Drive-by-wire chassis system vehicle road state parameter active enhanced sensing method

Abstract

The invention discloses an active enhanced sensing method for vehicle road state parameters of a drive-by-wire chassis system. The method comprises the following steps: constructing a three-degree-of-freedom vehicle dynamics model; constructing a state equation and a measurement equation for vehicle state parameter estimation, and performing real-time estimation to obtain vehicle state parameters; constructing a road state parameter recognition data set, and training a graph convolutional neural network based on the data set; outputting a road state parameter identification result in real time; change information of vehicle and road state parameters in a future time domain is obtained; the current vehicle state parameters, the current road state parameters and the vehicle and road state parameters in the future time domain are sent to a drive-by-wire chassis control system, and active enhanced sensing of the drive-by-wire chassis system on the vehicle and road state parameters is completed. According to the method, the change of the vehicle-road state parameters in the future time domain is predicted on the basis of enhanced perception of the vehicle-road state parameters, the long-time-domain prediction data of the vehicle-road state parameters are obtained, and the perception time domain range of the drive-by-wire chassis to the vehicle-road state parameters is actively enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle chassis information technology, and particularly relates to an active enhanced perception method for vehicle-road state parameters of a by-wire chassis system. Background Art

[0002] With the rapid development of intelligent vehicle technology, the vehicle chassis is undergoing a major technological transformation from a traditional mechanical chassis to a by-wire chassis with electrical signals as the medium. The by-wire chassis technology is based on the traditional vehicle chassis, replacing the mechanical operating mechanism or hydraulic control components with wire connections, and converting the chassis control instructions into electrical signals through sensors, so as to achieve precise control of the vehicle. It has now become an essential execution carrier for autonomous driving vehicles.

[0003] For autonomous driving vehicles, their by-wire chassis realizes the closed-loop feedback control of the control instructions of subsystems such as steering, braking, and driving issued by the autonomous driving system by perceiving the vehicle and road states. At the same time, by perceiving the vehicle-road state, it can also judge whether the operating state of the by-wire chassis has a fault and whether there are abnormal changes in the road state, so as to adjust its own control strategy in time, which is also the basis for ensuring the normal operation and high-precision control of the chassis. However, compared with the traditional chassis system, the by-wire chassis system cancels the mechanical mechanism, has more by-wire actuators and greater control freedom, and autonomous driving vehicles have strict requirements for the control response and accuracy of the chassis. This puts higher requirements on the perception accuracy, real-time performance, and time domain range of the by-wire chassis for vehicle-road state parameters.

[0004] Among the key vehicle-road parameters used in by-wire chassis control, the yaw angular velocity, longitudinal and lateral vehicle speeds, and center of mass side slip angle in vehicle state parameters, as well as the road adhesion system and slope in road state parameters, are particularly important. However, in the existing methods for perceiving vehicle-road state parameters of by-wire chassis, the dynamic time-varying tracking performance of vehicle state parameters is poor. When the vehicle state parameters have fast time-varying characteristics due to external disturbances, traditional methods are difficult to accurately track the parameter changes. For the perception of road state parameters, the existing methods require a certain road excitation to implement parameter perception, and the triggering frequency is low during actual vehicle driving, with large information lag and untimely parameter perception. In addition, for the perception of both vehicle and road state parameters, the existing methods have obvious limitations in the narrow time domain range, that is, they can only perceive the vehicle-road state parameters at the current operating moment, cannot predict the changes of key vehicle-road state parameters, and are difficult to support the forward-looking decision-making planning of the autonomous driving system and the anticipatory control requirements of the by-wire chassis system. There is an urgent need for an active enhanced perception method for vehicle-road state parameters of a by-wire chassis system to improve the perception accuracy, real-time performance, and time domain range of the by-wire chassis system for key vehicle-road state parameters. Summary of the Invention

[0005] Aiming at the deficiencies of the above-mentioned existing technologies, the purpose of the present invention is to provide an active enhanced perception method for vehicle-road state parameters of a wire-controlled chassis system, so as to solve the problems of low dynamic perception accuracy, perception lag and narrow perception time domain range existing in the existing chassis system parameter perception methods. On the one hand, the present invention strongly tracks and estimates vehicle state parameters, actively enhancing the perception accuracy and real-time performance of the wire-controlled chassis for vehicle state parameters. On the other hand, it uses on-vehicle image information to replace the original passive excitation state information of the chassis to actively identify road state parameters, actively enhancing the initiative and real-time performance of the wire-controlled chassis for perceiving road state parameters. At the same time, based on the enhanced perception of vehicle-road state parameters, the changes of vehicle-road state parameters in the future time domain are predicted to obtain long-time domain prediction data of vehicle-road state parameters, actively enhancing the perception time domain range of the wire-controlled chassis for vehicle-road state parameters.

