CN112671451B - Unmanned aerial vehicle data collection method and device, electronic device and storage medium - Google Patents
Unmanned aerial vehicle data collection method and device, electronic device and storage medium Download PDFInfo
- Publication number
- CN112671451B CN112671451B CN202011455224.3A CN202011455224A CN112671451B CN 112671451 B CN112671451 B CN 112671451B CN 202011455224 A CN202011455224 A CN 202011455224A CN 112671451 B CN112671451 B CN 112671451B
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- flight
- target
- energy consumption
- 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
Abstract
One or more embodiments of the present specification provide a method, an apparatus, an electronic device, and a storage medium for collecting data of an unmanned aerial vehicle, where the method, the apparatus, the electronic device, and the storage medium are applied to an unmanned aerial vehicle, and the method includes: determining a target area and determining a flight path model of the target area; determining the flight action of the unmanned aerial vehicle based on the state information and the flight track model of the unmanned aerial vehicle; and when the flight action is finished, determining the information age and energy consumption of all the target sensors so as to acquire and output the uploaded data of the target sensors. One or more embodiments of this description determine the flight action based on unmanned aerial vehicle's state information and flight track model, accomplish and acquire upload data and output according to the information age and the energy consumption of sensor after the flight action. With this information age and the energy consumption through planning unmanned aerial vehicle's flight route and combining sensor upload data to can in time update sensor upload data, thereby reduce the information age of uploading data and the energy consumption of sensor and unmanned aerial vehicle.
Description
Technical Field
One or more embodiments of the present specification relate to the field of unmanned aerial vehicle control technologies, and in particular, to an unmanned aerial vehicle data collection method, device, electronic device, and storage medium.
Background
With the continuous evolution of the internet of things, various internet of things devices, such as an environmental monitoring sensor, a health medical device, a monitoring device, and the like, exist in a network, and the sensor devices in the network need to collect data and transmit the data to a remote site, and the remote site is responsible for processing the data of the sensor to obtain corresponding information or make a corresponding decision. Here, the concept of age of information was introduced in order to evaluate the freshness of sensor data information in the network. The age of the information is considered from the perspective of the remote site and is defined as the time elapsed since the latest data packet from a sensor was generated. Due to the low capabilities and limited power of the sensor devices, some sensor devices in the network cannot transmit data directly to the remote site. The unmanned aerial vehicle is introduced to provide a data transmission channel with higher quality for the sensor equipment, reduce the energy consumption and the transmission failure probability of data transmission and forward the sensor data to the remote station.
With the continuous improvement of the quality requirements of users on the data of the internet of things, how to obtain the data with the minimum information age and the most 'fresh' by using the unmanned aerial vehicle becomes a hot problem to be solved urgently in the field.
Disclosure of Invention
In view of this, an object of one or more embodiments of the present specification is to provide a method, an apparatus, an electronic apparatus, and a storage medium for collecting data of a drone.
Based on the above purpose, one or more embodiments of the present specification provide a method for collecting data of an unmanned aerial vehicle, where the method is applied to an unmanned aerial vehicle, and the method includes:
determining a target area and determining a flight track model of the target area;
determining the flight action of the unmanned aerial vehicle based on the state information of the unmanned aerial vehicle and the flight track model;
when the unmanned aerial vehicle finishes the flight action, determining the information age and the energy consumption of all target sensors in a scanning range, acquiring the uploaded data of at least one target sensor according to the information age and the energy consumption, and allocating channel resources for the target sensor;
outputting the uploaded data to enable an external processor to update the information age of the corresponding target sensor according to the uploaded data.
In some embodiments, said obtaining uploaded data of at least one of said target sensors based on said age of information and said energy expenditure comprises:
and determining the channel information of the unmanned aerial vehicle and the sensor energy of the target sensor, and combining the information age and the energy consumption to select the target sensor.
In some embodiments, the flight trajectory model adopts a double-delay depth deterministic strategy algorithm, the algorithm introduces a deep neural network, and a network is trained by combining an actor network and two critic networks; the operator network comprises an online network and a target network, and the critical network comprises the online network and the target network.
In some embodiments, after determining the flight trajectory model of the target region, the method further includes:
determining the data transmission rate of the unmanned aerial vehicle under the flight trajectory model;
and if the data transmission rate is smaller than a set threshold value, updating the model parameters of the flight trajectory model.
In some embodiments, after the outputting the upload data, the method further comprises:
judging whether the unmanned aerial vehicle finishes data acquisition of all target sensors in the target area;
and if so, indicating the unmanned aerial vehicle to enter another target area.
Based on the same idea, one or more embodiments of this specification also provide an unmanned aerial vehicle data collection device, is applied to unmanned aerial vehicle, includes:
the determining module is used for determining a target area and determining a flight path model of the target area;
the calculation module is used for determining the flight action of the unmanned aerial vehicle based on the state information of the unmanned aerial vehicle and the flight track model;
the acquisition module is used for determining the information age and the energy consumption of all target sensors in a scanning range when the unmanned aerial vehicle finishes the flight action, acquiring the uploaded data of at least one target sensor according to the information age and the energy consumption, and allocating channel resources for the target sensor;
and the transmission module outputs the uploaded data so that an external processor can update the information age of the corresponding target sensor according to the uploaded data.
In some embodiments, the obtaining module obtains the uploaded data of at least one of the target sensors according to the age of the information and the energy consumption, and comprises:
and determining the channel information of the unmanned aerial vehicle and the sensor energy of the target sensor, and combining the information age and the energy consumption to select the target sensor.
In some embodiments, after the determining module determines the flight trajectory model of the target area, the determining module further comprises:
determining the data transmission rate of the unmanned aerial vehicle under the flight trajectory model;
and if the data transmission rate is smaller than a set threshold value, updating the model parameters of the flight trajectory model.
Based on the same concept, one or more embodiments of the present specification further provide an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the method according to any one of the above when executing the program.
Based on the same concept, one or more embodiments of the present specification also provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to implement the method of any one of the above.
