CN118158695A - Vehicle control method based on general sense integration, electronic equipment and storage medium - Google Patents
Vehicle control method based on general sense integration, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN118158695A CN118158695A CN202410579174.1A CN202410579174A CN118158695A CN 118158695 A CN118158695 A CN 118158695A CN 202410579174 A CN202410579174 A CN 202410579174A CN 118158695 A CN118158695 A CN 118158695A
- Authority
- CN
- China
- Prior art keywords
- prediction
- control
- channel data
- vehicle
- target vehicle
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 230000010354 integration Effects 0.000 title claims abstract description 21
- 238000012545 processing Methods 0.000 claims description 53
- 238000004891 communication Methods 0.000 claims description 50
- 238000012360 testing method Methods 0.000 claims description 47
- 238000012549 training Methods 0.000 claims description 36
- 230000004927 fusion Effects 0.000 claims description 35
- 239000011159 matrix material Substances 0.000 claims description 24
- 238000007493 shaping process Methods 0.000 claims description 13
- 230000004044 response Effects 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 230000015654 memory Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000007499 fusion processing Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 230000005540 biological transmission Effects 0.000 description 10
- 230000008447 perception Effects 0.000 description 10
- 238000001914 filtration Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002592 echocardiography Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000010287 polarization Effects 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
The application relates to the technical field of internet of vehicles, in particular to a vehicle control method based on general sense integration, electronic equipment and a storage medium. According to the vehicle control method based on the general sense integration, the vehicle control base station is required to acquire historical channel data of a target vehicle corresponding to a plurality of continuous time slots, then the historical channel data is input into a pre-trained beam prediction model to conduct beam prediction, a home wheel control beam is obtained, the home wheel control beam is sent to the target vehicle, home wheel echo signals responding to home wheel control operation are acquired from the target vehicle, the historical channel data is updated based on the home wheel control beam and the home wheel echo signals, and the historical channel data is returned to be input into the pre-trained beam prediction model to conduct beam prediction. Therefore, the control tasks such as accurate detection and tracking can be continuously performed on the target vehicle, and meanwhile, the signal cost is saved.
Description
Technical Field
The application relates to the technical field of internet of vehicles, in particular to a vehicle control method based on general sense integration, electronic equipment and a storage medium.
Background
The communication perception integration is an integrated system which combines a communication technology and a perception technology together to realize information acquisition, transmission and processing. In the communication perception integrated system, a communication technology is used for data transmission and communication connection, and a perception technology is used for environment information acquisition and analysis. By integrating communication and sensing functions, the system can achieve real-time data acquisition, transmission and processing, thereby better understanding and responding to environmental changes. When the sensing and communication integration is applied to the technology of the internet of vehicles, reliable communication and highly accurate sensing performance are required to be realized simultaneously, and the field can use beam tracking to improve the communication performance of the base station and the vehicles.
In the related art, the predicted beam tracking applied to the communication aware base station needs to cascade three stages: firstly, vehicle parameters are obtained through a matched filtering method according to communication echoes, then a Kalman filtering method is applied to track and predict state information of a vehicle, and finally, a wave beam optimization problem is solved, so that wave beams for communication perception control of the vehicle are formed. However, this method is computationally complex due to the need to track vehicle motion parameters, and the cascading process also creates additional signal overhead.
Disclosure of Invention
The present application aims to solve at least one of the technical problems existing in the prior art. Therefore, the application provides a vehicle control method, electronic equipment and storage medium based on general sense integration, which can realize the control of the vehicle by utilizing the communication sensing process of the base station and the vehicle and save signal cost.
According to a first aspect of the embodiment of the application, a vehicle control method based on general sense integration is applied to a vehicle control base station, and comprises the following steps:
Acquiring historical channel data of a target vehicle corresponding to a plurality of continuous time slots;
Inputting the historical channel data into a pre-trained beam prediction model for beam prediction to obtain a control beam of the present round; the home wheel control beam is used for performing home wheel control operation on the target vehicle;
transmitting a home wheel control beam to the target vehicle, and acquiring a home wheel echo signal from the target vehicle in response to the home wheel control operation;
Updating the historical channel data based on the home round control beam and the home round echo signal, and returning to perform beam prediction by inputting the historical channel data into a pre-trained beam prediction model until the home round control beam meets a first preset condition, and generating a target control beam based on the home round control beam;
and performing a target control operation on the target vehicle based on the target control beam so as to enable the target vehicle to execute an operation response action.
According to some embodiments of the application, the beam prediction model comprises a coding layer, a prediction layer;
the step of inputting the historical channel data into a pre-trained beam prediction model for beam prediction to obtain a current round of control beam comprises the following steps:
Inputting the historical channel data into a coding layer for feature coding processing to obtain corresponding target space features between the vehicle control base station and the target vehicle; wherein the target spatial feature reflects a spatially varying feature of the target vehicle corresponding in a plurality of consecutive time slots;
inputting the target space features into the prediction layer for azimuth prediction to obtain azimuth prediction features;
And carrying out beam forming processing based on the azimuth prediction characteristics to obtain the control beam of the present wheel.
According to some embodiments of the application, the vehicle control base station is configured to control a plurality of the target vehicles, and the beam prediction model further includes a fusion layer and a decoding layer;
and performing beam forming processing based on the azimuth prediction feature to obtain the home-wheel control beam, including:
Inputting the azimuth prediction features corresponding to each target vehicle into the fusion layer to perform feature fusion processing to obtain a fusion feature matrix;
and inputting the fusion feature matrix into a decoding layer for feature decoding processing to obtain the control beam of the present round.
