A Vehicle Positioning Method and Device Based on Data Analysis

Abstract

The present application provides a vehicle positioning method and device based on data analysis. The method includes: acquiring GPS positioning data and initializing the position information of the target vehicle according to the GPS positioning data; during the driving process of the vehicle, acquiring the driving trajectory data and driving state information of the target vehicle in real time, and performing dead reckoning based on the driving state information to obtain the relative position change information of the target vehicle; fusing the GPS positioning data and the relative position change information of the target vehicle to obtain fused positioning information; performing prediction processing using an interpolation algorithm based on the fused positioning information and the driving trajectory data to obtain predicted positioning information; and fusing the GPS positioning data and the predicted positioning information to obtain the positioning information of the target vehicle. This solution can improve the positioning accuracy and stability of the vehicle in complex environments.

Description

Technical Field

[0001] The present invention relates to the field of vehicle navigation, and particularly to a vehicle positioning method and device based on data analysis. Background Art

[0002] With the development of technology, vehicle positioning technology plays an increasingly important role in fields such as intelligent transportation and autonomous driving. Two commonly used positioning methods in the prior art include GPS positioning technology and Dead Reckoning (DR) technology.

[0003] Among them, GPS positioning technology uses the principle of satellite triangulation to determine the position by measuring the transmission time of satellite signals. Dead Reckoning (DR) technology deduces the position and attitude of the vehicle at each moment by using inertial navigation sensors. However, both GPS positioning technology and Dead Reckoning technology have certain limitations in complex environments, and there is a problem that the vehicle cannot be accurately and effectively positioned. Summary of the Invention

[0004] In view of the problems mentioned above, the present application is proposed to provide a vehicle positioning method and device based on data analysis that overcomes or at least partially solves the problems, including:

[0005] A vehicle positioning method based on data analysis includes the following steps: obtaining GPS positioning data, and initializing the position information of the target vehicle based on the GPS positioning data. During the driving process of the vehicle, obtaining the driving trajectory data and driving state information of the target vehicle in real time, and performing dead reckoning based on the driving state information to obtain the relative position change information of the target vehicle; the driving state information includes the speed, acceleration, and heading of the target vehicle. Fusing the GPS positioning data and the relative position change information of the target vehicle to obtain fused positioning information. Based on the fused positioning information and the driving trajectory data, using an interpolation algorithm for prediction processing to obtain predicted positioning information. Fusing the GPS positioning data and the predicted positioning information to obtain the positioning information of the target vehicle; wherein, during the fusion processing, the weight of the GPS positioning data will be dynamically adjusted according to the signal strength of the GPS positioning data.

[0006] Further, the fusing of the GPS positioning data and the relative position change information of the target vehicle includes: adopting an extended Kalman filter algorithm, using the GPS positioning data and the relative position change information as common input data, and transforming the state quantities of both into one state quantity for optimal estimation to obtain the fused fused positioning information.

[0007] Further, the data fusion of the GPS positioning data and the relative position change information of the target vehicle includes: based on a predefined objective function, using an iterative algorithm to perform data fusion on the GPS positioning data and the relative position change information of the target vehicle.

[0008] Further, the data fusion of the GPS positioning data and the relative position change information of the target vehicle includes: using the GPS positioning data to initialize the position estimate of the target vehicle. Execute the iterative process until a preset condition is met; wherein, the preset condition is to reach a predetermined number of iterations, and the iterative process includes: at each time step, based on the position estimate and the relative position change information of the previous time step, predict the vehicle position at the current time step; when new GPS positioning data is received, calculate the residual between the new GPS positioning data and the predicted vehicle position at the current time step, and use an iterative algorithm based on this residual to update the covariance matrix and the state vector of the position estimate.

[0009] Further, the prediction processing using the interpolation algorithm based on the fused positioning information and the driving trajectory data to obtain the predicted positioning information includes: based on the fused positioning information, determine the current position information of the target vehicle; extract historical position points from the driving trajectory data to form a historical position sequence, and based on this historical position sequence, establish a prediction model; use the prediction model and the current position information to predict the possible position of the target vehicle at future time steps to obtain the predicted positioning information.

[0010] Further, the prediction processing using the interpolation algorithm based on the fused positioning information and the driving trajectory data to obtain the predicted positioning information includes: based on the driving trajectory data, determine the driving mode or driving trend of the target vehicle; according to the driving mode or driving trend, adjust the parameters of the preset interpolation algorithm; use the adjusted interpolation algorithm to perform prediction processing in combination with the fused positioning information and the driving trajectory data to generate the predicted positioning information.

[0011] Further, the interpolation algorithm includes one or more of Kalman filtering, extended Kalman filtering, or particle filtering.

[0012] A vehicle positioning device based on data analysis, the device comprising: a first acquisition module for acquiring GPS positioning data and initializing the position information of a target vehicle according to the GPS positioning data; a second acquisition module for, during the driving of the vehicle, acquiring in real time the driving trajectory data and driving state information of the target vehicle, and performing dead reckoning based on the driving state information to obtain the relative position change information of the target vehicle; the driving state information including the speed, acceleration and heading of the target vehicle; a first fusion module for performing data fusion on the GPS positioning data and the relative position change information of the target vehicle to obtain fusion positioning information; a prediction module for performing prediction processing using an interpolation algorithm based on the fusion positioning information and the driving trajectory data to obtain predicted positioning information; a second fusion module for performing fusion processing on the GPS positioning data and the predicted positioning information to obtain the positioning information of the target vehicle; wherein, during the fusion processing, the weight of the GPS positioning data is dynamically adjusted according to the signal strength of the GPS positioning data.

[0013] A computer device comprising a processor, a memory, and a computer program stored on the memory and capable of running on the processor, wherein when the computer program is executed by the processor, it implements the vehicle positioning method based on data analysis as described in any one of the above.

[0014] A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the vehicle positioning method based on data analysis as described in any one of the above.

[0015] This application has the following advantages:

[0016] In the embodiments of the present application, compared with the existing GPS positioning technology or dead reckoning technology, there are certain limitations in complex environments, and there is a problem that the vehicle cannot be accurately and effectively positioned. The present application provides a solution to the core invention point, specifically: "Obtain GPS positioning data, and initialize the position information of the target vehicle based on the GPS positioning data. During the driving process of the vehicle, obtain the driving trajectory data and driving state information of the target vehicle in real time, and perform dead reckoning based on the driving state information to obtain the relative position change information of the target vehicle; the driving state information includes the speed, acceleration, and heading of the target vehicle. Perform data fusion on the GPS positioning data and the relative position change information of the target vehicle to obtain fusion positioning information. Based on the fusion positioning information and the driving trajectory data, use the interpolation algorithm to perform prediction processing to obtain predicted positioning information. Perform fusion processing on the GPS positioning data and the predicted positioning information to obtain the positioning information of the target vehicle; wherein, during the fusion processing, the weight of the GPS positioning data will be dynamically adjusted according to the signal strength of the GPS positioning data." First, the relative position change information of the target vehicle is obtained through the driving trajectory data and driving state information during the driving process of the target vehicle, and then the relative position change information and the GPS positioning data are used for data fusion to obtain a relatively accurate, reliable, and estimated fusion positioning information. Then, based on the fusion positioning information, further combine the driving trajectory data and use the interpolation algorithm for prediction processing to eliminate part of the error in the fusion positioning information and obtain a more accurate, reliable, and estimated predicted positioning information. Finally, perform fusion on the GPS positioning data and the predicted positioning information to obtain a positioning information that still maintains a high positioning accuracy when the GPS positioning data is affected. That is, the finally obtained positioning information of the target vehicle is less affected by the environment where the vehicle is located and can still maintain a high positioning accuracy and stability in complex environments or bad weather conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the present application, the accompanying drawings required for the description of the present application will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of the steps of a vehicle positioning method based on data analysis provided by an embodiment of the present application;

[0019] Figure 2 It is a structural block diagram of a vehicle positioning device based on data analysis provided by an embodiment of the present application;

[0020] Figure 3 It is a schematic structural diagram of a computer device provided by an embodiment of the present application.

[0021] Explanation of reference numerals:

[0022] 12. Computer device; 14. External device; 16. Processing unit; 18. Bus; 20. Network adapter; 22. I / O interface; 24. Display; 28. Memory; 30. Random access memory; 32. Cache memory; 34. Storage system; 40. Program / utilities; 42. Program module; 310. First acquisition module; 320. Second acquisition module; 330. First fusion module; 340. Prediction module; 350. Second fusion module. Detailed implementation manners

[0023] To make the objectives, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the accompanying drawings and specific implementation manners. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0024] The inventor found through analyzing the prior art that when GPS signals pass through the atmosphere, troposphere or encounter obstacles, various reflections will occur, resulting in a longer propagation path and thus ranging errors. Especially in poor weather conditions, such as rainy or cloudy days, the transmission of GPS signals will be greatly affected, resulting in a decrease in positioning accuracy. In addition, the dead reckoning (DR) technology deduces the position and attitude of a vehicle at each moment by using inertial navigation sensors. It does not need to rely on external signals, so it has advantages in some areas where GPS signals cannot cover. However, it is only suitable for short-term estimation and is greatly affected by the accuracy of inertial navigation sensors. That is, both GPS positioning technology and dead reckoning technology have certain limitations in complex environments and there is a problem that the vehicle cannot be accurately and effectively positioned.

[0025] Referring to Figure 1 , it shows a vehicle positioning method based on data analysis provided by an embodiment of the present application;

[0026] The method includes the following steps:

[0027] S110. Obtain GPS positioning data and initialize the position information of the target vehicle according to the GPS positioning data;

[0028] S120. During the vehicle driving process, obtain the driving trajectory data and driving state information of the target vehicle in real time, and perform dead reckoning based on the driving state information to obtain the relative position change information of the target vehicle; the driving state information includes the speed, acceleration, and heading of the target vehicle.

[0029] S130. Perform data fusion on the GPS positioning data and the relative position change information of the target vehicle to obtain the fused positioning information.

[0030] S140. Based on the fused positioning information and the driving trajectory data, use the interpolation algorithm to perform prediction processing to obtain the predicted positioning information.

[0031] S150. Perform fusion processing on the GPS positioning data and the predicted positioning information to obtain the positioning information of the target vehicle; among them, during the fusion processing, the weight of the GPS positioning data will be dynamically adjusted according to the signal strength of the GPS positioning data.

[0032] In the embodiments of the present application, compared with the existing GPS positioning technology or dead reckoning technology, there are certain limitations in complex environments, and there is a problem that the vehicle cannot be accurately and effectively positioned. The present application provides a solution to the core invention point, specifically: "Obtain GPS positioning data, and initialize the position information of the target vehicle based on the GPS positioning data. During the driving process of the vehicle, obtain the driving trajectory data and driving state information of the target vehicle in real time, and perform dead reckoning based on the driving state information to obtain the relative position change information of the target vehicle; the driving state information includes the speed, acceleration, and heading of the target vehicle. Perform data fusion on the GPS positioning data and the relative position change information of the target vehicle to obtain fusion positioning information. Based on the fusion positioning information and the driving trajectory data, use the interpolation algorithm to perform prediction processing to obtain predicted positioning information. Perform fusion processing on the GPS positioning data and the predicted positioning information to obtain the positioning information of the target vehicle; wherein, during the fusion processing, the weight of the GPS positioning data will be dynamically adjusted according to the signal strength of the GPS positioning data." First, the relative position change information of the target vehicle is obtained through the driving trajectory data and driving state information during the driving process of the target vehicle, and then the relative position change information and the GPS positioning data are used for data fusion to obtain a relatively accurate, reliable, and estimated fusion positioning information. Then, based on the fusion positioning information, further combine the driving trajectory data and use the interpolation algorithm to perform prediction processing, which can eliminate some errors in the fusion positioning information and obtain a more accurate, reliable, and estimated predicted positioning information. Finally, perform fusion on the GPS positioning data and the predicted positioning information to obtain a positioning information that still maintains a high positioning accuracy when the GPS positioning data is affected. That is, the finally obtained positioning information of the target vehicle is less affected by the environment where the vehicle is located and can still maintain a high positioning accuracy and stability in complex environments or bad weather conditions.

[0033] Next, a vehicle positioning method based on data analysis in this exemplary embodiment will be further described.

[0034] As described in step S110, obtain GPS positioning data, and initialize the position information of the target vehicle based on the GPS positioning data.

[0035] It should be noted that when the vehicle starts, it will establish a connection with the GPS satellite to receive the GPS positioning data sent by the satellite, and then the initial position of the target vehicle can be determined by parsing the longitude, latitude, time, and other information in the GPS positioning data, and it will be used as the starting point for subsequent positioning.

[0036] As described in step S120, during the driving of the vehicle, the driving trajectory data and driving state information of the target vehicle are obtained in real time, and dead reckoning is performed based on the driving state information to obtain the relative position change information of the target vehicle; the driving state information includes the speed, acceleration, and heading of the target vehicle.

[0037] It should be noted that the real-time position data of the target vehicle can be collected first by using GPS (Global Positioning System) or other similar positioning technologies, and these data are represented in the form of latitude and longitude coordinates. At the same time, the speed, acceleration, and heading information of the target vehicle are collected through sensors on the vehicle (such as speed sensors, acceleration sensors, and gyroscopes). Then, based on the obtained driving state information, the relative position change information of the vehicle within a short period of time is estimated by using dead reckoning algorithms (such as integration method, difference method, etc.).

[0038] Among them, in actual applications, the collected real-time position data (included in the driving trajectory data) and driving state information can be transmitted to the data processing center in real time. For example, real-time transmission is achieved through vehicle-to-vehicle (V2V) communication, vehicle-to-infrastructure (V2I) communication, or vehicle-to-cloud (V2C) communication, etc. Then, in the data processing center, the collected raw data is first preprocessed, including filtering, noise reduction, and verification, to improve the accuracy and reliability of the data. Then the formal dead reckoning process can be carried out. Dead reckoning is to use known starting position, speed, acceleration, heading and other parameters to calculate the position at the next moment. In this process, simple physical models (such as uniform motion model, uniformly accelerated model) or more complex dynamic models can be used. For example, based on the speed and heading of the target vehicle, the approximate driving direction and distance of the target vehicle within a short period of time (such as several seconds or several minutes) can be calculated, and then combined with the acceleration information, the calculation result can be further corrected to consider the possible acceleration or deceleration of the vehicle, so as to calculate the relative position change information of the target vehicle.

[0039] As described in step S130, the GPS positioning data and the relative position change information of the target vehicle are fused to obtain the fused positioning information.

[0040] It should be noted that after obtaining the relative position change information of the target vehicle relative to the starting position through the dead reckoning method based on the driving state information such as the speed, acceleration, and heading of the vehicle, the relative position change information obtained by dead reckoning can be verified and calibrated first to ensure its accuracy and reliability. Then, the GPS positioning data and the relative position change information are used as sensor data from different sources for fusion processing to make up for the limitations of single-sensor data and improve the overall positioning accuracy. Among them, the fused positioning information includes the latitude and longitude coordinates, speed, and direction of the target vehicle, etc.

[0041] Exemplarily, when performing data fusion, different weights can be assigned based on the reliability and accuracy of the GPS positioning data and the relative position change information. For example, when the GPS signal is good, a higher weight can be given to the GPS positioning data; while when the GPS signal is unstable or interrupted, the weight of the relative position change information can be increased.

[0042] As described in step S140, based on the fused positioning information and the driving trajectory data, prediction processing is performed using an interpolation algorithm to obtain predicted positioning information.

[0043] It should be noted that the fused positioning information includes the longitude and latitude coordinates, speed, direction, etc. of the vehicle, while the driving trajectory data includes time series data such as the position and speed of the vehicle over a past period of time (such as from several seconds to several minutes). Thus, when the fused positioning information and the driving trajectory data of the vehicle are available, an interpolation algorithm (such as linear interpolation, polynomial interpolation, etc.) can be used for prediction processing to obtain predicted positioning information. Since the prediction is based on the vehicle's historical motion pattern, speed, acceleration, and possible steering behavior, the vehicle positioning can be accurately predicted, achieving the purpose of further improving the accuracy and stability of the fused positioning information (the predicted positioning information is a positioning information with higher accuracy and stability than the fused positioning information).

[0044] In practical applications, features such as the rate of change of speed, acceleration, and steering rate can be first extracted from the driving trajectory data, and these features are analyzed to identify the vehicle's motion pattern (such as uniform motion, acceleration, deceleration, turning, etc.). Then, an appropriate interpolation algorithm is selected according to the characteristics of the data and the prediction requirements. For example, interpolation algorithms such as Kalman filter, extended Kalman filter, or particle filter can be selected.

[0045] Among them, when the interpolation algorithm performs prediction processing, it can also eliminate some errors in the fused positioning information to a certain extent. This is because the interpolation algorithm estimates unknown data points based on known data points (i.e., the fused positioning information and the driving trajectory data), thereby smoothing or correcting anomalies or errors in the data.

[0046] Specifically, the interpolation algorithm can smoothly estimate the value of an unknown point based on the surrounding data points. If there are accidental errors or noises in the fused positioning information, the interpolation algorithm can smooth these errors by considering the surrounding data points, making the prediction result more stable and accurate. And since the interpolation algorithm considers not only the current data points but also the historical data and driving trends. If there is a large error in the fused positioning information at a certain time point, but the driving trajectory data and other sensor data indicate that the vehicle is driving according to a certain trend, the interpolation algorithm can predict the future position based on this trend, thereby eliminating or reducing the errors in a single data source.

[0047] As described in step S150, the GPS positioning data and the predicted positioning information are fused to obtain the positioning information of the target vehicle; wherein, during the fusion process, the weight of the GPS positioning data is dynamically adjusted according to the signal strength of the GPS positioning data.

[0048] It should be noted that by fusing the GPS positioning data and the predicted positioning information, the advantages of both types of data can be comprehensively utilized to further improve the positioning accuracy and stability. Among them, the signal strength of the GPS positioning data can be measured by indicators such as the number of received satellites and signal quality, and classified. Thus, when using a data fusion algorithm (such as a Kalman filter, an extended Kalman filter, or a particle filter, etc.) to fuse the GPS positioning data and the predicted positioning information, the weight of the GPS positioning data can be dynamically calculated according to the signal strength of the GPS positioning data, and the GPS positioning data and the predicted positioning information are weighted according to this dynamic weight. Exemplarily, when the GPS signal is strong, the weight of the GPS positioning data can be set higher; when the signal is weak or unstable, the weight is correspondingly reduced.

[0049] In an embodiment of the present application, the specific process of "fusing the GPS positioning data and the relative position change information of the target vehicle" described in step S130 can be further described in combination with the following description.

[0050] As described in the following steps, the extended Kalman filter algorithm is used to take the GPS positioning data and the relative position change information as common input data, and the state quantities of the two are transformed into one state quantity for optimal estimation to obtain the fused positioning information after fusion.

[0051] It should be noted that since the GPS positioning data and the relative position change information of the target vehicle are usually non-linear, the extended Kalman filter (EKF) algorithm can be used for non-linear state estimation to handle non-linear problems by linearizing these models (such as using Taylor series expansion).

[0052] Among them, the basic steps in using the extended Kalman filter algorithm for data fusion include:

[0053] (1) State prediction and update: Based on the state estimation value at the previous moment (such as position, speed, etc.), and the dynamic model of the system (such as the motion model of the vehicle), predict the state value at the current moment. When new observation data (GPS positioning data and relative position change information) arrives, use the extended Kalman filter algorithm to update the state estimation value.

[0054] (2) Data fusion: The GPS positioning data and the relative position change information are used as the common input data. Since they are usually in different coordinate systems or have different dimensions, coordinate transformation and dimension unification are required first. The state variables of the two are transformed into a unified state variable, such as the three-dimensional position (longitude, latitude, altitude) and speed of the vehicle. Then, within the framework of the extended Kalman filter, based on the observed data and the system model, the updated value of the state variable, that is, the fused positioning information after fusion, is calculated.

[0055] In summary, in the above embodiments, the extended Kalman filter algorithm can effectively handle the non-linear problems in data fusion. Therefore, by fusing the GPS positioning data and the relative position change information through the extended Kalman filter algorithm, the advantages of the two data sources can be fully utilized to improve the positioning accuracy. Similarly, during the fusion process, the weights can be dynamically adjusted according to the actual situation of the GPS signal to ensure that relatively accurate positioning results can be obtained in various environments.

[0056] In an embodiment of the present application, the specific process of "performing data fusion on the GPS positioning data and the relative position change information of the target vehicle" described in step S130 can be further described in combination with the following description.

[0057] As described in the following steps, based on a predefined objective function, an iterative algorithm is used to perform data fusion on the GPS positioning data and the relative position change information of the target vehicle.

[0058] It should be noted that by optimizing the objective function through the iterative algorithm, the advantages of the GPS positioning data and the relative position change information can be fully utilized to improve the positioning accuracy. And since the iterative algorithm is optimized based on the objective function, various complex scenarios and constraint conditions can be flexibly handled. This makes the data fusion method have strong adaptability and robustness. At the same time, the definition of the objective function and the parameters of the iterative algorithm can also be adjusted to adapt to different application scenarios and requirements. For example, the weights of each item in the objective function can be adjusted according to the actual situation or new constraint conditions can be added. In addition, since the iterative algorithm usually has a fast convergence speed, the data fusion method can quickly fuse the GPS positioning data and the relative position change information of the target vehicle.

[0059] Among them, the objective function is the criterion for evaluating the quality of the fusion result, which is defined as minimizing the difference between the GPS positioning data and the relative position change information, while considering other possible constraint conditions (such as the continuity of speed, acceleration, etc.). It is defined as minimizing the difference between the GPS positioning data and the relative position change information, while considering other possible constraint conditions (such as the continuity of speed, acceleration, etc.). Then, an iterative algorithm (such as gradient descent method, least squares method, Gauss-Newton method, etc.) is used to gradually optimize the objective function, so as to obtain the fused positioning information. In each iteration, the algorithm adjusts the state estimate value according to the gradient or derivative information of the objective function to reduce the difference between the GPS positioning data and the relative position change information. The iterative process will continue until the preset stop condition is met (such as reaching the maximum number of iterations, the change in the objective function value is less than a certain threshold, etc.). During the iterative process, the GPS positioning data and the relative position change information are comprehensively considered. The algorithm dynamically adjusts the contribution degrees of the two in the fusion result according to the optimization direction of the objective function. It should be noted that since the GPS positioning data and the relative position change information may come from different coordinate systems or have different dimensions, appropriate coordinate transformation and dimension unification are required before fusion.

[0060] In summary, different from using the extended Kalman filter algorithm to fuse the GPS positioning data and the relative position change information of the target vehicle, in the above implementation method, since the iterative algorithm is optimized based on the objective function, various complex scenarios and constraint conditions can be flexibly processed. This makes the data fusion method have strong adaptability and robustness. That is, different application scenarios and requirements can be adapted by adjusting the definition of the objective function and the parameters of the iterative algorithm. For example, the weights of each item in the objective function can be adjusted according to the actual situation or new constraint conditions can be added.

[0061] In an embodiment of the present application, the specific process of "fusing the GPS positioning data and the relative position change information of the target vehicle" described in step S130 can be further described in combination with the following description.

[0062] As described in the following steps, the position estimate of the target vehicle is initialized using the GPS positioning data;

[0063] As described in the following steps, an iterative process is performed until a preset condition is met; wherein, the preset condition is reaching a predetermined number of iterations, and the iterative process includes: at each time step, predicting the vehicle position at the current time step based on the position estimate at the previous time step and the relative position change information; when new GPS positioning data is received, calculating the residual between the new GPS positioning data and the predicted vehicle position at the current time step, and updating the covariance matrix and state vector of the position estimate based on this residual using an iterative algorithm (such as a Kalman filter, an extended Kalman filter, an unscented Kalman filter, etc.). Among them, the covariance matrix represents the uncertainty of the state estimate, and the state vector contains state information such as the position and speed of the vehicle.

[0064] It should be noted that since the iterative process is performed at each time step, it can fuse GPS positioning data and relative position change information in real time to provide an accurate position estimate for the vehicle. And by using an iterative algorithm to update the covariance matrix and state vector of the position estimate, it can handle the noise and outliers in the GPS data and improve the robustness of the position estimate.

[0065] In an embodiment of the present application, the specific process of "performing prediction processing using an interpolation algorithm based on the fused positioning information and the driving trajectory data to obtain predicted positioning information" described in step S140 can be further described in combination with the following description.

[0066] As described in the following steps, based on the fused positioning information, determine the current position information of the target vehicle (usually including position coordinates such as the longitude, latitude, and altitude of the vehicle);

[0067] As described in the following steps, extract historical position points from the driving trajectory data (these historical position points are arranged in chronological order) to form a historical position sequence, and based on this historical position sequence, establish a prediction model (a prediction model can be established using statistical methods, machine learning algorithms, or time series analysis, etc., and the goal of the prediction model is to describe the law of the target vehicle position changing over time);

[0068] As described in the following steps, use the prediction model and the current position information to predict the possible position of the target vehicle at future time steps to obtain predicted positioning information.

[0069] It should be noted that by using the fused positioning information and the driving trajectory data and combining an interpolation algorithm for prediction processing, it can accurately and real-time predict the possible position of the target vehicle at future time steps and provide accurate and reliable estimated positioning data (predicted positioning information). Among them, the selection of the above prediction model can be determined according to specific application scenarios and requirements. For example, a linear regression model, a polynomial regression model, a support vector machine (SVM), a recurrent neural network (RNN), or a long short-term memory network (LSTM) can be used.

[0070] In one embodiment of the present application, the specific process of "performing prediction processing using an interpolation algorithm based on the fused positioning information and the driving trajectory data to obtain predicted positioning information" in step S140 can be further described in combination with the following description.

[0071] As described in the following steps, determine the driving mode or driving trend of the target vehicle based on the driving trajectory data;

[0072] As described in the following steps, adjust the parameters of the preset interpolation algorithm according to the driving mode or driving trend;

[0073] As described in the following steps, use the adjusted interpolation algorithm to perform prediction processing in combination with the fused positioning information and the driving trajectory data to generate predicted positioning information.

[0074] It should be noted that the above embodiments can more accurately predict the possible position of the target vehicle at future time steps. And when specifically applying the above embodiments, the driving characteristics of the target vehicle can be first extracted from the driving trajectory data, and these characteristics may include speed, acceleration, steering angle, road type, traffic conditions, etc. Then, machine learning algorithms (such as classifiers, clusterers, etc.) or statistical analysis methods are used to determine the driving mode or driving trend of the target vehicle based on the extracted driving characteristics. The driving mode can be uniform driving, accelerating, decelerating, turning, etc., and the driving trend may include straight driving, curved driving, lane changing, etc. Next, the parameters of the preset interpolation algorithm are adjusted according to the determined driving mode or driving trend. The purpose of adjusting the parameters is to make the interpolation algorithm more in line with the current driving mode or trend to improve the prediction accuracy. For example, in the high-speed driving mode, a smoother interpolation algorithm may be needed to reduce the fluctuation of the prediction results; while in the turning mode, a more flexible interpolation algorithm may be needed to adapt to the changes of the curve. Finally, the adjusted interpolation algorithm can be used to perform prediction processing in combination with the fused positioning information and the driving trajectory data. Here, the fused positioning information provides the current accurate position of the target vehicle, and the driving trajectory data provides the historical positions and driving characteristics. That is, the interpolation algorithm generates the predicted positions of the target vehicle at future time steps based on the current position and historical position data, as well as the adjusted parameters, and these predicted positions constitute the predicted positioning information.

[0075] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the related parts, refer to the partial description of the method embodiment.

[0076] Refer to Figure 2 , which shows a vehicle positioning device provided by an embodiment of the present application; the device includes:

[0077] The first acquisition module 310 is configured to acquire GPS positioning data and initialize the position information of the target vehicle based on the GPS positioning data;

[0078] The second acquisition module 320 is configured to, during the driving of the vehicle, acquire the driving trajectory data and driving state information of the target vehicle in real time, and perform dead reckoning based on the driving state information to obtain the relative position change information of the target vehicle; the driving state information includes the speed, acceleration, and heading of the target vehicle;

[0079] The first fusion module 330 is configured to perform data fusion on the GPS positioning data and the relative position change information of the target vehicle to obtain fused positioning information;

[0080] The prediction module 340 is configured to perform prediction processing using an interpolation algorithm based on the fused positioning information and the driving trajectory data to obtain predicted positioning information;

[0081] The second fusion module 350 is configured to perform fusion processing on the GPS positioning data and the predicted positioning information to obtain the positioning information of the target vehicle; wherein, during the fusion processing, the weight of the GPS positioning data will be dynamically adjusted according to the signal strength of the GPS positioning data.

[0082] In an embodiment of the present application, the first fusion module 330 is further configured to adopt an extended Kalman filter algorithm, use the GPS positioning data and the relative position change information as common input data, and transform the state quantities of both into one state quantity for optimal estimation to obtain the fused fused positioning information.

[0083] In an embodiment of the present application, the first fusion module 330 is further configured to perform data fusion on the GPS positioning data and the relative position change information of the target vehicle using an iterative algorithm according to a predefined objective function.

[0084] In an embodiment of the present application, the first fusion module 330 is further configured to: initialize the position estimate of the target vehicle using the GPS positioning data; execute an iterative process until a preset condition is met; wherein, the preset condition is to reach a predetermined number of iterations, and the iterative process includes: at each time step, predicting the vehicle position at the current time step based on the position estimate and relative position change information at the previous time step; when new GPS positioning data is received, calculating the residual between the new GPS positioning data and the predicted vehicle position at the current time step, and updating the covariance matrix and state vector of the position estimate using an iterative algorithm based on the residual.

[0085] In an embodiment of the present application, the prediction module 340 is further configured to: determine the current position information of the target vehicle according to the fused positioning information; extract historical position points from the driving trajectory data to form a historical position sequence, and establish a prediction model according to the historical position sequence; use the prediction model and the current position information to predict the possible position of the target vehicle at future time steps to obtain predicted positioning information.

[0086] In an embodiment of the present application, the prediction module 340 is further configured to: determine the driving mode or driving trend of the target vehicle according to the driving trajectory data; adjust the parameters of a preset interpolation algorithm according to the driving mode or driving trend; use the adjusted interpolation algorithm to perform prediction processing in combination with the fused positioning information and the driving trajectory data to generate predicted positioning information.

[0087] In an embodiment of the present application, the interpolation algorithm includes one or more of Kalman filtering, extended Kalman filtering, or particle filtering.

[0088] Refer to Figure 3 , there is shown a computer device 12 of the present application, and the computer device 12 is presented in the form of a general computing device; the computer device 12 includes: one or more processors or processing units 16, a memory 28, and a bus 18 connecting different system components (including the memory 28 and the processing unit 16).

[0089] The bus 18 can be one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any bus structure in a variety of bus structures. For example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0090] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media accessible by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0091] The memory 28 may include computer system readable media in the form of volatile memory, such as random access memory 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 can be used to read and write non-removable, non-volatile magnetic media (commonly referred to as a "hard disk drive"). Although Figure 3Not shown in the figure, a disk drive for reading and writing a removable non-volatile disk (such as a "floppy disk") and an optical disk drive for reading and writing a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) can be provided. In these cases, each drive can be connected to the bus 18 through one or more data medium interfaces. The memory can include at least one program product having a set (such as at least one) of program modules 42 configured to execute the functions of the embodiments of the present application.

[0092] The program / utility 40 having a set (at least one) of program modules 42 can be stored, for example, in the memory. Such program modules 42 include an operating system, one or more application programs, other program modules 42, and program data. The implementation of a network environment may be included in each or some combination of these examples. The program modules 42 generally execute the functions and / or methods in the embodiments described in the present application.

[0093] The computer device 12 can also communicate with one or more external devices 14 (such as a keyboard, a pointing device, a display 24, a camera, etc.), and can also communicate with one or more devices that enable an operator to interact with the computer device 12, and / or communicate with any device that enables the computer device 12 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication can be carried out through the I / O interface 22. Moreover, the computer device 12 can also communicate with one or more networks (such as a local area network (LAN)), a wide area network (WAN), and / or a public network (such as the Internet) through the network adapter 20. As Figure 3 shown, the network adapter 20 communicates with other modules of the computer device 12 through the bus 18. It should be understood that although Figure 3 not shown in the figure, other hardware and / or software modules can be used in combination with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units 16, external disk drive arrays, RAID systems, tape drives, and data backup storage systems 34, etc.

[0094] The processing unit 16 executes various functional applications and data processing by running the programs stored in the memory 28, such as implementing the vehicle positioning method based on data analysis provided by any embodiment of the present application.

[0095] That is, when the above processing unit 16 executes the above program, it can achieve: obtaining GPS positioning data, and initializing the position information of the target vehicle based on the GPS positioning data. During the vehicle driving process, the driving trajectory data and driving state information of the target vehicle are obtained in real time, and dead reckoning is performed based on the driving state information to obtain the relative position change information of the target vehicle; the driving state information includes the speed, acceleration, and heading of the target vehicle. The GPS positioning data and the relative position change information of the target vehicle are subjected to data fusion to obtain fusion positioning information. Based on the fusion positioning information and the driving trajectory data, prediction processing is performed using an interpolation algorithm to obtain predicted positioning information. The GPS positioning data and the predicted positioning information are subjected to fusion processing to obtain the positioning information of the target vehicle; wherein, during the fusion processing, the weight of the GPS positioning data is dynamically adjusted according to the signal strength of the GPS positioning data.

[0096] In an embodiment of the present application, there is also provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the vehicle positioning method based on data analysis provided in any embodiment of the present application.

[0097] That is, when the program is executed by a processor, it can achieve: obtaining GPS positioning data, and initializing the position information of the target vehicle based on the GPS positioning data. During the vehicle driving process, the driving trajectory data and driving state information of the target vehicle are obtained in real time, and dead reckoning is performed based on the driving state information to obtain the relative position change information of the target vehicle; the driving state information includes the speed, acceleration, and heading of the target vehicle. The GPS positioning data and the relative position change information of the target vehicle are subjected to data fusion to obtain fusion positioning information. Based on the fusion positioning information and the driving trajectory data, prediction processing is performed using an interpolation algorithm to obtain predicted positioning information. The GPS positioning data and the predicted positioning information are subjected to fusion processing to obtain the positioning information of the target vehicle; wherein, during the fusion processing, the weight of the GPS positioning data is dynamically adjusted according to the signal strength of the GPS positioning data.

[0098] Any combination of one or more computer-readable media may be employed. The computer-readable media may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device.

[0099] A computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which computer-readable program code is carried. Such a propagated data signal may take any of a variety of forms, including an electromagnetic signal, an optical signal, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0100] The computer program code for performing the operations of this application may be written in one or more programming languages or combinations thereof. The foregoing programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the operator's computer, partly on the operator's computer, as a stand-alone software package, partly on the operator's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the operator's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider). Each embodiment in this specification is described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts among the various embodiments may be referred to each other.

[0101] Although the preferred embodiments of the embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0102] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the element.

[0103] The above has introduced in detail the vehicle positioning method and device based on data analysis provided by the present application. Specific examples are used in this text to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A vehicle positioning method based on data analysis, characterized in that: The following steps are involved: Obtaining GPS positioning data, and initializing the location information of the target vehicle according to the GPS positioning data; During the driving process of the vehicle, the driving trajectory data and driving status information of the target vehicle are obtained in real time, and the dead reckoning is performed based on the driving status information to obtain the relative position change information of the target vehicle; The driving state information includes the speed, acceleration and heading of the target vehicle; The GPS positioning data and the relative position change information of the target vehicle are fused to obtain fused positioning information, wherein the fused positioning information includes the latitude and longitude, speed and direction of the target vehicle; Based on the fusion positioning information and driving trajectory data, the interpolation algorithm is used to perform prediction processing to obtain the predicted positioning information; The GPS positioning data and the predicted positioning information are fused to obtain the positioning information of the target vehicle; during the fusion process, the weight of the GPS positioning data is dynamically adjusted according to the signal strength of the GPS positioning data; The data fusion of the GPS positioning data and the relative position change information of the target vehicle includes: initializing the position estimation of the target vehicle using the GPS positioning data; performing an iterative process until a preset condition is satisfied; wherein the preset condition is reaching a predetermined number of iterations, and the iterative process includes: predicting the vehicle position at the current time step based on the position estimation and relative position change information at the previous time step at each time step; when new GPS positioning data is received, calculating the residual of the new GPS positioning data and the predicted vehicle position at the current time step, and updating the covariance matrix and state vector of the position estimation based on the residual using an iterative algorithm; The method of performing prediction processing based on the fused positioning information and driving trajectory data using an interpolation algorithm to obtain predicted positioning information includes: determining a driving mode or driving trend of a target vehicle based on the driving trajectory data; adjusting parameters of a preset interpolation algorithm based on the driving mode or driving trend; and performing prediction processing based on the adjusted interpolation algorithm in combination with the fused positioning information and driving trajectory data to generate predicted positioning information.

2. The method according to claim 1, characterized in that The interpolation algorithm includes one or more of Kalman filtering, extended Kalman filtering or particle filtering.

3. A vehicle positioning device based on data analysis, characterized in that: include: A first acquisition module, used to acquire GPS positioning data and initialize the location information of the target vehicle according to the GPS positioning data; A second acquisition module is used to acquire the target vehicle's driving trajectory data and driving status information in real time during the vehicle's driving process, and perform dead reckoning based on the driving status information to obtain the target vehicle's relative position change information; the driving status information includes the target vehicle's speed, acceleration and heading; The first fusion module is used to fuse the GPS positioning data and the relative position change information of the target vehicle to obtain fused positioning information, wherein the fused positioning information includes the latitude and longitude, speed and direction of the target vehicle, and the data fusion of the GPS positioning data and the relative position change information of the target vehicle includes: initializing the position estimate of the target vehicle using the GPS positioning data; executing an iterative process until a preset condition is satisfied; wherein the preset condition is reaching a predetermined number of iterations, and the iterative process includes: at each time step, based on the position estimate and relative position change information of the previous time step, predicting the vehicle position of the current time step; when new GPS positioning data is received, calculating the residual of the new GPS positioning data and the predicted vehicle position of the current time step, and using an iterative algorithm based on the residual to update the covariance matrix and state vector of the position estimate; The prediction module is used to perform prediction processing using an interpolation algorithm based on the fused positioning information and the driving trajectory data to obtain predicted positioning information, including: determining the driving mode or driving trend of the target vehicle based on the driving trajectory data; adjusting the parameters of the preset interpolation algorithm based on the driving mode or driving trend; and using the adjusted interpolation algorithm to perform prediction processing in combination with the fused positioning information and the driving trajectory data to generate predicted positioning information; The second fusion module is used to fuse the GPS positioning data and the predicted positioning information to obtain the positioning information of the target vehicle; wherein, during the fusion processing, the weight of the GPS positioning data will be dynamically adjusted according to the signal strength of the GPS positioning data.

4. A computer device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the method according to claim 1 or 2 when executed by the processor.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to claim 1 or 2 is implemented.

Images