Vehicle rear wheel steering accurate positioning method based on sensor data analysis

Abstract

The invention discloses a vehicle rear wheel steering accurate positioning method based on sensor data analysis, and relates to the technical field of vehicle positioning, and the method comprises the steps: collecting multi-source data of a vehicle, and carrying out the preprocessing of the collected multi-source data; fusing the preprocessed multi-source data to generate an initial pose of the vehicle; feature extraction is carried out on the preprocessed multi-source data, and vehicle driving state recognition is carried out through the extracted features; a Kalman filter is initialized based on the initial pose of the vehicle, and parameters of the Kalman filter are dynamically adjusted based on the driving state of the vehicle; the course angle change rate and the turning radius of the vehicle are calculated, course angle change and the turning radius are brought into a Kalman filter, and the final pose of the vehicle is generated. According to the method, the parameters of the Kalman filter are dynamically optimized, the adaptability and robustness of the filter in different driving states are improved, the dynamic characteristics of the vehicle are reflected more accurately, and the positioning precision and reliability are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle positioning, and in particular to a vehicle rear wheel steering precise positioning method based on sensor data analysis. Background Art

[0002] In recent years, with the rapid development of autonomous driving technology and intelligent transportation, vehicle positioning technology has gradually become a research hotspot. Traditional vehicle positioning methods mainly rely on single sensors, such as the global positioning system (GPS) and inertial measurement unit (IMU). However, the positioning accuracy and robustness of a single sensor in complex environments are often limited. To this end, multi-source sensor fusion technology has emerged to improve the accuracy and reliability of positioning by fusing data from multiple sensors. Multi-source sensor fusion technology combines data from multiple sensors such as GPS, IMU, wheel encoders, magnetometers, and cameras, and uses advanced data processing and fusion algorithms to achieve high-precision estimation of vehicle posture. At present, multi-source sensor fusion technology has been widely used in fields such as autonomous driving and drone navigation.

[0003] Although multi-source sensor fusion technology has made significant progress in improving positioning accuracy, there are still some shortcomings in practical applications. First, when processing multi-source data, existing technologies often use fixed parameter settings and cannot dynamically adapt to changes in the vehicle under different driving conditions. For example, when the vehicle turns, accelerates or decelerates, the noise characteristics of the sensor will change significantly, and filters with fixed parameters are difficult to effectively cope with these changes, resulting in a decrease in positioning accuracy. Secondly, when fusing multi-source data, existing technologies usually use simple weighted averages or Kalman filtering methods, which fail to fully utilize the complementary characteristics of various sensors. For example, GPS has weak signals in environments such as urban canyons and tunnels, while IMUs and wheel encoders can provide continuous motion information, but existing methods fail to fully tap the complementary advantages of these sensors, resulting in limited overall positioning performance. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a vehicle rear wheel steering precise positioning method based on sensor data analysis to solve the problems in the prior art that fixed parameter settings cannot adapt to different driving conditions and simple fusion methods fail to fully utilize the complementary characteristics of sensors.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, the present invention provides a method for precise positioning of vehicle rear wheel steering based on sensor data analysis, which includes collecting multi-source data of the vehicle and preprocessing the collected multi-source data; fusing the preprocessed multi-source data to generate an initial posture of the vehicle; extracting features from the preprocessed multi-source data, and identifying the vehicle's driving state through the extracted features; initializing a Kalman filter based on the vehicle's initial posture, and dynamically adjusting the parameters of the Kalman filter based on the vehicle's driving state; calculating the vehicle's heading angle change rate and turning radius, incorporating the heading angle change and turning radius into the Kalman filter, and generating the vehicle's final posture.

[0008] As a preferred solution of the vehicle rear wheel steering precise positioning method based on sensor data analysis described in the present invention, the multi-source data of the vehicle includes GPS data, IMU data, wheel encoder data, magnetometer data and camera data.

[0009] As a preferred solution of the vehicle rear wheel steering precise positioning method based on sensor data analysis described in the present invention, the preprocessing includes data cleaning, data standardization, data normalization, data filtering, and image grayscale and noise reduction.

[0010] As a preferred solution of the vehicle rear wheel steering precise positioning method based on sensor data analysis described in the present invention, wherein: the pre-processed multi-source data is fused to generate the initial posture of the vehicle, and the specific steps are as follows:

[0011] Based on the long short-term memory network model, a multi-source data fusion model is constructed;

[0012] The preprocessed multi-source data is input into the multi-source data fusion model, and the mean square error is used as the loss function to train the multi-source data fusion model. The expression for constructing the multi-source data fusion model is:

[0013]

[0014] Among them, X is GPS data, Z is IMU data, W is wheel encoder data, V is magnetometer data, and Y represents the initial posture of the vehicle.

[0015] As a preferred solution of the vehicle rear wheel steering precise positioning method based on sensor data analysis of the present invention, wherein: the feature extraction of the pre-processed multi-source data is performed, and the vehicle driving state is identified by the extracted features, and the specific steps are as follows:

[0016] Use convolutional neural networks to extract visual data features, and use long short-term memory networks to extract IMU data features, wheel encoder data features, and magnetometer data features;

[0017] The extracted features are concatenated into a single feature vector, and the concatenated feature vectors are fused using multiple fully connected layers to generate a comprehensive feature representation.

[0018] The comprehensive feature representation is classified using support vector machine to identify the driving status of the vehicle.

[0019] As a preferred solution of the vehicle rear wheel steering precise positioning method based on sensor data analysis described in the present invention, wherein: based on the initial posture of the vehicle, the Kalman filter is initialized, and based on the driving state of the vehicle, the parameters of the Kalman filter are dynamically adjusted through adaptive parameter adjustment, and the specific steps are as follows:

[0020] Initialize the Kalman filter based on the vehicle’s initial position Y;

[0021] Based on the vehicle driving state, define the driving state influencing factor γ S , through the driving state influence factor γ S , dynamically adjust the process noise covariance matrix Q and the observation noise covariance matrix R;

[0022] Through the prediction step and update step of the Kalman filter, adaptive parameter adjustment is performed, and the expression is:

[0023]

[0024] Among them, X k is the updated state vector, To predict the state vector at time step k-1 at time step k, P k|k-1 is the covariance matrix predicted at time step k to time step k-1, J is the observation matrix, H T is the transpose of the observation matrix, Z k is the observation value at the current moment, R0 is the initial observation noise covariance matrix, γ S is the driving state influencing factor, and k represents the time distribution.

[0025] As a preferred solution of the vehicle rear wheel steering precise positioning method based on sensor data analysis of the present invention, wherein: the specific steps of calculating the vehicle's heading angle change rate and turning radius are as follows:

[0026] Introducing driving state influencing factor γ S , calculate the vehicle's heading angle change rate and turning radius, the expression is:

[0027]

[0028] Among them, θ S is the rate of change of heading angle after adjustment, r STo adjust the rear turning radius, v is the vehicle speed, δ is the front wheel steering angle, and L is the vehicle wheelbase.

[0029] As a preferred solution of the vehicle rear wheel steering precise positioning method based on sensor data analysis described in the present invention, wherein: the heading angle change and turning radius are incorporated into the Kalman filter to generate the final posture of the vehicle, the specific steps are as follows:

[0030] The heading angle change and turning radius are incorporated into the state vector and model of the Kalman filter, and the final posture of the vehicle is extracted from the updated state vector to generate the final posture of the vehicle.

[0031] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for precise positioning of vehicle rear wheel steering based on sensor data analysis as described in the first aspect of the present invention is implemented.

[0032] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for precise positioning of vehicle rear wheel steering based on sensor data analysis as described in the first aspect of the present invention is implemented.

[0033] The beneficial effects of the present invention are as follows: through adaptive parameter adjustment based on the vehicle's driving state, the present invention dynamically optimizes the parameters of the Kalman filter, and improves the adaptability and robustness of the filter under different driving conditions; at the same time, by incorporating the heading angle change rate and turning radius of the rear-wheel steering model into the state vector and model of the Kalman filter, the present invention more accurately reflects the dynamic characteristics of the vehicle and significantly improves the accuracy and reliability of positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0035] Figure 1 This is a flow chart of the vehicle rear wheel steering precise positioning method based on sensor data analysis in Example 1.

[0036] Figure 2 This is a flow chart of adjusting the Kalman filter in Example 1. Figure 3 This is the Kalman filter framework diagram in Example 1. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0038] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0039] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0040] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a vehicle rear wheel steering precise positioning method based on sensor data analysis, comprising the following steps:

[0041] Collect multi-source data of vehicles and pre-process the collected multi-source data;

[0042] The vehicle’s multi-source data includes GPS data, IMU data, wheel encoder data, magnetometer data, and camera data;

[0043] It should be noted that GPS data includes the vehicle's latitude, longitude, altitude and other absolute position information, IMU data includes the vehicle's three-axis acceleration and three-axis angular velocity, wheel encoder data includes the wheel speed pulse data of the front and rear wheels, magnetometer data includes the geomagnetic field strength and direction information, and camera data is environmental image data;

[0044] Preprocessing includes data cleaning, data standardization, data normalization, data filtering, and image grayscale and denoising.

[0045] Fuse the preprocessed multi-source data to generate the initial posture of the vehicle;

[0046] Based on the long short-term memory network model, a multi-source data fusion model is constructed;

[0047] The preprocessed multi-source data is input into the multi-source data fusion model, and the mean square error is used as the loss function to train the multi-source data fusion model;

[0048] It should be noted that the posture includes the position and attitude of the vehicle. The preprocessed multi-source data is divided into a training set, a validation set, and a test set. The mean square error (MSE) is used as the loss function to measure the difference between the model output and the true value. The loss function is minimized by the optimizer. The LSTM model is trained using the training set data. The model parameters are adjusted by the back propagation algorithm to gradually reduce the value of the loss function. The model is validated using the validation set data to evaluate the performance of the model. The hyperparameters of the model, such as the learning rate, batch size, number of hidden layer nodes, etc., are adjusted according to the validation results. The final trained model is tested using the test set data to evaluate the performance of the model on unseen data.

[0049] The expression for constructing a multi-source data fusion model is:

[0050]

[0051] Among them, X is GPS data, Z is IMU data, W is wheel encoder data, V is magnetometer data, and Y represents the initial posture of the vehicle.

[0052] Extract features from preprocessed multi-source data and identify vehicle driving status based on the extracted features;

[0053] Use convolutional neural networks to extract visual data features, and use long short-term memory networks to extract IMU data features, wheel encoder data features, and magnetometer data features;

[0054] It should be noted that the convolutional neural network extracts local features and spatial structures in the image through convolutional layers, pooling layers and activation function operations. In vehicle driving state recognition, the convolutional neural network can effectively capture the road environment and traffic signs in the camera data;

[0055] It should be noted that the long short-term memory network is a special recurrent neural network that can capture long-term dependencies in time series data. In vehicle driving state recognition, LSTM can effectively process the time series characteristics of IMU data, wheel encoder data, and magnetometer data to capture the dynamic behavior of the vehicle.

[0056] The extracted features are concatenated into a single feature vector, and the concatenated feature vectors are fused using multiple fully connected layers to generate a comprehensive feature representation.

[0057] Multi-layer fully connected layers extract high-level abstract features through multi-layer linear transformations and nonlinear activation functions, enhance the representation ability of features, and provide more effective feature representation for subsequent classification tasks;

[0058] Use support vector machine to classify the comprehensive feature representation and identify the driving status of the vehicle;

[0059] The support vector machine separates samples of different categories by finding the optimal classification boundary. In vehicle driving state recognition, the support vector machine can effectively distinguish different driving states, such as going straight, turning left, turning right, accelerating, decelerating, etc.

[0060] Initialize the Kalman filter based on the initial position of the vehicle, and dynamically adjust the parameters of the Kalman filter based on the vehicle's driving status;

[0061] Based on the initial position Y of the vehicle, the state vector X0 of the Kalman filter is initialized, and the expression is:

[0062] X0=[φ,λ,h,v φ ,v λ ,v h ,θ,α,β];

[0063] Among them, φ is latitude, λ is longitude, h is altitude, θ is heading angle, α is pitch angle, β is roll angle, v φ is the initial latitude velocity, v λ is the initial longitude velocity, v h is the initial altitude speed;

[0064] Initialize the covariance matrix P0 of the Kalman filter, the expression is:

[0065]

[0066] Among them, σ φ is the standard deviation of the initial latitude, σ λ is the standard deviation of the initial longitude, σ h is the standard deviation of the initial height, is the standard deviation of the initial latitudinal velocity, is the standard deviation of the initial longitude velocity, is the standard deviation of the initial altitude velocity, σ θ is the standard deviation of the initial heading angle, σ α is the standard deviation of the initial pitch angle, σ β is the standard deviation of the initial roll angle;

[0067] Based on the vehicle driving state, define the driving state influencing factor γ S , through the driving state influence factor γ S , dynamically adjust the process noise covariance matrix Q and the observation noise covariance matrix R;

[0068] According to the identified driving state S, the driving state influencing factor γ is defined S ;

[0069] Dynamically adjust the process noise covariance matrix Q and the observation noise covariance matrix R, the expression is:

[0070] Q = γ S Q0;

[0071] R = γ S R0;

[0072] Among them, Q0 is the initial process noise covariance matrix, R0 is the initial observation noise covariance matrix;

[0073] Through the prediction step and update step of the Kalman filter, adaptive parameter adjustment is performed, and the expression is:

[0074]

[0075] Among them, X k is the updated state vector, To predict the state vector at time step k-1 at time step k, P k|k-1 is the covariance matrix predicted at time step k to time step k-1, H is the observation matrix, H T is the transpose of the observation matrix, Z k is the observation value at the current moment, R0 is the initial observation noise covariance matrix, γ S is the driving state influencing factor, k represents the time distribution;

[0076] The Kalman filter framework is shown in the figure Figure 3 shown.

[0077] Filtering steps:

[0078] 1) Time update:

[0079] State one-step prediction:

[0080]

[0081] One-step forecast mean square error of state:

[0082] P k / k-1 =Φ k / k-1 P k-1 Φ k / k-1 T +Q k-1 ;

[0083] 2) Measurement update:

[0084] Filter gain:

[0085]

[0086] State Estimation:

[0087]

[0088] Variance estimation:

[0089] P k =(IK k H k ) k / k-1 ;

[0090] The error-based state quantity X is selected to have a total of 18 dimensions:

[0091]

[0092] The state quantities are expressed as the three-dimensional misalignment angle φ, velocity error δv, position error δp, gyro zero bias ε b , plus zero bias Odometer external parameter k D . Among them, the odometer external parameter k D It represents the pitch deflection between the IMU body coordinate system and the body coordinate system, the odometer scale factor, and the heading deflection between the IMU body coordinate system and the body coordinate system. The roll deflection does not affect the speed measurement of the odometer, so it can be ignored here.

[0093] The observed quantity is:

[0094] Z1=[v ins -v gnss, p ins -p gnss ] T ;

[0095]

[0096] Z1 and Z2 represent the observation information of GNSS and odometer respectively measured at different times. Indicates the speed provided by the odometer From the vehicle coordinate system v system to the navigation coordinate system n system.

[0097] In the strapdown inertial navigation algorithm, the attitude of the vehicle is updated and solved. The dead reckoning algorithm based on the odometer can directly use the attitude matrix calculated by inertial navigation to transform the odometer measurement. The acceleration and deceleration of the vehicle during movement can help to reduce the error k. D Identification.

[0098] The rear wheels of traditional passenger vehicles are fixed wheels, and the vehicle speed value v is obtained D , combined with the vehicle kinematics model as integrity constraint, the velocity in the vehicle coordinate system can be obtained as:

[0099]

[0100] In actual situations, some models have four-wheel steering, which reduces the centripetal force of the vehicle when turning at high speed and prevents the vehicle from rolling over. It also provides a smaller turning radius at low speed, reduces the operating difficulty of the driver and improves the driving experience. For vehicles with four-wheel steering, three-dimensional velocity modeling of the vehicle is performed under the flight integrity constraint. Therefore, this patent will extract the rear wheel deflection angle information θ and calculate the vehicle's lateral, forward and vertical speeds. The modeling is as follows:

[0101]

[0102] Calculate the vehicle's heading angle change rate and turning radius, incorporate the heading angle change and turning radius into the Kalman filter, and generate the vehicle's final posture;

[0103] Introducing driving state influencing factor γ S , calculate the vehicle's heading angle change rate and turning radius, the expression is:

[0104]

[0105] Among them, θ S is the rate of change of heading angle after adjustment, r S is the adjusted turning radius, v is the vehicle speed, δ is the front wheel steering angle, and L is the vehicle wheelbase;

[0106] The heading angle change and turning radius are incorporated into the Kalman filter, and the final posture of the vehicle is extracted from the updated state vector to generate the final posture of the vehicle;

[0107] It should be noted that the heading angle change rate and turning radius are incorporated into the state vector of the Kalman filter to form an extended state vector expression:

[0108] X k =[φ k ,λ k ,h k ,θ k ,α k ,β k ,θ S ,r S ];

[0109] Among them, X k is the final posture.

[0110] This embodiment also provides a computer device, which is suitable for the case of a vehicle rear wheel steering precise positioning method based on sensor data analysis, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the vehicle rear wheel steering precise positioning method based on sensor data analysis as proposed in the above embodiment.

[0111] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0112] The present embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for accurately positioning the rear wheel steering of a vehicle based on sensor data analysis as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.

[0113] In summary, the present invention achieves this by: adaptive parameter adjustment based on the vehicle's driving state, dynamically optimizing the parameters of the Kalman filter and improving the adaptability and robustness of the filter under different driving states; at the same time, by incorporating the heading angle change rate and turning radius of the rear-wheel steering model into the state vector and model of the Kalman filter, the present invention more accurately reflects the dynamic characteristics of the vehicle and significantly improves the accuracy and reliability of positioning.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A vehicle rear wheel steering precise positioning method based on sensor data analysis, characterized in that: include, Collect multi-source data of vehicles and pre-process the collected multi-source data; Fuse the preprocessed multi-source data to generate the initial posture of the vehicle; Extract features from preprocessed multi-source data and identify vehicle driving status based on the extracted features; Initialize the Kalman filter based on the initial position of the vehicle, and dynamically adjust the parameters of the Kalman filter based on the vehicle's driving status; Calculate the vehicle's heading angle change rate and turning radius, incorporate the heading angle change and turning radius into the Kalman filter, and generate the vehicle's final posture.

2. The vehicle rear wheel steering precise positioning method based on sensor data analysis as claimed in claim 1, characterized in that: The multi-source data of the vehicle includes GPS data, IMU data, wheel encoder data, magnetometer data and camera data.

3. The vehicle rear wheel steering precise positioning method based on sensor data analysis as claimed in claim 2, characterized in that: The preprocessing includes data cleaning, data standardization, data normalization, data filtering, and image grayscale and noise reduction.

4. The vehicle rear wheel steering precise positioning method based on sensor data analysis as claimed in claim 3, characterized in that: The pre-processed multi-source data is fused to generate the initial posture of the vehicle. The specific steps are as follows: Based on the long short-term memory network model, a multi-source data fusion model is constructed; The preprocessed multi-source data is input into the multi-source data fusion model, and the mean square error is used as the loss function to train the multi-source data fusion model. The expression for constructing the multi-source data fusion model is: Among them, X is GPS data, Z is IMU data, W is wheel encoder data, V is magnetometer data, and Y represents the initial posture of the vehicle.

5. The vehicle rear wheel steering precise positioning method based on sensor data analysis as claimed in claim 4, characterized in that: The steps of extracting features from the preprocessed multi-source data and identifying the vehicle driving state through the extracted features are as follows: Use convolutional neural networks to extract visual data features, and use long short-term memory networks to extract IMU data features, wheel encoder data features, and magnetometer data features; The extracted features are concatenated into a single feature vector, and the concatenated feature vectors are fused using multiple fully connected layers to generate a comprehensive feature representation. The comprehensive feature representation is classified using support vector machine to identify the driving status of the vehicle.

6. The vehicle rear wheel steering precise positioning method based on sensor data analysis as claimed in claim 5, characterized in that: The Kalman filter is initialized based on the initial position of the vehicle, and the parameters of the Kalman filter are dynamically adjusted through adaptive parameter adjustment based on the driving state of the vehicle. The specific steps are as follows: Initialize the Kalman filter based on the vehicle’s initial position Y; Based on the vehicle driving state, define the driving state influencing factor γ S , through the driving state influence factor γ S , dynamically adjust the process noise covariance matrix Q and the observation noise covariance matrix R; Through the prediction step and update step of the Kalman filter, adaptive parameter adjustment is performed, and the expression is: Among them, X k is the updated state vector, To predict the state vector at time step k-1 at time step k, P k|k-1 is the covariance matrix predicted at time step k to time step k-1, J is the observation matrix, H T is the transpose of the observation matrix, Z k is the observation value at the current moment, R0 is the initial observation noise covariance matrix, γ S is the driving state influencing factor, and k represents the time distribution.

7. The vehicle rear wheel steering precise positioning method based on sensor data analysis as claimed in claim 6, characterized in that: The specific steps of calculating the vehicle's heading angle change rate and turning radius are as follows: Introducing driving state influencing factor γ S , calculate the vehicle's heading angle change rate and turning radius, the expression is: Among them, θ S is the rate of change of heading angle after adjustment, r S To adjust the rear turning radius, v is the vehicle speed, δ is the front wheel steering angle, and L is the vehicle wheelbase.

8. The vehicle rear wheel steering precise positioning method based on sensor data analysis as claimed in claim 7, characterized in that: The heading angle change and turning radius are incorporated into the Kalman filter to generate the final posture of the vehicle. The specific steps are as follows: The heading angle change and turning radius are incorporated into the state vector and model of the Kalman filter, and the final posture of the vehicle is extracted from the updated state vector to generate the final posture of the vehicle.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the vehicle rear wheel steering precise positioning method based on sensor data analysis as described in any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the vehicle rear wheel steering precise positioning method based on sensor data analysis as described in any one of claims 1 to 8 are implemented.

Images