, discover potential problems, and continue to improve the task performance capabilities of the drone.
According to another embodiment of the present invention, as shown in fig. 2, there is also provided an adaptive algorithm-based unmanned aerial vehicle group collaborative mapping system, the system including: the system comprises a task segmentation module 1, a task allocation module 2, an instruction sequence generation module 3, a mapping data transmission module 4, a fault processing and standby unmanned aerial vehicle scheduling module 5, a mapping result generation module 6 and an evaluation module 7;
The task segmentation module 1 is connected with the instruction sequence generation module 3 through the task distribution module 2, the instruction sequence generation module 3 is connected with the fault processing and standby unmanned aerial vehicle dispatching module 5 through the mapping data transmission module 4, and the fault processing and standby unmanned aerial vehicle dispatching module 5 is connected with the evaluation module 7 through the mapping result generation module 6;
the task segmentation module 1 is used for carrying out task segmentation on the mapping task to obtain subtasks with definite input and output requirements;
the task allocation module 2 is used for acquiring parameter information data of the unmanned aerial vehicle, combining attribute characteristics and clustering center similarity of the unmanned aerial vehicle and a load scheme set according to task scheduling parameters, and inputting the parameter information data into the self-adaptive algorithm so as to allocate the most suitable unmanned aerial vehicle and load for each subtask;
the instruction sequence generating module 3 is used for converting the planning scheme of the optimal flight path into an executable instruction sequence and inputting the executable instruction sequence into a flight control system of the unmanned aerial vehicle;
the mapping data transmission module 4 is used for the unmanned aerial vehicle to fly according to the distributed tasks and flight paths, and in the flight process, according to a set load scheme, the unmanned aerial vehicle collects mapping data by using the loaded mapping equipment, and then the mapping data is transmitted back to the control center through the wireless mesh network;
The fault processing and standby unmanned aerial vehicle dispatching module 5 is used for dispatching the standby unmanned aerial vehicle through a self-adaptive algorithm according to the attribute characteristics of the unmanned aerial vehicle and the similarity of the clustering center if the unmanned aerial vehicle encounters an emergency in the task execution process, and re-planning the task and the flight path;
the mapping result generation module 6 is used for acquiring mapping data transmitted back by all unmanned aerial vehicles by the control center, analyzing the mapping data and generating a final mapping result;
and the evaluation module 7 is used for feeding back according to the mapping result and the execution condition of the unmanned aerial vehicle, adaptively adjusting the parameters of the adaptive algorithm, and evaluating the whole process by using a preset index after the mapping task is completed.
In summary, by means of the above technical solution of the present invention, the whole implementation method is self-adaptive, which means that the implementation method can be flexibly adjusted according to actual task demands and performance characteristics of the unmanned aerial vehicle, which greatly improves the use efficiency and task completion quality of the unmanned aerial vehicle, and secondly, the system introduces concepts of fitness functions and data schemes, which enables the system to comprehensively evaluate pairing schemes of each unmanned aerial vehicle and task according to various factors, thereby selecting an optimal scheme, improving the overall utilization rate of resources, and furthermore, iterative search is performed by using a fish swarm algorithm, so that the system can quickly find a satisfactory solution in a complex search space, and finally, the method considers not only the execution efficiency, but also fairness, which has important significance in terms of guaranteeing the work pressure distribution balance of each unmanned aerial vehicle, improving the sustainability of the unmanned aerial vehicle for long-term use, etc.; according to the unmanned aerial vehicle, the state of the unmanned aerial vehicle is monitored in real time in the task execution process, if faults occur, the unmanned aerial vehicle can be immediately processed and re-planned in the task, when the unmanned aerial vehicle has faults, the most suitable standby unmanned aerial vehicle can be quickly selected according to the attribute characteristics and the similarity of the pre-trained clustering center of the unmanned aerial vehicle, one-by-one comparison is not needed, the comprehensive evaluation can be carried out according to the current battery quantity and distance, the efficiency of fault processing is improved, the faults can be predicted in two modes of an isolated forest model and a Bayesian network, the precision of fault prediction can be improved, dynamic task scheduling and flight path planning can be carried out according to real-time task scheduling parameters and flight path information in the task execution process, different flight environments are adapted, the unmanned aerial vehicle can locally operate the isolated model and the Bayesian network through forest edge calculation, the network delay is reduced, the quick response capability to the faults is improved, the anti-interference capability and the adaptability to various sudden events are enhanced.
