CN113485439B - Unmanned aerial vehicle shutdown path management method and system - Google Patents
Unmanned aerial vehicle shutdown path management method and system Download PDFInfo
- Publication number
- CN113485439B CN113485439B CN202110870365.XA CN202110870365A CN113485439B CN 113485439 B CN113485439 B CN 113485439B CN 202110870365 A CN202110870365 A CN 202110870365A CN 113485439 B CN113485439 B CN 113485439B
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- time
- priority
- parking
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 29
- 239000013598 vector Substances 0.000 claims description 45
- 239000011159 matrix material Substances 0.000 claims description 35
- 238000004458 analytical method Methods 0.000 claims description 21
- 238000013527 convolutional neural network Methods 0.000 claims description 18
- 238000011176 pooling Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000002123 temporal effect Effects 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000003064 k means clustering Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a method and a system for managing a shutdown path of an unmanned aerial vehicle, wherein the method comprises the following steps of obtaining the condition of the unmanned aerial vehicle, and judging the priority of the shutdown of the unmanned aerial vehicle according to the condition of the unmanned aerial vehicle; matching an optimal parking apron for unmanned aerial vehicle parking from a plurality of parking apron which are distributed in advance and arranged on the ground according to the priority of unmanned aerial vehicle parking and the real-time position data of the unmanned aerial vehicle; planning a parking path of the unmanned aerial vehicle according to the position of the optimal parking apron for parking the unmanned aerial vehicle; and controlling the unmanned aerial vehicle to fly to the optimal parking apron for parking according to the parking path of the unmanned aerial vehicle. According to the unmanned aerial vehicle shutdown path management method and system, a plurality of unmanned aerial vehicles can be managed simultaneously, so that centralized management is facilitated; in addition, the invention comprehensively evaluates the shutdown path of the unmanned aerial vehicle according to the condition of the unmanned aerial vehicle and the position of the parking apron, so as to ensure that all unmanned aerial vehicles can safely shutdown.
Description
Technical Field
The invention relates to the field of unmanned aerial vehicle control, in particular to a method and a system for managing a shutdown path of an unmanned aerial vehicle.
Background
In the process of executing the flight task, if an event requiring shutdown occurs, such as a fault or insufficient energy supply, etc., the unmanned aerial vehicle can only return to the flying spot, and the risk of crashing is greatly improved in the process that the unmanned aerial vehicle returns to the flying spot. Therefore, how to solve the problem of safe shutdown of the unmanned aerial vehicle is a urgent problem at present.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method and a system for managing a shutdown path of an unmanned aerial vehicle, which can simultaneously manage a plurality of unmanned aerial vehicles and ensure that the unmanned aerial vehicles can be safely shutdown.
The technical scheme for solving the technical problems is as follows: a method for managing the stop path of unmanned aerial vehicle is used for simultaneously managing multiple unmanned aerial vehicles,
s1, acquiring the condition of an unmanned aerial vehicle, and judging the priority of the unmanned aerial vehicle stopping according to the condition of the unmanned aerial vehicle;
s2, matching an optimal parking apron for the unmanned aerial vehicle to park from a plurality of parking apron which are distributed on the ground in advance according to the priority of the unmanned aerial vehicle parking and the real-time position data of the unmanned aerial vehicle;
s3, planning a parking path of the unmanned aerial vehicle according to the position of the optimal parking apron for parking the unmanned aerial vehicle;
s4, controlling the unmanned aerial vehicle to fly to the optimal parking apron to stop according to the stopping path of the unmanned aerial vehicle.
On the basis of the technical scheme, the invention can be improved as follows.
Further, the step S1 is specifically that,
s11, collecting electric quantity information and fault information of a plurality of unmanned aerial vehicles in real time;
s12, respectively carrying out data processing on the electric quantity information and the fault information of each unmanned aerial vehicle, and correspondingly obtaining the residual flight time and the fault severity level of each unmanned aerial vehicle;
s13, inputting a plurality of frames of residual flight time and fault severity levels of the unmanned aerial vehicle into a pre-trained convolutional neural network for processing, obtaining the priority of the plurality of frames of unmanned aerial vehicle shutdown, and outputting a priority queue.