According to some embodiments of the application, the decoding layer comprises a full convolutional neural network;
the step of inputting the fusion feature matrix into a decoding layer for feature decoding processing to obtain the control beam of the present wheel comprises the following steps:
And inputting the fusion feature matrix into a decoding layer so that the full convolution neural network carries out nonlinear transformation on the distribution power and the prediction angle corresponding to the fusion feature matrix to obtain the control beam of the present round.
According to some embodiments of the present application, before the step of inputting the historical channel data into a pre-trained beam prediction model to perform beam prediction, the method further includes pre-training the beam prediction model, and specifically includes:
acquiring channel sample information of a plurality of continuous time slots and sample label information corresponding to the channel sample information;
inputting the channel sample information and sample label information corresponding to the channel sample information into the original beam prediction model for iterative prediction training to obtain a training result of the round;
Comparing the training result of the round with the sample label information to obtain deviation data of the round;
And updating the beam prediction model based on the current round of deviation data, and returning to input the channel sample information and sample label information corresponding to the channel sample information into the beam prediction model for iterative prediction training until the current round of deviation data meets a training preset condition to obtain the pre-trained beam prediction model.
According to some embodiments of the application, the acquiring historical channel data of the target vehicle corresponding to a plurality of consecutive time slots includes:
Transmitting a first test beam to a target area, and acquiring a test feedback signal from the target vehicle in response to the first test beam; the target area is an environment area where the target vehicle is located;
and correcting and shaping the first test beam based on the test feedback signal to generate the historical channel data.
According to some embodiments of the application, the performing correction shaping processing on the first test beam based on the test feedback signal to generate the historical channel data includes:
Based on the test feedback signal, performing power adjustment processing, angle adjustment processing and initial shaping on the first test beam to obtain a second test beam;
and performing test communication with the target vehicle based on the second test beam to obtain the historical channel data.
According to a second aspect of the present application, a vehicle control method based on general sense integration is applied to a target vehicle, and includes:
Acquiring a home wheel control beam from a vehicle control base station; the present wheel control beam is obtained at the vehicle control base station by the following method: acquiring historical channel data of a target vehicle corresponding to a plurality of continuous time slots, and inputting the historical channel data into a pre-trained beam prediction model for beam prediction to obtain the control beam of the present wheel; the home wheel control beam is used for performing home wheel control operation on the target vehicle;
And responding to the home run control operation, transmitting a home run echo signal to the vehicle control base station so that the vehicle control base station can update the historical channel data based on the home run control beam and the home run echo signal, and returning to execute the input of the historical channel data into a pre-trained beam prediction model to perform beam prediction.
In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor storing a computer program, the processor implementing the vehicle control method according to any one of the embodiments of the first aspect or the second aspect of the application when executing the computer program.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a program that is executed by a processor to implement the vehicle control method according to any one of the embodiments of the first or second aspects of the present application.
According to the vehicle control method, the electronic equipment and the storage medium based on the general sense integration, the vehicle control method and the electronic equipment have at least the following beneficial effects:
According to the vehicle control method based on the general sense integration, a vehicle control base station is required to acquire historical channel data of a target vehicle corresponding to a plurality of continuous time slots, then the historical channel data is input into a pre-trained beam prediction model to conduct beam prediction, a home wheel control beam is obtained, the home wheel control beam is sent to the target vehicle, home wheel echo signals responding to the home wheel control operation are acquired from the target vehicle, the historical channel data are updated based on the home wheel control beam and the home wheel echo signals, and the historical channel data are input into the pre-trained beam prediction model to conduct beam prediction in a return mode. In this way, on the basis of updating the historical channel data, the input of the historical channel data into the pre-trained beam prediction model is performed to perform beam prediction, the historical channel data is updated based on the real channel data reflected in the echo signals of each round, and the control tasks such as accurate detection and tracking of the target vehicle can be continuously performed through the beam prediction and echo signal processing of a plurality of rounds, and meanwhile, the signal cost is saved.
Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
FIG. 1 is a schematic flow chart of a vehicle control method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of another vehicle control method according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of another vehicle control method according to an embodiment of the present application;
FIG. 4 is a schematic flow chart of another vehicle control method according to an embodiment of the present application;
FIG. 5 is a schematic flow chart of another vehicle control method according to an embodiment of the present application;
FIG. 6 is a schematic flow chart of another vehicle control method according to an embodiment of the present application;
fig. 7 is a schematic diagram of a beam prediction model according to an embodiment of the present application to implement beam prediction;
fig. 8 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the application.
In the description of the present application, a number means one or more, a number means two or more, and greater than, less than, exceeding, etc. are understood to not include the present number, and above, below, within, etc. are understood to include the present number. The description of the first and second is for the purpose of distinguishing between technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present application, it should be understood that the direction or positional relationship indicated with respect to the description of the orientation, such as up, down, left, right, front, rear, etc., is based on the direction or positional relationship shown in the drawings, is merely for convenience of describing the present application and simplifying the description, and does not indicate or imply that the apparatus or element to be referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present application.
In the description of the present specification, reference to the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
In the description of the present application, unless explicitly defined otherwise, terms such as arrangement, installation, connection, etc. should be construed broadly and the specific meaning of the terms in the present application can be determined reasonably by a person skilled in the art in combination with the specific content of the technical solution. In addition, the following description of specific steps does not represent limitations on the order of steps or logic performed, and the order of steps and logic performed between steps should be understood and appreciated with reference to what is described in the embodiments.