As can be seen from the foregoing, in one or more embodiments of the present specification, a data collection method, device, electronic device, and storage medium for a drone are provided, where the method includes: determining a target area and determining a flight track model of the target area; determining the flight action of the unmanned aerial vehicle based on the state information and the flight track model of the unmanned aerial vehicle; when the unmanned aerial vehicle finishes the flight action, determining the information age and the energy consumption of all target sensors in a scanning range, acquiring the uploaded data of at least one target sensor according to the information age and the energy consumption, and distributing channel resources for the target sensor; and outputting the uploaded data so that the external processor can update the information age of the corresponding target sensor according to the uploaded data. One or more embodiments of this description determine the flight action of unmanned aerial vehicle based on unmanned aerial vehicle's state information and flight track model to according to the information age and the energy consumption acquisition sensor of sensor upload data and output after accomplishing the flight action. With this information age and the energy consumption through planning unmanned aerial vehicle's flight route and combining sensor upload data to can in time update sensor upload data, thereby reduce the information age of uploading data and the energy consumption of sensor and unmanned aerial vehicle.
Drawings
In order to more clearly illustrate one or more embodiments or prior art solutions of the present specification, the drawings that are needed in the description of the embodiments or prior art will be briefly described below, and it is obvious that the drawings in the following description are only one or more embodiments of the present specification, and that other drawings may be obtained by those skilled in the art without inventive effort from these drawings.
Fig. 1 is a schematic flow chart of a method for collecting data of a drone according to one or more embodiments of the present disclosure;
fig. 2 is a schematic view of a scenario of a data collection method of a drone according to one or more embodiments of the present disclosure;
fig. 3 is a schematic view of a drone flight strategy of a drone data collection method according to one or more embodiments of the present disclosure;
fig. 4 is a simulation comparison diagram of a data collection method of a drone according to one or more embodiments of the present disclosure based on the number of target sensors;
fig. 5 is a schematic diagram illustrating comparison of simulation based on the side length of a target area in a data collection method of an unmanned aerial vehicle according to one or more embodiments of the present disclosure;
fig. 6 is a schematic diagram illustrating simulation comparison of a data collection method of a drone based on the number of hovers traversing all target sensors according to one or more embodiments of the present disclosure;
fig. 7 is a simulation comparison diagram of a unmanned aerial vehicle data collection method based on energy consumption of traversing all target sensors according to one or more embodiments of the present disclosure;
fig. 8 is a schematic structural diagram of an unmanned aerial vehicle data collection device according to one or more embodiments of the present disclosure;
fig. 9 is a schematic structural diagram of an electronic device according to one or more embodiments of the present disclosure.
Detailed Description
To make the objects, technical solutions and advantages of the present specification more apparent, the present specification is further described in detail below with reference to the accompanying drawings in combination with specific embodiments.
It should be noted that technical terms or scientific terms used in the embodiments of the present specification should have a general meaning as understood by those having ordinary skill in the art to which the present disclosure belongs, unless otherwise defined. The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element, article, or method step that precedes the word comprises, or does not exclude, other elements, articles, or method steps, and the like. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
As described in the background section, when a remote station receives data from a sensor, then at the current time, the age of the information from the sensor is the time interval from the time the data was collected by the sensor to the current time, and as time progresses, the age of the information increases linearly until the remote station receives a new data update for the sensor device. Intuitively, it is the age of the data information of the sensors in the network that continues to increase until the data is updated again at the remote site, collapsing to a low point, and then over time, the age of the information increases linearly until it is traversed again, and then decreases to a low point. In the data collection process, the data information age of the sensor device, the data transmission energy consumption of the sensor device and the flight energy consumption of the unmanned aerial vehicle are main factors considered in the data collection process of the unmanned aerial vehicle. How to plan the route of the unmanned aerial vehicle for acquiring data and keep the data of the sensor fresh is a hot problem to be solved urgently in the field.
In combination with the above practical situation, one or more embodiments of this specification provide an unmanned aerial vehicle data collection scheme, determine unmanned aerial vehicle's flight action based on unmanned aerial vehicle's state information and flight trajectory model to accomplish the information age and the energy consumption of flight action after and obtain sensor's upload data and output according to the sensor. With this information age and the energy consumption through planning unmanned aerial vehicle's flight route and combining sensor upload data to can in time update sensor upload data, thereby reduce the information age of uploading data and the energy consumption of sensor and unmanned aerial vehicle.
Referring to fig. 1, a schematic flow chart of a method for collecting data of an unmanned aerial vehicle according to an embodiment of the present specification specifically includes the following steps:
The step aims to calculate the flight track of the unmanned aerial vehicle in the target area according to the target area and the flight track model. Where multiple target sensor devices may be contained in the target area.
In some application scenarios, a data collection area may be divided into a plurality of target areas, and the area division method may be according to the number of sensor devices in a network, may be according to the period of data collection of the sensor devices, may be a classic k-means clustering method, and may also be according to the computing capability of a network data training module and the requirements of information ages of the sensor devices. The purpose of regional division is to improve the network data training efficiency. Then, the unmanned aerial vehicle trains a flight track model of each target area through an external network model training module according to the feedback data of the unmanned aerial vehicle and the position coordinates of the sensor; or the unmanned aerial vehicle trains a flight trajectory model of each target area according to the position coordinates of the sensor and the environment feedback data.
In some application scenes, the flight path model adopts a double-delay depth certainty strategy algorithm, the algorithm introduces a depth neural network, and a training network combining an actor network and two critic networks is adopted; the actor network comprises an online network and a target network, and the critic model comprises the online network and the target network.
Then, in some application scenarios, it may be determined whether the trajectory model at the current time needs to be updated. And if the model parameters need to be updated, updating the model parameters. The judgment criterion may be the time for setting model update, or may be the network utility obtained by the unmanned aerial vehicle under the current model, and if the performance is poor, the model parameters need to be updated. Namely, after determining the flight trajectory model of the target area, the method further includes: determining the data transmission rate of the unmanned aerial vehicle under the flight trajectory model; and if the data transmission rate is smaller than a set threshold value, updating the model parameters of the flight trajectory model. Meanwhile, in some application scenarios, whether the duration of the last model parameter update time is greater than a set threshold or not may be determined, whether the information age of the average target sensor is greater than the set threshold or not may be determined, and whether the energy consumption of the sensor and the unmanned aerial vehicle is greater than the set threshold or not may be determined. To judge whether the model parameters of the flight path model need to be updated. Those skilled in the art can make specific settings according to different specific application scenarios.
In a specific application scenario, a dual-delay depth deterministic strategy algorithm can be adopted to train data of the network. The double-delay depth certainty strategy algorithm comprises that the state space is the position coordinate of the unmanned aerial vehicle, the current information age of the sensor, the traversal condition of the sensor in the current area and the like. The action space comprises the flight direction, the flight distance, the flight speed and the like of the unmanned aerial vehicle. The return function is the information age of the sensor device, the weighted sum of the flight energy of the unmanned aerial vehicle and the transmission energy of the sensor device, the configured information age, the flight energy of the unmanned aerial vehicle and the weight value of the transmission energy of the sensor device can be adjusted according to the network state or the network requirement, for example, if the network bias reduces the flight energy of the unmanned aerial vehicle, the weight value of the energy consumption of the unmanned aerial vehicle is increased, and vice versa; if the network is heavier to reduce the energy consumption of the sensor, the weight value of the transmission energy consumption of the sensor is increased, and vice versa.
And 102, determining the flight action of the unmanned aerial vehicle based on the state information of the unmanned aerial vehicle and the flight track model.
This step aims at, confirms the flight action that unmanned aerial vehicle will carry out at present for control unmanned aerial vehicle following flight relevant action. The state information of the drone may include information ages of current data of all sensors in the target area, current position coordinates of the drone, traversal conditions of each sensor in the target area, and the like, and the traversal conditions may be the number of times of traversal of the sensor device after the drone enters the target area, or binary values indicating whether the sensor is traversed, for example, the traversal is 1, the traversal is not 0, and the like. The position coordinates are related to the unmanned aerial vehicle-initialized position coordinates. The flight action may include flight direction, flight distance, flight speed, and the like.
103, when the unmanned aerial vehicle finishes the flight action, determining the information age and the energy consumption of all target sensors in a scanning range, acquiring the uploaded data of at least one target sensor according to the information age and the energy consumption, and allocating channel resources for the target sensor.
The step aims to determine the information age and energy consumption of the target sensor, and based on the information age and energy consumption, determine which target sensors need to acquire the uploaded data and allocate channel resources for the target sensors to transmit the data. The method comprises the steps that uploaded data of target sensors are determined to be obtained, the uploaded data can be sorted according to information ages, and then a plurality of the uploaded data are obtained; or determining which target sensor to acquire through information age in combination with other auxiliary data, and the like. For example, after the drone executes the flight direction, flight distance, and flight speed decisions, the drone hovers to a location for data collection. The unmanned aerial vehicle selects one or more sensors according to the channel information of the sensors and based on the service capacity of the unmanned aerial vehicle, the information age of the sensors and the energy consumption of the sensors, allocates channel resources for the sensors and collects data.
In some application scenarios, the obtaining upload data of at least one of the target sensors according to the information age and the energy consumption comprises: and determining the channel information of the unmanned aerial vehicle and the sensor energy of the target sensor, and combining the information age and the energy consumption to select the target sensor.
And 104, outputting the uploaded data so that an external processor can update the information age of the corresponding target sensor according to the uploaded data.
The step aims to output the acquired uploading data so as to update the information age of the corresponding sensor. The output process can be in the process of flying of the unmanned aerial vehicle, namely, after the unmanned aerial vehicle finishes data collection at one place, the unmanned aerial vehicle can execute the next flying action, and when the next flying action is executed, the acquired data is output. And outputting the uploaded data, and storing, displaying, using or reprocessing the uploaded data. According to different application scenarios and implementation requirements, the specific output mode of the uploaded data can be flexibly selected.
For example, for an application scenario in which the method of the present embodiment is executed on a single device, the upload data may be directly output in a display manner on a display section (a display, a projector, etc.) of the current device, so that an operator of the current device can directly see the content of the upload data from the display section.
For another example, for an application scenario executed on a system composed of multiple devices by the method of this embodiment, the uploaded data may be sent to other preset devices serving as receivers in the system through any data communication manner (e.g., wired connection, NFC, bluetooth, wifi, cellular mobile network, etc.), so that the preset devices receiving the uploaded data may perform subsequent processing on the uploaded data. Optionally, the preset device may be a preset server, and the server is generally arranged at a cloud end and used as a data processing and storage center, which can store and distribute uploaded data; the receiver of the distribution is a terminal device, and the holder or operator of the terminal device may be a drone operator, a manager related to the target area, an entity needing to use the uploaded data, an individual, and the like.
For another example, for an application scenario executed on a system composed of multiple devices, the method of this embodiment may directly send the upload data to a preset terminal device in any data communication manner, where the terminal device may be one or more of the foregoing paragraphs.
Then, in some application scenarios, the unmanned aerial vehicle completes traversal of all sensors in the current target area, and the unmanned aerial vehicle enters the next data collection area, which is also determined according to the current training model. And executing the decision of the flight direction, the flight distance and the flight speed according to the training model of the next region and the current state. Namely, after the uploading data is output, the method further includes: judging whether the unmanned aerial vehicle finishes data acquisition of all target sensors in the target area; and if so, indicating the unmanned aerial vehicle to enter another target area.