Although the invention has been described with respect to the preferred embodiments, the embodiments are for illustrative purposes only and are not intended to limit the invention, as those skilled in the art will appreciate that various modifications can be made without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. The unmanned aerial vehicle group collaborative mapping method based on the self-adaptive algorithm is characterized by comprising the following steps of:
s1, performing task segmentation on a mapping task to obtain subtasks with definite input and output requirements;
s2, acquiring parameter information data of the unmanned aerial vehicle, and inputting the parameter information data into a self-adaptive algorithm by combining attribute characteristics and clustering center similarity of the unmanned aerial vehicle and a load scheme set according to task scheduling parameters, so as to allocate the most suitable unmanned aerial vehicle and load for each subtask;
s3, converting the planning scheme of the optimal flight path into an executed instruction sequence, and inputting the instruction sequence into a flight control system of the unmanned aerial vehicle;
s4, the unmanned aerial vehicle flies according to the distributed tasks and flight paths, and in the flight process, the unmanned aerial vehicle collects mapping data by using the loaded mapping equipment according to a set load scheme, and then the mapping data are transmitted back to the control center through a wireless mesh network;
S5, in the task execution process, if the unmanned aerial vehicle encounters an emergency, according to the attribute characteristics of the unmanned aerial vehicle and the similarity of the clustering center, the standby unmanned aerial vehicle is mobilized through a self-adaptive algorithm, and the task and the flight path are re-planned;
s6, the control center acquires mapping data transmitted back by all unmanned aerial vehicles, analyzes the mapping data and generates a final mapping result;
and S7, feeding back according to the mapping result and the execution condition of the unmanned aerial vehicle, adaptively adjusting parameters of the adaptive algorithm, and evaluating the whole process by using a preset index after the mapping task is completed.
2. The unmanned aerial vehicle group collaborative mapping method based on the adaptive algorithm according to claim 1, wherein the task segmentation of the mapping task to obtain subtasks with explicit input and output requirements comprises the steps of:
s11, analyzing the overall content and the target of the mapping task, and determining the setting requirement of the mapping task;
s12, dividing the whole mapping task into a plurality of subtasks for mapping each small area respectively;
s13, for each subtask, well-defined input and output are defined, wherein the input at least comprises the position and the size of the small area in the mapping task, and the output comprises mapping data of the small area in the mapping task.
3. The unmanned aerial vehicle group collaborative mapping method based on the adaptive algorithm according to claim 1, wherein the acquiring of the unmanned aerial vehicle parameter information data, the combination of the unmanned aerial vehicle attribute characteristics and the cluster center similarity and the load scheme set according to the task scheduling parameters, the input to the adaptive algorithm, so as to allocate the most suitable unmanned aerial vehicle and load for each subtask comprises the following steps:
s21, acquiring parameter information data of each unmanned aerial vehicle, wherein the parameter information data at least comprises flight speed, flight height and endurance time;
s22, dividing the unmanned aerial vehicles into different types by using a clustering algorithm according to the attribute characteristics of the unmanned aerial vehicles, and calculating the similarity between each unmanned aerial vehicle and a clustering center;
s23, setting a load scheme according to task parameters, and constructing an adaptability function of a shoal of fish algorithm;
s24, regarding each subtask as a fish, and determining the initial assignable unmanned aerial vehicle number of each subtask through a shoal of fish algorithm according to the subtask requirements and the fitness function;
s25, according to the similarity between each unmanned aerial vehicle and the subtasks, preferentially distributing the unmanned aerial vehicle to the subtasks which are most matched with the unmanned aerial vehicle;
s26, obtaining an allocation result, and iteratively searching for optimal load scheme allocation by using a shoal of fish algorithm according to the fitness function.