The communication perception integration is an integrated system which combines a communication technology and a perception technology together to realize information acquisition, transmission and processing. The integration can enable the system to be more intelligent, efficient and reliable, and provide better service and experience for various application scenes.
In the communication perception integrated system, a communication technology is used for data transmission and communication connection, and a perception technology is used for environment information acquisition and analysis. By integrating communication and sensing functions, the system can achieve real-time data acquisition, transmission and processing, thereby better understanding and responding to environmental changes.
The integration of sensing and communication requires both reliable communication and highly accurate sensing performance in the internet of vehicles technology, where beam tracking can be used to improve the base station and vehicle communication performance.
Beam tracking is a wireless communication technology for tracking the position of a moving object or communication partner and focusing a signal beam on the object to improve communication quality and reliability. The beam tracking can be realized by adjusting the phase and amplitude of each antenna in the antenna array, so that the signal beam is directed to a target or a communication counterpart, the signal attenuation and multipath interference are reduced, and the communication performance is improved.
In the related art, the predicted beam tracking applied to the communication aware base station needs to cascade three phases: firstly, vehicle parameters are obtained through a matched filtering method according to communication echoes, then a Kalman filtering method is applied to track and predict state information of the vehicle, including positions and speeds of the vehicle, and finally, a wave beam optimization problem is solved, so that wave beams for communication perception control of the vehicle are formed. However, this method is computationally complex due to the need to track vehicle motion parameters, and the cascading process also creates additional signal overhead.
Other related art attempts to directly generate a transmit beam at the next instant based on the input historical channel data directly based on a deep-learned end-to-end predictive beam tracking framework. However, these methods have been studied with an emphasis on optimizing the communication performance of the vehicle with the base station, while they can deal only with vehicles having simple behaviors such as straight traveling vehicles. These assumptions are inconsistent with real vehicle motion, and the beamforming design generated from the predictive model can affect system performance due to inaccurate channel information.
The present application aims to solve at least one of the technical problems existing in the prior art. Therefore, the application provides a vehicle control method, electronic equipment and storage medium based on general sense integration, which can realize the control of the vehicle by utilizing the communication sensing process of the base station and the vehicle and save signal cost.
The following is a further description based on the accompanying drawings.
It should be noted that, the vehicle control method according to the embodiment of the present application aims to realize control of the target vehicle by the vehicle control base station.
Referring to fig. 1, a vehicle control method based on general sense integration according to an embodiment of the present application may include:
In a vehicle control base station:
Step S101, historical channel data of a target vehicle corresponding to a plurality of continuous time slots is acquired;
step S102, inputting historical channel data into a pre-trained beam prediction model for beam prediction to obtain a control beam of the round;
Step S103, transmitting a control beam of the present wheel to the target vehicle;
In the target vehicle:
Step S104, acquiring a control beam of the present wheel from a vehicle control base station;
step S105, in response to the present wheel control operation, a present wheel echo signal is sent to a vehicle control base station;
In a vehicle control base station:
Step S106, acquiring a home wheel echo signal responding to the home wheel control operation from the target vehicle;
step S107, the historical channel data is updated based on the present round control beam and the present round echo signal, and the execution is returned to the pre-trained beam prediction model for beam prediction.
Through the vehicle control method based on the sense of unity shown in steps S101 to S107, it is necessary to acquire historical channel data of the target vehicle corresponding to a plurality of consecutive time slots by means of the vehicle control base station, then input the historical channel data into the pre-trained beam prediction model for beam prediction to obtain the own-wheel control beam, transmit the own-wheel control beam to the target vehicle, acquire the own-wheel echo signal in response to the own-wheel control operation from the target vehicle, update the historical channel data based on the own-wheel control beam and the own-wheel echo signal, and return to perform the input of the historical channel data into the pre-trained beam prediction model for beam prediction. In this way, on the basis of updating the historical channel data, the input of the historical channel data into the pre-trained beam prediction model is performed to perform beam prediction, the historical channel data is updated based on the real channel data reflected in the echo signals of each round, and the control tasks such as accurate detection and tracking of the target vehicle can be continuously performed through the beam prediction and echo signal processing of a plurality of rounds, and meanwhile, the signal cost is saved.
Step S101 of some embodiments obtains historical channel data for a target vehicle corresponding to a plurality of consecutive time slots. It should be noted that, the historical channel data refers to the data about the channel characteristics and the transmission condition recorded previously between the vehicle control base station and the target vehicle. Such data may include information such as signal power, signal-to-noise ratio, multipath fading conditions, transmission delay, etc., for analyzing and predicting the performance and characteristics of the channel. Through analysis and processing of historical channel data, a model of the channel can be established for describing the characteristics and change rules of the channel.
Referring to fig. 2, according to some embodiments of the present application, step S101 of acquiring historical channel data of a target vehicle corresponding to a plurality of consecutive time slots may include:
Step S201, a first test beam is sent to a target area, and a test feedback signal responding to the first test beam is obtained from a target vehicle; the target area is an environment area where the target vehicle is located;
Step S202, correction shaping processing is carried out on the first test beam based on the test feedback signal, and historical channel data is generated.
It should be noted that, since the historical channel data refers to data about channel characteristics and transmission conditions recorded previously between the vehicle control base station and the target vehicle, the data is used to analyze and predict the performance and characteristics of the channel. Based on the above, the embodiment of the application can send the first test beam to the target area, acquire the test feedback signal responding to the first test beam from the target vehicle, and analyze the performance and the characteristics of the channel between the vehicle control base station and the target vehicle on the basis of the test feedback signal.
It should be appreciated that the first test beam may be delivered to the target vehicle by way of an omni-directional broadcast and then precisely adjusted based on the signal fed back by the target vehicle.
In some more specific embodiments, because of uncertainty of the initial position of the target vehicle, the vehicle control base station needs to send a first test beam to the target area to obtain a test feedback signal of the response of the target vehicle, so as to perform correction and shaping processing on the first test beam based on the test feedback signal, thereby achieving initial beam shaping and estimation of historical channel data.
Referring to fig. 3, according to some embodiments of the present application, step S202 performs correction shaping processing on the first test beam based on the test feedback signal, and generating historical channel data may include:
step S301, performing power adjustment processing, angle adjustment processing and initial shaping on the first test beam based on the test feedback signal to obtain a second test beam;
Step S302, test communication is carried out on the basis of the second test beam and the target vehicle, and historical channel data are obtained.
It should be noted that, the correction and shaping processing is performed on the first test beam based on the test feedback signal to generate the historical channel data, specifically, the vehicle control base station may first send a downlink beam to the running target vehicle, then perform the power adjustment processing and the angle adjustment processing through the feedback beam, and further perform the initial beam shaping, and in this process, start to communicate with the running target vehicle and perform data transmission.
Referring to fig. 4, before the historical channel data is input into the pre-trained beam prediction model for beam prediction in step S102 to obtain the control beam of the present round, the method further includes pre-training the beam prediction model, specifically includes:
step S401, obtaining channel sample information of a plurality of continuous time slots and sample label information corresponding to the channel sample information;
Step S402, inputting channel sample information and sample label information corresponding to the channel sample information into an original beam prediction model for iterative prediction training to obtain a training result of the round;
step S403, comparing the training result of the round with sample label information to obtain deviation data of the round;
Step S404, updating the beam prediction model based on the current round of deviation data, and returning to execute the iterative prediction training of inputting the channel sample information and the sample label information corresponding to the channel sample information into the beam prediction model until the current round of deviation data meets the training preset condition, thereby obtaining the pre-trained beam prediction model.
The beam prediction model is pre-trained, and the aim is to train the capability of the beam prediction model for more accurate beam prediction.
Step S401 of some embodiments obtains channel sample information of a plurality of consecutive slots, sample tag information corresponding to the channel sample information. It should be noted that, the channel sample information in the embodiment of the present application refers to sample information required for training a beam prediction model in advance, where the channel sample information can describe channel characteristics and may include information such as channel gain, phase, noise, and the like. The sample label information is information reflecting the true characteristics of the channel and is used as a training label, and the sample label information is input into an original beam prediction model together with the channel sample information to carry out iterative prediction training.
In step S402 of some embodiments, the channel sample information and the sample label information corresponding to the channel sample information are input into the original beam prediction model to perform iterative prediction training, so as to obtain the training result of the present round. It should be noted that, the original beam prediction model refers to a prediction model that has not been trained in advance. In the embodiment of the application, the channel sample information and the sample label information corresponding to the channel sample information are input into the original beam prediction model for iterative prediction training, so as to train the capability of the beam prediction model for more accurate beam prediction. The iterative predictive training of each round can obtain a corresponding training result of the round, and it is understood that the training result of the round is used for representing the beam prediction capability of the beam prediction model of the iterative predictive training of the current round.
Step S403 to step S404 of some embodiments, compare the training result of the present round with the sample tag information to obtain the deviation data of the present round, update the beam prediction model based on the deviation data of the present round, and return to execute the iterative prediction training of inputting the channel sample information and the sample tag information corresponding to the channel sample information into the beam prediction model until the deviation data of the present round meets the preset training condition, so as to obtain the pre-trained beam prediction model. After each round of iterative training obtains the training result of the present round, the present round of deviation data (for example, a loss function) is obtained by comparing the training result of the present round with sample label information, so as to update model parameters of a beam prediction model based on the present round of deviation data, and then, the iterative prediction training is performed by inputting channel sample information and sample label information corresponding to the channel sample information into the beam prediction model. Until the deviation data of the current round meets the training preset condition, the capability of the beam prediction model for more accurate beam prediction is improved and the expected level is reached, and on the basis, the corresponding beam prediction model can be used as the pre-trained beam prediction model.
In step S102 of some embodiments, the historical channel data is input into a pre-trained beam prediction model to perform beam prediction, so as to obtain the control beam of the present round. The beam prediction refers to predicting information such as a position and a velocity of a target using a beam forming technique. The beam forming technique is a technique of combining a beam capable of focusing and pointing in a specific direction by using a plurality of antenna elements. By forming and controlling the wave beam, the positioning, tracking and identifying of the target can be realized. In the embodiment of the application, the basic principle of beam prediction is to estimate the position and the speed of the target vehicle by using the received historical channel data, so as to generate the control beam of the present wheel on the basis. The present wheel control beam is used for carrying out present wheel control operation on a target vehicle, and can be particularly used for adjusting the position and the speed of the target vehicle.
Referring to fig. 5, a beam prediction model includes a coding layer, a prediction layer, according to some embodiments of the application;
Step S102 inputs the historical channel data into a pre-trained beam prediction model to perform beam prediction, so as to obtain a current round of control beam, which may include:
Step S501, inputting historical channel data into a coding layer for feature coding processing to obtain corresponding target space features between a vehicle control base station and a target vehicle; the target space features reflect the corresponding space change features of the target vehicle in a plurality of continuous time slots;
Step S502, inputting the target space characteristics into a prediction layer for azimuth prediction to obtain azimuth prediction characteristics;
Step S503, performing beam forming processing based on the azimuth prediction feature, to obtain the control beam of the present round.
Step S501 of some embodiments, inputting historical channel data into a coding layer for feature coding processing, so as to obtain a corresponding target space feature between a vehicle control base station and a target vehicle; wherein the target spatial signature reflects spatially varying signatures of the target vehicle in a plurality of consecutive time slots. It should be noted that, the historical channel data is input into the coding layer to perform feature coding processing, so as to obtain the corresponding target space feature between the vehicle control base station and the target vehicle from the echo feature corresponding to each time slot in the historical channel data, where the target space feature is used to characterize the space factor corresponding to the signal transmission between the vehicle control base station and the target vehicle.
In step S502 of some embodiments, the target spatial feature is input into a prediction layer to perform azimuth prediction, so as to obtain an azimuth prediction feature. After the encoding layer extracts the target spatial feature from the historical channel data, the encoding layer needs to further input the target spatial feature into the prediction layer to perform azimuth prediction, so as to obtain the azimuth prediction feature. It should be noted that the azimuth prediction feature is used to provide a reference during the forming process for the beam that needs to be predicted.
In step S503 of some embodiments, beam forming processing is performed based on the azimuth prediction feature, so as to obtain the control beam of the present round. It is emphasized that beam tracking is used to track the position of a moving object or communication partner and focus a signal beam on the object to improve communication quality and reliability. In the embodiment of the application, the target space features are used for representing the space factors corresponding to the signal transmission between the vehicle control base station and the target vehicle, so that the target space features are extracted from the historical channel data at the coding layer, the prediction layer is required to be further utilized to obtain the azimuth prediction features by adjusting the phase and the amplitude of each antenna in the antenna array on the basis of the target space features, and the azimuth prediction features are utilized to carry out the wave beam forming processing, so that the signal wave beam can be directed to a target or a communication counterpart, the signal attenuation and the multipath interference are reduced, and the communication performance is improved.
Referring to fig. 6, a vehicle control base station is used to control a plurality of target vehicles, and a beam prediction model further includes a fusion layer and a decoding layer according to some embodiments of the present application;
Step S503 performs beam forming processing based on the azimuth prediction feature to obtain a current round of control beam, which may include:
Step S601, inputting the azimuth prediction features corresponding to each target vehicle into a fusion layer for feature fusion processing to obtain a fusion feature matrix;
step S602, inputting the fusion feature matrix into a decoding layer for feature decoding processing to obtain the control beam of the present round.
It should be noted that, multiple access interference refers to a problem caused by mutual interference of signals between users when multiple users share the same channel. When the vehicle control method of the embodiment of the application is applied to a multiple access system, the vehicle control base station and a plurality of target vehicles simultaneously use the same frequency spectrum resource for communication, so that different target vehicles can mutually interfere to influence the communication quality and the system performance. In order to cope with multiple access interference, the beam prediction model in the embodiment of the application further comprises a fusion layer and a decoding layer. The fusion layer is used for fusing the azimuth prediction features corresponding to each target vehicle to obtain a fusion feature matrix; and further, inputting the fusion feature matrix into a decoding layer for feature decoding processing to obtain the control beam of the round.
According to some embodiments of the application, the decoding layer comprises a full convolutional neural network. Step S602 inputs the fusion feature matrix into a decoding layer to perform feature decoding processing, so as to obtain a control beam of the present round, which may include:
And inputting the fusion feature matrix into a decoding layer so that the full convolution neural network performs nonlinear transformation on the distributed power and the predicted angle corresponding to the fusion feature matrix to obtain the control beam of the round.
It should be noted that, the full convolutional neural network (Fully Convolutional Network, FCN) is a neural network structure, and replaces the full connection layer in the conventional convolutional neural network with a convolutional layer, so as to accept any size input and output the prediction result with the same size. The full convolution neural network is generally used for tasks such as image segmentation, and can effectively process spatial relations between input and output, so that the understanding and expression capacity of the model on the whole image information are improved. In addition, cascading features are typically used to describe the hierarchy of the system or signal, the relationships between components, and the dependencies between levels. In the areas of signal processing, pattern recognition, machine learning, etc., cascading features may help extract higher level information to better understand and process data.
In the embodiment of the application, the distributed power and the prediction angle corresponding to the fusion feature matrix are subjected to nonlinear transformation based on the full convolution neural network, and the cascade features are adjusted, so that the control beam of the round is formed according to the fusion feature matrix prediction.
Referring to fig. 7, in some more specific embodiments of the present application, a vehicle control base station is configured to control a plurality of target vehicles, and a beam prediction model includes an encoding layer, a prediction layer, a fusion layer, and a decoding layer.
In fig. 7, the history channel information of the target vehicle 1 is represented as {The historical channel information of the target vehicle 2 is expressed as {/>The historical channel information of the target vehicle 3 is expressed as {Historical channel information of target vehicle K is denoted {/>}。
It should be noted that, each target vehicle corresponds to an encoding layer, and the encoding layer includes a plurality of parallel encoders, and each encoder is configured to receive a piece of historical channel data. Wherein,The number of time slots corresponding to the historical channel information. Specifically, each encoder includes a convolutional layer, a pooling layer, and a flat layer, and these encoders may have the same network structure; n represents the current round of beam prediction.
In addition, a Long Short-Term Memory (LSTM) is a common cyclic neural network structure, which is used for processing sequence data, and particularly has good effects in the fields of natural language processing, time sequence prediction and the like. Compared with the traditional circulating neural network, the LSTM introduces a gating mechanism, can better capture long-term dependence, and avoids the problems of gradient disappearance or gradient explosion and the like. The main structure of the LSTM network includes three gating units: forget Gate (Forget Gate), input Gate (Input Gate) and Output Gate (Output Gate). These gating units can control the flow of information to efficiently process long sequence data.
In the embodiment of the application, the prediction layer can comprise a plurality of LSTM modules connected in series, each LSTM module receives a target space feature generated after the historical channel information is encoded, and the orientation prediction feature can be obtained after the orientation prediction is carried out on the target space feature. If the historical channel information of a target vehicle is expressed as {Then the corresponding target spatial feature of a target vehicle may be expressed as/>. Further, the processing procedure of the prediction layer for the target spatial feature can be expressed as: /(I)。/>Representing network parameters
Thus, each LSTM module can utilize the pastThe dependency relationship between the historical channel information provides basis for beam prediction of the next time slot.
It is clear that the fusion layer is used for fusing the azimuth prediction features corresponding to the K target vehicles together. If it isThe output of the fusion feature matrix as a fusion layer can be expressed as. Specifically, embodiments of the present application may determine a full convolutional neural network as a fusion layer. And carrying out nonlinear transformation on the allocated power and the prediction angle corresponding to the fusion feature matrix based on the full convolution neural network, and adjusting cascade features, so that the control beam of the round is formed according to the fusion feature matrix prediction.
Still further, the decoding layer is used for fusing the feature matrixAnd the input decoding layer performs characteristic decoding processing to obtain the control beam of the round. Based on this, the present round of steering beam can be expressed as/>. In some more specific embodiments, the full convolutional neural network may be used as a decoding layer to achieve fusion of feature matrices/>Based on the above, nonlinear transformation is performed on the allocated power and the predicted angle of the beam forming matrix, thereby obtaining the control beam of the present round.
Step S103 of some embodiments transmits the present wheel control beam to the target vehicle. After the wheel control beam is generated, the wheel control beam can be sent to the target vehicle to control the running of the target vehicle;
Step S104 of some embodiments obtains the present wheel control beam from the vehicle control base station. The target vehicle receives the own-wheel control beam transmitted from the vehicle control base station.
Step S105 of some embodiments transmits a home round echo signal to the vehicle control base station in response to the home round control operation. It is emphasized that the present wheel control beam is used for performing present wheel control operations on a target vehicle, and may be used in particular to adjust target vehicle position and speed. It should be noted that, since the present wheel control beam is generated by the vehicle control base station for controlling the travel of the target vehicle, the target vehicle adjusts its own position and speed based on the present wheel control beam immediately after the present wheel control beam is acquired. The home round echo signal refers to a signal fed back by the target vehicle after the vehicle control base station sends the home round echo signal to the target vehicle. The echo signal of the present wheel carries parameter information of the target vehicle, including the position, speed, size and the like of the target.
Step S106 of some embodiments acquires a home-wheel echo signal from the target vehicle in response to the home-wheel control operation. The vehicle control base station can realize detection, tracking and identification of the target vehicle through processing and analyzing the echo signals of the own wheels.
Note that the characteristics of the echo signal include:
time domain characteristics: the delay of the echo signal in time reflects the distance between the target and the radar system, and the distance of the target can be determined by measuring the delay;
Frequency domain characteristics: the frequency characteristic of the echo signal reflects the speed information of the target, and the speed of the target can be obtained through the Doppler effect;
polarization characteristics: the polarization state of the echo signal reflects the feedback characteristic of the target to the electromagnetic wave and can be used for distinguishing the property and the shape of the target;
Strength characteristics: the intensity of the echo signal reflects the feedback capacity of the target to the radar wave, and can be used for judging the size and the feedback sectional area of the target.
After the vehicle control base station obtains the own-wheel echo signal of the own-wheel control operation, the vehicle control base station can obtain accurate channel information of the target vehicle at the current moment by performing operations such as signal processing, filtering, target detection, tracking and the like on the own-wheel echo signal.
In step S107 of some embodiments, historical channel data is updated based on the current round of control beam and the current round of echo signal, and the input of the historical channel data into the pre-trained beam prediction model is returned to be performed for beam prediction until the current round of control beam meets a first preset condition, and a target control beam is generated based on the current round of control beam. It is emphasized that after the echo signal of the vehicle control base station responding to the present wheel control operation is obtained, the vehicle control base station can obtain accurate channel information between the target vehicle and the vehicle control base station at the current moment through performing operations such as signal processing, filtering, target detection, tracking and the like on the echo signal. Further, after obtaining accurate channel information of the target vehicle at the current moment, the accurate channel information needs to be integrated into the historical channel data, so that the historical channel data is updated. On the basis of updating the historical channel data, the historical channel data is returned to be input into a pre-trained beam prediction model for beam prediction, the historical channel data is updated based on the real channel data reflected in echo signals of each round, and accurate detection and tracking of a target vehicle can be continuously achieved through beam prediction and echo signal processing of a plurality of rounds, so that the performance and reliability of vehicle control are improved.
In some more specific embodiments, the number of rounds of beam prediction and echo signal processing may be terminated based on the satisfaction of the first preset condition. The first preset condition may be satisfied when the number of corresponding control passes of the control beam of the present wheel reaches the expected number, for example, the vehicle control base station is preset to perform n-pass control on the target vehicle, and after the control beam of the present wheel of the nth control pass is sent to the target vehicle, the first preset condition is satisfied immediately, and beam prediction and echo signal processing of the present wheel can be terminated.
It should be appreciated that the first preset condition may be flexibly set according to the application scenario, and is not limited to the above example.
Referring to fig. 8, fig. 8 illustrates a hardware structure of an electronic device of another embodiment, the electronic device including:
The processor 801 may be implemented by a general-purpose CPU (central processing unit), a microprocessor, an application-specific integrated circuit (ApplicationSpecificIntegratedCircuit, ASIC), or one or more integrated circuits, etc. for executing related programs to implement the technical solution provided by the embodiments of the present application;
Memory 802 may be implemented in the form of read-only memory (ReadOnlyMemory, ROM), static storage, dynamic storage, or random access memory (RandomAccessMemory, RAM), among others. The memory 802 may store an operating system and other application programs, and when the technical solutions provided in the embodiments of the present disclosure are implemented by software or firmware, relevant program codes are stored in the memory 802, and the processor 801 invokes a vehicle control method for executing the embodiments of the present disclosure;
An input/output interface 803 for implementing information input and output;
The communication interface 804 is configured to implement communication interaction between the device and other devices, and may implement communication in a wired manner (e.g., USB, network cable, etc.), or may implement communication in a wireless manner (e.g., mobile network, WIFI, bluetooth, etc.);
a bus 805 that transfers information between the various components of the device (e.g., the processor 801, the memory 802, the input/output interface 803, and the communication interface 804);
wherein the processor 801, the memory 802, the input/output interface 803, and the communication interface 804 implement communication connection between each other inside the device through a bus 805.
Embodiments of the present application also provide a computer program product comprising a computer program. The processor of the computer device reads the computer program and executes it, causing the computer device to execute the vehicle control method described above.
The terms "first," "second," "third," "fourth," and the like in the description of the present disclosure and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein, for example. Furthermore, the terms "comprises," "comprising," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in this disclosure, "at least one" means one or more, and "a plurality" means two or more. "and/or" for describing the association relationship of the association object, the representation may have three relationships, for example, "a and/or B" may represent: only a, only B and both a and B are present, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
It should be understood that in the description of the embodiments of the present application, plural (or multiple) means two or more, and that greater than, less than, exceeding, etc. are understood to not include the present number, and that greater than, less than, within, etc. are understood to include the present number.
In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present disclosure may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the various embodiments of the present disclosure. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory RAM), a magnetic disk, or an optical disk, etc., which can store program codes.
It should also be appreciated that the various embodiments provided by the embodiments of the present application may be arbitrarily combined to achieve different technical effects.
The above is a specific description of the embodiments of the present disclosure, but the present disclosure is not limited to the above embodiments, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the present disclosure, and are included in the scope of the present disclosure as defined in the claims.
Claims (10)
1. The utility model provides a vehicle control method based on sense of general integration, which is characterized in that the method is applied to a vehicle control base station and comprises the following steps:
Acquiring historical channel data of a target vehicle corresponding to a plurality of continuous time slots;
Inputting the historical channel data into a pre-trained beam prediction model for beam prediction to obtain a control beam of the present round; the home wheel control beam is used for performing home wheel control operation on the target vehicle;
transmitting a home wheel control beam to the target vehicle, and acquiring a home wheel echo signal from the target vehicle in response to the home wheel control operation;
and updating the historical channel data based on the current round of control beam and the current round of echo signals, and returning to perform beam prediction by inputting the historical channel data into a pre-trained beam prediction model.
2. The method of claim 1, wherein the beam prediction model comprises a coding layer, a prediction layer;
the step of inputting the historical channel data into a pre-trained beam prediction model for beam prediction to obtain a current round of control beam comprises the following steps:
Inputting the historical channel data into a coding layer for feature coding processing to obtain corresponding target space features between the vehicle control base station and the target vehicle; wherein the target spatial feature reflects a spatially varying feature of the target vehicle corresponding in a plurality of consecutive time slots;
inputting the target space features into the prediction layer for azimuth prediction to obtain azimuth prediction features;
And carrying out beam forming processing based on the azimuth prediction characteristics to obtain the control beam of the present wheel.
3. The method of claim 2, wherein the vehicle control base station is configured to control a plurality of the target vehicles, the beam prediction model further comprising a fusion layer and a decoding layer;
and performing beam forming processing based on the azimuth prediction feature to obtain the home-wheel control beam, including:
Inputting the azimuth prediction features corresponding to each target vehicle into the fusion layer to perform feature fusion processing to obtain a fusion feature matrix;
and inputting the fusion feature matrix into a decoding layer for feature decoding processing to obtain the control beam of the present round.
4. The method of claim 3, wherein the decoding layer comprises a full convolutional neural network;
the step of inputting the fusion feature matrix into a decoding layer for feature decoding processing to obtain the control beam of the present wheel comprises the following steps:
And inputting the fusion feature matrix into a decoding layer so that the full convolution neural network carries out nonlinear transformation on the distribution power and the prediction angle corresponding to the fusion feature matrix to obtain the control beam of the present round.
5. The method of claim 1, further comprising pre-training the beam prediction model before the inputting the historical channel data into the pre-trained beam prediction model for beam prediction to obtain the current round of control beams, specifically comprising:
acquiring channel sample information of a plurality of continuous time slots and sample label information corresponding to the channel sample information;
inputting the channel sample information and sample label information corresponding to the channel sample information into the original beam prediction model for iterative prediction training to obtain a training result of the round;
Comparing the training result of the round with the sample label information to obtain deviation data of the round;
And updating the beam prediction model based on the current round of deviation data, and returning to input the channel sample information and sample label information corresponding to the channel sample information into the beam prediction model for iterative prediction training until the current round of deviation data meets a training preset condition to obtain the pre-trained beam prediction model.
6. The method of claim 1, wherein the acquiring historical channel data for the target vehicle corresponding to a plurality of consecutive time slots comprises:
Transmitting a first test beam to a target area, and acquiring a test feedback signal from the target vehicle in response to the first test beam; the target area is an environment area where the target vehicle is located;
and correcting and shaping the first test beam based on the test feedback signal to generate the historical channel data.
7. The method of claim 6, wherein the performing correction shaping processing on the first test beam based on the test feedback signal to generate the historical channel data comprises:
Based on the test feedback signal, performing power adjustment processing, angle adjustment processing and initial shaping on the first test beam to obtain a second test beam;
and performing test communication with the target vehicle based on the second test beam to obtain the historical channel data.
8. A vehicle control method based on general sense integration is characterized by being applied to a target vehicle and comprising the following steps:
Acquiring a home wheel control beam from a vehicle control base station; the present wheel control beam is obtained at the vehicle control base station by the following method: acquiring historical channel data of a target vehicle corresponding to a plurality of continuous time slots, and inputting the historical channel data into a pre-trained beam prediction model for beam prediction to obtain the control beam of the present wheel; the home wheel control beam is used for performing home wheel control operation on the target vehicle;
And responding to the home run control operation, transmitting a home run echo signal to the vehicle control base station so that the vehicle control base station can update the historical channel data based on the home run control beam and the home run echo signal, and returning to execute the input of the historical channel data into a pre-trained beam prediction model to perform beam prediction.
9. An electronic device, comprising: a memory, a processor storing a computer program, the processor implementing the vehicle control method based on the sense of general integration according to any one of claims 1 to 8 when executing the computer program.
10. A computer-readable storage medium storing a program that is executed by a processor to implement the through-sense integration-based vehicle control method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410579174.1A CN118158695A (en) | 2024-05-11 | 2024-05-11 | Vehicle control method based on general sense integration, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410579174.1A CN118158695A (en) | 2024-05-11 | 2024-05-11 | Vehicle control method based on general sense integration, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118158695A true CN118158695A (en) | 2024-06-07 |
Family
ID=91297162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410579174.1A Pending CN118158695A (en) | 2024-05-11 | 2024-05-11 | Vehicle control method based on general sense integration, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118158695A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115412844A (en) * | 2022-08-25 | 2022-11-29 | 北京大学 | Real-time alignment method for vehicle networking beams based on multi-mode information synaesthesia |
| CN115865157A (en) * | 2022-11-24 | 2023-03-28 | 电子科技大学 | Method for intelligent reflecting surface to assist multi-user communication prediction beam forming |
| CN117676609A (en) * | 2023-12-08 | 2024-03-08 | 东南大学 | Neural network-based beam prediction method for radar-assisted communication |
-
2024
- 2024-05-11 CN CN202410579174.1A patent/CN118158695A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115412844A (en) * | 2022-08-25 | 2022-11-29 | 北京大学 | Real-time alignment method for vehicle networking beams based on multi-mode information synaesthesia |
| CN115865157A (en) * | 2022-11-24 | 2023-03-28 | 电子科技大学 | Method for intelligent reflecting surface to assist multi-user communication prediction beam forming |
| CN117676609A (en) * | 2023-12-08 | 2024-03-08 | 东南大学 | Neural network-based beam prediction method for radar-assisted communication |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111954228B (en) | Beam management method, beam management device, electronic equipment and computer readable storage medium | |
| CN114342457B (en) | User equipment positioning device and method | |
| CN112152948B (en) | Wireless communication processing method and device | |
| US10460581B1 (en) | Determining a confidence for a motion zone identified as a location of motion for motion detected by wireless signals | |
| US10743143B1 (en) | Determining a motion zone for a location of motion detected by wireless signals | |
| EP3969932A1 (en) | Determining motion zones in a space traversed by wireless signals | |
| Chiou et al. | An adaptive location estimator using tracking algorithms for indoor WLANs | |
| Liu et al. | Artificial intelligence based mobile tracking and antenna pointing in satellite-terrestrial network | |
| CN116710806A (en) | Collaborative environment sensing in wireless networks | |
| Sun et al. | JPBA of ARN for target tracking in clutter | |
| Klus et al. | Transfer learning for convolutional indoor positioning systems | |
| Zhu et al. | Low‐angle target tracking using frequency‐agile refined maximum likelihood algorithm | |
| Suchanski et al. | Radio environment maps for military cognitive networks: construction techniques vs. map quality | |
| JP7380890B2 (en) | Beamforming prediction device, method and program | |
| CN117676609A (en) | Neural network-based beam prediction method for radar-assisted communication | |
| Yu et al. | Indoor passive localisation based on reliable CSI extraction | |
| Tian et al. | Deep-learning based high-precision localization with massive MIMO | |
| CN118158695A (en) | Vehicle control method based on general sense integration, electronic equipment and storage medium | |
| CN116634358A (en) | Terminal positioning method and device and nonvolatile storage medium | |
| CN111628837A (en) | Channel modeling method and device | |
| US20220394653A1 (en) | Method and apparatus of positioning for accomodating wireless-environment change | |
| Lv et al. | Accessorial locating for internet of vehicles based on doa estimation in industrial transportation | |
| Mukhtar | Machine learning enabled-localization in 5g and lte using image classification and deep learning | |
| CN114764610A (en) | Channel estimation method based on neural network and communication device | |
| Ghadian et al. | Designing adaptive time resource management cost function for cognitive radar |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |