Parking control method, device, equipment, medium and vehicle

By preprocessing the environmental data of the parking system and expanding the application of the Kalman filter module, the problems of noise interference and detection of blind spots in traditional parking systems are solved, and the distance measurement accuracy and reliability of the parking system are improved. A safer and more convenient parking experience.

CN119025795APending Publication Date: 2024-11-26ZHEJIANG GEELY HLDG GRP CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411126630.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

Traditional ultrasonic parking systems have noise interference and blind spot detection problems when processing sensor data, resulting in unstable distance measurement and insufficient positioning of obstacles, affecting the performance and reliability of the parking system.

Method used

By preprocessing the environment data around the vehicle, the external state vector is obtained and the extended Kalman filter module is used to predict and fusion, and noise and filter interference are removed, and the ability to adapt to environmental changes is enhanced.

Benefits of technology

It significantly improves the distance measurement accuracy and stability of the parking system, improves obstacle positioning and parking space detection, enhances the performance and reliability of the parking system, and provides drivers with a safer and more convenient parking experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119025795A_ABST
    Figure CN119025795A_ABST
Patent Text Reader

Abstract

The invention relates to a parking control method, device and equipment, a medium and a vehicle, and the method comprises the steps: carrying out the preprocessing of the data of the environment around the vehicle at the current moment, and obtaining an initial state vector; wherein the preprocessing comprises denoising, filtering and data format conversion; obtaining an external state vector, and predicting an optimal prediction state vector at the current moment through an extended Kalman filtering module according to the external state vector; fusing the optimal prediction state vector with the initial state vector to obtain a target state vector; and controlling the vehicle to park based on the target state vector. The performance and reliability of the parking system can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle technology, and in particular to a parking control method, device, equipment, medium and vehicle. Background Art

[0002] In parking systems, ultrasonic sensors are widely used to detect obstacles around the vehicle and available parking spaces. However, traditional ultrasonic parking systems have some challenges in processing sensor data. For example, there are limitations in obstacle positioning and storage location detection, especially when obstacles or storage locations are located in the detection blind spot of the ultrasonic radar probe, the system may not be able to accurately detect these points; secondly, co-frequency interference is a common problem that may cause the ranging value of ultrasonic sensor data to be unstable, similar to noise interference.

[0003] Therefore, the deficiencies in existing processing of sensor data will seriously affect the performance and reliability of the parking system. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a parking control method, device, equipment, medium and vehicle.

[0005] According to one aspect of the present disclosure, a parking control method is provided, comprising:

[0006] At the current moment, preprocessing the environmental data around the vehicle to obtain an initial state vector; wherein the preprocessing includes: denoising, filtering and data format conversion;

[0007] Acquire an external state vector, and predict the optimal predicted state vector at the current moment according to the external state vector through an extended Kalman filter module;

[0008] Merging the optimal predicted state vector with the initial state vector to obtain a target state vector;

[0009] The vehicle is controlled to park based on the target state vector.

[0010] According to another aspect of the present disclosure, a parking control device is provided, comprising:

[0011] A data preprocessing module is used to preprocess the environmental data around the vehicle at the current moment to obtain an initial state vector; wherein the preprocessing includes: denoising, filtering and data format conversion;

[0012] A filtering module, used to obtain an external state vector, and predict the optimal predicted state vector at the current moment according to the external state vector through an extended Kalman filter module;

[0013] A vector fusion module, used to fuse the optimal predicted state vector with the initial state vector to obtain a target state vector;

[0014] A parking control module is used to control the vehicle to park based on the target state vector.

[0015] According to another aspect of the present disclosure, an electronic device is provided, the electronic device comprising:

[0016] processor;

[0017] a memory for storing instructions executable by the processor;

[0018] The processor is used to read the executable instructions from the memory and execute the instructions to implement the above method.

[0019] According to another aspect of the present disclosure, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute the above method.

[0020] According to another aspect of the present disclosure, a vehicle is further provided, comprising: the parking control device as described above, the electronic device as described above, and / or the computer-readable storage medium as described above.

[0021] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0022] The technical solution provided by the disclosed embodiment includes: at the current moment, first pre-processing the environmental data around the vehicle to obtain an initial state vector; then obtaining the external state vector, and predicting the optimal predicted state vector at the current moment according to the external state vector through the extended Kalman filter module; then fusing the optimal predicted state vector with the initial state vector to obtain the target state vector; finally controlling the vehicle to park based on the target state vector. This technical solution can effectively handle the same-frequency interference and significantly improve the ranging accuracy and stability of the parking system by pre-processing the environmental data such as denoising and filtering; the extended Kalman filter module in this solution enhances the adaptability to environmental changes by flexibly using the external state vector to update and optimize the predicted state vector, and better avoids the errors and fluctuations existing in traditional technologies; by using the external state vector to update the state and fusing the optimal predicted state vector with the initial state vector, it can effectively improve the deficiencies of obstacle positioning and parking space detection in the parking system, improve the performance and reliability of the parking system, and provide drivers with a safer and more convenient parking experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0025] Figure 1 A flowchart of a parking control method provided by an embodiment of the present disclosure;

[0026] Figure 2 A schematic diagram of different filtering results provided by an embodiment of the present disclosure;

[0027] Figure 3 A structural block diagram of a parking control device provided in an embodiment of the present disclosure;

[0028] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0030] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0031] Considering the shortcomings of the existing sensor data processing, the performance and reliability of the automatic parking system will be seriously affected. Based on this, the embodiments of the present disclosure provide a parking control method, device, equipment, medium and vehicle. The technical solution applies the extended Kalman filter (Extended Kalman Filter, EKF) to the data processing in the automatic parking system. For ease of understanding, the embodiments of the present disclosure are described below.

[0032] Figure 1A flowchart of a parking control method provided in an embodiment of the present disclosure, which can be applied to the scene of parking or reversing a car, uses an external state vector to update the state, can more flexibly use external information, and improve the performance and stability of the parking system. The method can be executed by a parking control device, which can be implemented by software and / or hardware, such as an electronic device or a server. Among them, the electronic device may include a vehicle-mounted host, a tablet computer, a desktop computer, a laptop computer, a smart phone and other devices with communication functions. The server can be a cloud server or a server cluster and other devices with storage and computing functions. This embodiment takes an electronic device as an example of an execution subject to describe the parking control method.

[0033] Reference Figure 1 The parking control method provided by the embodiment of the present disclosure may include the following steps.

[0034] S102, at the current moment, preprocessing the environmental data around the vehicle to obtain an initial state vector; wherein the preprocessing includes: denoising, filtering and data format conversion.

[0035] In this embodiment, at the current moment (moment k), environmental data about the vehicle's surroundings are first received from the ultrasonic sensor; the environmental data includes but is not limited to: location information of the vehicle, and distance information between the vehicle and surrounding obstacles.

[0036] The received environmental data is denoised to remove noise signals in the environmental data. In environmental data, co-channel interference is also a common problem, which may cause fluctuations in the ranging results of ultrasonic data, affecting the stability and performance of the parking system. It is generally difficult to remove co-channel interference by denoising, so this embodiment filters the denoised environmental data. In a specific example, filters such as bandpass filters or digital filters can be used to suppress co-channel interference signals, thereby reducing the impact of co-channel interference on the performance of the parking system and improving ranging accuracy and stability.

[0037] The data format of the denoised and filtered environmental data is converted to generate an initial state vector.

[0038] S104, obtaining an external state vector, and predicting the optimal predicted state vector at the current moment according to the external state vector through an extended Kalman filter module.

[0039] In some state update modes, the state update is performed only in the extended Kalman filter module. Considering the external data such as the environment map outside the vehicle, the environment image, the speed of the vehicle relative to the external obstacles, etc., it will also have an impact on parking. Based on this, this embodiment introduces the external state vector into the extended Kalman filter module, and uses the external state vector in the extended Kalman filter module to perform a more accurate state update.

[0040] The external state vector in this embodiment may include: an actual external state vector or a predicted external state vector; accordingly, the process of obtaining the external state vector may include: determining whether the vehicle's external detection data is received at the current moment; if so, generating the actual external state vector based on the external detection data; if not, performing blind spot state prediction based on historical external detection data to generate a predicted external state vector; wherein the historical external detection data is the latest external detection data received before the current moment.

[0041] In a specific embodiment, the vehicle's external detection data can be collected through sensors such as the vehicle's speed sensor, ultrasonic radar, and camera. The external detection data includes: external environment maps, parking space markings, environmental images, the position, height, angle, and distance of obstacles identified from the environmental images from the vehicle, the speed of the vehicle relative to the obstacle, the moving speed of the obstacle, etc.

[0042] It is easy to understand that when encountering a detection blind spot, the vehicle's sensors cannot effectively collect the above-mentioned external detection data; specifically, when an obstacle or parking space is outside the detection range of the ultrasonic radar probe, the key data of these points cannot be accurately detected, resulting in the accuracy and safety of parking being affected.

[0043] In this case, this embodiment determines whether the external detection data of the vehicle is received at the current time k; if the external detection data can be received, it means that as the vehicle moves, the vehicle at the current time k is not in the detection blind spot, so the actual external state vector is generated according to the external detection data. Specifically, the external detection data can be de-noised, filtered, and converted into a data format to generate an actual external state vector that can reflect the actual external environment.

[0044] If no external detection data is received, it means that as the vehicle moves, the vehicle at the current time k enters the detection blind spot. Therefore, the blind spot state is predicted based on the historical external detection data to generate a predicted external state vector.

[0045] The historical external detection data is the latest external detection data received before the current moment. If the current moment k is the first time that the external detection data is not received, the external detection data collected at the moment before the current moment k (moment k-1) is used as the historical external detection data; if the current moment k is not the first time that the external detection data is not received, the search starts from the current moment k to the previous collection moment until the latest received external detection data is determined as the historical external detection data. Then, the blind spot state is predicted based on the historical external detection data to generate a predicted external state vector that can reflect the external prediction environment.

[0046] In this embodiment, in response to the situation where the actual external state vector cannot be obtained in the blind spot, the blind spot state is predicted based on the historical external detection data to generate a predicted external state vector. This can effectively make up for the missing external state vector in the blind spot and improve the ability to perceive environmental changes. This enables the parking system to more accurately identify and respond to various complex scenarios, improve the detection accuracy of information such as obstacles or parking spaces in the blind spot, and help enhance the safety and reliability of parking.

[0047] After acquiring the external state vector, the extended Kalman filter module predicts the optimal predicted state vector at the current moment based on the external state vector. Among them, the extended Kalman filter module can be applied to data processing in the parking system. The extended Kalman filter is a state estimation method based on Bayesian filtering, which achieves the optimal estimation of the state by recursively estimating the state of the system. In the parking system, the extended Kalman filter module is usually used to fuse the sensor measurement value with the vehicle state, thereby improving the system's perception of the vehicle's surrounding environment.

[0048] In this embodiment, the optimal predicted state vector at the current moment is predicted according to the external state vector by using the extended Kalman filter module, which may specifically include the following contents.

[0049] According to the extended Kalman filter module and the optimal predicted state vector at the previous moment, the predicted state vector at the current moment is determined. For details, please refer to the following formula (1);

[0050]

[0051] in, represents the predicted state vector at the current time k, represents the optimal prediction state vector of the previous moment k-1, B k represents the control matrix of vehicle k at the current moment, u k represents the control input vector of vehicle k at the current moment.

[0052] Construct the observation vector based on the predicted state vector at the current moment.

[0053] The prediction error covariance is calculated based on the prediction state vector at the current moment. For details, please refer to the following formula (2):

[0054]

[0055] in, represents the prediction error covariance at the current time k, P k-1 represents the prediction error covariance of the previous moment k-1, A k represents the adaptive coefficient switching function, Q k Indicates that the system noise vector at the current moment k obeys a normal distribution with a mean of 0.

[0056] The Kalman gain is calculated based on the prediction error covariance, which can be specifically referred to in the following formula (3);

[0057]

[0058] Among them, K k represents the Kalman gain at the current time k, H k Represents the conversion matrix from the predicted state vector at the current time k to the observed variable, R k It means that at the current moment k obeys the Gaussian white noise with a normal distribution and a mean of 0.

[0059] Determine the state vector difference between the external state vector and the predicted state vector at the current moment, that is: in, Represents the external state vector.

[0060] According to the predicted state vector, Kalman gain, observation vector and state vector difference at the current moment, the predicted state vector at the current moment is updated and optimized to obtain the optimal predicted state vector at the current moment. Specifically, the optimal predicted state vector at the current moment can be obtained according to the following update formula (4):

[0061]

[0062] in, represents the optimal predicted state vector at the current time k, represents the predicted state vector at the current time k, K k represents the Kalman gain, z k represents the observation vector, H k Represents the predicted state vector at the current time k With the observation vector z k The relationship matrix between represents the external state vector, α k Represents the weighting coefficient.

[0063] This embodiment further includes: referring to the following formula (5), updating the error covariance based on the Kalman gain at the current moment:

[0064]

[0065] Among them, P k represents the updated error covariance at the current time k, P k Can be used to calculate the prediction error covariance of the next moment k+1

[0066] After the state vector of the traditional extended Kalman filter module is initialized, the state is only updated inside the extended Kalman filter module, and no external information is used for state update. This method has certain limitations when dealing with co-frequency interference and tracking obstacles and parking spots entering blind spots. In contrast, the extended Kalman filter module in this embodiment can use external state vectors for state updates. This method breaks through the limitation that the extended Kalman filter module only updates the state internally, and can more flexibly use external state vectors representing external information. Based on this, the problem of co-frequency interference and tracking of obstacles and parking spots entering blind spots is effectively improved, thereby improving the adaptability and robustness of the parking system.

[0067] S106, merge the optimal predicted state vector with the initial state vector to obtain a target state vector. In specific implementation, the optimal predicted state vector and the initial state vector may be weighted summed to obtain the target state vector.

[0068] like Figure 2 As shown, the squares represent the obstacle positioning results that are subject to co-frequency interference when the vehicle is stationary, and the circles represent the actual positions of the obstacles. The left figure uses an ordinary Kalman filter algorithm, and the triangles represent the filtering results under this Kalman filter algorithm; the right figure is the extended Kalman filter module that uses the external state vector in this embodiment, and the optimal predicted state vector is merged with the initial state vector to obtain the filtering result after the target state vector is obtained. It can be clearly seen that the filtering effect represented by the triangle in the right figure is better than the filtering effect represented by the triangle in the left figure, a large amount of noise is removed, and the filtering result is more accurate; the right Figure 3 The filtering results represented by the angle shape can effectively track these obstacle points and parking spots, thereby improving the system's ability to perceive environmental changes and further enhancing the safety and reliability of the parking system.

[0069] S108, control the vehicle to park based on the target state vector. Specifically, the optimal predicted state vector, the initial state vector, the target state vector and other data processed and optimized by the extended Kalman filter module can all be transmitted to the parking system to control the automatic navigation and parking operation of the vehicle at the next time k+1.

[0070] It is understandable that at the next time k+1, the above steps S102-S108 will be executed again, including: at time k+1, preprocessing the environmental data around the vehicle to obtain the initial state vector; obtaining the external state vector, and predicting the optimal predicted state vector at time k+1 based on the external state vector through the extended Kalman filter module; fusing the optimal predicted state vector with the initial state vector to obtain the target state vector; and controlling the vehicle to park at the next time k+2 based on the target state vector. And so on, until the vehicle completes parking.

[0071] Therefore, in the entire parking process of this embodiment, as the vehicle moves and the environment changes during parking, the extended Kalman filter module will receive the external state vector in real time, and use the external state vector to update the optimal prediction state vector in real time, so that it can continue to effectively track obstacle points and parking spots, maintain a more accurate perception of environmental changes, thereby better adapting to complex environments and changing scenarios, and further enhancing the safety and reliability of parking.

[0072] In summary, the parking control method provided by the embodiment of the present disclosure includes: at the current moment, first pre-processing the environmental data around the vehicle to obtain an initial state vector; then obtaining the external state vector, and predicting the optimal predicted state vector at the current moment according to the external state vector through the extended Kalman filter module; then fusing the optimal predicted state vector with the initial state vector to obtain the target state vector; finally controlling the vehicle to park based on the target state vector. This technical solution can effectively handle the same-frequency interference and significantly improve the ranging accuracy and stability of the parking system by pre-processing the environmental data such as denoising and filtering; the extended Kalman filter module in this solution enhances the adaptability to environmental changes by flexibly using the external state vector to update and optimize the predicted state vector, and better avoids the errors and fluctuations existing in traditional technologies; by using the external state vector to update the state and fusing the optimal predicted state vector with the initial state vector, it can effectively improve the shortcomings of obstacle positioning and parking space detection in the parking system, improve the performance and reliability of the parking system, and provide drivers with a safer and more convenient parking experience.

[0073] Figure 3 This is a structural block diagram of a parking control device provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware, such as an electronic device or a server, for implementing the above parking control method. Figure 3 As shown, the parking control device may include the following modules:

[0074] The data preprocessing module 210 is used to preprocess the environmental data around the vehicle at the current moment to obtain an initial state vector; wherein the preprocessing includes: denoising, filtering and data format conversion;

[0075] A filtering module 220, used for acquiring an external state vector, and predicting the optimal predicted state vector at the current moment according to the external state vector through an extended Kalman filter module;

[0076] A vector fusion module 230, configured to fuse the optimal predicted state vector with the initial state vector to obtain a target state vector;

[0077] The parking control module 240 is configured to control the vehicle to park based on the target state vector.

[0078] The implementation principle and technical effects of the device provided in this embodiment are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0079] Figure 4 The structure diagram of an electronic device provided by the embodiment of the present disclosure is shown in FIG. Figure 4 As shown, the electronic device 300 includes one or more processors 301 and a memory 302 .

[0080] The processor 301 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 300 to perform desired functions.

[0081] The memory 302 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 301 may execute the program instructions to implement the parking control method of the embodiment of the present disclosure described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0082] In one example, the electronic device 300 may further include: an input device 303 and an output device 304 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0083] In addition, the input device 303 may also include, for example, a keyboard, a mouse, and the like.

[0084] The output device 304 can output various information to the outside, including the determined distance information, direction information, etc. The output device 304 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0085] Of course, to simplify, Figure 4 Only some of the components related to the present disclosure in the electronic device 300 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 300 may also include any other appropriate components.

[0086] Furthermore, this embodiment also provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the above parking control method.

[0087] Furthermore, this embodiment also provides a vehicle, which may include: the parking control device as described above, the electronic device as described above, and / or the computer-readable storage medium as described above.

[0088] A parking control method, device, electronic device and computer program product of a medium provided in the embodiments of the present disclosure include a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method described in the previous method embodiments. The specific implementation can be found in the method embodiments and will not be repeated here.

[0089] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0090] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A parking control method, characterized in that: include: At the current moment, preprocessing the environmental data around the vehicle to obtain an initial state vector; wherein the preprocessing includes: denoising, filtering and data format conversion; Acquire an external state vector, and predict the optimal predicted state vector at the current moment according to the external state vector through an extended Kalman filter module; Merging the optimal predicted state vector with the initial state vector to obtain a target state vector; The vehicle is controlled to park based on the target state vector.

2. The method according to claim 1, characterized in that The method of predicting the optimal predicted state vector at the current moment according to the external state vector by using the extended Kalman filter module includes: Determine the predicted state vector at the current moment according to the extended Kalman filter module and the optimal predicted state vector at the previous moment; Constructing an observation vector based on the predicted state vector at the current moment; Calculating a prediction error covariance based on the prediction state vector at the current moment; Calculating a Kalman gain based on the prediction error covariance; Determine a state vector difference between the external state vector and the predicted state vector at the current moment; The predicted state vector at the current moment is updated and optimized according to the predicted state vector at the current moment, the Kalman gain, the observation vector and the state vector difference to obtain the optimal predicted state vector at the current moment.

3. The method according to claim 2, characterized in that The updating and optimizing of the predicted state vector at the current moment according to the predicted state vector at the current moment, the Kalman gain, the observation vector and the state vector difference to obtain the optimal predicted state vector at the current moment includes: The optimal prediction state vector at the current moment is obtained according to the following update formula: in, represents the optimal prediction state vector at the current time k, represents the predicted state vector at the current time k, K k represents the Kalman gain, z k represents the observation vector, the H k Represents the predicted state vector at the current time k With the observation vector z k The relationship matrix between represents the external state vector, α k Represents the weighting coefficient.

4. The method according to claim 1, characterized in that: The external state vector includes: an actual external state vector or a predicted external state vector; the obtaining of the external state vector includes: Determining whether external detection data of the vehicle is received at the current moment; If yes, generating the actual external state vector according to the external detection data; If not, the blind spot state is predicted based on the historical external detection data to generate a predicted external state vector; wherein the historical external detection data is the latest external detection data received before the current moment.

5. The method according to claim 1, characterized in that The step of fusing the optimal predicted state vector with the initial state vector to obtain a target state vector includes: The optimal predicted state vector and the initial state vector are weightedly summed to obtain a target state vector.

6. The method according to claim 1, characterized in that The method further comprises: Receive environmental data around the vehicle from an ultrasonic sensor; wherein the environmental data includes: position information of the vehicle, and distance information between the vehicle and surrounding obstacles.

7. A parking control device, characterized in that: include: A data preprocessing module is used to preprocess the environmental data around the vehicle at the current moment to obtain an initial state vector; wherein the preprocessing includes: denoising, filtering and data format conversion; A filtering module, used to obtain an external state vector, and predict the optimal predicted state vector at the current moment according to the external state vector through an extended Kalman filter module; A vector fusion module, used to fuse the optimal predicted state vector with the initial state vector to obtain a target state vector; A parking control module is used to control the vehicle to park based on the target state vector.

8. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device implements the method according to any one of claims 1 to 6.

10. A vehicle, characterized in that: include: The parking control device according to claim 7, the electronic device according to claim 8 and / or the computer-readable storage medium according to claim 9.