[0006] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0007] An active enhanced perception method for vehicle-road state parameters of a wire-controlled chassis system of the present invention comprises the following steps:

[0008] (1) Construct a three-degree-of-freedom vehicle dynamics model including vehicle yaw motion, lateral motion and longitudinal motion;

[0009] (2) Based on the vehicle dynamics model in step (1), construct a state equation and a measurement equation for estimating vehicle state parameters. The vehicle state parameters include: yaw angular velocity, sideslip angle of the center of mass, and longitudinal and lateral vehicle speeds; and use the Kalman filter method to estimate the vehicle state parameters in real time;

[0010] (3) Offline collect road image information including different adhesion coefficients and slopes, extract road image features and perform data annotation on road type and road slope data, construct a road state parameter recognition data set, and train a graph convolutional neural network based on the data set;

[0011] (4) Real-time collect road image information during vehicle operation and input it into the network model trained in step (3) to output the road state parameter recognition result in real time;

[0012] (5) Use an encoder-decoder network to perform long-time domain prediction on the current vehicle state parameters in step (2) and the current road state parameters in step (4) to obtain the change information of vehicle-road state parameters in the future time domain;

[0013] (6) Send the current vehicle state parameters in step (2), the current road state parameters in step (4), and the vehicle-road state parameters in the future time domain in step (5) to the wire-controlled chassis control system to complete the active enhanced perception of vehicle-road state parameters by the wire-controlled chassis system.

[0014] Further, the modeling process of the three - degree - of - freedom vehicle dynamics model in step (1) is as follows:

[0015] (11) Combine the components of the absolute acceleration of the vehicle's center of mass along the axes of the vehicle coordinate system to obtain the vehicle's longitudinal and lateral kinematic equations:

[0016] (1)

[0017] In the formula, and are the absolute longitudinal acceleration and the absolute lateral acceleration of the vehicle respectively; and are the longitudinal speed and the lateral speed of the vehicle in the vehicle coordinate system respectively; and are the longitudinal acceleration and the lateral acceleration of the vehicle in the vehicle coordinate system respectively; is the yaw angular velocity of the vehicle;

[0018] (12) Analyze the vehicle dynamics characteristics and combine D'Alembert's principle and Newton's second law to obtain the vehicle's longitudinal dynamics equation as follows:

[0019] (2)

[0020] In the formula, m is the total vehicle mass, F x-i is the longitudinal force exerted on the vehicle along the x - axis of the oxy vehicle coordinate system; F l-i are the longitudinal tire forces of each wheel of the vehicle, where i = fl, fr, rl, rr, fl represents the left - front wheel, fr represents the right - front wheel, rl represents the left - rear wheel, and rr represents the right - rear wheel; is the longitudinal tire force of the left - front wheel, is the longitudinal tire force of the right - front wheel, is the longitudinal tire force of the left - rear wheel, is the longitudinal tire force of the right - rear wheel; F c-fl is the lateral tire force of the left - front wheel, F c-fr is the lateral tire force of the right - front wheel; is the front - wheel steering angle;

[0021] (13) According to the dynamics characteristics analysis in step (12), obtain the vehicle's lateral dynamics equation as follows:

[0022] (3)

[0023] In the formula, F y-i is the lateral force exerted on the vehicle along the y - axis of the oxy vehicle coordinate system; is the lateral tire force of the left - rear wheel; is the lateral tire force of the right - rear wheel;

[0024] (14) Based on the dynamic characteristic analysis in step (12), the vehicle yaw motion equation is obtained as follows:

[0025] (4)

[0026] In the formula, M z-i is the yaw moment generated by the forces on each wheel of the vehicle around the z-axis of the vehicle coordinate system oxy; I z is the moment of inertia of the vehicle around the z-axis; l f and l r are the distances from the vehicle's center of mass to the front axle and the rear axle respectively; B v is the vehicle track width;

[0027] (15) Construct the longitudinal force and lateral force expression equations of the whole vehicle as follows:

[0028] (5)

[0029] In the formula, C cf , C cr are the cornering stiffness of the front wheels and the cornering stiffness of the rear wheels respectively; , are the front wheel cornering angle and the rear wheel cornering angle respectively;

[0030] (16) Combine the equations in steps (11)-(15) to construct a three-degree-of-freedom whole vehicle dynamics model as follows:

[0031] (6)

[0032] In the formula, is the vehicle yaw angular acceleration, and are the vehicle center of mass sideslip angle and the vehicle center of mass sideslip angular acceleration respectively.

[0033] Furthermore, step (2) specifically includes:

[0034] (21) Construct a state equation and a measurement equation for vehicle state parameter estimation with the yaw angular velocity, the center of mass sideslip angle, and the longitudinal vehicle speed as state variables and the vehicle front wheel steering angle and the vehicle absolute longitudinal acceleration as system input variables as follows:

[0035] (7)

[0036] In the formula, f is the system state equation function; h is the measurement equation function; x(t)=[ω r , β, v x is the system state vector at time t; is the rate of change of the system state vector with respect to time at time t; z(t) = [a y is the system measurement vector at time t; u(t) = [δ f , a x is the system input vector at time t; w(t) and v(t) are the system inherent noise and measurement noise at time t respectively; Q is the system inherent noise variance; R is the measurement noise variance; G represents the normal distribution;

[0037] (22) The equation in step (21) is discretized using the forward Euler method as follows:

[0038] (8)

[0039] where A and B are the Jacobian matrices obtained by taking the partial derivatives of f and h with respect to the system state vector x respectively; x(k) and x(k + 1) are the system state vectors at times k and k + 1 respectively; u(k) and z(k) are the system input vector and system measurement vector at time k respectively; w(k) and are the system inherent noise and measurement noise at time k respectively;

[0040] (23) Make a one-step prediction of the system state as follows:

[0041] (9)

[0042] where is the state prediction value obtained by making a one-step prediction of the estimate at time k - 1; is the state estimate value at time k - 1;

[0043] (24) Combine the orthogonality principle and introduce a decay factor to calculate the system prediction covariance matrix at time k as follows:

[0044] (10)

[0045] where P k-1 is the estimate covariance matrix at time k - 1; is the transpose matrix of matrix A; is the decay factor used to adjust the Kalman filter gain K k such that the estimation residual satisfies orthogonality, expressed as:

[0046] (11)

[0047] where is the covariance matrix of the output difference; is the transpose matrix of matrix B;

[0048] (25) Solve the attenuation factor , as follows:

[0049] (12)

[0050] Wherein, is a function for calculating the trace of a matrix;

[0051] (26) Calculate the system state at time k, which is the estimated value of the vehicle state parameters, as follows:

[0052] (13)

[0053] Wherein, is the estimated value of the vehicle state parameters at time k, including yaw rate, sideslip angle of the center of mass, and longitudinal vehicle speed. The lateral vehicle speed v y = v x β; z k is the system measurement value at time k, which is the measured value of the absolute lateral acceleration;

[0054] (27) Calculate the covariance matrix of the estimated value at time k , as follows:

[0055] (14)

[0056] Wherein, I is the identity matrix.

[0057] Further, the step (3) specifically includes:

[0058] (31) Collect road images with different adhesion coefficients offline, perform semantic segmentation on the images to extract road features in the images. For the road adhesion coefficient μ, the road types are divided into asphalt road, concrete road surface, gravel road, dirt road, snow-covered road, and icy road, and the corresponding adhesion coefficients μ are 0.75, 0.75, 0.6, 0.55, 0.25, and 0.15 respectively; at the same time, the asphalt road, concrete road, stone road, and dirt road are further subdivided, including wet and waterlogged conditions, and the corresponding adhesion coefficients μ are 0.65 for wet asphalt road, 0.6 for waterlogged asphalt road, 0.65 for wet concrete road, 0.6 for waterlogged concrete road, 0.5 for wet gravel road, 0.45 for waterlogged gravel road, 0.45 for wet dirt road, 0.3 for waterlogged dirt road, 0.25 for snow-covered road, and 0.15 for icy road. Record the wet asphalt road as type 1, the waterlogged asphalt road as type 2, the wet concrete road as type 3, the waterlogged concrete road as type 4, the wet gravel road as type 5, the waterlogged gravel road as type 6, the wet dirt road as type 7, the waterlogged dirt road as type 8, the snow-covered road as type 9, and the icy road as type 10, and construct a dataset containing road images, road adhesion coefficient annotations, and road types;