Further, the convolutional neural network comprises an input layer, a space-time convolutional layer, a pooling layer and an output layer which are sequentially connected;
in the step S13, the specific process of the convolutional neural network to process the remaining flight time and the fault severity level of the plurality of unmanned aerial vehicles is that,
s131, the input layer performs matrix standardization processing on the input residual flight time and fault severity level of a plurality of unmanned aerial vehicles to obtain an input matrix;
s132, the space-time convolution layer carries out space-time convolution operation on the input matrix to obtain a feature vector;
s133, the pooling layer pools the feature vectors to obtain pooled vectors;
and S134, the output layer outputs the pooled vector to obtain the priority of stopping the unmanned aerial vehicle, and outputs a priority queue.
Further, the space-time convolution layer is provided with two convolution kernels, namely a time convolution kernel and a space convolution kernel; the input matrix comprises a time sub-matrix corresponding to the remaining flight time of the unmanned aerial vehicle and a space sub-matrix corresponding to the fault severity level of the unmanned aerial vehicle;
in the step S132, the space-time convolution layer performs a space-time convolution operation on the input matrix, specifically;
s1321, performing vector dot product operation on the time submatrices by utilizing the time convolution check to obtain time characteristic submatrices;
s1322, performing vector dot product operation on the space submatrices by utilizing the space convolution check to obtain space feature submatrices;
s1323, performing a weighting operation on the temporal feature sub-vector and the spatial feature sub-vector to obtain the feature vector.
Further, the S2 is specifically that,
s21, constructing an apron network according to a plurality of apron which are distributed and arranged on the ground in advance;
s22, acquiring the position data of each unmanned aerial vehicle in real time, loading the position data of each unmanned aerial vehicle into the priority queue, and forming a priority position queue by the position data of each unmanned aerial vehicle corresponding to the priority of each unmanned aerial vehicle in the priority queue;
s23, based on the priority position queue, clustering analysis is carried out on the tarmac network by adopting a clustering analysis method, and the optimal tarmac for each unmanned aerial vehicle to stop is obtained.
Further, the step S23 is specifically that,
s231, clustering the tarmac network by using a K-Means clustering algorithm according to the length Q of the priority position queue to obtain Q tarmac sets;
s232, analyzing in the Q apron sets by using a Hungary analysis method based on the priority position queue to obtain an optimal apron set distributed by each unmanned aerial vehicle;
s233, analyzing the set of the tarmac allocated to each unmanned aerial vehicle by adopting a Fei Luoyi de analysis method to obtain the optimal tarmac allocated to each unmanned aerial vehicle.
Further, in S231, the obtained number of tarmac in each tarmac set is within a preset range.
Further, the step S3 is specifically that,
s31, based on a shortest path method, respectively carrying out initial planning on the flight path of each unmanned aerial vehicle according to the real-time position of each unmanned aerial vehicle and the position of the optimal parking apron to obtain an initial planning path of each unmanned aerial vehicle;
s32, judging whether at least two unmanned aerial vehicles exist in all the unmanned aerial vehicles or not according to a time axis, wherein collision occurs when the unmanned aerial vehicles fly according to corresponding initial planned paths;
s33, taking the initial planning path of the unmanned aerial vehicle which cannot collide as a corresponding stopping path of the unmanned aerial vehicle; and adjusting the initial planning path of the unmanned aerial vehicle which is crashed, so that the initial planning path of the unmanned aerial vehicle is not crashed with any other unmanned aerial vehicle, and taking the adjusted initial planning path as a shutdown path corresponding to the unmanned aerial vehicle.
Based on the unmanned aerial vehicle shutdown path management method, the invention further provides an unmanned aerial vehicle shutdown path management system.
A system for managing a parking path of an unmanned aerial vehicle is used for simultaneously managing a plurality of unmanned aerial vehicles, and comprises the following modules,
the system comprises a shutdown priority calculation module, a control module and a control module, wherein the shutdown priority calculation module is used for acquiring the condition of an unmanned aerial vehicle and judging the shutdown priority of the unmanned aerial vehicle according to the condition of the unmanned aerial vehicle;
the optimal apron matching module is used for matching the optimal apron for the unmanned aerial vehicle to stop from a plurality of apron which are distributed in advance and arranged on the ground according to the priority of the unmanned aerial vehicle and the real-time position data of the unmanned aerial vehicle;
a parking path planning module for planning a parking path of the unmanned aerial vehicle according to the position of the optimal parking apron for parking the unmanned aerial vehicle;
and the parking control module is used for controlling the unmanned aerial vehicle to fly to the optimal parking apron for parking according to the parking path of the unmanned aerial vehicle.