4. A method of collaborative mapping of unmanned aerial vehicle clusters based on adaptive algorithms according to claim 3, wherein the determining the initial assignable unmanned aerial vehicle number for each subtask by the shoal algorithm based on the subtask requirements and fitness function by treating each subtask as a fish comprises the steps of:
s241, generating an initial fish swarm, wherein each fish represents an initial mapping scheme of a subtask and the unmanned aerial vehicle;
s242, calculating the fitness value of each fish;
s243, iteratively updating the fish shoal through the shoal gathering and rear-end collision of the fish shoal algorithm to continuously optimize the fitness value of the fish shoal;
s244, outputting fish with the highest final fitness value when the iteration number reaches a set condition, acquiring an initial mapping scheme of the optimal task and the unmanned aerial vehicle, and determining the number of unmanned aerial vehicles which can be initially allocated to each subtask;
the formula for calculating the fitness value of each fish is as follows:
；
wherein,
in the method, in the process of the invention,a value representing an fitness function;
representing the number of subtasks;
representing the rate requirements of the subtasks;
indicate->Proportional fairness coefficient for subtasks;
representing the total power constraint in the subtask;
representing subtasks;
indicate->The power sum of the sub-carriers to which the sub-tasks are allocated;
Indicate->Subtasks in->Power values on subcarriers;
indicate->Subtasks in->Channel gain on subcarriers.
5. The unmanned aerial vehicle group collaborative mapping method based on the adaptive algorithm according to claim 4, wherein the steps of obtaining the allocation result and iteratively searching for optimal load scheme allocation by using the fish swarm algorithm according to the fitness function comprise the following steps:
s261, acquiring the number of unmanned aerial vehicles which can be initially allocated to each subtask;
s262, constructing an adaptability function of the load scheme, and simultaneously considering the efficiency and fairness of load distribution;
s263, initializing load fish groups, wherein each load fish represents a load scheme;
s264, calculating the fitness value of each load fish, and evaluating the advantages and disadvantages of the load scheme according to the fitness function;
s265, iteratively updating the load fish swarm through the swarm and rear-end collision operation of the fish swarm algorithm, so that the fitness value of the load fish swarm is continuously optimized, and outputting the load fish with the highest fitness value when the iteration termination condition is reached, so as to obtain the optimal load scheme distribution.
6. The unmanned aerial vehicle group collaborative mapping method based on the adaptive algorithm according to claim 1, wherein in the task execution process, if the unmanned aerial vehicle encounters an emergency, the unmanned aerial vehicle is mobilized for standby by the adaptive algorithm according to the attribute characteristics of the unmanned aerial vehicle and the similarity of the clustering center, and the task and the flight path are re-planned, comprising the following steps:
S51, monitoring the state of the unmanned aerial vehicle in real time in the task execution process, and inputting the condition parameters of the unmanned aerial vehicle into an isolated forest model for fault prediction;
s52, combining the real-time state and the historical fault data of the unmanned aerial vehicle, and predicting the probability of fault occurrence by utilizing a Bayesian network;
s53, detecting the occurrence of an emergency through a sensor and a radar, and analyzing the fault type of the current unmanned aerial vehicle by utilizing an isolated forest model;
s54, comparing the fault type result analyzed by the isolated forest model with the predicted result of the Bayesian network, if the predicted result is consistent, determining the final fault type, otherwise, returning to the step S51;
s55, when the final fault type is achieved, selecting alternative unmanned aerial vehicles by referring to the attribute characteristics of the unmanned aerial vehicles and the similarity of the clustering centers trained in advance, and simultaneously selecting the best standby unmanned aerial vehicle to replace the failed unmanned aerial vehicle by considering the current battery quantity of each alternative unmanned aerial vehicle and the distance between each alternative unmanned aerial vehicle and the failed unmanned aerial vehicle;
s56, after the standby unmanned aerial vehicle is started, reestablishing task configuration by utilizing original task planning and flight path information;
and S57, in the process of continuously executing the task, operating an isolated forest model and a Bayesian network on the unmanned aerial vehicle by utilizing edge calculation, and optimizing task allocation and flight path planning in real time according to the task scheduling parameters of the unmanned aerial vehicle and the attribute characteristics of the unmanned aerial vehicle, thereby realizing dynamic scheduling and fault prevention.
7. The unmanned aerial vehicle group collaborative mapping method according to claim 6, wherein the probability prediction of fault occurrence by utilizing a bayesian network by combining real-time status and historical fault data of unmanned aerial vehicles comprises the steps of:
s521, collecting real-time state information of the current unmanned aerial vehicle;
s522, collecting historical fault data;
s523, combining the real-time state information and the historical fault data to serve as input data of the Bayesian network;
s524, initializing a Bayesian network, and presetting prior probability in each node in the network;
s525, when the unmanned aerial vehicle executes a task, the collected real-time state data is used as an observation value to be input into a network, and the state of the network is updated;
s526, running a Bayesian inference algorithm, and updating probability distribution of each node in the network according to the provided observation data;
s527, checking the probability value of the node related to the fault, and predicting the occurrence probability of the fault.
8. The unmanned aerial vehicle group collaborative mapping method based on the adaptive algorithm according to claim 7, wherein the detecting the occurrence of an emergency event by a sensor and a radar and analyzing the fault type of the current unmanned aerial vehicle by using an isolated forest model comprises the following steps:
S531, setting a sensor and a radar of the unmanned aerial vehicle, and monitoring the flight state and the surrounding environment in real time;
s532, when the sensor and the radar detect abnormal signals or sudden changes, determining that an emergency occurs;
s533, collecting navigation data of the unmanned aerial vehicle, environment data acquired by a sensor and associated data of the type of the emergent event;
s534, extracting feature data of the associated data, and inputting the feature data into the isolated forest model to obtain an anomaly score;
s535, judging the fault type of the unmanned aerial vehicle according to the magnitude of the abnormality score.
9. The unmanned aerial vehicle group collaborative mapping method based on the adaptive algorithm according to claim 8, wherein in the process of continuously executing the task, an isolated forest model and a bayesian network are operated on the unmanned aerial vehicle by utilizing edge calculation, and task allocation and flight path planning are optimized in real time according to task scheduling parameters of the unmanned aerial vehicle and attribute characteristics of the unmanned aerial vehicle, so that dynamic scheduling and fault prevention are realized, and the method comprises the following steps:
s571, an edge calculation function on the unmanned aerial vehicle is used, and an isolated forest model and a Bayesian network are operated on the unmanned aerial vehicle at the same time, so that network delay is reduced;
S572, collecting task scheduling parameters and attribute characteristic data of the unmanned aerial vehicle in real time in the process of executing tasks by the unmanned aerial vehicle;
s573, analyzing the collected parameters and characteristic data in real time through an isolated forest model and a Bayesian network to obtain the current state and the occurrence risk of the unmanned aerial vehicle;
s574, performing dynamic scheduling of tasks according to the data analysis result, and if the model predicts faults which occur in the future, adjusting the scheduling in advance to avoid the influence of the faults on the tasks;
and S575, optimizing the flight path of the unmanned aerial vehicle in real time according to the data analysis result, and planning the flight path in advance to avoid a small area if the model predicts that a fault or risk occurs in a small area.
10. An adaptive algorithm-based unmanned aerial vehicle group collaborative mapping system for implementing the adaptive algorithm-based unmanned aerial vehicle group collaborative mapping method according to any of claims 1-9, the system comprising: the system comprises a task segmentation module, a task allocation module, an instruction sequence generation module, a mapping data transmission module, a fault processing and standby unmanned aerial vehicle scheduling module, a mapping result generation module and an evaluation module;
the task segmentation module is connected with the instruction sequence generation module through the task distribution module, the instruction sequence generation module is connected with the fault processing and standby unmanned aerial vehicle dispatching module through the mapping data transmission module, and the fault processing and standby unmanned aerial vehicle dispatching module is connected with the evaluation module through the mapping result generation module;
The task segmentation module is used for carrying out task segmentation on the mapping task to obtain subtasks with definite input and output requirements;
the task allocation module is used for acquiring parameter information data of the unmanned aerial vehicle, combining attribute characteristics and clustering center similarity of the unmanned aerial vehicle and a load scheme set according to task scheduling parameters, and inputting the parameter information data into the self-adaptive algorithm so as to allocate the most suitable unmanned aerial vehicle and load for each subtask;
the instruction sequence generation module is used for converting a planning scheme of the optimal flight path into an executable instruction sequence and inputting the executable instruction sequence into a flight control system of the unmanned aerial vehicle;
the unmanned aerial vehicle is used for acquiring mapping data by using the loaded mapping equipment in the flight process according to the assigned task and the flight path, and then transmitting the mapping data back to the control center through the wireless mesh network;
the fault processing and standby unmanned aerial vehicle scheduling module is used for scheduling the standby unmanned aerial vehicle through a self-adaptive algorithm according to the attribute characteristics of the unmanned aerial vehicle and the similarity of the clustering center if the unmanned aerial vehicle encounters an emergency in the task execution process, and re-planning the task and the flight path;
The mapping result generation module is used for acquiring mapping data transmitted back by all unmanned aerial vehicles by the control center, analyzing the mapping data and generating a final mapping result;
the evaluation module is used for feeding back according to the mapping result and the execution condition of the unmanned aerial vehicle, adaptively adjusting the parameters of the adaptive algorithm, and evaluating the whole process by using a preset index after the mapping task is completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311623442.7A CN117348424B (en) | 2023-11-30 | 2023-11-30 | Unmanned aerial vehicle group collaborative mapping method and system based on self-adaptive algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311623442.7A CN117348424B (en) | 2023-11-30 | 2023-11-30 | Unmanned aerial vehicle group collaborative mapping method and system based on self-adaptive algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117348424A true CN117348424A (en) | 2024-01-05 |
| CN117348424B CN117348424B (en) | 2024-03-08 |
Family
ID=89357849
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311623442.7A Active CN117348424B (en) | 2023-11-30 | 2023-11-30 | Unmanned aerial vehicle group collaborative mapping method and system based on self-adaptive algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117348424B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109819037A (en) * | 2019-01-29 | 2019-05-28 | 武汉鸿瑞达信息技术有限公司 | A kind of method and system of adaptive polo placement and communication |
| CN110264026A (en) * | 2019-04-22 | 2019-09-20 | 北京邮电大学 | The online method for allocating tasks of rescue aircraft based on two-stage planning in earthquake rescue |
| CN110703802A (en) * | 2019-11-04 | 2020-01-17 | 中国科学院自动化研究所 | Automatic bridge detection method and system based on multi-unmanned aerial vehicle cooperative operation |
| CN111126770A (en) * | 2019-11-26 | 2020-05-08 | 浙江工业大学 | Task scheduling method of cross-layer shuttle storage system |
| CN111199360A (en) * | 2020-01-13 | 2020-05-26 | 西安电子科技大学 | Unmanned aerial vehicle task allocation planning method |
| CN111488946A (en) * | 2020-04-28 | 2020-08-04 | 东南大学 | Radar servo system fault diagnosis method based on information fusion |
| CN112270488A (en) * | 2020-11-09 | 2021-01-26 | 中国电子技术标准化研究院 | Unmanned aerial vehicle cluster task allocation method and device and unmanned aerial vehicle cluster system |
| CN116384436A (en) * | 2023-01-10 | 2023-07-04 | 中国人民解放军陆军工程大学 | Unmanned aerial vehicle 'bee colony' countermeasure method |
| KR20230111405A (en) * | 2022-01-18 | 2023-07-25 | 국방과학연구소 | Task allocating apparatus and operation method thereof |
| CN116595864A (en) * | 2023-04-23 | 2023-08-15 | 南昌航空大学 | Multi-unmanned aerial vehicle task allocation method based on mean shift clustering algorithm optimization |
-
2023
- 2023-11-30 CN CN202311623442.7A patent/CN117348424B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109819037A (en) * | 2019-01-29 | 2019-05-28 | 武汉鸿瑞达信息技术有限公司 | A kind of method and system of adaptive polo placement and communication |
| CN110264026A (en) * | 2019-04-22 | 2019-09-20 | 北京邮电大学 | The online method for allocating tasks of rescue aircraft based on two-stage planning in earthquake rescue |
| CN110703802A (en) * | 2019-11-04 | 2020-01-17 | 中国科学院自动化研究所 | Automatic bridge detection method and system based on multi-unmanned aerial vehicle cooperative operation |
| CN111126770A (en) * | 2019-11-26 | 2020-05-08 | 浙江工业大学 | Task scheduling method of cross-layer shuttle storage system |
| CN111199360A (en) * | 2020-01-13 | 2020-05-26 | 西安电子科技大学 | Unmanned aerial vehicle task allocation planning method |
| CN111488946A (en) * | 2020-04-28 | 2020-08-04 | 东南大学 | Radar servo system fault diagnosis method based on information fusion |
| CN112270488A (en) * | 2020-11-09 | 2021-01-26 | 中国电子技术标准化研究院 | Unmanned aerial vehicle cluster task allocation method and device and unmanned aerial vehicle cluster system |
| KR20230111405A (en) * | 2022-01-18 | 2023-07-25 | 국방과학연구소 | Task allocating apparatus and operation method thereof |
| CN116384436A (en) * | 2023-01-10 | 2023-07-04 | 中国人民解放军陆军工程大学 | Unmanned aerial vehicle 'bee colony' countermeasure method |
| CN116595864A (en) * | 2023-04-23 | 2023-08-15 | 南昌航空大学 | Multi-unmanned aerial vehicle task allocation method based on mean shift clustering algorithm optimization |
Non-Patent Citations (1)
| Title |
|---|
| 汪照 等: "基于鱼群算法的OFDMA自适应资源分配", 物理学报 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117348424B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11209816B2 (en) | Autonomous long range aerial vehicles and fleet management system | |
| CN109102101B (en) | Wind speed prediction method and system for wind power plant | |
| KR102089564B1 (en) | Tethered gyroglider control systems | |
| CN115167408A (en) | Route planning system patrols and examines based on photovoltaic power plant | |
| CN116865258B (en) | Hierarchical distributed power supply intelligent power grid construction method | |
| CN117270569A (en) | Mountain fire identification inspection method based on dynamic path planning | |
| CN117348424B (en) | Unmanned aerial vehicle group collaborative mapping method and system based on self-adaptive algorithm | |
| CN108805427B (en) | Power distribution network running state risk early warning system based on big data | |
| CN117592975A (en) | Operation and maintenance decision processing method and system for electromechanical equipment of expressway based on cloud computing | |
| CN117251825A (en) | Multi-sensor data fusion platform for new energy power station | |
| CN117411115A (en) | Detection control method and device for energy storage power supply state, electronic equipment and medium | |
| KR102476392B1 (en) | Smart factory operation analysis system and method | |
| CN117494009A (en) | Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform | |
| CN116384695A (en) | Unmanned aerial vehicle operation monitoring method and system based on independent overruling and combined overruling | |
| CN104301388A (en) | Large running system monitoring and analyzing management system | |
| CN115776638A (en) | Intelligent optimization method and system for safety rate of relay system of unmanned aerial vehicle | |
| EP4113095A1 (en) | Wear state prediction method, wear state prediction device and wear state prediction program | |
| CN116112947A (en) | Digital twin system construction method, modeling method, network optimization method and device | |
| CN111371484B (en) | Unmanned aerial vehicle base station control method, device and system and computer readable storage medium | |
| CN113407945A (en) | Man-machine cooperation based large-scale Fuzzing optimization system and method | |
| CN117806355A (en) | Control method and system for electric power line inspection unmanned aerial vehicle | |
| CN117557929B (en) | Unit collaborative optimization method based on multiple application scenes | |
| JPWO2020189607A1 (en) | Information processing equipment | |
| CN117376108B (en) | Intelligent operation and maintenance method and system for Internet of things equipment | |
| CN117146831B (en) | Fruit tree growth state evaluation method and system based on machine learning and unmanned aerial vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |