Vehicle position prediction method and device, storage medium and electronic equipment

Abstract

The invention discloses a vehicle position prediction method and device, a storage medium and electronic equipment, and relates to the traffic field, and the method comprises the steps: determining an i-th state transition matrix according to the i-th state parameter of a target vehicle, determining an i-th estimated position matrix according to the i-th state transition matrix and an (i-1)-th predicted position matrix, and determining the i-th estimated position matrix according to the i-th estimated position matrix and the (i-1)-th predicted position matrix; determining an ith measurement position matrix according to the ith measurement parameter of the target vehicle; determining an ith gain matrix according to the (i-1) th gain matrix and a preset uncertainty matrix; and determining an ith predicted position matrix according to the ith estimated position matrix, the ith measured position matrix and the ith gain matrix. The technical problem that the prediction accuracy of the vehicle position is low is solved.

Description

Technical Field

[0001] This application relates to the field of transportation, and in particular, to a method and device for predicting the position of a vehicle, a storage medium, and an electronic device. Background Art

[0002] In the related art, the position of a vehicle is predicted based on historical data and a statistical model, or a probability model. In the former case, different weights are set for different sensors based on experience, and the predicted position is determined as the weighted sum of the data collected by each sensor. In this way, the accuracy of the prediction result depends on whether the weight setting is accurate, and the weights set according to experience often have biases, such as being too high or too low. It can be understood that this will result in a low accuracy rate of the prediction result.

[0003] In the latter case, the position of the vehicle is predicted based on the corrected probability and historical data. For example, the vehicle is driving on the main road, but according to the corrected probability, it is predicted that the vehicle is driving on the secondary road. In this way, the accuracy of the prediction result is affected by whether the probability correction is accurate, and there are often certain errors in the probability correction.

[0004] In view of the problem of the low accuracy rate of the prediction of the vehicle position, no effective solution has been proposed yet. Summary of the Invention

[0005] Embodiments of this application provide a method and device for predicting the position of a vehicle, a storage medium, and an electronic device, so as to at least solve the technical problem of the low accuracy rate of the prediction of the vehicle position.

[0006] According to one aspect of the embodiments of the present application, a method for predicting a vehicle position is provided, including: determining an i-th state transition matrix according to the i-th state parameter of a target vehicle, determining an i-th estimated position matrix according to the i-th state transition matrix and an (i - 1)-th predicted position matrix, and determining an i-th measured position matrix according to the i-th measurement parameter of the target vehicle, where the i-th state parameter includes driving parameters of the target vehicle output by a first set of measuring devices on the target vehicle at the i-th moment, the (i - 1)-th predicted position matrix is used to represent the predicted position of the target vehicle at the (i - 1)-th moment, i is a positive integer greater than or equal to 2, the i-th measurement parameter includes driving parameters of the target vehicle output by a second set of measuring devices located outside the target vehicle at the i-th moment, and the i-th measured position matrix is used to represent the measured position of the target vehicle at the i-th moment; determining an i-th gain matrix according to an (i - 1)-th gain matrix and a preset uncertainty matrix, where the uncertainty matrix is used to represent the covariance of a first measurement noise matrix, the first measurement noise matrix is used to represent the mean of P differences, the j-th difference among the P differences is the difference between the measured position of a reference vehicle represented by the j-th measured position matrix among the P measured position matrices and the j-th actual position among the preset P actual positions, the j-th actual position is the actual position of the reference vehicle at the j-th moment among the P moments, P is a positive integer, and j is a positive integer less than or equal to P; determining an i-th predicted position matrix according to the i-th estimated position matrix, the i-th measured position matrix, and the i-th gain matrix, where the i-th predicted position matrix is used to represent the predicted position of the target vehicle at the i-th moment.

[0007] According to another aspect of the embodiments of the present application, a prediction device for vehicle position is further provided, including: a first determination unit, configured to determine the i-th state transition matrix according to the i-th state parameter of the target vehicle, determine the i-th estimated position matrix according to the i-th state transition matrix and the (i - 1)-th predicted position matrix, and determine the i-th measured position matrix according to the i-th measurement parameter of the target vehicle, where the i-th state parameter includes the driving parameters of the target vehicle output by the first set of measurement devices on the target vehicle at the i-th moment, the (i - 1)-th predicted position matrix is used to represent the predicted position of the target vehicle at the (i - 1)-th moment, i is a positive integer greater than or equal to 2, the i-th measurement parameter includes the driving parameters of the target vehicle output by the second set of measurement devices located outside the target vehicle at the i-th moment, and the i-th measured position matrix is used to represent the measured position of the target vehicle at the i-th moment; a second determination unit, configured to determine the i-th gain matrix according to the (i - 1)-th gain matrix and a preset uncertainty matrix, where the uncertainty matrix is used to represent the covariance of the first measurement noise matrix, the first measurement noise matrix is used to represent the mean of P differences, the j-th difference among the P differences is the difference between the measured position of the reference vehicle represented by the j-th measured position matrix among the P measured position matrices and the j-th actual position among the preset P actual positions, the j-th actual position is the actual position of the reference vehicle at the j-th moment among the P moments, P is a positive integer, and j is a positive integer less than or equal to P; a third determination unit, configured to determine the i-th predicted position matrix according to the i-th estimated position matrix, the i-th measured position matrix and the i-th gain matrix, where the i-th predicted position matrix is used to represent the predicted position of the target vehicle at the i-th moment.

[0008] Optionally, the first determination unit includes: a first determination module, configured to determine M position change parameters according to the N driving parameters when the i-th state parameter includes N driving parameters, where the N driving parameters include the driving parameters of the target vehicle output by each of the N measurement devices at the i-th moment, the first set of measurement devices includes the N measurement devices, N is a positive integer greater than or equal to 2, the M position change parameters are used to represent the position change amount of the target vehicle at the i-th moment, and M is a positive integer greater than or equal to 2; a second determination module, configured to determine the i-th state transition matrix as including the M position change parameters.

[0009] Optionally, the first determining module is configured to: when the N driving parameters include the speed of the target vehicle and the heading angle of the target vehicle, determine the first position change parameter to be equal to the product of the sine value of the heading angle and the speed, and determine the second position change parameter to be equal to the product of the cosine value of the heading angle and the speed, where the M position change parameters include the first position change parameter and the second position change parameter; the second determining module is configured to: set the i-th state transition matrix as a diagonal matrix with a dimension of 2×2, where the first position change parameter and the second position change parameter are included on the diagonal of the diagonal matrix.

[0010] Optionally, the first determining unit includes: a first execution module configured to perform a multiplication operation on the i-th state transition matrix and the (i-1)-th predicted position matrix to obtain a first product matrix; a second execution module configured to perform an addition operation on the first product matrix and a preset second measurement noise matrix to obtain the i-th estimated position matrix, where the second measurement noise matrix is used to represent the difference between Q actual positions obtained in advance and the reference position, the k-th actual position among the Q actual positions is the actual position reached by the target vehicle when starting from the starting actual position and driving for a preset duration according to the reference state parameters for the k-th time, the reference position is the estimated position of the target vehicle represented by the reference estimated position matrix, the reference estimated position matrix is an estimated position matrix determined according to the reference state transition matrix and a pre-determined starting position matrix, the starting position matrix is used to represent the starting actual position of the target vehicle, the reference state transition matrix is a state transition matrix determined according to the reference state parameters, the reference state parameters include the driving parameters of the target vehicle output by the first group of measurement devices at the reference time, the starting actual position is the position of the target vehicle at the reference time, Q is a positive integer, and k is a positive integer greater than or equal to 1 and less than or equal to Q.

[0011] Optionally, the first determining unit includes: a third execution module configured to perform a multiplication operation on a preset measurement conversion matrix and the i-th measurement matrix when the driving parameters included in the i-th measurement parameter form the i-th measurement matrix to obtain a second product matrix, where the second product matrix is used to represent the initial measurement position of the target vehicle at the i-th time, and the measurement conversion matrix is an identity matrix; a third determining module configured to determine the i-th measurement position matrix to be equal to the matrix obtained by performing an addition operation on the second product matrix and the first measurement noise matrix.

[0012] Optionally, the second determination unit includes: a fourth determination module, configured to determine an i-th state covariance matrix according to the (i-1)-th gain matrix, the (i-1)-th state covariance matrix, and a preset measurement transformation matrix; and a fifth determination module, configured to determine the i-th gain matrix according to the i-th state covariance matrix, the uncertainty matrix, and the measurement transformation matrix.

[0013] Optionally, the fourth determination module is configured to: perform a product operation on the (i-1)-th gain matrix and the measurement transformation matrix to obtain a third product matrix; subtract the third product matrix from a preset identity matrix to obtain a first difference matrix; and perform a product operation on the transpose of the first difference matrix, the (i-1)-th state covariance matrix, and the first difference matrix to obtain the i-th state covariance matrix.

[0014] Optionally, the fifth determination module is configured to: perform a product operation on the transpose of the measurement transformation matrix, the i-th state covariance matrix, and the measurement transformation matrix to obtain a fourth product matrix; perform an addition operation on the fourth product matrix and the uncertainty matrix to obtain a first sum matrix; and perform a product operation on the fourth product matrix and the transpose of the first sum matrix to obtain the i-th gain matrix.

[0015] Optionally, the apparatus further includes: an execution unit, configured to perform a mean operation on the R×R noise values when the first measurement noise matrix includes R×R noise values to obtain a noise mean; and a fourth determination unit, configured to determine the uncertainty matrix according to the noise mean and the R×R noise values.

[0016] Optionally, the fourth determination unit includes: a subtraction module, configured to subtract each noise data in the R×R noise values in the first measurement noise matrix from the noise mean to obtain a difference measurement noise matrix; a fourth execution module, configured to perform a product operation on the transpose of the difference measurement noise matrix and the difference measurement noise matrix to obtain a fifth product matrix; and a division module, configured to divide the fifth product matrix by 2×R×R to obtain the uncertainty matrix.

[0017] Optionally, the third determination unit includes: a sixth determination module, configured to determine an i-th predicted position matrix according to the i-th estimated position matrix, the i-th measured position matrix, the i-th gain matrix, and a preset measurement transformation matrix.

[0018] Optionally, the sixth determination module is configured to: perform a product operation on the measurement transformation matrix and the i-th estimated position matrix to obtain a sixth product matrix; subtract the sixth product matrix from the i-th measured position matrix to obtain a second difference matrix; perform a product operation on the i-th gain matrix and the second difference matrix to obtain a seventh product matrix; perform an addition operation on the i-th estimated position matrix and the seventh product matrix to obtain the i-th predicted position matrix.

[0019] Optionally, the apparatus further includes: a fifth determination unit configured to, when i is equal to 1, determine the i-th estimated position matrix to be equal to the i-th measured position matrix.

[0020] Optionally, the apparatus further includes: a sixth determination unit configured to, when i is equal to 1, determine the (i - 1)-th state covariance matrix to be a preset state covariance matrix, and determine the (i - 1)-th gain matrix according to the (i - 1)-th state covariance matrix, the uncertainty matrix, and the measurement transformation matrix.

[0021] Optionally, the j-th measured position matrix is a measured position matrix determined according to the j-th measurement parameter among P measurement parameters, and the j-th measurement parameter includes the driving parameter of the reference vehicle output by the second set of measurement devices at the j-th moment.

[0022] According to another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium, in which a computer program is stored, and the computer program is configured to execute the above vehicle position prediction method when running.

[0023] According to another aspect of the embodiments of the present application, there is also provided an electronic device, including a memory and a processor, a computer program is stored in the memory, and the processor is configured to execute the above vehicle position prediction method through the computer program.

[0024] In the embodiments of the present application, the gain matrix used for predicting the vehicle position is determined according to a preset uncertainty matrix, and the uncertainty matrix is used to represent the covariance of the first measurement noise matrix. It can be understood that the difference between the measured position determined according to the driving parameter of the vehicle output by the second set of measurement devices located outside the vehicle and the actual position of the vehicle is considered in the gain matrix. It can be understood that when predicting the position of the vehicle, the noise in the driving parameter of the vehicle output by the second set of measurement devices is considered, achieving the technical effect of improving the accuracy of predicting the vehicle position and solving the technical problem of low accuracy of predicting the vehicle position. Description of the Drawings

[0025] The accompanying drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0026] Figure 1 is a hardware structure diagram of an optional vehicle position prediction method according to an embodiment of the present application;

[0027] Figure 2 is a schematic diagram of an application scenario of an optional vehicle position prediction method according to an embodiment of the present application;

[0028] Figure 3 is a schematic flowchart of an optional vehicle position prediction method according to an embodiment of the present application;

[0029] Figure 4 is a schematic diagram of an optional determination of the i-th state transition matrix according to an embodiment of the present application Figure 1 ;

[0030] Figure 5 is a schematic diagram of an optional determination of the i-th state transition matrix according to an embodiment of the present application Figure 2 ;

[0031] Figure 6 is a schematic diagram of an optional determination of the second measurement noise matrix according to an embodiment of the present application;

[0032] Figure 7 is a schematic diagram of an optional determination of the i-th measurement position matrix according to an embodiment of the present application;

[0033] Figure 8 is a schematic diagram of an optional determination of the i-th state covariance matrix according to an embodiment of the present application;

[0034] Figure 9 is a schematic diagram of an optional determination of the i-th gain matrix according to an embodiment of the present application;

[0035] Figure 10 is a schematic diagram of an optional determination of the uncertainty matrix according to an embodiment of the present application;

[0036] Figure 11 is a schematic diagram of an optional vehicle position prediction method according to an embodiment of the present application;

[0037] Figure 12 is a structural block diagram of an optional vehicle position prediction device according to an embodiment of the present application;

[0038] Figure 13 is a schematic structural diagram of an optional electronic device according to an embodiment of the present application;

[0039] Figure 14 It is a block diagram of the computer system of an optional electronic device according to an embodiment of the present application. Detailed implementation manners

[0040] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0041] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0042] First, some nouns or terms that appear during the description of the embodiments of the present application are applicable to the following explanations:

[0043] Road network data: Road network data abstracts the road conditions in the real world into point-line information and stores it for various map services. It is the data basis for map display and map services.

[0044] User trajectory: The moving path of a user in space. When a user of a map application uses the map for navigation, the map application will periodically and real-time obtain the trajectory point information of the user. This information includes the longitude and latitude of the user's location GPS (Global Positioning System), the direction of the GPS, the speed at the current position, and the timestamp of the current marking position. Some software can also obtain the vehicle information of the current user by connecting to the hardware of the vehicle the user is riding in, such as information about the turn signal, handbrake, foot brake, fuel level, steering wheel, etc. The set composed of all the trajectory points of a user within a period of time is usually called the trajectory of this user. The set of all users' trajectories is called all the trajectory information of this map source.

[0045] Prediction: The process of estimating future events based on historical data and the current state.

[0046] It should be noted that the relevant information (including but not limited to user location information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set up between this system and relevant users or institutions. Before obtaining relevant information, a request for acquisition needs to be sent to the aforementioned users or institutions through the interface, and after receiving the consent information feedback from the aforementioned users or institutions, the relevant information is obtained.

[0047] According to one aspect of the embodiments of the present application, a method for predicting the vehicle position is provided. Optionally, in this embodiment, the above method for predicting the vehicle position can be applied to an environment as Figure 1 shown. Among them, it may include but is not limited to the terminal device 102 and the server 112. In the terminal device 102, it may include but is not limited to the deployment of the measurement device 108. The method for predicting the vehicle position in the embodiments of the present application can be implemented through the following steps.

[0048] Step S102: Obtain the i-th state and the i-th measurement parameter of the target vehicle.

[0049] Step S104: Send the i-th state and the i-th measurement parameter of the target vehicle to the server 112.

[0050] Step S106: Determine the i-th state transition matrix, the i-th estimated position matrix, and determine the i-th measurement position matrix.

[0051] Step S108: Determine the i-th gain matrix.

[0052] Step S110: Determine the i-th predicted position matrix.

[0053] Step S112: Send the i-th predicted position matrix to the terminal device 102.

[0054] As an optional example, in the method for predicting the vehicle position in the embodiments of the present application, some steps (such as steps S106 to S108 and step S112 in the above steps) may be executed by the server 112, and another part of the steps (such as steps S102 and S104 in the above steps) may be executed by the terminal device 102.

[0055] To better understand the vehicle position prediction method in the embodiments of the present application, the vehicle position prediction method in the embodiments of the present application will be explained and described below in conjunction with optional embodiments, which may but are not limited to being applicable to the embodiments of the present application.

[0056] As Figure 2 shown, the target vehicle 202 is traveling on the road. A first set of measuring devices 104 is deployed on the target vehicle 202, and a second set of measuring devices 206 is deployed on the road. In such a case, the vehicle position prediction method in the embodiments of the present application can be implemented but is not limited to through the following steps.

[0057] Step S202: Determine the i-th state transition matrix according to the i-th state parameter of the target vehicle 202. Determine the i-th estimated position matrix according to the i-th state transition matrix and the (i - 1)-th predicted position matrix. Determine the i-th measured position matrix according to the i-th measurement parameter of the target vehicle 202, where the i-th state parameter includes the driving parameters of the target vehicle 202 output by the first set of measuring devices 104 on the target vehicle 202 at the i-th moment, the (i - 1)-th predicted position matrix is used to represent the predicted position of the target vehicle 202 at the (i - 1)-th moment, i is a positive integer greater than or equal to 2, the i-th measurement parameter includes the driving parameters of the target vehicle 202 output by the second set of measuring devices 206 outside the target vehicle 202 at the i-th moment, and the i-th measured position matrix is used to represent the measured position of the target vehicle 202 at the i-th moment.

[0058] Step S204: Determine the i-th gain matrix according to the (i - 1)-th gain matrix and a preset uncertainty matrix, where the uncertainty matrix is used to represent the covariance of the first measurement noise matrix, the first measurement noise matrix is used to represent the mean of P differences, the j-th difference among the P differences is the difference between the measured position of the reference vehicle represented by the j-th measured position matrix among the P measured position matrices and the j-th actual position among the preset P actual positions, the j-th actual position is the actual position of the reference vehicle at the j-th moment among the P moments, P is a positive integer, and j is a positive integer less than or equal to P;

[0059] Step S206: Determine the i-th predicted position matrix according to the i-th estimated position matrix, the i-th measured position matrix, and the i-th gain matrix, where the i-th predicted position matrix is used to represent the predicted position of the target vehicle 202 at the i-th moment.

[0060] Optionally, in this embodiment, the above terminal device 102 may include, but is not limited to, at least one of the following: mobile phone (such as Android mobile phone, iOS mobile phone, etc.), laptop computer, tablet computer, handheld computer, MID (Mobile Internet Devices), PAD, desktop computer, smart TV, etc. The target client may be a video client, instant messaging client, browser client, education client, etc. The above network may include, but is not limited to: wired network, wireless network, where the wired network includes: local area network, metropolitan area network, and wide area network, and the wireless network includes: Bluetooth, WIFI, and other networks that implement wireless communication. The above server may be a single server, or a server cluster composed of multiple servers, or a cloud server. The above is only an example, and this embodiment does not make any limitation thereto.

[0061] As Figure 3 shown, the process of the vehicle position prediction method may include the following steps:

[0062] Step S302, determine the i-th state transition matrix according to the i-th state parameter of the target vehicle, determine the i-th estimated position matrix according to the i-th state transition matrix and the (i - 1)-th predicted position matrix, and determine the i-th measured position matrix according to the i-th measurement parameter of the target vehicle, where the i-th state parameter includes the driving parameters of the target vehicle output by the first set of measurement devices on the target vehicle at the i-th moment, the (i - 1)-th predicted position matrix is used to represent the predicted position of the target vehicle at the (i - 1)-th moment, i is a positive integer greater than or equal to 2, the i-th measurement parameter includes the driving parameters of the target vehicle output by the second set of measurement devices outside the target vehicle at the i-th moment, and the i-th measured position matrix is used to represent the measured position of the target vehicle at the i-th moment.

[0063] The first set of measurement devices on the target vehicle may include, but is not limited to, one or more measurement devices. The first set of measurement devices may include, but is not limited to, sensors and cameras, etc. For example, the sensors may include, but are not limited to, wheel speed sensors, deceleration sensors, and pressure sensors, etc. The driving parameters of the target vehicle measured by each measurement device in the first set of measurement devices may be the same or different. For example, both measurement device 1 and measurement device 2 in the first set of measurement devices are used to measure the speed and heading angle of the target vehicle, or measurement device 1 is used to measure the speed of the target vehicle, and measurement device 2 is used to measure the heading angle of the target vehicle, etc.

[0064] The i-th state parameter can be obtained, but is not limited to, when the target vehicle is in a state of driving or not driving. The i-th state parameter can include, but is not limited to, the driving parameters of the target vehicle output by the first group of measuring devices on the target vehicle at the i-th moment, such as speed, heading angle, and slope angle, etc. The i-th state transfer matrix can be determined, but is not limited to, based on the i-th state parameter. It can be understood that the driving parameters of the target vehicle output by the first group of measuring devices on the target vehicle at the i-th moment at different moments can be, but are not limited to, the same, or different, or partially the same. Then, the state transfer matrices corresponding to different moments can be, but are not limited to, the same or different.

[0065] The i-th estimated position matrix can be determined based on, but is not limited to, the i-th state transfer matrix and the i-1-th predicted position matrix. It can be understood that the i-th estimated position matrix (or called, a priori state estimate) is determined based on the state transfer matrix at the current moment and the predicted position matrix of the target vehicle at the previous moment (or called, a posteriori state estimate).

[0066] The second group of measuring devices located outside the target vehicle may include but is not limited to one or more measuring devices. The second group of measuring devices may include but is not limited to measuring devices used to measure the position of the target vehicle, such as cameras on the road, various sensors in the Sky Eye system, etc.

[0067] The i-th measurement parameter can be obtained, but is not limited to, when the target vehicle is in a state of driving or not driving. The i-th measurement parameter can include, but is not limited to, the driving parameters of the target vehicle output by the second group of measurement devices at the i-th moment, such as the driving speed and driving direction of the target vehicle. At this time, the target vehicle can be, but is not limited to, in a state of driving or not driving. The i-th measurement position matrix is ​​used to represent the measurement position of the target vehicle at the i-th moment. The measurement position can be a two-dimensional position or a three-dimensional position, etc., such as the longitude position and latitude position of the target vehicle, or the position of the target vehicle in geodetic coordinates, etc.

[0068] Step S304, determining the i-th gain matrix according to the i-1-th gain matrix and a preset uncertainty matrix, wherein the uncertainty matrix is ​​used to represent the covariance of the first measurement noise matrix, the first measurement noise matrix is ​​used to represent the mean of P differences, the j-th difference among the P differences is the difference between the measurement position of the reference vehicle represented by the j-th measurement position matrix among the P measurement position matrices and the j-th actual position among the preset P actual positions, the j-th actual position is the actual position of the reference vehicle at the j-th moment among the P moments, P is a positive integer, and j is a positive integer less than or equal to P.

[0069] There may be noise in the output of the second set of measurement devices for the driving parameters of the reference vehicle. Such noise can come from, but is not limited to, the second set of measurement devices and environmental factors. For example, the second set of measurement devices may be damaged or there may be high wind resistance in the environment, etc. Such noise may cause the driving parameters of the reference vehicle output by the second set of measurement devices to be inaccurate.

[0070] To improve the accuracy of the driving parameters of the reference vehicle output by the second set of measurement devices, the driving parameters of the reference vehicle output by the second set of measurement devices can be corrected, but are not limited to this. The reference vehicle can include, but is not limited to, the target vehicle, or a vehicle different from the target vehicle, etc.

[0071] The preset uncertainty matrix can be used to represent, but is not limited to, the covariance of the first measurement noise matrix. The first measurement noise matrix is used to represent the mean of P differences. The j-th difference among the P differences is the difference between the measured position of the reference vehicle represented by the j-th measurement position matrix among the P measurement position matrices (for example, two-dimensional position or three-dimensional position, etc., such as the longitude and latitude position of the vehicle, the position of the vehicle in the geodetic coordinate system, etc.) and the j-th actual position among the preset P actual positions (for example, two-dimensional position or three-dimensional position, etc., such as the longitude and latitude position of the vehicle, the position of the vehicle in the geodetic coordinate system, etc.). It can be understood that the first measurement noise matrix can be used to represent, but is not limited to, the noise carried in the driving parameters of the reference vehicle output by the second set of measurement devices.

[0072] The i-th gain matrix can be determined based on, but is not limited to, the (i - 1)-th gain matrix and the preset uncertainty matrix. It can be understood that there is a corresponding gain matrix at different times, that is, the gain matrix is updated in real time, and the gain matrix is obtained based on the uncertainty matrix, which improves the accuracy of the gain matrix by comprehensively considering the noise in the driving parameters of the vehicle output by the second set of measurement devices.

[0073] Step S306: Determine the i-th predicted position matrix according to the i-th estimated position matrix, the i-th measured position matrix, and the i-th gain matrix, where the i-th predicted position matrix is used to represent the predicted position of the target vehicle at the i-th moment.

[0074] To improve the accuracy of the determined predicted position of the target vehicle, the driving parameters output by the first set of measurement devices on the vehicle, the driving parameters output by the second set of measurement devices located outside the vehicle, and the noise in the driving parameters of the reference vehicle output by the second set of measurement devices can be combined to jointly determine the predicted position of the target vehicle, but are not limited to this.

[0075] For example, but not limited to, the i-th predicted position matrix can be determined based on the i-th estimated position matrix, the i-th measured position matrix, and the i-th gain matrix. In this way, by comprehensively considering the driving parameters of the vehicle output by the second set of measurement devices, the accuracy of the predicted position of the target vehicle is improved.

[0076] In the above manner, the gain matrix used for predicting the vehicle position is determined based on a preset uncertainty matrix, and the uncertainty matrix is used to represent the covariance of the first measurement noise matrix. It can be understood that the difference between the measured position determined according to the driving parameters of the vehicle output by the second set of measurement devices located outside the vehicle and the actual position of the vehicle is considered in the gain matrix. It can be understood that when predicting the position of the vehicle, the noise in the driving parameters of the vehicle output by the second set of measurement devices is considered, achieving the technical effect of improving the accuracy of predicting the vehicle position and solving the technical problem of low accuracy in predicting the vehicle position.

[0077] As an alternative solution, but not limited to, the i-th state transition matrix can be determined based on the i-th state parameter of the target vehicle in the following manner:

[0078] S11. When the i-th state parameter includes N driving parameters, M position change parameters are determined based on the N driving parameters, where the N driving parameters include the driving parameters of the target vehicle output by each of the N measurement devices at the i-th moment, the first set of measurement devices includes the N measurement devices, N is a positive integer greater than or equal to 2, and the M position change parameters are used to represent the position change amount of the target vehicle at the i-th moment, and M is a positive integer greater than or equal to 2.

[0079] S12. The i-th state transition matrix is determined to include the M position change parameters.

[0080] Estimating the M position change parameters can be used, but not limited to, to represent the position change amount between the position of the target vehicle at the i-th moment and the position of the target vehicle at the i - 1-th moment. For example, the difference between the position of the target vehicle at the i-th moment and the position of the target vehicle at the i - 1-th moment. Optionally, the position of the target vehicle at the i-th moment can be determined, but not limited to, based on the N driving parameters and the position of the target vehicle at the i - 1-th moment.

[0081] For example, the position coordinates of the target vehicle at the (i - 1)-th moment are (0, 0), and the i-th state parameter may but is not limited to include the speed of the target vehicle (e.g., v = 1 m / s) and the heading angle (θ = 45°). Then, the time interval between the i-th moment and the (i - 1)-th moment is 1 s, and the position of the target vehicle at the i-th moment may but is not limited to be (1, 1).

[0082] The state transition matrix may but is not limited to be a matrix used to describe the dynamic evolution process of the user's trajectory. For example, the position data of a user at the i-th moment is It can be understood that the i-th state parameter is:[[]]END] Among them, the first row and the second row in the i-th state parameter respectively represent the driving parameters of the target vehicle collected by two measuring devices in the first group of measuring devices. The user's trajectory can be predicted by the state transition matrix, for example, the state transition matrix Then, the prediction result is:[[]]END]

[0083] In this way, by using the data collected by the first group of measuring devices on the target vehicle, the corresponding state transition matrix at different moments is determined in real time, improving the real-time performance of the state transition matrix.[[]]END]

[0084] As an alternative solution, the above method further includes:[[]]END]

[0085] S21. Determining M position change parameters according to the N driving parameters includes: when the N driving parameters include the speed of the target vehicle and the heading angle of the target vehicle, determining the first position change parameter to be equal to the product of the sine value of the heading angle and the speed, and determining the second position change parameter to be equal to the product of the cosine value of the heading angle and the speed, where the M position change parameters include the first position change parameter and the second position change parameter.[[]]END]

[0086] S22. Determining the i-th state transition matrix to include the M position change parameters includes: setting the i-th state transition matrix as a diagonal matrix with a dimension of 2×2, where the first position change parameter and the second position change parameter are included on the diagonal of the diagonal matrix.[[]]END]

[0087] Optionally, in this embodiment, it is also possible but not limited to determine M position change parameters according to N driving parameters in the following manner: when the N driving parameters include the speed of the target vehicle, the heading angle of the target vehicle, and the slope angle of the road where the target vehicle is located, determine the third position change parameter to be equal to the product of the sine value of the heading angle, the cosine value of the slope angle, and the speed, and determine the fourth position change parameter to be equal to the product of the cosine value of the heading angle, the cosine value of the slope angle, and the speed, where the M position change parameters include the third position change parameter and the fourth position change parameter; the step of determining the i-th state transition matrix to include the M position change parameters includes: setting the i-th state transition matrix as a diagonal matrix with a dimension of 2×2, where the third position change parameter and the fourth position change parameter are included on the diagonal of the diagonal matrix.

[0088] To better understand the process of determining the i-th state transition matrix in the embodiments of the present application, the process of determining the i-th state transition matrix in the embodiments of the present application will be explained and described below in conjunction with optional embodiments.

[0089] As shown in Figure 4 For example, it is possible but not limited to take the first set of measurement devices 104 including measurement devices 104-1, 104-2, and 104-3 as an example, where measurement device 104-1 is used to measure the heading angle θ of the target vehicle, measurement device 104-2 is used to measure the speed v of the target vehicle, and measurement device 104-3 is used to measure the speed φ of the road surface on which the target vehicle is traveling. In such a case, it is possible but not limited to determine the i-th state transition matrix A i as where v*sin θ*cosφ and v*cos θ*cosφ are position change parameters.

[0090] As shown in Figure 5 For example, it is possible but not limited to take the first set of measurement devices 104 including measurement devices 104-1 and 104-23 as an example, where measurement device 104-1 is used to measure the heading angle θ of the target vehicle, and measurement device 104-2 is used to measure the speed v of the target vehicle. In such a case, it is possible but not limited to determine the i-th state transition matrix A i as where v*sin θ and v*cos θ are position change parameters.

[0091] As an optional solution, it is possible but not limited to determine the i-th estimated position matrix according to the i-th state transition matrix and the (i-1)-th predicted position matrix in the following manner:

[0092] S31. Perform a multiplication operation on the i-th state transition matrix and the (i - 1)-th predicted position matrix to obtain a first product matrix.

[0093] S32. Perform an addition operation on the first product matrix and a preset second measurement noise matrix to obtain the i-th estimated position matrix, where the second measurement noise matrix is used to represent the difference between Q actual positions obtained in advance and the reference position. The k-th actual position among the Q actual positions is the actual position reached by the target vehicle when starting from the starting actual position and driving for a preset duration according to the reference state parameters for the k-th time. The reference position is the estimated position of the target vehicle represented by the reference estimated position matrix. The reference estimated position matrix is an estimated position matrix determined according to the reference state transition matrix and a pre-determined starting position matrix. The starting position matrix is used to represent the starting actual position of the target vehicle. The reference state transition matrix is a state transition matrix determined according to the reference state parameters. The reference state parameters include the driving parameters of the target vehicle output by the first group of measurement devices at the reference time. The starting actual position is the position of the target vehicle at the reference time. Q is a positive integer, and k is a positive integer greater than or equal to 1 and less than or equal to Q.

[0094] Optionally, in this embodiment, the reference estimated position matrix can be obtained, but is not limited to, by the following method: perform a multiplication operation on the reference state transition matrix and a pre-determined starting position matrix to obtain the reference estimated position matrix.

[0095] Optionally, the second measurement noise matrix can be obtained, but is not limited to, by the following method: when the difference between the Q actual positions and the reference position includes Q differences and the second measurement noise matrix includes S×S data, each of the S×S data is determined as the mean of the Q differences, or the standard deviation of the Q differences, or the variance of the Q differences, etc.

[0096] Optionally, the second measurement noise matrix can be obtained in the following ways, but not limited to: determining each data in the second measurement noise matrix as the radius of a target circle, or a set of major and minor radii of a target ellipse. The target circle or the target ellipse has the reference position as the center point, and the target circle or the target ellipse includes Q actual positions. The k-th actual position among the Q actual positions is the actual position that the target vehicle reaches after traveling for a preset duration from the starting actual position for the k-th time according to the reference state parameters. The reference position is the estimated position of the target vehicle represented by the reference estimated position matrix. The reference estimated position matrix is an estimated position matrix determined according to the reference state transition matrix and a pre-determined starting position matrix. The starting position matrix is used to represent the starting actual position of the target vehicle. The reference state transition matrix is a state transition matrix determined according to the reference state parameters. The reference state parameters include the driving parameters of the target vehicle output by the first set of measuring devices at the reference moment. The starting actual position is the position where the target vehicle is located at the reference moment. Q is a positive integer, and k is a positive integer greater than or equal to 1 and less than or equal to Q.

[0097] There may be noise in the driving parameters of the target vehicle output by the first set of measuring devices on the target vehicle. These noises can come from, but are not limited to, the first set of measuring devices and environmental factors. For example, the first set of measuring devices may be damaged or the wind resistance in the environment is large, etc. These noises may cause the driving parameters of the target vehicle output by the first set of measuring devices to be inaccurate.

[0098] To improve the accuracy of the driving parameters of the target vehicle output by the first set of measuring devices, the driving parameters output by the first set of measuring devices on the target vehicle can be corrected, for example Figure 6 As shown, the second measurement noise matrix is used to represent the difference between the pre-acquired Q actual positions (for example, actual position 1 to actual position 6) and the reference position. The k-th actual position among the Q actual positions is the actual position that the target vehicle reaches after traveling for a preset duration (for example, 1 s) from the starting actual position for the k-th time according to the reference state parameters (for example, speed is 1 m / s, heading angle is 45°). The reference position is the estimated position of the target vehicle represented by the reference estimated position matrix. The reference estimated position matrix is an estimated position matrix determined according to the reference state transition matrix and a pre-determined starting position matrix. The starting position matrix is used to represent the starting actual position of the target vehicle. The reference state transition matrix is a state transition matrix determined according to the reference state parameters. The reference state parameters include the driving parameters of the target vehicle output by the first set of measuring devices at the reference moment (for example, speed and heading angle, etc.). The starting actual position is the position where the target vehicle is located at the reference moment.

[0099] In such a case, it is possible but not limited to fit a circle including the actual positions 1 to 6 with the reference position as the center of the circle, and determine the radius r of the circle as the average value of the differences between the Q actual positions (for example, the actual positions 1 to the actual position 6) and the reference position.

[0100] It should be noted that in the embodiments of the present application, there is no limitation on the figure formed by fitting the reference position and the Q actual positions. For example, the reference position and the Q actual positions can also be fitted into an ellipse, and the major radius and minor radius corresponding to the ellipse are determined as the data included in the second measurement noise matrix. The reference position and the Q actual positions can also be fitted into a sector, and the radius of the sector is determined as the data included in the second measurement noise matrix, and so on.

[0101] In this way, it is achieved to determine the second measurement noise matrix corresponding to the target vehicle through the differences between the pre-acquired Q actual positions and the reference position. It can be understood that the accuracy of the second measurement noise matrix is improved.

[0102] Optionally, in the embodiments of the present application, the i-th estimated position matrix can be determined by the following formula (1) but not limited to this:

[0103]

[0104] Wherein, is the i-th estimated position matrix, A i is the i-th state transition matrix, is the (i - 1)-th predicted position matrix, and W is the preset second measurement noise matrix.

[0105] As an optional solution, the i-th measurement position matrix can be determined by the following method but not limited to this according to the i-th measurement parameter of the target vehicle:

[0106] S41. When the driving parameters included in the i-th measurement parameter form the i-th measurement matrix, perform a product operation on the preset measurement conversion matrix and the i-th measurement matrix to obtain a second product matrix, where the second product matrix is used to represent the initial measurement position of the target vehicle at the i-th moment, and the measurement conversion matrix is an identity matrix.

[0107] S42. Determine the i-th measurement position matrix to be equal to the matrix obtained by performing an addition operation on the second product matrix and the first measurement noise matrix.

[0108] Optionally, in various embodiments of the present application, the measurement conversion matrix is used to convert the i-th measurement parameter into the i-th initial measurement position matrix, and the i-th initial measurement position matrix is used to represent the initial measurement position of the target vehicle at the i-th moment. The dimension of the measurement conversion matrix can be set according to actual needs, but is not limited thereto. The present application does not limit this. For example, the measurement conversion matrix can be a 3×3 identity matrix, or a 2×2 identity matrix, etc.

[0109] Optionally, in various embodiments of the present application, the i-th measurement position matrix can be determined by, but is not limited to, the following formula (2):

[0110]

[0111] wherein, \(Z_i\) is the i-th measurement position matrix, \(H\) is the measurement conversion matrix, is the i-th measurement matrix, and \(V\) is the first measurement noise matrix.

[0112] As Figure 7 shown, the preset measurement conversion matrix can be, but is not limited to, The i-th measurement matrix can be, but is not limited to, The first measurement noise matrix can be, but is not limited to, Perform a multiplication operation on the measurement conversion matrix and the i-th measurement matrix to obtain a second product matrix as Determine the i-th measurement position matrix to be equal to the matrix obtained by performing an addition operation on the second product matrix and the first measurement noise matrix. For example, the i-th measurement position matrix is:

[0113] In this way, when determining the measurement position of the target vehicle, the noise in the driving parameters of the target vehicle output by the second set of measurement devices located outside the vehicle is considered, improving the accuracy of determining the measurement position of the target vehicle.

[0114] As an alternative solution, the i-th gain matrix can be determined by, but is not limited to, the following method according to the (i - 1)-th gain matrix and the preset uncertainty matrix: Determine the i-th state covariance matrix according to the (i - 1)-th gain matrix, the (i - 1)-th state covariance matrix, and the preset measurement conversion matrix; Determine the i-th gain matrix according to the i-th state covariance matrix, the uncertainty matrix, and the measurement conversion matrix.

[0115] Optionally, in various embodiments of the present application, the i-th state covariance matrix may be determined, but not limited to, based on the (i-1)-th gain matrix, the (i-1)-th state covariance matrix, and a preset measurement transformation matrix. It can be understood that there is a corresponding state covariance matrix at each moment, which improves the real-time performance of the state covariance matrix.

[0116] Optionally, in various embodiments of the present application, the i-th gain matrix may be determined, but not limited to, based on the i-th state covariance matrix, the uncertainty matrix, and the measurement transformation matrix. It can be understood that there is a corresponding gain matrix at each moment, which improves the real-time performance of the gain matrix.

[0117] As an optional solution, the i-th state covariance matrix may be determined, but not limited to, by the following method based on the (i-1)-th gain matrix, the (i-1)-th state covariance matrix, and a preset measurement transformation matrix:

[0118] S61, perform a multiplication operation on the (i-1)-th gain matrix and the measurement transformation matrix to obtain a third product matrix.

[0119] S62, subtract the third product matrix from the preset identity matrix to obtain a first difference matrix.

[0120] S63, perform a multiplication operation on the transpose of the first difference matrix, the (i-1)-th state covariance matrix, and the first difference matrix to obtain the i-th state covariance matrix.

[0121] Optionally, in various embodiments of the present application, the i-th state covariance matrix may be determined, but not limited to, by the following formula (3):

[0122] P i =(I-k i-1 *H) T *P i-1 *(I-k i-1 *H) (3)

[0123] where P i is the i-th state covariance matrix, I is the preset identity matrix, k i-1 is the (i-1)-th gain matrix, H is the measurement transformation matrix, and T represents the transpose.

[0124] To better understand the process of determining the i-th state covariance matrix in the embodiments of the present application, the method for determining the i-th state covariance matrix in the embodiments of the present application will be explained and described below in conjunction with optional embodiments, which may be applicable, but not limited to, the embodiments of the present application.

[0125] Such as Figure 8As shown, the (i - 1)-th gain matrix can be, but is not limited to, The measurement conversion matrix can be, but is not limited to, Then, perform a multiplication operation on the (i - 1)-th gain matrix and the measurement conversion matrix to obtain a third product matrix as Subtract the preset identity matrix from the third product matrix to obtain a first difference matrix

[0126] Perform a multiplication operation on the transpose of the first difference matrix, the (i - 1)-th state covariance matrix, and the first difference matrix to obtain the i-th state covariance matrix as

[0127] In this way, the corresponding state covariance matrix at each moment is updated, improving the real-time performance of the state covariance matrix.

[0128] As an optional solution, the i-th gain matrix can be determined, but is not limited to, by the following method:

[0129] S71: Perform a multiplication operation on the transpose of the measurement conversion matrix, the i-th state covariance matrix, and the measurement conversion matrix to obtain a fourth product matrix.

[0130] S72: Perform an addition operation on the fourth product matrix and the uncertainty matrix to obtain a first sum matrix.

[0131] S73: Perform a multiplication operation on the fourth product matrix and the transpose of the first sum matrix to obtain the i-th gain matrix.

[0132] Optionally, in each embodiment of the present application, the i-th gain matrix can be determined, but is not limited to, by the following formula (4):

[0133]

[0134] where k i is the i-th gain matrix, H is the measurement conversion matrix, P i is the i-th state covariance matrix, R is the uncertainty matrix, and T represents the transpose.

[0135] To better understand the process of determining the i-th gain matrix in the embodiments of the present application, the following optionally combines embodiments to explain and illustrate the method for determining the i-th gain matrix in the embodiments of the present application, which can be, but is not limited to, applicable to the embodiments of the present application.

[0136] As Figure 9 shown, the measurement conversion matrix can be, but is not limited to, The i-th state covariance matrix can be, but is not limited to, In such a case, a product operation is performed on the transpose of the measurement transformation matrix, the i-th state covariance matrix, and the measurement transformation matrix to obtain a fourth product matrix. For the fourth product matrix and the uncertainty matrix An addition operation is performed to obtain a first sum matrix. A product operation is performed on the transpose of the fourth product matrix and the first sum matrix to obtain the i-th gain matrix.

[0137] In this way, the corresponding gain matrix is calculated according to the state covariance matrix corresponding to each moment, improving the real-time performance of the gain matrix.

[0138] As an alternative solution, the above method further includes:

[0139] S81. When the first measurement noise matrix includes R×R noise values, an averaging operation is performed on the R×R noise values to obtain a noise mean.

[0140] S82. Determine the uncertainty matrix according to the noise mean and the R×R noise values.

[0141] Optionally, in various embodiments of the present application, the first measurement noise matrix may but is not limited to include R×R noise values, and each of the R×R noise values may but is not limited to be the same or different.

[0142] Optionally, in various embodiments of the present application, each of the noise values in the first measurement noise matrix may but is not limited to represent the noise carried in the measurement position determined according to the driving parameters of the vehicle output by the second set of sensors located outside the vehicle.

[0143] As an alternative solution, the uncertainty matrix may but is not limited to be determined according to the noise mean and the R×R noise values in the following manner:

[0144] S91. Subtract the noise mean from each of the R×R noise values in the first measurement noise matrix to obtain a difference measurement noise matrix.

[0145] S92. Perform a product operation on the transpose of the difference measurement noise matrix and the difference measurement noise matrix to obtain a fifth product matrix.

[0146] S93. Divide the fifth product matrix by 2×R×R to obtain the uncertainty matrix.

[0147] Optionally, in various embodiments of the present application, the uncertainty matrix may but is not limited to be determined by the following formula (5):

[0148]

[0149] Wherein, R is an uncertainty matrix, V is a first measurement noise matrix, E(V) is the noise mean, n is equal to 2×R×R, and T represents the transpose.

[0150] As Figure 10 shown, the first measurement noise matrix can be but is not limited to

[0151] Perform a mean operation on the R×R noise values to obtain a noise mean of 0.29775. Subtract the noise mean from each noise data in the R×R noise values in the first measurement noise matrix to obtain a difference measurement noise matrix Perform a product operation on the transpose of the difference measurement noise matrix and the difference measurement noise matrix to obtain a fifth product matrix. Divide the fifth product matrix by 2×R×R (for example, 8) to obtain the uncertainty matrix

[0152] As an alternative solution, the i-th predicted position matrix can be but is not limited to be determined according to the i-th estimated position matrix, the i-th measured position matrix, and the i-th gain matrix in the following manner:

[0153] S101. Determine the i-th predicted position matrix according to the i-th estimated position matrix, the i-th measured position matrix, the i-th gain matrix, and a preset measurement conversion matrix.

[0154] Optionally, in each embodiment of the present application, the i-th predicted position matrix can be but is not limited to be determined according to the i-th estimated position matrix, the i-th measured position matrix, the i-th gain matrix, and a preset measurement conversion matrix. In this way, the trajectory of the user is predicted through a linear system model and observation data, taking into account uncertainty and noise, and improving the accuracy of the determined predicted position matrix.

[0155] As an alternative solution, the i-th predicted position matrix can be but is not limited to be determined according to the i-th estimated position matrix, the i-th measured position matrix, the i-th gain matrix, and a preset measurement conversion matrix in the following manner:

[0156] S111. Perform a product operation on the measurement conversion matrix and the i-th estimated position matrix to obtain a sixth product matrix.

[0157] S112. Subtract the sixth product matrix from the i-th measured position matrix to obtain a second difference matrix.

[0158] S113. Perform a multiplication operation on the i-th gain matrix and the second difference matrix to obtain a seventh product matrix.

[0159] S114. Perform an addition operation on the i-th estimated position matrix and the seventh product matrix to obtain the i-th predicted position matrix.

[0160] Optionally, in various embodiments of the present application, the i-th predicted position matrix can be determined by, but not limited to, the following formula (6):

[0161]

[0162] where, is the i-th predicted position matrix, is the i-th estimated position matrix, zi is the i-th measured position matrix, and H is the measurement conversion matrix.

[0163] In this way, the user's historical position information and real-time position observation data are effectively combined, improving the prediction accuracy of the vehicle position. And a covariance matrix is introduced to describe the uncertainty of the user position data, making the prediction result more credible. By optimizing the state transition matrix A and the observation matrix H, the computational complexity is reduced, making the prediction method highly efficient in practical applications.

[0164] As an alternative solution, the above method further includes:

[0165] S121. When i is equal to 1, determine the i-th estimated position matrix to be equal to the i-th measured position matrix.

[0166] Optionally, in various embodiments of the present application, when i is equal to 1, the (i - 1)-th predicted position matrix does not exist yet. In such a case, the i-th estimated position matrix can be determined to be equal to the i-th measured position matrix by, but not limited to, for example, determining the i-th estimated position matrix as the measured position matrix of the target vehicle at the i-th moment.

[0167] As an alternative solution, the above method further includes:

[0168] When i is equal to 1, determine the (i - 1)-th state covariance matrix as a preset state covariance matrix, and determine the (i - 1)-th gain matrix according to the (i - 1)-th state covariance matrix, the uncertainty matrix, and the measurement conversion matrix.

[0169] Optionally, in various embodiments of the present application, when i equals 1, the (i - 1)-th state covariance matrix (e.g., P0) is determined as a preset state covariance matrix, and then the (i - 1)-th gain matrix (e.g., k0) is calculated and determined according to the above formula (4).

[0170] As an optional solution, the j-th measurement position matrix is a measurement position matrix determined according to the j-th measurement parameter among the P measurement parameters, and the j-th measurement parameter includes the driving parameters of the reference vehicle output by the second set of measurement devices at the j-th moment.

[0171] To improve the accuracy of the determined first measurement noise matrix, the measurement position matrix of the reference vehicle can be measured multiple times, and the j-th measurement parameter can be obtained when the reference vehicle is in a driving state or a non-driving state. The j-th measurement parameter can include, but is not limited to, the driving parameters of the reference vehicle output by the second set of measurement devices at the j-th moment, such as the driving speed and driving direction of the reference vehicle. At this time, the reference vehicle can be in a driving state or a non-driving state. The j-th measurement position matrix is used to represent the measurement position of the reference vehicle at the j-th moment, and the measurement position can be a two-dimensional position or a three-dimensional position, etc., such as the longitude and latitude positions of the reference vehicle, or the position of the reference vehicle in the geodetic coordinate system, etc.

[0172] To better understand the process of the vehicle position prediction method in the embodiments of the present application, the vehicle position prediction method in the embodiments of the present application will be explained and described below in conjunction with optional embodiments, which can be applicable to the embodiments of the present application.

[0173] As Figure 11 shown, historical position data can be obtained, for example, by GPS satellites to obtain the measurement position of the vehicle and the trajectory information output by the measurement devices on the terminal device (such as a car machine or a mobile phone, etc.), and this information is sent to the receiving server to use these data to train the current linear system prediction model.

[0174] For example, initialization is performed first. The linear system prediction model is initialized, which can include, but is not limited to, the initial state and the state transition matrix. Among them, the initial state is usually estimated using historical data, and the state transition matrix describes the change of position over time.

[0175] Then prediction is performed: the linear system prediction model is used to predict the future position of the user. During the prediction process, the linear system prediction model will consider the uncertainty and noise in the historical data and combine the state transition matrix to obtain the predicted value of the future position.

[0176] In addition, updates will be performed to update the state of the linear system prediction model using the current state and the state transition matrix. During the update process, the linear system prediction model combines the predicted value and the current observation value to update the state, so as to improve the accuracy of the prediction. The linear system prediction model continuously optimizes the state estimation during each iteration, thereby improving the accuracy of the prediction result.

[0177] Use the trained linear system prediction model to predict the future position of the vehicle. The prediction result can be output to an application program, for example, for advertising placement, traffic management, and big data mining production, etc. By the vehicle position prediction method in the embodiments of the present application, the influence of uncertainty and noise can be considered, thereby providing a more accurate prediction result. By improving the accuracy of the prediction, the effect of related services and the user experience can be improved.

[0178] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0179] According to another aspect of the embodiments of the present application, there is also provided an apparatus for implementing the above vehicle position prediction method. As Figure 12 shown, the apparatus includes:

[0180] A first determination unit 1202, configured to determine the i-th state transition matrix according to the i-th state parameter of the target vehicle, determine the i-th estimated position matrix according to the i-th state transition matrix and the (i - 1)-th predicted position matrix, and determine the i-th measured position matrix according to the i-th measurement parameter of the target vehicle, where the i-th state parameter includes the driving parameters of the target vehicle output by the first set of measurement devices on the target vehicle at the i-th moment, the (i - 1)-th predicted position matrix is used to represent the predicted position of the target vehicle at the (i - 1)-th moment, i is a positive integer greater than or equal to 2, the i-th measurement parameter includes the driving parameters of the target vehicle output by the second set of measurement devices located outside the target vehicle at the i-th moment, and the i-th measured position matrix is used to represent the measured position of the target vehicle at the i-th moment;

[0181] A second determination unit 1204, configured to determine an i-th gain matrix according to an (i-1)-th gain matrix and a preset uncertainty matrix, where the uncertainty matrix is used to represent the covariance of a first measurement noise matrix, the first measurement noise matrix is used to represent the mean of P differences, and the j-th difference among the P differences is the difference between the measured position of a reference vehicle represented by the j-th measurement position matrix among P measurement position matrices and the j-th actual position among P preset actual positions, and the j-th actual position is the actual position of the reference vehicle at the j-th moment among P moments, P is a positive integer, and j is a positive integer less than or equal to P;

[0182] A third determination unit 1206, configured to determine an i-th predicted position matrix according to the i-th estimated position matrix, the i-th measured position matrix, and the i-th gain matrix, where the i-th predicted position matrix is used to represent the predicted position of the target vehicle at the i-th moment.

[0183] Through the embodiments provided in this application, the gain matrix used for predicting the vehicle position is determined according to a preset uncertainty matrix, and the uncertainty matrix is used to represent the covariance of the first measurement noise matrix. It can be understood that the difference between the measured position determined according to the driving parameters of the vehicle output by the second set of measurement devices located outside the vehicle and the actual position of the vehicle is considered in the gain matrix. It can be understood that the noise in the driving parameters of the vehicle output by the second set of measurement devices is considered when predicting the position of the vehicle, achieving the technical effect of improving the accuracy of predicting the vehicle position and solving the technical problem of low accuracy of predicting the vehicle position.

[0184] As an optional solution, the first determination unit includes:

[0185] A first determination module, configured to determine M position change parameters according to the N driving parameters when the i-th state parameter includes N driving parameters, where the N driving parameters include the driving parameters of the target vehicle output by each of N measurement devices at the i-th moment, the first set of measurement devices includes the N measurement devices, N is a positive integer greater than or equal to 2, and the M position change parameters are used to represent the position change amount of the target vehicle at the i-th moment, and M is a positive integer greater than or equal to 2;

[0186] A second determination module, configured to determine the i-th state transition matrix as including the M position change parameters.

[0187] As an alternative, the first determination module is configured to: when the N driving parameters include the speed of the target vehicle and the heading angle of the target vehicle, determine the first position change parameter to be equal to the product of the sine value of the heading angle and the speed, and determine the second position change parameter to be equal to the product of the cosine value of the heading angle and the speed, where the M position change parameters include the first position change parameter and the second position change parameter;

[0188] The second determination module is configured to: set the i-th state transition matrix as a 2×2 diagonal matrix, where the diagonal of the diagonal matrix includes the first position change parameter and the second position change parameter.

[0189] As an alternative, the first determination unit includes:

[0190] A first execution module, configured to perform a multiplication operation on the i-th state transition matrix and the (i - 1)-th predicted position matrix to obtain a first product matrix;

[0191] A second execution module, configured to perform an addition operation on the first product matrix and a preset second measurement noise matrix to obtain the i-th estimated position matrix, where the second measurement noise matrix is used to represent the difference between Q actual positions obtained in advance and the reference position. The k-th actual position among the Q actual positions is the actual position reached by the target vehicle when starting from the starting actual position and driving for a preset duration according to the reference state parameters for the k-th time. The reference position is the estimated position of the target vehicle represented by the reference estimated position matrix. The reference estimated position matrix is an estimated position matrix determined according to the reference state transition matrix and a pre-determined starting position matrix. The starting position matrix is used to represent the starting actual position of the target vehicle. The reference state transition matrix is a state transition matrix determined according to the reference state parameters. The reference state parameters include the driving parameters of the target vehicle output by the first set of measurement devices at the reference time. The starting actual position is the position of the target vehicle at the reference time. Q is a positive integer, and k is a positive integer greater than or equal to 1 and less than or equal to Q.

[0192] As an alternative, the first determination unit includes:

[0193] A third execution module, configured to perform a multiplication operation on a preset measurement conversion matrix and the i-th measurement matrix when the driving parameters included in the i-th measurement parameter form the i-th measurement matrix, to obtain a second product matrix, where the second product matrix is used to represent the initial measurement position of the target vehicle at the i-th moment, and the measurement conversion matrix is an identity matrix;

[0194] A third determination module, configured to determine the i-th measurement position matrix to be equal to a matrix obtained by performing an addition operation on the second product matrix and the first measurement noise matrix.

[0195] As an alternative solution, the second determination unit includes:

[0196] A fourth determination module, configured to determine the i-th state covariance matrix according to the (i - 1)-th gain matrix, the (i - 1)-th state covariance matrix, and a preset measurement transformation matrix;

[0197] A fifth determination module, configured to determine the i-th gain matrix according to the i-th state covariance matrix, the uncertainty matrix, and the measurement transformation matrix.

[0198] As an alternative solution, the fourth determination module is configured to:

[0199] Perform a product operation on the (i - 1)-th gain matrix and the measurement transformation matrix to obtain a third product matrix;

[0200] Subtract the third product matrix from a preset identity matrix to obtain a first difference matrix;

[0201] Perform a product operation on the transpose of the first difference matrix, the (i - 1)-th state covariance matrix, and the first difference matrix to obtain the i-th state covariance matrix.

[0202] As an alternative solution, the fifth determination module is configured to:

[0203] Perform a product operation on the transpose of the measurement transformation matrix, the i-th state covariance matrix, and the measurement transformation matrix to obtain a fourth product matrix;

[0204] Perform an addition operation on the fourth product matrix and the uncertainty matrix to obtain a first sum matrix;

[0205] Perform a product operation on the fourth product matrix and the transpose of the first sum matrix to obtain the i-th gain matrix.

[0206] As an alternative solution, the apparatus further includes:

[0207] An execution unit, configured to perform a mean operation on the R×R noise values when the first measurement noise matrix includes R×R noise values to obtain a noise mean;

[0208] A fourth determination unit, configured to determine the uncertainty matrix according to the noise mean and the R×R noise values.

[0209] As an alternative, the fourth determination unit includes:

[0210] A subtraction module, configured to subtract each noise data in the R×R noise values in the first measurement noise matrix from the noise mean value to obtain a difference measurement noise matrix;

[0211] A fourth execution module, configured to perform a multiplication operation on the transpose of the difference measurement noise matrix and the difference measurement noise matrix to obtain a fifth product matrix;

[0212] A division module, configured to divide the fifth product matrix by 2×R×R to obtain the uncertainty matrix.

[0213] As an alternative, the third determination unit includes:

[0214] A sixth determination module, configured to determine the i-th predicted position matrix according to the i-th estimated position matrix, the i-th measured position matrix, the i-th gain matrix, and a preset measurement conversion matrix.

[0215] As an alternative, the sixth determination module is configured to:

[0216] Perform a multiplication operation on the measurement conversion matrix and the i-th estimated position matrix to obtain a sixth product matrix;

[0217] Subtract the sixth product matrix from the i-th measured position matrix to obtain a second difference matrix;

[0218] Perform a multiplication operation on the i-th gain matrix and the second difference matrix to obtain a seventh product matrix;

[0219] Perform an addition operation on the i-th estimated position matrix and the seventh product matrix to obtain the i-th predicted position matrix.

[0220] As an alternative, the device further includes:

[0221] A fifth determination unit, configured to, when i is equal to 1, determine the i-th estimated position matrix to be equal to the i-th measured position matrix.

[0222] As an alternative, the device further includes:

[0223] A sixth determination unit, configured to, when i is equal to 1, determine the (i - 1)-th state covariance matrix to be a preset state covariance matrix, and determine the (i - 1)-th gain matrix according to the (i - 1)-th state covariance matrix, the uncertainty matrix, and the measurement conversion matrix.

[0224] As an alternative, the j-th measurement position matrix is a measurement position matrix determined according to the j-th measurement parameter among the P measurement parameters, and the j-th measurement parameter includes the driving parameters of the reference vehicle output by the second set of measurement devices at the j-th moment.

[0225] According to another aspect of the embodiments of the present invention, there is also provided an electronic device for implementing the above vehicle position prediction method. The electronic device may be Figure 1 the terminal device or server shown. This embodiment takes the electronic device as a server as an example for illustration. As Figure 13 shown, the electronic device includes a memory 1302 and a processor 1304. A computer program is stored in the memory 1302, and the processor 1304 is configured to execute the steps in any one of the above method embodiments through the computer program.

[0226] Optionally, in this embodiment, the above electronic device may be at least one of multiple network devices in a computer network.

[0227] Optionally, in this embodiment, the above processor may be configured to execute the following steps through the computer program:

[0228] S1. Determine the i-th state transition matrix according to the i-th state parameter of the target vehicle. Determine the i-th estimated position matrix according to the i-th state transition matrix and the (i - 1)-th predicted position matrix. Determine the i-th measurement position matrix according to the i-th measurement parameter of the target vehicle, where the i-th state parameter includes the driving parameters of the target vehicle output by the first set of measurement devices on the target vehicle at the i-th moment, the (i - 1)-th predicted position matrix is used to represent the predicted position of the target vehicle at the (i - 1)-th moment, i is a positive integer greater than or equal to 2, the i-th measurement parameter includes the driving parameters of the target vehicle output by the second set of measurement devices located outside the target vehicle at the i-th moment, and the i-th measurement position matrix is used to represent the measurement position of the target vehicle at the i-th moment;

[0229] S2. Determine the i-th gain matrix according to the (i - 1)-th gain matrix and a preset uncertainty matrix, where the uncertainty matrix is used to represent the covariance of the first measurement noise matrix, the first measurement noise matrix is used to represent the mean of P differences, the j-th difference among the P differences is the difference between the measurement position of the reference vehicle represented by the j-th measurement position matrix among the P measurement position matrices and the j-th actual position among the preset P actual positions, the j-th actual position is the actual position of the reference vehicle at the j-th moment among the P moments, P is a positive integer, and j is a positive integer less than or equal to P;

[0230] S3. Determine the i-th predicted position matrix according to the i-th estimated position matrix, the i-th measured position matrix, and the i-th gain matrix, where the i-th predicted position matrix is used to represent the predicted position of the target vehicle at the i-th moment.

[0231] Optionally, those of ordinary skill in the art can understand that Figure 13 The structure shown is only schematic, and the electronic device or electronic equipment can also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, and terminal devices such as Mobile Internet Devices (MID), PAD, etc. Figure 13 It does not limit the structure of the above-mentioned electronic device or electronic equipment. For example, the electronic device or electronic equipment may further include Figure 13 more or fewer components (such as a network interface, etc.) than those shown, or have a different configuration from Figure 13 that shown.

[0232] Among them, the memory 1302 can be used to store software programs and modules, such as the program instructions / modules corresponding to the vehicle position prediction method and device in the embodiments of the present invention. The processor 1304 executes various functional applications and data processing by running the software programs and modules stored in the memory 1302, that is, implements the above-mentioned vehicle position prediction method. The memory 1302 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 1302 may further include a memory remotely disposed relative to the processor 1304, and these remote memories can be connected to the terminal through a network. Examples of the above network include but are not limited to the Internet, an enterprise internal network, a local area network, a mobile communication network, and combinations thereof. Among them, the memory 1302 can specifically but not limitedly be used to store information such as sample features of items and target virtual resource accounts. As an example, as Figure 13 shown, the above memory 1302 may include but is not limited to the first determination unit 1202, the second determination unit 1204, and the third determination unit 1206 in the above vehicle position prediction device. In addition, it may further include but is not limited to other module units in the above vehicle position prediction device, which will not be elaborated in this example.

[0233] Optionally, the above-mentioned transmission device 1306 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wired network and a wireless network. In one example, the transmission device 1306 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers through a network cable, so as to communicate with the Internet or a local area network. In one example, the transmission device 1306 is a Radio Frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0234] In addition, the above-mentioned electronic device further includes: a display 1308, which is used to display the above-mentioned order information to be processed; and a connection bus 1310, which is used to connect each module component in the above-mentioned electronic device.

[0235] In other embodiments, the above-mentioned terminal device or server can be a node in a distributed system. Among them, the distributed system can be a blockchain system, and the blockchain system can be a distributed system formed by connecting the multiple nodes through network communication. Among them, the nodes can form a peer-to-peer network, and any form of computing device, such as electronic devices like servers and terminals, can become a node in the blockchain system by joining the peer-to-peer network.

[0236] Figure 14 A computer system structure block diagram of an electronic device for implementing the embodiments of the present application is schematically shown. It should be noted that Figure 14 The shown computer system 1400 of the electronic device is only an example, and should not bring any limitations to the functions and usage scopes of the embodiments of the present application. As Figure 14 shown, the computer system 1400 includes a central processing unit 1401 (Central Processing Unit, CPU), which can execute various appropriate actions and processes according to the program stored in the read-only memory 1402 (Read-Only Memory, ROM) or the program loaded from the storage part 1408 into the random access memory 1403 (Random Access Memory, RAM). In the random access memory 1403, various programs and data required for system operation are also stored. The central processing unit 1401, the read-only memory 1402, and the random access memory 1403 are connected to each other through a bus 1404. The input / output interface 1405 (Input / Output interface, that is, I / O interface) is also connected to the bus 1404.

[0237] The following components are connected to the input / output interface 1405: an input section 1406 including a keyboard, a mouse, etc.; an output section 1407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1408 including a hard disk, etc.; and a communication section 1409 including a network interface card such as a local area network card, a modem, etc. The communication section 1409 performs communication processing via a network such as the Internet. A drive 1410 is also connected to the input / output interface 1405 as needed. A removable medium 1411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1410 as needed so that a computer program read from it can be installed into the storage section 1408 as needed.

[0238] According to one aspect of the present application, there is provided a computer-readable storage medium, and a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in various alternative implementations in the above embodiments.

[0239] Optionally, in this embodiment, the above computer-readable storage medium may be set to store a computer program for executing the following steps:

[0240] S1, determine the i-th state transition matrix according to the i-th state parameter of the target vehicle, determine the i-th estimated position matrix according to the i-th state transition matrix and the (i - 1)-th predicted position matrix, and determine the i-th measured position matrix according to the i-th measurement parameter of the target vehicle, where the i-th state parameter includes the driving parameters of the target vehicle output by the first set of measurement devices on the target vehicle at the i-th moment, the (i - 1)-th predicted position matrix is used to represent the predicted position of the target vehicle at the (i - 1)-th moment, i is a positive integer greater than or equal to 2, the i-th measurement parameter includes the driving parameters of the target vehicle output by the second set of measurement devices located outside the target vehicle at the i-th moment, and the i-th measured position matrix is used to represent the measured position of the target vehicle at the i-th moment;

[0241] S2. Determine the i-th gain matrix according to the (i - 1)-th gain matrix and a preset uncertainty matrix, where the uncertainty matrix is used to represent the covariance of the first measurement noise matrix, the first measurement noise matrix is used to represent the mean of P differences, the j-th difference among the P differences is the difference between the measured position of the reference vehicle represented by the j-th measurement position matrix among the P measurement position matrices and the j-th actual position among the preset P actual positions, the j-th actual position is the actual position of the reference vehicle at the j-th moment among the P moments, P is a positive integer, and j is a positive integer less than or equal to P;

[0242] S3. Determine the i-th predicted position matrix according to the i-th estimated position matrix, the i-th measured position matrix, and the i-th gain matrix, where the i-th predicted position matrix is used to represent the predicted position of the target vehicle at the i-th moment.

[0243] Optionally, in this embodiment, those of ordinary skill in the art can understand that all or part of the steps in the above various methods can be completed by instructing the relevant hardware of the terminal device through a program, and this program can be stored in a computer-readable storage medium. The storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0244] If the integrated unit in the above embodiments is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in the above computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention.

[0245] In the above embodiments of the present invention, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0246] In several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of units or modules can be in an electrical or other form.

[0247] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0248] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0249] In the embodiments of this application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other related parts to achieve a predetermined goal, and can be fully or partially implemented by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of the overall module or unit that includes the function of that module or unit.

[0250] The above is only the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for predicting the position of a vehicle, characterized in that, Including: Determine the $i$-th state transition matrix according to the $i$-th state parameter of the target vehicle, determine the $i$-th estimated position matrix according to the $i$-th state transition matrix and the $(i - 1)$-th predicted position matrix, and determine the $i$-th measured position matrix according to the $i$-th measurement parameter of the target vehicle. Wherein, the $i$-th state parameter includes the driving parameters of the target vehicle output by the first set of measurement devices on the target vehicle at the $i$-th moment, the $(i - 1)$-th predicted position matrix is used to represent the predicted position of the target vehicle at the $(i - 1)$-th moment, $i$ is a positive integer greater than or equal to 2, the $i$-th measurement parameter includes the driving parameters of the target vehicle output by the second set of measurement devices located outside the target vehicle at the $i$-th moment, and the $i$-th measured position matrix is used to represent the measured position of the target vehicle at the $i$-th moment; Determine the $i$-th gain matrix according to the $(i - 1)$-th gain matrix and a preset uncertainty matrix. Wherein, the uncertainty matrix is used to represent the covariance of the first measurement noise matrix, the first measurement noise matrix is used to represent the mean of $P$ differences, and the $j$-th difference among the $P$ differences is the difference between the measured position of the reference vehicle represented by the $j$-th measured position matrix among the $P$ measured position matrices and the $j$-th actual position among the preset $P$ actual positions. The $j$-th actual position is the actual position of the reference vehicle at the $j$-th moment among the $P$ moments, $P$ is a positive integer, and $j$ is a positive integer less than or equal to $P$; Determine the $i$-th predicted position matrix according to the $i$-th estimated position matrix, the $i$-th measured position matrix and the $i$-th gain matrix. Wherein, the $i$-th predicted position matrix is used to represent the predicted position of the target vehicle at the $i$-th moment.

2. The method according to claim 1, wherein The step of determining the $i$-th state transition matrix according to the $i$-th state parameter of the target vehicle includes: When the $i$-th state parameter includes $N$ driving parameters, determine $M$ position change parameters according to the $N$ driving parameters. Wherein, the $N$ driving parameters include the driving parameters of the target vehicle output by each of the $N$ measurement devices at the $i$-th moment, the first set of measurement devices includes the $N$ measurement devices, $N$ is a positive integer greater than or equal to 2, and the $M$ position change parameters are used to represent the position change amount of the target vehicle at the $i$-th moment, $M$ is a positive integer greater than or equal to 2; Determine the $i$-th state transition matrix to include the $M$ position change parameters.

3. The method according to claim 2, wherein Including: The step of determining $M$ position change parameters according to the $N$ driving parameters includes: when the $N$ driving parameters include the speed of the target vehicle and the heading angle of the target vehicle, determine the first position change parameter to be equal to the product of the sine value of the heading angle and the speed, and determine the second position change parameter to be equal to the product of the cosine value of the heading angle and the speed. Wherein, the $M$ position change parameters include the first position change parameter and the second position change parameter; Determining the i-th state transition matrix to include the M position change parameters includes: setting the i-th state transition matrix as a 2×2 diagonal matrix, where the first position change parameter and the second position change parameter are included on the diagonal of the diagonal matrix.

4. The method according to claim 1, wherein Determining the i-th estimated position matrix according to the i-th state transition matrix and the (i - 1)-th predicted position matrix includes: Performing a product operation on the i-th state transition matrix and the (i - 1)-th predicted position matrix to obtain a first product matrix; Performing a summation operation on the first product matrix and a preset second measurement noise matrix to obtain the i-th estimated position matrix, where the second measurement noise matrix is used to represent the difference between Q actual positions obtained in advance and the reference position. The k-th actual position among the Q actual positions is the actual position reached by the target vehicle when starting from the starting actual position and driving for a preset duration according to the reference state parameters for the k-th time. The reference position is the estimated position of the target vehicle represented by the reference estimated position matrix. The reference estimated position matrix is an estimated position matrix determined according to the reference state transition matrix and a pre-determined starting position matrix. The starting position matrix is used to represent the starting actual position of the target vehicle. The reference state transition matrix is a state transition matrix determined according to the reference state parameters. The reference state parameters include the driving parameters of the target vehicle output by the first group of measurement devices at the reference time. The starting actual position is the position of the target vehicle at the reference time. Q is a positive integer, and k is a positive integer greater than or equal to 1 and less than or equal to Q.

5. The method according to claim 1, wherein Determining the i-th measurement position matrix according to the i-th measurement parameter of the target vehicle includes: When the driving parameters included in the i-th measurement parameter form an i-th measurement matrix, performing a product operation on a preset measurement conversion matrix and the i-th measurement matrix to obtain a second product matrix, where the second product matrix is used to represent the initial measurement position of the target vehicle at the i-th moment, and the measurement conversion matrix is an identity matrix; Determining the i-th measurement position matrix to be equal to the matrix obtained by performing an addition operation on the second product matrix and the first measurement noise matrix.

6. The method according to claim 1, characterized in that, Determining the i-th gain matrix according to the (i - 1)-th gain matrix and a preset uncertainty matrix includes: Determining the i-th state covariance matrix according to the (i - 1)-th gain matrix, the (i - 1)-th state covariance matrix, and a preset measurement conversion matrix; Determining the i-th gain matrix according to the i-th state covariance matrix, the uncertainty matrix, and the measurement conversion matrix.

7. The method according to claim 6, wherein Determining the i-th state covariance matrix according to the (i - 1)-th gain matrix, the (i - 1)-th state covariance matrix, and a preset measurement conversion matrix includes: Performing a product operation on the (i - 1)-th gain matrix and the measurement conversion matrix to obtain a third product matrix; Subtract the preset identity matrix from the third product matrix to obtain a first difference matrix; Perform a product operation on the transpose of the first difference matrix, the (i - 1)-th state covariance matrix, and the first difference matrix to obtain the i-th state covariance matrix.

8. The method according to claim 6, wherein The determining the i-th gain matrix according to the i-th state covariance matrix, the uncertainty matrix, and the measurement transformation matrix includes: Perform a product operation on the transpose of the measurement transformation matrix, the i-th state covariance matrix, and the measurement transformation matrix to obtain a fourth product matrix; Perform an addition operation on the fourth product matrix and the uncertainty matrix to obtain a first sum matrix; Perform a product operation on the fourth product matrix and the transpose of the first sum matrix to obtain the i-th gain matrix.

9. The method according to claim 6, wherein The method further includes: When the first measurement noise matrix includes R×R noise values, perform a mean operation on the R×R noise values to obtain a noise mean; Determine the uncertainty matrix according to the noise mean and the R×R noise values.

10. The method according to claim 9, wherein The determining the uncertainty matrix according to the noise mean and the R×R noise values includes: Subtract the noise mean from each noise data in the R×R noise values in the first measurement noise matrix to obtain a difference measurement noise matrix; Perform a product operation on the transpose of the difference measurement noise matrix and the difference measurement noise matrix to obtain a fifth product matrix; Divide the fifth product matrix by 2×R×R to obtain the uncertainty matrix.

11. The method according to claim 1, wherein The determining the i-th predicted position matrix according to the i-th estimated position matrix, the i-th measured position matrix, and the i-th gain matrix includes: Determine the i-th predicted position matrix according to the i-th estimated position matrix, the i-th measured position matrix, the i-th gain matrix, and a preset measurement transformation matrix.

12. The method according to claim 11, wherein The determining the i-th predicted position matrix according to the i-th estimated position matrix, the i-th measured position matrix, the i-th gain matrix, and a preset measurement transformation matrix includes: Perform a product operation on the measurement transformation matrix and the i-th estimated position matrix to obtain a sixth product matrix; Subtract the sixth product matrix from the i-th measured position matrix to obtain a second difference matrix; Perform a product operation on the i-th gain matrix and the second difference matrix to obtain a seventh product matrix; Perform an addition operation on the i-th estimated position matrix and the seventh product matrix to obtain the i-th predicted position matrix.

13. The method according to claim 1, characterized in that, The method further includes: When i is equal to 1, determine the i-th estimated position matrix to be equal to the i-th measured position matrix.

14. The method according to claim 6, wherein The method further includes: When i is equal to 1, determine the (i - 1)-th state covariance matrix to be a preset state covariance matrix, and determine the (i - 1)-th gain matrix according to the (i - 1)-th state covariance matrix, the uncertainty matrix, and the measurement transformation matrix.

15. The method according to any one of claims 1 to 14, wherein the j-th measurement position matrix is a measurement position matrix determined according to the j-th measurement parameter among P measurement parameters, and the j-th measurement parameter includes the driving parameters of the reference vehicle output by the second set of measurement devices at the j-th moment.

16. A prediction device for vehicle position, characterized in that, comprising: a first determination unit, configured to determine an i-th state transition matrix according to an i-th state parameter of the target vehicle, determine an i-th estimated position matrix according to the i-th state transition matrix and an (i - 1)-th predicted position matrix, and determine an i-th measurement position matrix according to the i-th measurement parameter of the target vehicle, wherein the i-th state parameter includes the driving parameters of the target vehicle output by a first set of measurement devices on the target vehicle at the i-th moment, the (i - 1)-th predicted position matrix is used to represent the predicted position of the target vehicle at the (i - 1)-th moment, i is a positive integer greater than or equal to 2, the i-th measurement parameter includes the driving parameters of the target vehicle output by a second set of measurement devices located outside the target vehicle at the i-th moment, and the i-th measurement position matrix is used to represent the measurement position of the target vehicle at the i-th moment; a second determination unit, configured to determine an i-th gain matrix according to an (i - 1)-th gain matrix and a preset uncertainty matrix, wherein the uncertainty matrix is used to represent the covariance of a first measurement noise matrix, the first measurement noise matrix is used to represent the mean of P differences, the j-th difference among the P differences is the difference between the measurement position of the reference vehicle represented by the j-th measurement position matrix among the P measurement position matrices and the j-th actual position among the preset P actual positions, the j-th actual position is the actual position of the reference vehicle at the j-th moment among the P moments, P is a positive integer, and j is a positive integer less than or equal to P; a third determination unit, configured to determine an i-th predicted position matrix according to the i-th estimated position matrix, the i-th measurement position matrix and the i-th gain matrix, wherein the i-th predicted position matrix is used to represent the predicted position of the target vehicle at the i-th moment.

17. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when running, executes the method according to any one of claims 1 to 15.

18. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 15 through the computer program.

Images