CN111220159B - Path optimization method for multi-unmanned aerial vehicle cooperative inspection task - Google Patents
Path optimization method for multi-unmanned aerial vehicle cooperative inspection task Download PDFInfo
- Publication number
- CN111220159B CN111220159B CN202010084540.8A CN202010084540A CN111220159B CN 111220159 B CN111220159 B CN 111220159B CN 202010084540 A CN202010084540 A CN 202010084540A CN 111220159 B CN111220159 B CN 111220159B
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- station
- inspection target
- inspection
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/104—Simultaneous control of position or course in three dimensions specially adapted for aircraft involving a plurality of aircrafts, e.g. formation flying
Abstract
The invention provides a path optimization method for a multi-unmanned aerial vehicle collaborative inspection task, and particularly relates to the technical field of unmanned aerial vehicles, wherein the method can comprise the following steps: the method comprises the steps of firstly determining relevant parameters of a routing inspection target, unmanned aerial vehicle parameters for executing a routing inspection task, station parameters of the unmanned aerial vehicle and total task execution duration in a target area, setting course angle dispersion of the unmanned aerial vehicle, further determining the routing inspection target which can be accessed by the unmanned aerial vehicle from each station based on routing inspection target relevant information, station relevant information and task execution duration, and simultaneously establishing and optimizing a multi-station multi-unmanned aerial vehicle path problem MDMV-MURP model to obtain an optimal path planning scheme for each unmanned aerial vehicle to access the routing inspection target. Based on the method provided by the embodiment of the invention, the credibility of the information acquired by all unmanned aerial vehicles in the given task time is the maximum.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicles, in particular to a path optimization method for a cooperative inspection task of multiple unmanned aerial vehicles.
Background
Unmanned aerial vehicles have been widely used in military inspection and electric power tower inspection and other scenes. In order to improve the efficiency of the task of patrolling and examining, can adopt many unmanned aerial vehicles to expand patrolling and examining to the target area simultaneously from different directions usually, these unmanned aerial vehicles can follow different websites usually moreover and start. Unmanned aerial vehicle can acquire the image of patrolling and examining the target through its sensor that carries on, synthesizes the image that acquires the different grade type sensor and can promote the credibility of the information of acquireing greatly, for example: the military target or the electric tower is photographed through the visible light radar and the synthetic aperture radar.
At present, when the task allocation is carried out to a plurality of unmanned aerial vehicles executing the task by the traditional scheme, the detection error of a sensor carried by the unmanned aerial vehicle is not considered, and all the unmanned aerial vehicles are assumed to start from the same station and can only visit the target once. Therefore, the unmanned aerial vehicle path cannot be optimized, and the completion quality of the routing inspection task is low.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a path optimization method for a multi-unmanned aerial vehicle collaborative inspection task, which can plan paths of unmanned aerial vehicles from multiple sites under multiple constraint conditions, and furthest exert the cruising ability of the unmanned aerial vehicles by optimizing the access times of the unmanned aerial vehicles to inspection targets, thereby improving the completion quality of the inspection task.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
the invention provides a path optimization method for a multi-unmanned aerial vehicle collaborative inspection task, which is characterized by comprising the following steps:
determining the coordinates and the importance degree of a plurality of inspection targets which need a plurality of unmanned aerial vehicles to execute inspection tasks in a target area;
determining the task execution time length for executing the inspection task;
acquiring the number of stations, station numbers and station coordinates of multiple stations of the unmanned aerial vehicle;
acquiring relevant parameters of the unmanned aerial vehicle accessing the inspection target; the relevant parameters include: the type of sensor carried, the flight speed and/or the minimum turning radius;
determining the type of a sensor carried by the unmanned aerial vehicle from each station and a detection error of the sensor;
setting course angle dispersion of the unmanned aerial vehicle, and determining a plurality of course angles of the unmanned aerial vehicle based on the course angle dispersion of the unmanned aerial vehicle;
determining the routing inspection targets which can be accessed by the unmanned aerial vehicle from each station based on the routing inspection target related information, the station related information and the task execution duration;
establishing a multi-site revisitable multi-unmanned aerial vehicle path problem MDMV-MURP model;
acquiring an initial path planning scheme set of the multiple unmanned aerial vehicles for executing the cooperative inspection tasks by adopting the MDMV-MURP model according to the coordinates and the importance degree of each inspection target, the task execution duration and the inspection target which can be accessed by each unmanned aerial vehicle;
and optimizing the initial path planning scheme set by adopting a genetic algorithm introducing a double fitness function so as to obtain an optimal path planning scheme of each unmanned aerial vehicle for accessing any one or more routing inspection targets.
Optionally, setting a heading angle dispersion of the unmanned aerial vehicle, and determining a plurality of heading angles of the unmanned aerial vehicle based on the heading angle dispersion of the unmanned aerial vehicle, including:
describing the motion state of the unmanned aerial vehicle by using a duren vehicle model, and setting the course angle dispersion of the unmanned aerial vehicle to be 8;
and determining that the plurality of heading angles of the unmanned aerial vehicle are respectively 0 degrees, 45 degrees, 90 degrees, 135 degrees, 180 degrees, 225 degrees, 270 degrees and 315 degrees, and numbering the heading angles.
Optionally, before determining the routing inspection targets that the unmanned aerial vehicle from each station can access based on the routing inspection target related information, the station related information, and the task execution duration, the method further includes:
calculating the first flight time of the unmanned aerial vehicle from each station to each inspection target under all course angles, storing by using a three-dimensional matrix, and recording a sending matrix;
calculating a second flight time from each inspection target to each station of the unmanned aerial vehicle under all the course angles, storing the second flight time by using a three-dimensional matrix, and recording the second flight time as a return matrix;
and calculating the third flight time of each unmanned aerial vehicle among all the inspection targets under all the course angles, storing the third flight time by using the three-dimensional matrix, and recording the third flight time as a target-to-target matrix.
Optionally, in the departure matrix, a row indicates a heading angle number when the unmanned aerial vehicle departs, a column indicates a heading angle number when the unmanned aerial vehicle accesses the inspection target, and a page indicates a number of a station of the unmanned aerial vehicle;
in the return matrix, a row represents a course angle number when the unmanned aerial vehicle accesses the last inspection target, and a column represents a course angle number when the unmanned aerial vehicle returns to the station from the last inspection target; the page indicates the number of the drone station;
in the target-to-target matrix, a row represents a heading angle number when the unmanned aerial vehicle accesses the current inspection target, a column represents a heading angle number when the unmanned aerial vehicle accesses the next inspection target, and a page represents a number of an unmanned aerial vehicle station.
Optionally, determining, based on the routing inspection target related information, the site related information, and the task execution duration, a routing inspection target accessible to the unmanned aerial vehicle from each site includes:
and determining the routing inspection target which can be accessed by the unmanned aerial vehicle starting from each station based on the routing inspection target coordinates and the station coordinates, the starting matrix, the returning matrix and the relevant parameters of each unmanned aerial vehicle.
Optionally, the initial path planning scheme set includes a plurality of path planning schemes, where the path planning schemes include a station number and a task execution sequence of each drone in each of the multiple drones;
wherein the task execution sequence comprises: unmanned aerial vehicle's starting point, the target's that patrols and examines serial number, unmanned aerial vehicle's terminal point of passing through in proper order.
Optionally, the target function of the MDMV-MURP model is expressed by equation (1):
wherein i is the number of the inspection target, wiTo patrol the weight of object i, pkThe detection error of the sensor carried by the unmanned aerial vehicle at the kth station, K is the number of the unmanned aerial vehicle stations, K is the number of the unmanned aerial vehicle stations,
and N is the number of the routing inspection targets and Max is a maximum function, wherein the decision variables from the routing inspection target i to the routing inspection target j are decision variables.
Optionally, the constraints of the MDMV-MURP model are expressed using equations (2) to (6):
wherein, K is the serial number of unmanned aerial vehicle website, and K is unmanned aerial vehicleNumber of stations, DkIndicating the k-th drone site,
for the kth site DkThe decision variables of the drone from the station to the inspection target i,
for the kth site DkThe unmanned aerial vehicle decides variables from the inspection target i to the station, and U is a set of unmanned aerial vehicles;
the decision variable from patrol objective h to patrol objective i for the drone at the kth station,
the decision variables of the unmanned aerial vehicle of the kth station from the inspection target i to the inspection target j are determined, and T is a set of inspection targets;
the flight time length, t, from station to inspection target i of the unmanned aerial vehicle at the kth stationijThe flight time from the inspection target i to the inspection target j of the unmanned aerial vehicle is determined; t istaskA task execution duration;
equation (6) is a binary decision variable
Is taken from the value of
When the number of the unmanned aerial vehicles is 1, the unmanned aerial vehicle representing the k station selects a path from the inspection target i to the inspection target j when the number of the unmanned aerial vehicles is 1
A value of 0 indicates that the drone at the kth station has not selected this path.
Optionally, optimizing the initial path planning scheme set by using a genetic algorithm introducing a double fitness function to obtain an optimal path planning scheme for each unmanned aerial vehicle to access any one or more of the inspection targets, including:
establishing a chromosome evaluation mechanism of the double fitness function, namely a total useful information fitness function Fit1 and a total flight time fitness function Fit2, wherein the calculation formula is as follows:
wherein i is the number of the inspection target, wiTo patrol the weight of object i, pkThe detection error of the sensor carried by the unmanned aerial vehicle at the kth station, K is the unmanned aerial vehicle station number, K is the number of the unmanned aerial vehicle stations,
decision variables of the unmanned aerial vehicle of the kth station from the inspection target i to the inspection target j are determined, and N is the number of the inspection targets;
wherein K is the number of the unmanned aerial vehicle sites, DkIndicating the k-th drone site,
for the kth site DkThe decision variables of the drone from the station to the inspection target i,
for the kth site DkFrom patrol target i to station DkU is the set of unmanned aerial vehicles;
the decision variable of the unmanned plane of the kth station from the inspection target h to the inspection target i,
a decision variable from a patrol target i to a patrol target j of the unmanned aerial vehicle of the kth station is represented by T, which is a set of patrol targets;
the flight time from the station to the inspection target i of the unmanned aerial vehicle at the kth station, tijThe flight time from the inspection target i to the inspection target j of the unmanned aerial vehicle is set;
the Fit1 value of the formula (7) is total useful information of the path planning scheme represented by the chromosome, the greater the Fit1 value is, the higher the fitness of the chromosome is, the Fit2 value of the formula (8) is the total flight time of the path planning scheme represented by the chromosome, and the smaller the Fit2 value is, the higher the fitness of the chromosome is;
and taking Fit1 as a main fitness function and Fit2 as an auxiliary fitness function, comparing Fit1 values of all path planning schemes, and comparing Fit2 values when the Fit1 values are the same, so that the initial path planning scheme set is optimized to obtain an optimal path planning scheme for each unmanned aerial vehicle to visit any one or more routing inspection targets.
(III) advantageous effects
The invention provides a heterogeneous multi-unmanned aerial vehicle cooperative task allocation and path optimization method. Compared with the prior art, the method has the following beneficial effects:
1. in a multi-unmanned aerial vehicle inspection scene, path planning is carried out on a plurality of unmanned aerial vehicles starting from different sites, an inspection target of each unmanned aerial vehicle and an access sequence of the allocated inspection targets are determined, and finally a flyable path is optimized according to the access sequence of each unmanned aerial vehicle, so that the reliability of information acquired by all unmanned aerial vehicles in a given task time is the maximum;
2. by the aid of the optimization method of loop iteration, the number of times of the unmanned aerial vehicles visiting the inspection target is optimized for inspection tasks needing to be completed by the multiple unmanned aerial vehicles in a coordinated mode, useful information obtained by all the unmanned aerial vehicles is maximized, and accordingly the completion quality of the inspection tasks is improved.
3. The robustness of the genetic algorithm is good, so that the difference of results of multiple runs is small.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a path optimization method for a multi-unmanned aerial vehicle collaborative inspection task according to an embodiment of the application;
fig. 2 is a schematic diagram of a specific execution scene of a multi-unmanned aerial vehicle cooperative inspection task according to an embodiment of the application;
fig. 3 is a schematic view of a multi-unmanned aerial vehicle cooperative inspection task scene according to an embodiment of the application;
FIG. 4 is an optimal unmanned aerial vehicle flyable path in the inspection task scenario shown in FIG. 3;
FIG. 5 is a schematic view of discretization of a heading angle according to an embodiment of the present application;
fig. 6(a) - (b) are schematic diagrams of path planning schemes with the same expected benefit but different total flight duration according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are a part of the embodiments of the present invention, but not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the application provides a method for distributing and optimizing the paths of the cooperative tasks of the heterogeneous multi-unmanned aerial vehicles.
In order to solve the technical problems, the general idea of the embodiment of the application is as follows:
the method comprises the steps of firstly determining relevant parameters of a plurality of inspection targets needing a plurality of unmanned aerial vehicles to execute inspection tasks, unmanned aerial vehicle parameters for executing the inspection tasks, station parameters of the unmanned aerial vehicles and total task execution duration in a target area, setting course angle dispersion of the unmanned aerial vehicles, further determining the inspection targets which can be accessed by the unmanned aerial vehicles from each station based on the relevant information of the inspection targets, the relevant information of the stations and the task execution duration, simultaneously establishing and utilizing a multi-station multi-unmanned aerial vehicle path problem MDMV-MURP model to obtain an initial path planning scheme set of the multi-unmanned aerial vehicles for executing the collaborative inspection tasks, and optimizing to obtain an optimal path planning scheme of each unmanned aerial vehicle for accessing any one or more inspection targets.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Fig. 1 is a schematic flow chart of a path optimization method for a multi-unmanned aerial vehicle collaborative inspection task according to an embodiment of the present application, and as can be seen from fig. 1, the path optimization method for the multi-unmanned aerial vehicle collaborative inspection task provided by this embodiment may include:
step S101, determining the coordinates and the importance degree of a plurality of inspection targets in a target area, wherein the inspection targets need to be executed by a plurality of unmanned aerial vehicles;
step S102, determining the task execution time length for executing the inspection task;
step S103, acquiring the number of stations, station numbers and station coordinates of multiple stations of the unmanned aerial vehicle;
step S104, acquiring relevant parameters of the unmanned aerial vehicle accessing the inspection target; the relevant parameters include: the type of sensor carried, the flight speed and/or the minimum turning radius;
step S105, determining the type of a sensor carried by the unmanned aerial vehicle from each station and a detection error of the sensor;
s106, setting course angle dispersion of the unmanned aerial vehicle, and determining a plurality of course angles of the unmanned aerial vehicle based on the course angle dispersion of the unmanned aerial vehicle;
step S107, determining the routing inspection targets which can be accessed by the unmanned aerial vehicle from each station based on the routing inspection target related information, the station related information and the task execution duration;
step S108, establishing a multi-site revisiting multi-unmanned aerial vehicle path problem MDMV-MURP model;
step S109, acquiring an initial path planning scheme set of the multiple unmanned aerial vehicles for executing the cooperative inspection tasks according to the coordinates and the importance degree of each inspection target, the task execution duration and the inspection targets which can be accessed by each unmanned aerial vehicle by adopting an MDMV-MURP model;
and S110, optimizing the initial path planning scheme set by adopting a genetic algorithm introducing a double fitness function to obtain an optimal path planning scheme of each unmanned aerial vehicle for accessing any one or more inspection targets.
Based on the method provided by the embodiment of the invention, path planning can be carried out on a plurality of unmanned aerial vehicles sent from different stations, the routing inspection target of each unmanned aerial vehicle and the access sequence of the distributed routing inspection targets are determined, and finally a flyable path is optimized according to the access sequence of each unmanned aerial vehicle, so that the reliability of information acquired by all unmanned aerial vehicles in the given task time is the maximum.
In practical applications, since the drone can rapidly enter an inspection area and rapidly capture image and video data through a sensor mounted thereon, the drone has been widely used in target inspection of various scenes.
Fig. 2 is a schematic diagram of a specific execution scene of a multi-unmanned aerial vehicle cooperative task according to an embodiment of the application, and as can be seen from fig. 2, according to a plurality of inspection targets (e.g., power towers) requiring the multi-unmanned aerial vehicle cooperative inspection in a task area, determining the multi-unmanned aerial vehicle cooperative task to determine useful information of each inspection target, starting from different stations, all unmanned aerial vehicles inspect different targets, inspecting as many targets as possible within a task time, and accessing inspection targets with higher importance by using unmanned aerial vehicles equipped with different types of sensors for a plurality of times, so as to maximize the reliability of the acquired information.
The following describes the steps S101 to S110 in detail.
Referring to the above step S101, first, the coordinates and the importance of a plurality of inspection targets in the target area that require the plurality of drones to perform the inspection task are determined. The target area summarized in this embodiment refers to a designated area where an inspection task needs to be performed, such as military inspection or power tower inspection. For executing the inspection of the electric power tower, the inspection target can be a multi-loop electric power tower or a common telegraph pole and the like, and the main purpose of the inspection of the electric power tower of the multi-unmanned aerial vehicle is to inspect as many electric power towers as possible within the specified task time and acquire accurate image information so as to carry out targeted fault diagnosis. Within a limited mission duration, the drone can only patrol a limited number of power towers, so it is necessary to selectively access some of the patrol targets, such as: the multi-loop power tower is used as a preferential inspection target. Therefore, the respective importance levels of different inspection targets in the target area are different, and in this embodiment, the importance level of the inspection target can be represented by a weight, and the inspection target is more important when the weight value is larger. The application scenario provided by the embodiment of the invention is shown in fig. 3, D1 and D2 are distributed to represent two sites, 1-23 are inspection targets, and meanwhile, according to an important target priority selection principle, the deeper the color is, the more important the target is, the darker the color is first selected as priority access, as can be seen from fig. 3, the closer to the center, the inspection target has the higher weight, wherein the inspection target 12 has the largest weight, and then 7, 8, 16, 17, 10, 11, 13 and 14 are sequentially reduced, and 1 and 23 are equal and the smallest.
Fig. 4 is an optimal unmanned aerial vehicle flyable path, and solid lines and dotted lines in fig. 4 respectively represent the flyable paths of two heterogeneous unmanned aerial vehicles.
In this embodiment, each inspection target in the target area may also be set according to different attributes of the inspection target, and the weight of the inspection target may be w in generaliThe coordinate of each inspection target can be obtained by a GPS or expressed by {1,2, …,10}, and the coordinate of each inspection target can be obtained by a GPS orOther ways to obtain this are not limiting of the present invention. Of course, the target area in practical application may also be an area of other attributes that requires the unmanned aerial vehicle to perform inspection, and the present invention is not limited.
Referring to the step S102, a task execution time length for executing the inspection task is determined.
In this embodiment, the execution duration of executing the inspection task needs to be determined first to provide a data basis for reasonably planning the path of the unmanned aerial vehicle in the following, and the execution duration may be set according to different scenarios, which is not limited in the present invention. The task execution duration in this embodiment is specific to all drones, that is, the quality of completion of the task is determined by how many targets all drones have completed the patrol task within a specified time (regardless of the return duration). The duration of the task is long, the duration of the unmanned aerial vehicle can be not considered, and in practical application, the duration of the unmanned aerial vehicle is generally far greater than the duration of the task, so that the time for the unmanned aerial vehicle to return to a station is not considered during path planning.
Referring to step S103, the station number, and the station coordinates of the multiple stations of the unmanned aerial vehicle are obtained.
In the embodiment of the invention, the unmanned aerial vehicle can actually execute the inspection task at a plurality of sites, namely, a plurality of unmanned aerial vehicles can trigger the inspection task from a plurality of sites. In the embodiment of the invention, the station of the unmanned aerial vehicle can be used as the starting point and the end point of the inspection task executed on the inspection target by the unmanned aerial vehicle at the same time. The station coordinates can be used as the starting point coordinates and the ending point coordinates of the unmanned aerial vehicle at the same time, or different stations can be used as the starting point or the ending point, and the total number of stations, the number of starting point stations and the number of ending point stations can be set according to different application scenes, which is not limited in the invention. Specifically, when the site coordinates are obtained, the site coordinates can be obtained by using a GPS or other methods, which is not limited in the present invention.
Referring to the step S104, relevant parameters of the unmanned aerial vehicle accessing the inspection target are obtained. Introduced above, in this embodiment, all drones may be of the same model, carry the same sensors, and therefore may obtain relevant parameters of the drone accessing the inspection target, which may include the type of sensor carried, the flight speed, and/or the minimum turning radius. In addition, relevant parameters of the drone may also include drone number, and the like. Through the acquisition to unmanned aerial vehicle relevant parameter, can follow-up in optimizing the unmanned aerial vehicle route, rational utilization unmanned aerial vehicle's the ability of patrolling and examining to promote every unmanned aerial vehicle's availability factor. Wherein, unmanned aerial vehicle serial number is the only serial number that can carry out the one-to-one with unmanned aerial vehicle.
Referring to step S105 described above, the type of sensor carried by the drone from each station and its detection error are determined.
After the unmanned aerial vehicle enters a target area, the image and video data are rapidly captured through the mounted sensor. For every unmanned aerial vehicle promptly, can also acquire the type and the detection error of its sensor that carries to can carry out individualized planning route according to every unmanned aerial vehicle's characteristic when carrying out the task of patrolling and examining for the planning of every unmanned aerial vehicle follow-up, give full play to every unmanned aerial vehicle's advantage, in order to adopt the unmanned aerial vehicle of low detection error or visit many times in order to accomplish the task of patrolling and examining as far as accurate high-efficiently to important target of patrolling and examining.
With the electric power tower that is located the mountain area patrols and examines the region, because unmanned aerial vehicle can not receive the topography influence and reach the shaft tower top fast to through the sensor of carrying on catch image and video data fast, so has been widely used in the electric power tower patrols and examines.
Referring to the step S106, the course angle dispersion of the unmanned aerial vehicle is set, and a plurality of course angles of the unmanned aerial vehicle are determined based on the course angle dispersion of the unmanned aerial vehicle.
Since the unmanned aerial vehicle is constrained by dynamics, the flyability of the path of the unmanned aerial vehicle must be ensured when the unmanned aerial vehicle is subjected to path planning, and particularly, the flyable path must be a quadratic and microminiable smooth curve. The shortest feasible path model (abbreviated as a 'dubin model') of the plane incomplete vehicle proposed by Dubins can meet the dynamic constraint of the unmanned aerial vehicle, so that in the embodiment of the invention, the dubin model can be used for describing the motion state of the unmanned aerial vehicle.
The state q of the dubin vehicle is composed of its coordinates (x, y) in a plane and its direction angle θ. One of the features of the duren vehicle model is that the shortest path between two states of the duren vehicle is affected by the minimum turning radius ρ, and the motion model of the duren vehicle with constant flying speed v and control input u can be described as:
u >0 represents a left turn, u <0 represents a right turn, u ═ 0 represents a straight line, and u ═ 1 represents that the unmanned aerial vehicle makes a turn at a minimum turning radius.
The following 2 factors need to be considered when planning a path for each drone using the duren car model: the minimum turning radius of the unmanned aerial vehicle; and secondly, the course angle of the unmanned aerial vehicle when accessing each target.
Due to the fact that the minimum turning radius of the heterogeneous unmanned aerial vehicles is different, the shortest paths of the heterogeneous unmanned aerial vehicles flying between 2 identical targets are different, as shown in fig. 4, and in fig. 4, a solid line and a dotted line respectively represent flight paths of two heterogeneous unmanned aerial vehicles.
Therefore, the embodiment of the invention optimizes the course angle when the unmanned aerial vehicle accesses each target by using the course angle dispersion method (namely, setting course dispersion and dividing 360 degrees into a plurality of course angles). In the embodiment of the invention, the course angle dispersion N of the unmanned aerial vehicle is setθAt 8, the plurality of heading angles of the drone are determined to be 0 °,45 °,90 °,135 °,180 °,225 °,270 °,315 °, respectively, and are numbered for each heading angle (the number is a unique number corresponding to each heading angle, respectively). FIG. 5 is a course angle dispersion NθSchematic when 8. The number sequence of the heading angles shown in fig. 5 is 0-7, for example, the heading angle number of the unmanned aerial vehicle in fig. 5 is 7, and the calculation formula of the heading angle number and the heading angle is as follows:
in addition, the embodiment of the invention is also proved by numerical experiments that: course angle dispersion NθSetting to 8 resulted in the optimal solution for all experiments.
Referring to step S107 described above, the patrol target accessible to the unmanned aerial vehicle from each station is determined based on the patrol target-related information, the station-related information, and the task execution time length.
As mentioned above, by setting the course angle dispersion, the possible course angle of the drone when performing a mission can be determined. Therefore, before determining the routing inspection targets that can be accessed by the unmanned aerial vehicle from each station, the departure matrix, the return matrix, and the target-to-target matrix may be obtained, specifically, as follows:
calculating the first flight time of the unmanned aerial vehicle from each station to each inspection target under all course angles, storing by using a three-dimensional matrix, and recording a sending matrix;
calculating a second flight time from each inspection target to each station of the unmanned aerial vehicle under all the course angles, storing the second flight time by using a three-dimensional matrix, and recording the second flight time as a return matrix;
and calculating the third flight time of each unmanned aerial vehicle among all the inspection targets under all the course angles, storing the third flight time by using the three-dimensional matrix, and recording the third flight time as a target-to-target matrix.
Further, in the departure matrix, rows represent the heading angle numbers of the unmanned aerial vehicle when departing, columns represent the heading angle numbers of the unmanned aerial vehicle when accessing the inspection target, and pages represent the numbers of the unmanned aerial vehicle stations;
in the return matrix, the row represents the heading angle number when the unmanned aerial vehicle accesses the last inspection target, and the column represents the heading angle number when the unmanned aerial vehicle returns to the station from the last inspection target; the page indicates the number of the drone station;
in the target-to-target matrix, a row represents a course angle number when the unmanned aerial vehicle accesses the current inspection target, a column represents a course angle number when the unmanned aerial vehicle accesses the next inspection target, and a page represents a number of the unmanned aerial vehicle station.
After the departure matrix, the return matrix and the matrix from the target to the target are determined, the patrol target which can be accessed by the unmanned aerial vehicle departing from each station can be determined based on the patrol target coordinates, the station coordinates, the departure matrix, the return matrix and the relevant parameters of each unmanned aerial vehicle.
Therefore, a certain path planning scheme can be rapidly obtained through the starting matrix, the returning matrix and the target-to-target matrix, the path planning scheme comprises unmanned aerial vehicle station numbers of each plurality of unmanned aerial vehicles and a task execution sequence, and the task execution sequence comprises: the starting point of the unmanned aerial vehicle, the serial number of the inspection target and the terminal point of the unmanned aerial vehicle sequentially pass through.
Referring to the step S108, a multi-site revisitable multi-drone path problem MDMV-MURP model is established.
In the present embodiment, the objective function of the MDMV-MURP model is expressed by the following formula (1):
wherein i is the number of the inspection target, wiTo patrol the weight of object i, pkFor the detection error of the sensor carried by the unmanned aerial vehicle at the kth station, K is the number of the unmanned aerial vehicle station, and K is the number of the unmanned aerial vehicle stations, xij kAnd N is the number of the routing inspection targets and Max is a maximum function, wherein the decision variables from the routing inspection target i to the routing inspection target j are decision variables.
And the constraint conditions of the MDMV-MURP model are expressed by formulas (2) to (6):
wherein K is the number of the unmanned aerial vehicle sites, DkIndicating the k-th drone site,
for the kth site DkThe decision variables of the drone from the station to the inspection target i,
for the kth site DkThe unmanned aerial vehicle decides variables from the inspection target i to the station, and U is a set of unmanned aerial vehicles;
the decision variable from patrol objective h to patrol objective i for the drone at the kth station,
the decision variables of the unmanned aerial vehicle of the kth station from the inspection target i to the inspection target j are determined, and T is a set of inspection targets;
the flight time length, t, from station to inspection target i of the unmanned aerial vehicle at the kth stationijThe flight time from the inspection target i to the inspection target j of the unmanned aerial vehicle is determined; t istaskA task execution duration;
equation (6) is a binary decision variable
Is taken from the value of
When the number of the unmanned aerial vehicles is 1, the unmanned aerial vehicle representing the k station selects a path from the inspection target i to the inspection target j when the number of the unmanned aerial vehicles is 1
A value of 0 indicates that the drone at the kth station has not selected this path.
It should be noted that, in this embodiment, the task completion time does not need to consider the time when the drone returns to the station from the last target, because the drone is regarded as completing the task as long as it acquires the image information of the target within the specified time.
Referring to the step S109, after the MDMV-MURP model is established, the MDMV-MURP model may be used to obtain an initial path planning scheme set for the multiple unmanned aerial vehicles to execute the collaborative inspection task according to the coordinates of each inspection target, the importance thereof, the task execution duration, and the inspection target that each unmanned aerial vehicle can access.
Optionally, the initial task allocation scheme set mentioned in this embodiment includes a plurality of task allocation schemes; each task allocation scheme can comprise the unmanned aerial vehicle number and the task execution sequence of each heterogeneous multi-unmanned aerial vehicle; wherein the task execution sequence comprises: the starting point of the unmanned aerial vehicle and the routing inspection target numbers sequentially pass through.
Referring to step S110, after the initial path planning scheme set is obtained, the initial path planning scheme set is optimized by using a genetic algorithm introduced with a double fitness function to obtain an optimal path planning scheme for each unmanned aerial vehicle to access any one or more inspection targets.
Genetic algorithm (genetic algorithm) is a computational model of the biological evolution process that simulates the natural selection and genetic mechanism of darwinian biological evolution theory, and is a method for searching for an optimal solution by simulating the natural evolution process.
In an optional embodiment of the present application, the fitness of the chromosome represents the goodness of the path planning scheme, and according to the optimized objective function of MDMV-MURP, the greater the useful information obtained by the path planning scheme calculated by the formula (1), the better the scheme is. However, since there are multiple selectable heading angles for the drone to access the target, the scenario with the same expected revenue may have different total flight times as shown in fig. 6, the scenario shown in fig. 6(a) is identical to the scenario shown in fig. 6(b) for accessing the potential target, and the number of accesses for each potential target is identical, so the expected revenue for both scenarios is also identical, but the total flight time for the scenario shown in fig. 6(b) is shorter.
Meanwhile, a chromosome evaluation mechanism of the double fitness function is established, namely a total useful information fitness function Fit1 and a total flight time fitness function Fit2, and the calculation formula is as follows:
wherein i is the number of the inspection target, wiTo patrol the weight of object i, pkThe detection error of the sensor carried by the unmanned aerial vehicle at the kth station, K is the unmanned aerial vehicle station number, K is the number of the unmanned aerial vehicle stations,
and N is the number of the routing inspection targets, and is a decision variable from the routing inspection target i to the routing inspection target j.
Wherein K is the number of the unmanned aerial vehicle sites, DkIndicating the k-th drone site,
for the kth site DkThe decision variables of the drone from the station to the inspection target i,
for the kth site DkFrom patrol target i to station DkU is the set of unmanned aerial vehicles;
the decision variable of the unmanned plane of the kth station from the inspection target h to the inspection target i,
a decision variable from a patrol target i to a patrol target j of the unmanned aerial vehicle of the kth station is represented by T, which is a set of patrol targets;
the flight time from the station to the inspection target i of the unmanned aerial vehicle at the kth station, tijThe flight time from the inspection target i to the inspection target j of the unmanned aerial vehicle is set;
the Fit1 value of the formula (7) is total useful information of the path planning scheme represented by the chromosome, the greater the Fit1 value is, the higher the fitness of the chromosome is, the Fit2 value of the formula (8) is the total flight time of the path planning scheme represented by the chromosome, and the smaller the Fit2 value is, the higher the fitness of the chromosome is;
and taking Fit1 as a main fitness function and Fit2 as an auxiliary fitness function, comparing Fit1 values of all path planning schemes, and comparing Fit2 values when the Fit1 values are the same, so that the initial path planning scheme set is optimized to obtain an optimal path planning scheme for each unmanned aerial vehicle to access any one or more routing inspection targets.
And optimizing the initial path planning scheme set through multiple iterations by adopting a genetic algorithm introducing a double fitness function, so that an optimal path planning scheme for each unmanned aerial vehicle to access any one or more routing inspection targets can be obtained. It should be noted that, each constant parameter in the formula provided in this embodiment may be adjusted according to actual needs, and all reasonable variations of the formula provided in the above embodiments are within the protection scope of the present invention.
In summary, compared with the prior art, the method has the following beneficial effects:
1. in a multi-unmanned aerial vehicle inspection scene, path planning is carried out on a plurality of unmanned aerial vehicles starting from different sites, an inspection target of each unmanned aerial vehicle and an access sequence of the allocated inspection targets are determined, and finally a flyable path is optimized according to the access sequence of each unmanned aerial vehicle, so that the reliability of information acquired by all unmanned aerial vehicles in a given task time is the maximum;
2. by the aid of the optimization method of loop iteration, the number of times of the unmanned aerial vehicles visiting the inspection target is optimized for inspection tasks needing to be completed by the multiple unmanned aerial vehicles in a coordinated mode, useful information obtained by all the unmanned aerial vehicles is maximized, and accordingly the completion quality of the inspection tasks is improved.
It is noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. A path optimization method for a multi-unmanned aerial vehicle collaborative inspection task is characterized by comprising the following steps:
determining the coordinates and the importance degree of a plurality of inspection targets which need a plurality of unmanned aerial vehicles to execute inspection tasks in a target area;
determining the task execution time length for executing the inspection task;
acquiring the number of stations, station numbers and station coordinates of multiple stations of the unmanned aerial vehicle;
acquiring relevant parameters of the unmanned aerial vehicle accessing the inspection target; the relevant parameters include: the type of sensor carried, the flight speed and/or the minimum turning radius;
determining the type of a sensor carried by the unmanned aerial vehicle from each station and a detection error of the sensor;
setting course angle dispersion of the unmanned aerial vehicle, and determining a plurality of course angles of the unmanned aerial vehicle based on the course angle dispersion of the unmanned aerial vehicle;
determining the routing inspection targets which can be accessed by the unmanned aerial vehicle from each station based on the routing inspection target related information, the station related information and the task execution duration;
establishing a multi-site revisitable multi-unmanned aerial vehicle path problem MDMV-MURP model;
wherein the target function of the MDMV-MURP model is expressed by formula (1):
wherein i is the number of the inspection target, wiTo patrol the weight of object i, pkThe detection error of the sensor carried by the unmanned aerial vehicle at the kth station, K is the number of the unmanned aerial vehicle stations, K is the number of the unmanned aerial vehicle stations,
the method comprises the steps that decision variables from a routing inspection target i to a routing inspection target j are obtained, N is the number of the routing inspection targets, and Max is a maximum function;
the constraints of the MDMV-MURP model are expressed by formulas (2) to (6):
wherein K is the number of the unmanned aerial vehicle sites, DkIndicating the k-th drone site,
for the kth site DkThe decision variables of the drone from the station to the inspection target i,
for the kth site DkFrom patrol target i to station DkU is the set of unmanned aerial vehicles;
the decision variable of the unmanned plane of the kth station from the inspection target h to the inspection target i,
the decision variables of the unmanned aerial vehicle of the kth station from the inspection target i to the inspection target j are determined, and T is a set of the inspection targets;
the flight time from the station to the inspection target i of the unmanned aerial vehicle at the kth station, tijThe flight time from the inspection target i to the inspection target j of the unmanned aerial vehicle is set; t istaskA task execution duration;
equation (6) is a binary decision variable
Is taken from the value of
When the number of the unmanned aerial vehicles is 1, the unmanned aerial vehicle representing the k station selects a path from the inspection target i to the inspection target j when the number of the unmanned aerial vehicles is 1
A value of 0 indicates that the drone at the kth station has not selected this path;
acquiring an initial path planning scheme set of the multiple unmanned aerial vehicles for executing the cooperative inspection tasks by adopting the MDMV-MURP model according to the coordinates and the importance degree of each inspection target, the task execution duration and the inspection target which can be accessed by each unmanned aerial vehicle;
and optimizing the initial path planning scheme set by adopting a genetic algorithm introducing a double fitness function so as to obtain an optimal path planning scheme of each unmanned aerial vehicle for accessing any one or more routing inspection targets.
2. The method of claim 1, wherein setting a heading angle dispersion of the drone and determining a plurality of heading angles of the drone based on the heading angle dispersion of the drone comprises:
describing the motion state of the unmanned aerial vehicle by using a duren vehicle model, and setting the course angle dispersion of the unmanned aerial vehicle to be 8;
and determining that the plurality of heading angles of the unmanned aerial vehicle are respectively 0 degrees, 45 degrees, 90 degrees, 135 degrees, 180 degrees, 225 degrees, 270 degrees and 315 degrees, and numbering the heading angles.
3. The method of claim 1, wherein before determining the patrol targets accessible to the drones from each of the sites based on the patrol target-related information, the site-related information, and the task execution duration, further comprising:
calculating the first flight time of the unmanned aerial vehicle from each station to each inspection target under all course angles, storing by using a three-dimensional matrix, and recording a sending matrix;
calculating a second flight time from each inspection target to each station of the unmanned aerial vehicle under all course angles, storing the second flight time by using a three-dimensional matrix, and recording the second flight time as a return matrix;
and calculating the third flight time of each unmanned aerial vehicle among all the inspection targets under all the course angles, storing the third flight time by using the three-dimensional matrix, and recording the third flight time as a target-to-target matrix.
4. The method of claim 3,
in the departure matrix, a row represents a heading angle number when the unmanned aerial vehicle departs, a column represents a heading angle number when the unmanned aerial vehicle accesses the inspection target, and a page represents a number of an unmanned aerial vehicle station;
in the return matrix, a row represents a course angle number when the unmanned aerial vehicle accesses the last inspection target, and a column represents a course angle number when the unmanned aerial vehicle returns to the station from the last inspection target; the page indicates the number of the drone station;
in the target-to-target matrix, a row represents a course angle number when the unmanned aerial vehicle accesses the current inspection target, a column represents a course angle number when the unmanned aerial vehicle accesses the next inspection target, and a page represents a number of an unmanned aerial vehicle station.
5. The method of claim 3, wherein determining the patrol targets accessible to the drones from each site based on the patrol target-related information, the site-related information, and the task execution duration comprises:
and determining the routing inspection target which can be accessed by the unmanned aerial vehicle starting from each station based on the routing inspection target coordinates and the station coordinates, the starting matrix, the returning matrix and the relevant parameters of each unmanned aerial vehicle.
6. The method of claim 5, wherein the initial set of path planning scenarios comprises a plurality of path planning scenarios comprising drone site numbers, task execution orders for each of the plurality of drones;
wherein the task execution sequence comprises: the starting point of unmanned aerial vehicle, the serial number of the target of patrolling and examining that passes through in proper order, unmanned aerial vehicle's terminal point.
7. The method of claim 1, wherein optimizing the initial set of path planning schemes to obtain an optimal path planning scheme for each of the drones to access any one or more of the inspection targets using a genetic algorithm incorporating a bi-fitness function comprises:
establishing a chromosome evaluation mechanism of the double fitness function, namely a total useful information fitness function Fit1 and a total flight time fitness function Fit2, wherein the calculation formula is as follows:
wherein i is the number of the inspection target, wiTo patrol the weight of object i, pkIs the absence of the k siteThe detection error of the sensors carried by the human-computer, K is the unmanned plane station number, and K is the number of the unmanned plane stations,
decision variables of the unmanned aerial vehicle of the kth station from the inspection target i to the inspection target j are determined, and N is the number of the inspection targets;
wherein K is the number of the unmanned aerial vehicle sites, DkIndicating the k-th drone site,
for the kth site DkThe decision variables of the drone from the station to the inspection target i,
for the kth site DkFrom patrol target i to station DkU is the set of unmanned aerial vehicles;
the decision variable of the unmanned plane of the kth station from the inspection target h to the inspection target i,
the decision variables of the unmanned aerial vehicle of the kth station from the inspection target i to the inspection target j are determined, and T is a set of the inspection targets;
the flight time from the station to the inspection target i of the unmanned aerial vehicle at the kth station, tijFor the flight time of the unmanned aerial vehicle from the inspection target i to the inspection target j,
for the kth site DkThe flight time of the unmanned aerial vehicle from the inspection target i to the station point;
the Fit1 value of the formula (7) is total useful information of the path planning scheme represented by the chromosome, the greater the Fit1 value is, the higher the fitness of the chromosome is, the Fit2 value of the formula (8) is the total flight time of the path planning scheme represented by the chromosome, and the smaller the Fit2 value is, the higher the fitness of the chromosome is;
and taking Fit1 as a main fitness function and Fit2 as an auxiliary fitness function, comparing Fit1 values of all path planning schemes, and comparing Fit2 values when the Fit1 values are the same, so that the initial path planning scheme set is optimized to obtain an optimal path planning scheme for each unmanned aerial vehicle to access any one or more routing inspection targets.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010084540.8A CN111220159B (en) | 2020-02-10 | 2020-02-10 | Path optimization method for multi-unmanned aerial vehicle cooperative inspection task |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010084540.8A CN111220159B (en) | 2020-02-10 | 2020-02-10 | Path optimization method for multi-unmanned aerial vehicle cooperative inspection task |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111220159A CN111220159A (en) | 2020-06-02 |
| CN111220159B true CN111220159B (en) | 2021-09-28 |
Family
ID=70828498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010084540.8A Active CN111220159B (en) | 2020-02-10 | 2020-02-10 | Path optimization method for multi-unmanned aerial vehicle cooperative inspection task |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111220159B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112783195B (en) * | 2020-12-18 | 2023-09-19 | 深圳供电局有限公司 | Routing inspection route planning method and device for multiple unmanned aerial vehicles and computer equipment |
| CN112683276B (en) * | 2020-12-30 | 2022-06-24 | 广东安恒电力科技有限公司 | Unmanned aerial vehicle routing inspection cable path planning method based on mixed discrete wolf algorithm |
| CN113064449B (en) * | 2021-03-31 | 2024-03-12 | 广东电网有限责任公司电力调度控制中心 | Unmanned aerial vehicle scheduling method and system |
| CN113011780B (en) * | 2021-04-13 | 2022-05-31 | 江苏方天电力技术有限公司 | Task allocation method for multi-unmanned aerial vehicle cooperative power inspection |
| CN113255870B (en) * | 2021-04-19 | 2023-08-04 | 北京市遥感信息研究所 | Region revisit path optimization method, device, equipment and medium |
| CN113485429B (en) * | 2021-07-23 | 2022-01-18 | 安徽有云智能科技有限公司 | Route optimization method and device for air-ground cooperative traffic inspection |
| CN113867392A (en) * | 2021-10-13 | 2021-12-31 | 上海翼枭航空科技有限公司 | Intelligent inspection method, system, equipment and storage medium for unmanned aerial vehicle |
| CN114326812B (en) * | 2021-12-31 | 2023-08-29 | 中国铁路上海局集团有限公司合肥房建公寓段 | Path planning method for autonomous inspection of unmanned aerial vehicle high-speed rail station house |
| CN115952942B (en) * | 2023-03-13 | 2023-06-02 | 季华实验室 | Multi-target inspection scheduling planning method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279913A (en) * | 2014-06-30 | 2016-01-27 | 惠州市德赛西威汽车电子股份有限公司 | Vehicle road accident rescue calling system and method |
| CN107238388A (en) * | 2017-05-27 | 2017-10-10 | 合肥工业大学 | Multiple no-manned plane task is distributed and trajectory planning combined optimization method and device |
| US10170006B2 (en) * | 2016-09-27 | 2019-01-01 | International Business Machines Corporation | Route planning for multi-unmanned aerial vehicle-based package delivery |
| CN110083173A (en) * | 2019-04-08 | 2019-08-02 | 合肥工业大学 | The optimization method of unmanned plane formation patrol task distribution |
| CN110428111A (en) * | 2019-08-08 | 2019-11-08 | 西安工业大学 | Multi-Tasking method for planning track when UAV/UGV collaboration is long |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11453494B2 (en) * | 2016-05-20 | 2022-09-27 | Skydio, Inc. | Unmanned aerial vehicle area surveying |
-
2020
- 2020-02-10 CN CN202010084540.8A patent/CN111220159B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279913A (en) * | 2014-06-30 | 2016-01-27 | 惠州市德赛西威汽车电子股份有限公司 | Vehicle road accident rescue calling system and method |
| US10170006B2 (en) * | 2016-09-27 | 2019-01-01 | International Business Machines Corporation | Route planning for multi-unmanned aerial vehicle-based package delivery |
| CN107238388A (en) * | 2017-05-27 | 2017-10-10 | 合肥工业大学 | Multiple no-manned plane task is distributed and trajectory planning combined optimization method and device |
| CN110083173A (en) * | 2019-04-08 | 2019-08-02 | 合肥工业大学 | The optimization method of unmanned plane formation patrol task distribution |
| CN110428111A (en) * | 2019-08-08 | 2019-11-08 | 西安工业大学 | Multi-Tasking method for planning track when UAV/UGV collaboration is long |
Non-Patent Citations (2)
| Title |
|---|
| Multi-UAV coordinate communication path planning based on grid map and ant-algorithm;Li, Zexi;《2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)》;20171231;1584-1587 * |
| 多无人机协同搜索多目标的路径规划问题研究;刘文兵，王艺栋;《电光与控制》;20190331;第26卷(第3期);35-38,73 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111220159A (en) | 2020-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111220159B (en) | Path optimization method for multi-unmanned aerial vehicle cooperative inspection task | |
| CN111352417B (en) | Rapid generation method of heterogeneous multi-unmanned aerial vehicle cooperative path | |
| CN109990790B (en) | Unmanned aerial vehicle path planning method and device | |
| CN112465738B (en) | Photovoltaic power station online operation and maintenance method and system based on infrared and visible light images | |
| CN111310992B (en) | Multi-unmanned aerial vehicle path optimization method for rapid evaluation after earthquake disaster | |
| CN112947591A (en) | Path planning method, device, medium and unmanned aerial vehicle based on improved ant colony algorithm | |
| CN113703472A (en) | Path optimization method and device for cooperative inspection of multiple unmanned aerial vehicles and vehicles | |
| CN111239550A (en) | Unmanned aerial vehicle full-automatic multi-machine cooperative power transmission line fault identification method for inspection | |
| CN114724021B (en) | Data identification method and device, storage medium and electronic device | |
| CN115147745A (en) | Small target detection method based on urban unmanned aerial vehicle image | |
| CN112327930A (en) | Routing inspection path determining method and device | |
| CN110018694B (en) | Unmanned aerial vehicle collaborative search method for target with discontinuous observation characteristic | |
| CN116245871A (en) | Power transmission line abnormal target detection method based on improved YOLOX algorithm | |
| CN116736891A (en) | Autonomous track planning system and method for multi-machine collaborative inspection power grid line | |
| CN111399533B (en) | Heterogeneous multi-unmanned aerial vehicle cooperative task allocation and path optimization method | |
| CN117171893B (en) | Unmanned aerial vehicle flight short board analysis method and system based on artificial intelligence | |
| CN115297303B (en) | Image data acquisition and processing method and device suitable for power grid power transmission and transformation equipment | |
| Changxin et al. | UAV Electric Patrol Path Planning Based on Improved Ant Colony Optimization-A* Algorithm | |
| Medrano et al. | UAS: IoT on-line sensors for power line inspection | |
| CN116627180B (en) | Unmanned aerial vehicle patrol planning method and device, electronic equipment and storage medium | |
| CN112449309B (en) | Active induction type wireless self-organizing network construction method and device and computer equipment | |
| CN111310636A (en) | Thermal imaging and smoke recognition based integrated forest fire prevention IA-PCNN algorithm | |
| CN117474292B (en) | 5G transmission-based scheduling system and scheduling method for network-connected unmanned aerial vehicle | |
| CN116909320B (en) | Electric power collaborative inspection strategy analysis method based on ant colony algorithm | |
| CN113240708B (en) | Bilateral flow semantic consistency method for tracking 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 |