The beneficial effects of the invention are as follows: according to the unmanned aerial vehicle shutdown path management method and system, a plurality of unmanned aerial vehicles can be managed simultaneously, so that centralized management is facilitated; in addition, the invention comprehensively evaluates the shutdown path of the unmanned aerial vehicle according to the condition of the unmanned aerial vehicle and the position of the parking apron, so as to ensure that all unmanned aerial vehicles can safely shutdown.
Drawings
FIG. 1 is a flow chart of a method for unmanned aerial vehicle shutdown path management according to the present invention;
FIG. 2 is a process flow diagram of shutdown priority;
FIG. 3 is a schematic diagram of a convolutional neural network;
FIG. 4 is a schematic diagram of priority queue generation;
FIG. 5 is a flow chart of a space-time convolution operation;
FIG. 6 is an optimal tarmac matching flow;
FIG. 7 is a specific flowchart of a clustering analysis of a tarmac network using a clustering analysis method;
FIG. 8 is a flow chart of a downtime path planning;
fig. 9 is a block diagram of a system for managing a parking path of an unmanned aerial vehicle according to the present invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
As shown in fig. 1, a method for managing a downtime path of an unmanned aerial vehicle for simultaneously managing a plurality of unmanned aerial vehicles, includes the steps of,
s1, acquiring the condition of an unmanned aerial vehicle, and judging the priority of the unmanned aerial vehicle stopping according to the condition of the unmanned aerial vehicle;
s2, matching an optimal parking apron for the unmanned aerial vehicle to park from a plurality of parking apron which are distributed on the ground in advance according to the priority of the unmanned aerial vehicle parking and the real-time position data of the unmanned aerial vehicle;
s3, planning a parking path of the unmanned aerial vehicle according to the position of the optimal parking apron for parking the unmanned aerial vehicle;
s4, controlling the unmanned aerial vehicle to fly to the optimal parking apron to stop according to the stopping path of the unmanned aerial vehicle.
In the invention, the parking apron is provided with a plurality of parking apron, so that the unmanned aerial vehicle can select the optimal parking apron to park according to the parking priority without returning to a flying spot after an event needing to park, such as a fault or insufficient energy supply, and the like, thereby greatly reducing the crash risk of the unmanned aerial vehicle.
In this particular embodiment: as shown in fig. 2, the S1 is specifically,
s11, collecting electric quantity information and fault information of a plurality of unmanned aerial vehicles in real time;
s12, respectively carrying out data processing on the electric quantity information and the fault information of each unmanned aerial vehicle, and correspondingly obtaining the residual flight time and the fault severity level of each unmanned aerial vehicle;
s13, inputting a plurality of frames of residual flight time and fault severity levels of the unmanned aerial vehicle into a pre-trained convolutional neural network for processing, obtaining the priority of the plurality of frames of unmanned aerial vehicle shutdown, and outputting a priority queue.
According to the method, the parking priority of the unmanned aerial vehicle is comprehensively evaluated according to the condition of the unmanned aerial vehicle and the position of the parking apron, then the optimal parking apron is determined according to the parking priority, and further a parking path is planned, so that all unmanned aerial vehicles can be safely parked.
Specifically, as shown in fig. 3, the convolutional neural network comprises an input layer, a space-time convolutional layer, a pooling layer and an output layer which are sequentially connected;
as shown in fig. 4, in the S13, the specific process of the convolutional neural network to process the remaining flight time and the fault severity level of a plurality of unmanned aerial vehicles is that,
s131, the input layer performs matrix standardization processing on the input residual flight time and fault severity level of a plurality of unmanned aerial vehicles to obtain an input matrix;
s132, the space-time convolution layer carries out space-time convolution operation on the input matrix to obtain a feature vector;
s133, the pooling layer pools the feature vectors to obtain pooled vectors;
and S134, the output layer outputs the pooled vector to obtain the priority of stopping the unmanned aerial vehicle, and outputs a priority queue.
Furthermore, the space-time convolution layer is provided with two convolution kernels, namely a time convolution kernel and a space convolution kernel; the input matrix includes a temporal sub-matrix corresponding to a remaining time of flight of the drone and a spatial sub-matrix corresponding to a failure severity level of the drone. As shown in fig. 5, in S132, the space-time convolution layer performs a space-time convolution operation on the input matrix, specifically;
s1321, performing vector dot product operation on the time submatrices by utilizing the time convolution check to obtain time characteristic submatrices;
s1322, performing vector dot product operation on the space submatrices by utilizing the space convolution check to obtain space feature submatrices;
s1323, performing a weighting operation on the temporal feature sub-vector and the spatial feature sub-vector to obtain the feature vector.
In the invention, the double-core convolutional neural network is adopted to respectively carry out time convolution and space convolution operation, and then weighting operation is carried out, so as to ensure that more accurate shutdown priority is obtained.
In this particular embodiment: as shown in fig. 6, the S2 is specifically,
s21, constructing an apron network according to a plurality of apron which are distributed and arranged on the ground in advance;
s22, acquiring the position data of each unmanned aerial vehicle in real time, loading the position data of each unmanned aerial vehicle into the priority queue, and forming a priority position queue by the position data of each unmanned aerial vehicle corresponding to the priority of each unmanned aerial vehicle in the priority queue;
s23, based on the priority position queue, clustering analysis is carried out on the tarmac network by adopting a clustering analysis method, and the optimal tarmac for each unmanned aerial vehicle to stop is obtained.
Specifically, as shown in fig. 7, the S23 is specifically,
s231, clustering the tarmac network by using a K-Means clustering algorithm according to the length Q of the priority position queue to obtain Q tarmac sets;
s232, analyzing in the Q apron sets by using a Hungary analysis method based on the priority position queue to obtain an optimal apron set distributed by each unmanned aerial vehicle;
s233, analyzing the set of the tarmac allocated to each unmanned aerial vehicle by adopting a Fei Luoyi de analysis method to obtain the optimal tarmac allocated to each unmanned aerial vehicle.
Further, in S231, the number of tarmac in each obtained tarmac set is within a preset range.
The invention analyzes the parking apron network by adopting a clustering analysis method based on the priority position queue, and can conveniently, quickly and accurately obtain the optimal parking apron.
In this particular embodiment: as shown in fig. 8, the S3 is specifically,
s31, based on a shortest path method, respectively carrying out initial planning on the flight path of each unmanned aerial vehicle according to the real-time position of each unmanned aerial vehicle and the position of the optimal parking apron to obtain an initial planning path of each unmanned aerial vehicle;
s32, judging whether at least two unmanned aerial vehicles exist in all the unmanned aerial vehicles or not according to a time axis, wherein collision occurs when the unmanned aerial vehicles fly according to corresponding initial planned paths;
s33, taking the initial planning path of the unmanned aerial vehicle which cannot collide as a corresponding stopping path of the unmanned aerial vehicle; and adjusting the initial planning path of the unmanned aerial vehicle which is crashed, so that the initial planning path of the unmanned aerial vehicle is not crashed with any other unmanned aerial vehicle, and taking the adjusted initial planning path as a shutdown path corresponding to the unmanned aerial vehicle.
The invention carries out path planning based on the shortest path method, can obtain the optimal shutdown path, can finely adjust the path in space or time when individual paths conflict, ensures that all shutdown paths do not conflict, ensures that the whole shutdown path reaches the optimal state, and integrally improves the shutdown safety.
Based on the unmanned aerial vehicle shutdown path management method, the invention further provides an unmanned aerial vehicle shutdown path management system.
As shown in fig. 9, a system for managing a parking path of a drone for simultaneously managing a plurality of drones, includes the following modules,
the system comprises a shutdown priority calculation module, a control module and a control module, wherein the shutdown priority calculation module is used for acquiring the condition of an unmanned aerial vehicle and judging the shutdown priority of the unmanned aerial vehicle according to the condition of the unmanned aerial vehicle;
the optimal apron matching module is used for matching the optimal apron for the unmanned aerial vehicle to stop from a plurality of apron which are distributed in advance and arranged on the ground according to the priority of the unmanned aerial vehicle and the real-time position data of the unmanned aerial vehicle;
a parking path planning module for planning a parking path of the unmanned aerial vehicle according to the position of the optimal parking apron for parking the unmanned aerial vehicle;
and the parking control module is used for controlling the unmanned aerial vehicle to fly to the optimal parking apron for parking according to the parking path of the unmanned aerial vehicle.
In this particular embodiment: the shutdown priority computation module is specifically configured to,
collecting the electric quantity information and fault information of a plurality of unmanned aerial vehicles in real time;
respectively carrying out data processing on the electric quantity information and the fault information of each unmanned aerial vehicle to correspondingly obtain the residual flight time and the fault severity level of each unmanned aerial vehicle;
and inputting the residual flight time and fault severity level of the multiple unmanned aerial vehicles into a pre-trained convolutional neural network for processing, obtaining the priority of the multiple unmanned aerial vehicles for stopping, and outputting a priority queue.