In a specific application scenario, in the flight scenario of the unmanned aerial vehicle shown in fig. 2 and 3, there are one unmanned aerial vehicle device, one remote station, and M target sensor devices in the network. As shown in fig. 2, the data transmission process in the network is divided into two phases: the first stage sensor transmits the collected data to the unmanned aerial vehicle, the unmanned aerial vehicle is in a hovering state at the moment, the second stage unmanned aerial vehicle transmits the received data to the remote site, and the unmanned aerial vehicle is in a flying stage at the moment. The unmanned aerial vehicle has two states in the network, one is a flight state in which the unmanned aerial vehicle transmits collected data to a remote site, and the other is a hovering state in which the unmanned aerial vehicle receives data from a sensor. As shown in fig. 3, the drone is always in the hover/flight alternate process in the network. And when the unmanned aerial vehicle flies to the next suspension point, the data collected by the previous suspension point can be ensured to be transmitted to the remote station.
In the t-th unmanned aerial vehicle hovering/flying process, a channel model between the unmanned aerial vehicle and the target sensor is modeled into a line-of-sight and non-line-of-sight combined transmission model, and the channel model
It is established that,
wherein f is c Is the center frequency, alpha is the path loss factor, eta 1 ,η 2 (η 2 ＞η 1 > 1) is the extreme path loss factor for line of sight and non-line of sight respectively, and c is the speed of light. Los refers to line-of-sight channel, NLos refers to non-line-of-sight channel, d m Refers to the transmission distance between the drone and the sensor. In fact, the line-of-sight path loss probability depends on the propagation environment, and in the t-th flight \ hover process, the probability that the channel between the unmanned aerial vehicle and the target sensor m is the line-of-sight
In order to realize the purpose,
wherein C and D represent propagation parameters,
indicating the elevation angle at which the drone is transported with the sensor,where H represents the flying height of the drone,
representing the horizontal distance of the drone from the target sensor m. Then, the probability that the channel between the drone and the target sensor m is not line of sight
Is composed of
At time t, the channel gain between the drone and the target sensor m
Is composed of
Wherein the content of the first and second substances,
representing a normalized line-of-sight probability.
Representing the channel gain at a transmission distance of 1 meter. Data transmission rate from unmanned aerial vehicle to target sensor m
In order to realize the purpose,
data transmission rate of unmanned aerial vehicle and remote station
In order to realize the purpose,
wherein the content of the first and second substances,
representing the bandwidth resources allocated by the drone to target sensor m,
representing the transmission power, σ, of the target sensor m 2 Representing the channel gaussian white noise.
Indicating the bandwidth allocated by the drone to send data to the base station,
representing the transmission power at which the drone transmits data to the base station,
representing the channel gain of the drone to the base station.
Thereafter, the concept of information age is introduced, which is considered from the perspective of the remote site. Receiving data of a certain sensor device at a remote station, wherein the data is not updated at any time tau, and the time when the sensor m collects the data is o m (τ), then the information age of the sensor data is
Until there is a new data update at the remote site, then o m (τ) is changed to the time when the updated data is generated.
Introducing a binary parameter
Indicating whether sensor m was scheduled by the drone, i.e.,
specifically, at the time when the t-th hover/flight procedure ends, the information age of the data of sensor m
In order to realize the purpose,
wherein, t smp,t The time interval from the time of acquiring the uploading data to the time of uploading the data is represented by the sensor; t is t col,t Expressed as the time sensor data is uploaded to the drone; t is t fly,t Representing the time of flight of the drone. When the unmanned aerial vehicle flies to the next suspension point, all the data collected by the last suspension point are unloaded.
Age of information representing data of the sensor device at the time the t-1 th hover/flight procedure ends.
The information age sum a of the data of all sensor devices in the network t In order to realize the purpose,
energy consumption in the network is divided into two parts, namely energy consumption of the sensor and energy consumption of flight of the unmanned aerial vehicle.
Energy consumption of sensor m during the t-flight/hover
In order to realize the purpose of the method,
wherein the content of the first and second substances,
representing the amount of data collected by target sensor m during the t-th flight/hover.
Total energy consumption of all sensor devices in the network
In order to realize the purpose,
the flight energy consumption of the drone is,
wherein the content of the first and second substances,
representing the energy consumption of the drone in flight and hovering, respectively. V is the flight speed of the drone,
representing time of flight, U, of the drone tip Representing the rotational speed of the drone blade. ρ represents the air density and Λ represents the rotor area. P 0 And P i Is two fixed values representing the blade profile power and the induced drag power, respectively, at hover. V is 0 Denotes the average rotor induced velocity, d 0 And s represent fuselage drag ratio and rotor stability factor, respectively.
[l t ，θ t ，V t ]Representing the flight decision for the drone to fly/hover at the t-th flight,in order to achieve the purpose of minimizing the information age of the data of the sensor, the energy consumption of the sensor and the flight energy consumption of the unmanned aerial vehicle, a utility function U of the network is defined as,
that is, what the present embodiment is to achieve is:
s.t.c1：V t ≤υ max
c2：x min ≤x t ≤x max ，y min ≤y t ≤y max ，
wherein l t Distance of flight, θ, for the t-th hover/flight of the drone t Flight direction for the t-th hover/flight of the drone, V t Flight speed, v, for the t-th hover/flight of the drone max Is a speed threshold of the drone, x min ，x max ，y min ，y max Is the extreme coordinates of the target area and,
the number of sensors scheduled for drones, δ is the sensor number threshold scheduled for drones. T represents the total number of flight/hover processes, E [ ·]Representing the desired function for a limited number of flight/hover processes. ζ and ω represent weighting coefficients of the energy consumption of the target sensor and the drone, respectively.
Representing the energy consumption of the UAV during a hover/flight.
By optimizing the flight distance, flight direction, flight speed and channel allocation of the unmanned aerial vehicle, the weighted sum of the average information age, the sensor energy and the unmanned aerial vehicle energy is maximized. Meanwhile, the limiting conditions are as follows: the flight speed of the unmanned aerial vehicle is lower than a threshold value, the flight area of the unmanned aerial vehicle is limited, the total communication bandwidth of the unmanned aerial vehicle is limited, and the number of sensors for parallel scheduling of the unmanned aerial vehicle is limited.
Defining a state space set of the network, wherein in the t-th hovering/flying process, the state space of the unmanned aerial vehicle is s t ＝<q t ,A t ,C>First part q t ＝[x t ,y t ] T Representing the current position coordinates of the drone, second part
Age of information representing data of all sensors in the network, third part
Indicating the scheduling status of each sensor in the current area if
Indicating that the sensor is serviced by the drone.
Defining the action space of the unmanned aerial vehicle as a t ＝<l t ,θ t ,V t ,b t >Wherein l is t Representing the flight distance, theta t ∈(0,2π]Indicating the direction of flight of the drone.
The reward equation for a drone is defined as,
The state transition probability is that when the unmanned aerial vehicle is in accordance with the current state s t Selection action a t Then, the next state s is entered t +1 The transition probability of this state is denoted as P(s) t+1 |s t ,a t ). Based on assumptions about the evolution of drone mobility and information age, this series of state changes over time can be validated to conform to the markov chain process, specific transition probabilities
In order to realize the purpose of the method,
the proposed algorithm is evolved from the Q-learning algorithm. A long-term discount utility function is defined as,
wherein γ ∈ (0, 1)]Representing a discount factor, gamma t-1 The discount factor of the first t-1 item state transition process is represented, and the above expression can be represented as an optimization equation of the unmanned plane path planning process of the state transition process. E π [·]Representing the desired function under all policies. According to the Beltzmann optimization equation, the optimal utility function is obtained as,
further, the right side of the above formula is rewritten as,
then, obtain
Wherein, the first and the second end of the pipe are connected with each other,
representing a set of actions of the drone.
The optimal utility function equation can be derived from Q * (s, a) obtaining a mixture of,
ε∈(0,1]the learning rate is represented, and two conditions that the Q-learning method converges to the optimal solution are met: 1) The state transition probability under the optimal stationary control strategy is stationary; 2)
Is a finite value; 3) The state-action pairs are accessed indefinitely.
Because the state space of unmanned aerial vehicle path planning is huge, on the basis of a Q-learning algorithm, a deep neural network is introduced, and based on an operator-critic algorithm framework, a double-delay deep certainty strategy algorithm is provided to solve the unmanned aerial vehicle path optimization problem in the data collection process.
In a specific application scenario, the shown flight trajectory model algorithm for determining the target area has three main networks, namely an operator network and two critic networks. The actor network includes two networks, namely an online network and a target network. Each Critic network includes two networks, namely an online network and a target network. The network parameters of the respective network are introduced,
respectively representing network parameters of an online network and a target network in an operator network,
respectively represent; online network and target network parameters in two Critic networks. The algorithm comprises a playback memory storage space D for storing historical experience data in a training process, a small batch of samples I for network parameter training, and random sample selection for breaking the correlation between experiences. The algorithm has the main characteristics that 1) the algorithm is compared with a depth certainty strategy gradient algorithm, the algorithm comprises two critic networks, the minimum Q-value in the two critic networks is taken, and the problem of over-estimation is solved; 2) A delay updating strategy is adopted, and the updating delay of the parameters of the target network is slower than that of the parameters of the online network; 3) the smoothness of the target network enables the Q equation to be changed smoothly in all the action choices by adding noise to the selected actions, and the action selection strategy is less affected by errors of the Q equation.
Updating process of the critic network:
in the proposed algorithm, the goal of the critic network is to emulate a Q-table without dimension constraints. The Deep Q-learning algorithm (DQN) introduces a Deep neural network as an evaluator of the equation. The critic network is trained by continuously minimizing a loss function
As shown in the drawing, it is shown that,
wherein
s t Represents a state space, a t Representing the motion space, z t Which is indicative of a target value for the target,in particular, as shown in the figure,
during the training process, small batches are sampled
Sampled from the playback memory D for training of network parameters. Based on a gradient descent mechanism, parameters
The update procedure of (a) is as follows,
wherein, the first and the second end of the pipe are connected with each other,
representing loss function
For parameter
The gradient value of (a).
Representing the desired function in different states. Q i Represents the Q-value of the online network of the ith (i =1,2) Critic network.
Represents Q i For the parameters
The gradient value of (a).
Indicating the number of samples sampled in small batches. Alpha (alpha) ("alpha") c Indicating the learning rate of the Critic network.
Updating process of the Actor network:
the purpose of Actor network training is to generate a deterministic strategy μ. A gradient descent algorithm is used to iteratively evaluate and refine the strategy mu. Based on small batch samples I, and network parameters
To obtain
Wherein the content of the first and second substances,
the Q-value function representing the first Critic network for all the small batches of samples is the average of the gradient values for the action taken.
Represents the gradient value of the Q-value function of the first Critic network for action a.
Representing the gradient values of the policy function for different states.
Network parameters
The update is that,
wherein alpha is a Indicating the learning rate of the Actor network.
The parameters of the target network of the Actor network and the critic network are updated slower than those of the online network, the parameters of the target network are updated to,
wherein the value v represents an update coefficient of a parameter of a target network of the Actor network and the critic network.
In a specific application scenario, the effect of the scheme can be further explained through simulation, the data collection area of the unmanned aerial vehicle is a 200 × 200 area, 40 sensor devices are totally deployed, it is assumed that the unmanned aerial vehicle can collect data of three sensor nodes at most simultaneously, channel propagation parameters C and D are respectively set to 0.14 and 11.95, a path loss factor is set to 2, the carrier center frequency is 2GHz, and an additional path loss factor η is provided 1 ,η 2 Set to 1.2 and 3, respectively. The flying height of the unmanned aerial vehicle is 50.
The parameters of the proposed dual-delay deep deterministic strategy algorithm are set to be that in simulation, a fully-connected deep neural network of 300 neurons at 2 layers is adopted, and the ReLU function and the tanh function are respectively adopted as the activation function. Playback memory storage space is 500000, batch sample size is 2000, and the learning discount factor is set to 0.99. The learning rate of the actor network is 0.0001, the learning rate of the critic network is 0.001, and the maximum iteration number is E max Set to 2000, the maximum number of steps per iteration is T max Set to 1000. Because sensor equipment is evenly distributed at random in the network, in this simulation, divide unmanned aerial vehicle data collection area into 4 regions on average, at this moment, the model training has better convergence effect.
Three comparison algorithms are introduced to highlight the superiority of the proposed algorithm.
Comparison algorithm 1: planning the unmanned aerial vehicle path based on a DRL algorithm;
comparison algorithm 2: an unmanned aerial vehicle path planning algorithm based on the operator-critic of the composite action;
comparison algorithm 3: a greedy algorithm based on distance.
As shown in fig. 4: at 100X 100m 2 Within the area, the average information age of the data of the sensors in the network changes as the number of sensors increases. In the algorithm, as the number of sensors increases, the average information age of the data increases first and then decreases, so that the algorithm can effectively reduce the average information age by comparing with other algorithms. As shown in fig. 5: the number of sensors in a sub-area (namely a target area) for collecting data of the unmanned aerial vehicle is fixed, the collecting area of the sub-area is enlarged, and the change condition of the method along with the increase of the side length of the sub-area is verified. As the side length of the sub-region is increased, the average information age in the network is increased, and compared with a comparison algorithm, the algorithm can obtain the minimum average information age. As shown in fig. 6, as the side length of the sub-area increases, the number of hover/flight processes traversed by the sub-area sensor increases, and compared with the comparison algorithm, the proposed algorithm can obtain the minimum number of hover/flight processes traversed by the sub-area sensor. As shown in fig. 7, as the side length of the sub-area increases, the energy consumption of the drone increases, and compared with the comparison algorithm, the proposed algorithm can achieve the minimum energy consumption of the drone.
In combination with the above practical situations, one or more embodiments of the present specification provide a method for collecting data of an unmanned aerial vehicle, where the method is applied to an unmanned aerial vehicle, and the method includes: determining a target area and determining a flight track model of the target area; determining the flight action of the unmanned aerial vehicle based on the state information and the flight track model of the unmanned aerial vehicle; when the unmanned aerial vehicle finishes the flight action, determining the information age and the energy consumption of all target sensors in a scanning range, acquiring the uploaded data of at least one target sensor according to the information age and the energy consumption, and allocating channel resources for the target sensor; and outputting the uploaded data so that the external processor can update the information age of the corresponding target sensor according to the uploaded data. One or more embodiments of this description determine the flight action of unmanned aerial vehicle based on unmanned aerial vehicle's state information and flight track model to according to the information age and the energy consumption acquisition sensor of sensor upload data and output after accomplishing the flight action. With this information age and the energy consumption through planning unmanned aerial vehicle's flight route and combining sensor upload data to can in time update sensor upload data, thereby reduce the information age of uploading data and the energy consumption of sensor and unmanned aerial vehicle.
It should be noted that the method of one or more embodiments of the present disclosure may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the devices may perform only one or more steps of the method of one or more embodiments of the present disclosure, and the devices may interact with each other to complete the method.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Based on the same inventive concept, one or more embodiments of the present specification further provide an unmanned aerial vehicle data collection device, as shown in fig. 8, applied to an unmanned aerial vehicle, including:
a determining module 801, configured to determine a target area and determine a flight trajectory model of the target area;
the calculation module 802 determines the flight action of the unmanned aerial vehicle based on the state information of the unmanned aerial vehicle and the flight trajectory model;
an obtaining module 803, configured to determine information ages and energy consumptions of all target sensors within a scanning range when the unmanned aerial vehicle completes the flight action, obtain upload data of at least one target sensor according to the information ages and the energy consumptions, and allocate a channel resource to the target sensor;
the transmission module 804 outputs the uploaded data, so that the external processor can update the information age of the corresponding target sensor according to the uploaded data.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, the functionality of the various modules may be implemented in the same one or more pieces of software and/or hardware in implementing one or more embodiments of the present description.
The device of the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
As an optional embodiment, the obtaining module 803 is further configured to:
and determining the channel information of the unmanned aerial vehicle and the sensor energy of the target sensor, and combining the information age and the energy consumption to select the target sensor.
As an optional embodiment, the flight trajectory model adopts a double-delay depth deterministic strategy algorithm, the algorithm introduces a deep neural network, and a training network combining an actor network and two critic networks is adopted; the actor network comprises an online network and a target network, and the critic model comprises the online network and the target network.
As an alternative embodiment, the determining module 801 is further configured to:
determining the data transmission rate of the unmanned aerial vehicle under the flight trajectory model;
and if the data transmission rate is less than a set threshold value, updating the model parameters of the flight track model.
As an optional embodiment, the transmission module 804 is further configured to:
judging whether the unmanned aerial vehicle finishes data acquisition of all target sensors in the target area;
and if so, indicating the unmanned aerial vehicle to enter another target area.
One or more embodiments of the present specification further provide an electronic device based on the same inventive concept. The electronic device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to implement the unmanned aerial vehicle data collection method according to any one of the embodiments.
Fig. 9 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 910, a memory 920, an input/output interface 930, a communication interface 940, and a bus 950. Wherein the processor 910, the memory 920, the input/output interface 930, and the communication interface 940 are communicatively coupled to each other within the device via a bus 950.
The processor 910 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 920 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 920 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 920 and called by the processor 910 to be executed.
The input/output interface 930 is used for connecting an input/output module to realize information input and output. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 940 is used for connecting a communication module (not shown in the figure) to implement communication interaction between the present device and other devices. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, bluetooth and the like).
It should be noted that although the above-mentioned device only shows the processor 910, the memory 920, the input/output interface 930, the communication interface 940 and the bus 950, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only the components necessary to implement the embodiments of the present disclosure, and need not include all of the components shown in the figures.
The device of the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, one or more embodiments of the present specification further provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to implement a method for unmanned aerial vehicle data collection as described in any of the above embodiments.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, for storing information may be implemented in any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the spirit of the present disclosure, features from the above embodiments or from different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present description as described above, which are not provided in detail for the sake of brevity.
In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures for simplicity of illustration and discussion, and so as not to obscure one or more embodiments of the description. Further, devices may be shown in block diagram form in order to avoid obscuring the understanding of one or more embodiments of the present description, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the one or more embodiments of the present description are to be implemented (i.e., such specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the disclosure, it should be apparent to one skilled in the art that one or more embodiments of the disclosure can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present disclosure has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations thereof will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures, such as Dynamic RAM (DRAM), may use the discussed embodiments.
It is intended that the one or more embodiments of the present specification embrace all such alternatives, modifications and variations as fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of one or more embodiments of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (8)
1. The data collection method of the unmanned aerial vehicle is applied to the unmanned aerial vehicle and comprises the following steps:
determining a target area and determining a flight track model of the target area;
determining the flight action of the unmanned aerial vehicle based on the state information of the unmanned aerial vehicle and the flight track model;
when the unmanned aerial vehicle finishes the flight action, determining the information age and the energy consumption of all target sensors in a scanning range, acquiring the uploaded data of at least one target sensor according to the information age and the energy consumption, and allocating channel resources for the target sensor;
outputting the uploaded data to enable an external processor to update the information age of the corresponding target sensor according to the uploaded data;
the acquiring of the uploaded data of at least one target sensor according to the information age and the energy consumption comprises:
determining channel information of the unmanned aerial vehicle and sensor energy of the target sensor, and selecting the target sensor by combining with the information age and the energy consumption;
through optimizing unmanned aerial vehicle's flying distance, direction of flight, airspeed and distribute to target sensor's bandwidth resource, maximize the utility function of unmanned aerial vehicle network, thereby the minimizing target sensor's information age, sensor energy consumption and unmanned aerial vehicle flight energy consumption, wherein:
defining utility function U of the unmanned aerial vehicle network as:
wherein T represents the total number of flight/hover processes, E [ ·]Representing the desired function for a limited number of flight/hover processes, A t Information age sum representing data of all the target sensors in the network, ζ represents a weight coefficient of energy consumption of the target sensors, ω represents a weight coefficient of energy consumption of the drone,
representing the total energy consumption of all said target sensors in the network,
representing a total energy consumption of the drone during a hover/flight;
the constraint conditions of the utility function U comprise:
wherein, V t Representing the flight speed, v, of the drone at the t-th hover/flight max Representing a speed threshold, x, of the drone t 、y t Representing the current position coordinates, x, of the drone min 、x max 、y min 、y max The extreme coordinates of the target area are represented,
represents bandwidth resources allocated by the drone to target sensors M, M represents the number of target sensors,
represents bandwidth resources allocated by the drone to all target sensors,
representing the number of target sensors scheduled by the drone, δ being the threshold number of target sensors scheduled by the drone.
2. The method according to claim 1, characterized in that the flight path model adopts a double-delay deep deterministic strategy algorithm, the algorithm introduces a deep neural network, and a network is trained by combining an operator network and two critic networks; the actor network comprises an online network and a target network, and the critic network comprises the online network and the target network.
3. The method of claim 1, wherein after determining the flight trajectory model of the target region, further comprising:
determining the data transmission rate of the unmanned aerial vehicle under the flight trajectory model;
and if the data transmission rate is less than a set threshold value, updating the model parameters of the flight track model.
4. The method of claim 1, wherein after outputting the uploaded data, further comprising:
judging whether the unmanned aerial vehicle finishes data acquisition of all target sensors in the target area;
and if so, indicating the unmanned aerial vehicle to enter another target area.
5. The utility model provides an unmanned aerial vehicle data collection equipment which characterized in that is applied to unmanned aerial vehicle, includes:
the determining module is used for determining a target area and determining a flight track model of the target area;
the calculation module is used for determining the flight action of the unmanned aerial vehicle based on the state information of the unmanned aerial vehicle and the flight track model;
the acquisition module is used for determining the information age and the energy consumption of all target sensors in a scanning range when the unmanned aerial vehicle finishes the flight action, acquiring the uploaded data of at least one target sensor according to the information age and the energy consumption, and allocating channel resources for the target sensor;
the transmission module outputs the uploaded data so that an external processor can update the information age of the corresponding target sensor according to the uploaded data;
the acquisition module acquires uploaded data of at least one target sensor according to the information age and the energy consumption, and the acquisition module comprises:
determining channel information of the unmanned aerial vehicle and sensor energy of the target sensor, and combining the information age and the energy consumption to select the target sensor;
the acquisition module is further configured to: through optimizing unmanned aerial vehicle's flying distance, flight direction, flying speed and distribution target sensor's bandwidth resource, maximize the utility function of unmanned aerial vehicle network, thereby the minimization target sensor's information age, sensor energy consumption and unmanned aerial vehicle flight energy consumption, wherein:
defining utility function U of the unmanned aerial vehicle network as:
wherein T represents the total number of flight/hover processes, E [ ·]Representing the desired function for a limited number of flight/hover processes, A t An age of information representing data of all of the target sensors in the network, ζ represents a weight coefficient of energy consumption of the target sensors, ω represents a weight coefficient of energy consumption of the drone,
representing the total energy consumption of all said target sensors in the network,
representing a total energy consumption of the drone during a hover/flight;
the constraint conditions of the utility function U comprise:
wherein, V t Representing the flight speed, v, of the drone at the t-th hover/flight max Representing a speed threshold, x, of the drone t 、y t Representing the current position coordinates, x, of the drone min 、x max 、y min 、y max An extreme coordinate representing the target area is shown,
representing bandwidth resources allocated by the drone to target sensors M, M representing the number of target sensors,
represents the bandwidth resources allocated by the drone to all target sensors,
representing the number of target sensors scheduled by the drone, δ being a threshold number of target sensors scheduled by the drone.
6. The apparatus of claim 5, wherein after the determining module determines the flight trajectory model of the target region, further comprising:
determining the data transmission rate of the unmanned aerial vehicle under the flight trajectory model;
and if the data transmission rate is less than a set threshold value, updating the model parameters of the flight track model.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 4 when executing the program.
8. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to implement the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011455224.3A CN112671451B (en) | 2020-12-10 | 2020-12-10 | Unmanned aerial vehicle data collection method and device, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011455224.3A CN112671451B (en) | 2020-12-10 | 2020-12-10 | Unmanned aerial vehicle data collection method and device, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112671451A CN112671451A (en) | 2021-04-16 |
| CN112671451B true CN112671451B (en) | 2022-11-18 |
Family
ID=75402706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011455224.3A Active CN112671451B (en) | 2020-12-10 | 2020-12-10 | Unmanned aerial vehicle data collection method and device, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112671451B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113110558B (en) * | 2021-05-12 | 2022-04-08 | 南京航空航天大学 | Hybrid propulsion unmanned aerial vehicle demand power prediction method |
| CN113472842B (en) * | 2021-05-24 | 2023-01-10 | 北京邮电大学 | User state perception method in mobile edge computing network and related equipment |
| CN113438315B (en) * | 2021-07-02 | 2023-04-21 | 中山大学 | Internet of things information freshness optimization method based on double-network deep reinforcement learning |
| CN114389679B (en) * | 2022-01-13 | 2023-04-11 | 吉林大学 | Multi-antenna unmanned aerial vehicle sensing and transmission optimization method based on information age minimization |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109990790A (en) * | 2019-03-29 | 2019-07-09 | 北京邮电大学 | A kind of unmanned plane paths planning method and device |
| CN110190888A (en) * | 2019-05-06 | 2019-08-30 | 北京邮电大学 | A kind of unmanned plane formation gathering method and device based on information timeliness |
| CN110543185A (en) * | 2019-07-19 | 2019-12-06 | 宁波大学 | unmanned aerial vehicle data collection method based on minimum information age |
| CN111367315A (en) * | 2020-03-11 | 2020-07-03 | 北京邮电大学 | Trajectory planning method and device applied to information collection of unmanned aerial vehicle |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109002051B (en) * | 2014-07-31 | 2022-10-11 | 深圳市大疆创新科技有限公司 | Virtual sightseeing system and method realized by using unmanned aerial vehicle |
-
2020
- 2020-12-10 CN CN202011455224.3A patent/CN112671451B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109990790A (en) * | 2019-03-29 | 2019-07-09 | 北京邮电大学 | A kind of unmanned plane paths planning method and device |
| CN110190888A (en) * | 2019-05-06 | 2019-08-30 | 北京邮电大学 | A kind of unmanned plane formation gathering method and device based on information timeliness |
| CN110543185A (en) * | 2019-07-19 | 2019-12-06 | 宁波大学 | unmanned aerial vehicle data collection method based on minimum information age |
| CN111367315A (en) * | 2020-03-11 | 2020-07-03 | 北京邮电大学 | Trajectory planning method and device applied to information collection of unmanned aerial vehicle |
Non-Patent Citations (1)
| Title |
|---|
| Age of Information in a Cellular Internet of UAVs: Sensing and Communication Trade-Off Design;Shuhang Zhang等;《IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS》;20201031;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112671451A (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112671451B (en) | Unmanned aerial vehicle data collection method and device, electronic device and storage medium | |
| You et al. | Hybrid offline-online design for UAV-enabled data harvesting in probabilistic LoS channels | |
| CN111786713B (en) | Unmanned aerial vehicle network hovering position optimization method based on multi-agent deep reinforcement learning | |
| Zhu et al. | Learning-based computation offloading approaches in UAVs-assisted edge computing | |
| CN113190039A (en) | Unmanned aerial vehicle acquisition path planning method based on hierarchical deep reinforcement learning | |
| CN108810849B (en) | Unmanned aerial vehicle computing task migration method and device and unmanned aerial vehicle | |
| CN113395654A (en) | Method for task unloading and resource allocation of multiple unmanned aerial vehicles of edge computing system | |
| CN109000651B (en) | Path planning method and path planning device | |
| US10785297B2 (en) | Intelligent dataset migration and delivery to mobile internet of things devices using fifth-generation networks | |
| Zhu et al. | UAV‐enabled computation migration for complex missions: A reinforcement learning approach | |
| Dai et al. | Delay-sensitive energy-efficient UAV crowdsensing by deep reinforcement learning | |
| CN112636811B (en) | Relay unmanned aerial vehicle deployment method and device | |
| Ho et al. | UAV control for wireless service provisioning in critical demand areas: A deep reinforcement learning approach | |
| CN114339842B (en) | Method and device for designing dynamic trajectory of unmanned aerial vehicle cluster in time-varying scene based on deep reinforcement learning | |
| CN113485409A (en) | Unmanned aerial vehicle path planning and distribution method and system for geographic fairness | |
| Hua et al. | Drl-based energy efficient communication coverage control in hierarchical hap-lap network | |
| CN114173359B (en) | Heterogeneous network resource scheduling method used in industrial Internet of things environment | |
| CN114007231A (en) | Heterogeneous unmanned aerial vehicle data unloading method and device, electronic equipment and storage medium | |
| CN107682812B (en) | link adaptation method and device for heterogeneous multi-communication link convergence network | |
| Shi et al. | Age of information optimization with heterogeneous uavs based on deep reinforcement learning | |
| CN112579290B (en) | Computing task migration method of ground terminal equipment based on unmanned aerial vehicle | |
| CN113727278A (en) | Path planning method, access network equipment and flight control equipment | |
| CN116321237A (en) | Unmanned aerial vehicle auxiliary internet of vehicles data collection method based on deep reinforcement learning | |
| Yin et al. | Trajectory optimization for age of information minimization in UAV communication systems | |
| Chu et al. | Fast or slow: An autonomous speed control approach for UAV-assisted IoT data collection networks |
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 |