According to the method, the parking priority of the unmanned aerial vehicle is comprehensively evaluated according to the condition of the unmanned aerial vehicle and the position of the parking apron, then the optimal parking apron is determined according to the parking priority, and further a parking path is planned, so that all unmanned aerial vehicles can be safely parked.
Specifically, the convolutional neural network comprises an input layer, a space-time convolutional layer, a pooling layer and an output layer which are sequentially connected;
the convolutional neural network processes the remaining flight time and fault severity level of a plurality of unmanned aerial vehicles in a specific process,
the input layer performs matrix standardization processing on the input residual flight time and fault severity level of a plurality of unmanned aerial vehicles to obtain an input matrix;
the space-time convolution layer performs space-time convolution operation on the input matrix to obtain a feature vector;
the pooling layer pools the feature vectors to obtain pooled vectors;
and the output layer outputs the pooled vector to obtain the priority of a plurality of unmanned aerial vehicle shutdown, and outputs a priority queue.
Furthermore, the space-time convolution layer is provided with two convolution kernels, namely a time convolution kernel and a space convolution kernel; the input matrix includes a temporal sub-matrix corresponding to a remaining time of flight of the drone and a spatial sub-matrix corresponding to a failure severity level of the drone. The space-time convolution layer carries out space-time convolution operation on the input matrix specifically as follows;
performing vector dot product operation on the time submatrices by utilizing the time convolution check to obtain time characteristic submatrices;
performing vector dot product operation on the space submatrices by utilizing the space convolution check to obtain space characteristic submatrices;
and carrying out weighting operation on the time characteristic sub-vector and the space characteristic sub-vector to obtain the characteristic vector.
In the invention, the double-core convolutional neural network is adopted to respectively carry out time convolution and space convolution operation, and then weighting operation is carried out, so as to ensure that more accurate shutdown priority is obtained.
In this particular embodiment: the best apron matching module is specifically for use in,
constructing a parking apron network according to a plurality of parking apron which are arranged on the ground in a pre-distributed manner;
acquiring the position data of each unmanned aerial vehicle in real time, loading the position data of each unmanned aerial vehicle into the priority queue, and forming a priority position queue by the position data of each unmanned aerial vehicle corresponding to the priority of each unmanned aerial vehicle in the priority queue;
and carrying out cluster analysis on the tarmac network by adopting a clustering analysis method based on the priority position queue to obtain the optimal tarmac for each unmanned aerial vehicle to stop.
Specifically, the clustering analysis method is adopted to perform clustering analysis on the tarmac network, specifically,
clustering the tarmac network by using a K-Means clustering algorithm according to the length Q of the priority position queue to obtain Q tarmac sets;
analyzing in the Q apron sets by using a Hungary analysis method based on the priority position queue to obtain an optimal apron set distributed by each unmanned aerial vehicle;
and analyzing the apron set allocated to each unmanned aerial vehicle by adopting a fee Luo Yide analysis method to obtain the optimal apron allocated to each unmanned aerial vehicle.
Further, the number of tarmac in each obtained tarmac set is within a preset range.
The invention analyzes the parking apron network by adopting a clustering analysis method based on the priority position queue, and can conveniently, quickly and accurately obtain the optimal parking apron.
In this particular embodiment: the shutdown path planning module is particularly adapted to,
based on a shortest path method, respectively carrying out initial planning on the flight path of each unmanned aerial vehicle according to the real-time position of each unmanned aerial vehicle and the position of the optimal parking apron to obtain an initial planning path of each unmanned aerial vehicle;
judging whether at least two unmanned aerial vehicles in all unmanned aerial vehicles collide when flying according to corresponding initial planned paths based on a time axis;
taking the initial planning path of the unmanned aerial vehicle which cannot collide as a corresponding stopping path of the unmanned aerial vehicle; and adjusting the initial planning path of the unmanned aerial vehicle which is crashed, so that the initial planning path of the unmanned aerial vehicle is not crashed with any other unmanned aerial vehicle, and taking the adjusted initial planning path as a shutdown path corresponding to the unmanned aerial vehicle.
The invention carries out path planning based on the shortest path method, can obtain the optimal shutdown path, can finely adjust the path in space or time when individual paths conflict, ensures that all shutdown paths do not conflict, ensures that the whole shutdown path reaches the optimal state, and integrally improves the shutdown safety.
According to the unmanned aerial vehicle shutdown path management method and system, a plurality of unmanned aerial vehicles can be managed simultaneously, so that centralized management is facilitated; in addition, the invention comprehensively evaluates the shutdown path of the unmanned aerial vehicle according to the condition of the unmanned aerial vehicle and the position of the parking apron, so as to ensure that all unmanned aerial vehicles can safely shutdown.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (6)
1. The unmanned aerial vehicle shutdown path management method is characterized by comprising the following steps of: is used for simultaneously managing a plurality of unmanned aerial vehicles, and comprises the following steps,
s1, acquiring the condition of an unmanned aerial vehicle, and judging the priority of the unmanned aerial vehicle stopping according to the condition of the unmanned aerial vehicle;
s2, matching an optimal parking apron for the unmanned aerial vehicle to park from a plurality of parking apron which are distributed on the ground in advance according to the priority of the unmanned aerial vehicle parking and the real-time position data of the unmanned aerial vehicle;
s3, planning a parking path of the unmanned aerial vehicle according to the position of the optimal parking apron for parking the unmanned aerial vehicle;
s4, controlling the unmanned aerial vehicle to fly to the optimal parking apron for parking according to the parking path of the unmanned aerial vehicle;
the step S1 is specifically that,
s11, collecting electric quantity information and fault information of a plurality of unmanned aerial vehicles in real time;
s12, respectively carrying out data processing on the electric quantity information and the fault information of each unmanned aerial vehicle, and correspondingly obtaining the residual flight time and the fault severity level of each unmanned aerial vehicle;
s13, inputting the residual flight time and fault severity level of a plurality of unmanned aerial vehicles into a pre-trained convolutional neural network for processing, obtaining the priority of the shutdown of the unmanned aerial vehicles, and outputting a priority queue;
the convolutional neural network comprises an input layer, a space-time convolutional layer, a pooling layer and an output layer which are sequentially connected;
in the step S13, the specific process of the convolutional neural network to process the remaining flight time and the fault severity level of the plurality of unmanned aerial vehicles is that,
s131, the input layer performs matrix standardization processing on the input residual flight time and fault severity level of a plurality of unmanned aerial vehicles to obtain an input matrix;
s132, the space-time convolution layer carries out space-time convolution operation on the input matrix to obtain a feature vector;
s133, the pooling layer pools the feature vectors to obtain pooled vectors;
s134, the output layer outputs the pooled vector to obtain the priority of the shutdown of a plurality of unmanned aerial vehicles, and outputs a priority queue;
the space-time convolution layer is provided with two convolution kernels, namely a time convolution kernel and a space convolution kernel; the input matrix comprises a time sub-matrix corresponding to the remaining flight time of the unmanned aerial vehicle and a space sub-matrix corresponding to the fault severity level of the unmanned aerial vehicle;
in the step S132, the space-time convolution layer performs a space-time convolution operation on the input matrix, specifically;
s1321, performing vector dot product operation on the time submatrices by utilizing the time convolution check to obtain time characteristic submatrices;
s1322, performing vector dot product operation on the space submatrices by utilizing the space convolution check to obtain space feature submatrices;
s1323, performing a weighting operation on the temporal feature sub-vector and the spatial feature sub-vector to obtain the feature vector.
2. The unmanned aerial vehicle shutdown path management method of claim 1, wherein: the step S2 is specifically that,
s21, constructing an apron network according to a plurality of apron which are distributed and arranged on the ground in advance;
s22, acquiring the position data of each unmanned aerial vehicle in real time, loading the position data of each unmanned aerial vehicle into the priority queue, and forming a priority position queue by the position data of each unmanned aerial vehicle corresponding to the priority of each unmanned aerial vehicle in the priority queue;
s23, based on the priority position queue, clustering analysis is carried out on the tarmac network by adopting a clustering analysis method, and the optimal tarmac for each unmanned aerial vehicle to stop is obtained.
3. The unmanned aerial vehicle shutdown path management method of claim 2, wherein: the step S23 is specifically that,
s231, clustering the tarmac network by using a K-Means clustering algorithm according to the length Q of the priority position queue to obtain Q tarmac sets;
s232, analyzing in the Q apron sets by using a Hungary analysis method based on the priority position queue to obtain an optimal apron set distributed by each unmanned aerial vehicle;
s233, analyzing the set of the tarmac allocated to each unmanned aerial vehicle by adopting a Fei Luoyi de analysis method to obtain the optimal tarmac allocated to each unmanned aerial vehicle.
4. A method of unmanned aerial vehicle shutdown path management according to claim 3, wherein: in S231, the number of tarmac in each obtained tarmac set is within a preset range.
5. The unmanned aerial vehicle shutdown path management method of claim 2, wherein: the step S3 is specifically that,
s31, based on a shortest path method, respectively carrying out initial planning on the flight path of each unmanned aerial vehicle according to the real-time position of each unmanned aerial vehicle and the position of the optimal parking apron to obtain an initial planning path of each unmanned aerial vehicle;
s32, judging whether at least two unmanned aerial vehicles exist in all the unmanned aerial vehicles or not according to a time axis, wherein collision occurs when the unmanned aerial vehicles fly according to corresponding initial planned paths;
s33, taking the initial planning path of the unmanned aerial vehicle which cannot collide as a corresponding stopping path of the unmanned aerial vehicle; and adjusting the initial planning path of the unmanned aerial vehicle which is crashed, so that the initial planning path of the unmanned aerial vehicle is not crashed with any other unmanned aerial vehicle, and taking the adjusted initial planning path as a shutdown path corresponding to the unmanned aerial vehicle.
6. An unmanned aerial vehicle shutdown path management system, characterized in that: is used for simultaneously managing a plurality of unmanned aerial vehicles, comprises the following modules,
the system comprises a shutdown priority calculation module, a control module and a control module, wherein the shutdown priority calculation module is used for acquiring the condition of an unmanned aerial vehicle and judging the shutdown priority of the unmanned aerial vehicle according to the condition of the unmanned aerial vehicle;
the optimal apron matching module is used for matching the optimal apron for the unmanned aerial vehicle to stop from a plurality of apron which are distributed in advance and arranged on the ground according to the priority of the unmanned aerial vehicle and the real-time position data of the unmanned aerial vehicle;
a parking path planning module for planning a parking path of the unmanned aerial vehicle according to the position of the optimal parking apron for parking the unmanned aerial vehicle;
the parking control module is used for controlling the unmanned aerial vehicle to fly to the optimal parking apron for parking according to the parking path of the unmanned aerial vehicle;
the shutdown priority computation module is specifically configured to,
collecting the electric quantity information and fault information of a plurality of unmanned aerial vehicles in real time;
respectively carrying out data processing on the electric quantity information and the fault information of each unmanned aerial vehicle to correspondingly obtain the residual flight time and the fault severity level of each unmanned aerial vehicle;
inputting the residual flight time and fault severity level of a plurality of unmanned aerial vehicles into a pre-trained convolutional neural network for processing, obtaining the shutdown priority of the unmanned aerial vehicles, and outputting a priority queue;
the convolutional neural network comprises an input layer, a space-time convolutional layer, a pooling layer and an output layer which are sequentially connected;
the convolutional neural network processes the remaining flight time and fault severity level of a plurality of unmanned aerial vehicles in a specific process,
the input layer performs matrix standardization processing on the input residual flight time and fault severity level of a plurality of unmanned aerial vehicles to obtain an input matrix;
the space-time convolution layer performs space-time convolution operation on the input matrix to obtain a feature vector;
the pooling layer pools the feature vectors to obtain pooled vectors;
the output layer outputs the pooled vector to obtain the priority of a plurality of unmanned aerial vehicle shutdown, and outputs a priority queue;
the space-time convolution layer is provided with two convolution kernels, namely a time convolution kernel and a space convolution kernel; the input matrix comprises a time sub-matrix corresponding to the remaining flight time of the unmanned aerial vehicle and a space sub-matrix corresponding to the fault severity level of the unmanned aerial vehicle;
the space-time convolution layer carries out space-time convolution operation on the input matrix specifically as follows;
performing vector dot product operation on the time submatrices by utilizing the time convolution check to obtain time characteristic submatrices;
performing vector dot product operation on the space submatrices by utilizing the space convolution check to obtain space characteristic submatrices;
and carrying out weighting operation on the time characteristic sub-vector and the space characteristic sub-vector to obtain the characteristic vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110870365.XA CN113485439B (en) | 2021-07-30 | 2021-07-30 | Unmanned aerial vehicle shutdown path management method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110870365.XA CN113485439B (en) | 2021-07-30 | 2021-07-30 | Unmanned aerial vehicle shutdown path management method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113485439A CN113485439A (en) | 2021-10-08 |
| CN113485439B true CN113485439B (en) | 2023-07-07 |
Family
ID=77943634
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110870365.XA Active CN113485439B (en) | 2021-07-30 | 2021-07-30 | Unmanned aerial vehicle shutdown path management method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113485439B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116859990B (en) * | 2023-06-26 | 2024-04-19 | 北京锐士装备科技有限公司 | Unmanned aerial vehicle flight management method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111158401A (en) * | 2020-01-20 | 2020-05-15 | 北京理工大学 | Distributed unmanned aerial vehicle path planning system and method for encouraging space-time data exploration |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108945503A (en) * | 2018-07-03 | 2018-12-07 | 北京航空航天大学 | A kind of police unmanned plane airplane parking area site selecting method of highway |
| CN108995823B (en) * | 2018-07-26 | 2022-01-04 | 楚山(深圳)新能源科技有限公司 | Unmanned aerial vehicle wireless shared charging parking apron and wireless charging method with priority |
| CN112109575B (en) * | 2020-09-10 | 2022-03-08 | 军事科学院系统工程研究院军事新能源技术研究所 | Charging method, device and system for unmanned aerial vehicle |
| CN112465219A (en) * | 2020-11-25 | 2021-03-09 | 北京化工大学 | Method for constructing airplane general assembly material distribution network based on near field communication |
| CN112241182B (en) * | 2020-12-20 | 2021-03-16 | 深圳联和智慧科技有限公司 | Unmanned aerial vehicle route planning control method and system based on intelligent lamp pole and parking apron |
-
2021
- 2021-07-30 CN CN202110870365.XA patent/CN113485439B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111158401A (en) * | 2020-01-20 | 2020-05-15 | 北京理工大学 | Distributed unmanned aerial vehicle path planning system and method for encouraging space-time data exploration |
Non-Patent Citations (1)
| Title |
|---|
| 基于深度强化学习的无人机数据采集和路径规划研究;牟治宇;张煜;范典;刘君;高飞飞;;物联网学报(03);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113485439A (en) | 2021-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9694765B2 (en) | Control system for an automotive vehicle | |
| CN111462481B (en) | Cloud brain intelligent transportation system comprising multifunctional unmanned vehicle | |
| US11288963B2 (en) | Autonomous vehicles featuring vehicle intention system | |
| CN111487991B (en) | Unmanned aerial vehicle cluster-oriented security level prediction method and system | |
| EP3850551A1 (en) | Systems and methods for managing energy storage systems | |
| CN109109863B (en) | Intelligent device and control method and device thereof | |
| CN113485439B (en) | Unmanned aerial vehicle shutdown path management method and system | |
| CN108615412A (en) | Flight plan analysis system and method for unmanned vehicle | |
| CN111488803A (en) | Airport target behavior understanding system integrating target detection and target tracking | |
| CN109460065A (en) | Unmanned aerial vehicle cluster formation characteristic identification method and system based on potential function | |
| WO2007093224A1 (en) | Decision making unit for autonomous platform | |
| Huang et al. | Sequential experimentation to efficiently test automated vehicles | |
| CN115195748A (en) | Data-driven intelligent automobile personification decision planning system and method | |
| CN111353599A (en) | Correctness preserving optimization for deep neural networks | |
| Kong et al. | Bayesian deep learning for aircraft hard landing safety assessment | |
| EP3413245A1 (en) | Vehicle wash assessment | |
| CN108762225A (en) | A kind of failure in flight control system copes with decision making device | |
| CN111368971B (en) | Unmanned aerial vehicle cluster cooperative landing sequencing method and system | |
| CN116226787B (en) | Commercial vehicle danger probability prediction method, equipment and medium | |
| CN113253292B (en) | Unmanned aerial vehicle early warning processing method and system based on artificial intelligence technology | |
| CN115514787B (en) | Intelligent unmanned aerial vehicle auxiliary decision-making planning method and device for Internet of vehicles environment | |
| CN114721692A (en) | System, method and device for upgrading automatic driving model | |
| US11853068B1 (en) | Vehicle trajectory controller safety margin | |
| CN112561166A (en) | Vehicle scheduling method and device, storage medium and electronic device | |
| CN114462740A (en) | Flight mission evaluation method, device, equipment and computer readable storage medium |
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 |