[0059] (32) Offline collect road images with different slopes, perform semantic segmentation on the images to extract road features in the images, divide the road slopes into transverse slopes and longitudinal slopes , label the road slope s of the image in degrees, and construct a data set containing different road images and road slope labels;

[0060] (33) Use the ResNet network to identify the road adhesion coefficient, and connect a fully connected layer and a Softmax layer after the network. Use the data set constructed in step (31) as the training set, use 80% of the data as the training set, and the remaining 20% of the data as the validation set. Use the road image data as the input and the road type as the output to train the graph convolutional neural network. The trained network model is denoted as the adhesion coefficient recognition network model;

[0061] (34) Use the lightweight MobileNetv3 network to identify the road slope, and connect a fully connected layer after the network. Use the data set constructed in step (32) as the training set, use 80% of the data as the training set, and the remaining 20% of the data as the validation set. Use the road image data as the input and the road transverse slope and longitudinal slope as the output to train the graph convolutional neural network. The trained network model is denoted as the road slope recognition network model.

[0062] Further, the specific steps of step (4) include:

[0063] (41) Real-time collect the road image information in front of the vehicle during operation;

[0064] (42) Input the road image information collected in step (41) into the trained adhesion coefficient recognition network model and road slope recognition network model respectively, and output the road type and road transverse and longitudinal slope information 、 ;

[0065] (43) Based on the road type and road transverse and longitudinal slope information output in step (42) 、 , convert the road type into the corresponding road adhesion coefficient μ information, and output the real-time road adhesion coefficient and road transverse and longitudinal slope information in real time.

[0066] Further, the specific steps of step (5) include:

[0067] (51) Select a bidirectional GRU network as the encoding network and a GRU network as the decoding network, and perform offline training. The encoding network uses the historical data sequence of the vehicle-road state parameters with a length of 2 seconds and a sampling interval of 0.1 second as the network input, expressed as:

[0068] (15)

[0069] Where N in is the network input, representing the historical sequence of vehicle-road state parameters; S i is the vehicle-road state parameter vector corresponding to the i-th moment, and each element in the vector represents the value of the corresponding vehicle-road state parameter at the i-th moment, where i = k - 19, k - 18, …, k; are respectively the vehicle yaw rate, the centroid side slip angle, the vehicle longitudinal speed in the vehicle coordinate system, the vehicle lateral speed in the vehicle coordinate system, the road adhesion coefficient, the road lateral slope, and the road longitudinal slope at the i-th moment;

[0070] (52) After the historical data sequence of vehicle-road state parameters is input into the bidirectional GRU encoding network, the final output result of the bidirectional GRU encoding network is as follows:

[0071] (16)

[0072] Where h is the hidden state output by the bidirectional GRU encoding network; hf i is the hidden state output by the forward GRU encoding network in the bidirectional GRU encoding network at the i-th moment; hb i is the hidden state output by the backward GRU encoding network in the bidirectional GRU encoding network at the i-th moment;

[0073] (53) Perform time encoding on the hidden state obtained in step (52) to obtain the time encoding vector as follows:

[0074] (17)

[0075] Where is the time encoding vector at the k-th moment; is the weight of the hidden state of the encoding network at the i-th moment; is the correlation score between the hidden state of the encoding network at the i-th moment and the hidden state of the decoding network at the k - 1-th moment ; V α , W α and U α are the weight matrices of the scoring network; h i is the hidden state output by the bidirectional GRU encoding network at the i-th moment;

[0076] (54) Perform feature encoding on all feature vectors of the hidden state obtained in step (52) to obtain the feature encoding vector as follows:

[0077] (18)

[0078] Where is the feature encoding vector at time k; d is the dimension of the hidden state feature vector; is the weight of the p-th dimensional feature vector; is the correlation score between the p-th dimensional feature vector and the decoder hidden state at time k-1 ; V ℓ 、W ℓ and U ℓ are the weight matrices of the scoring network; f p is the feature vector of the p-th dimension, representing the numerical combination of the p-th dimension of all hidden states;

[0079] (55) Concatenate the time encoding vector and the feature encoding vector to obtain the context vector C output by the encoding network at time k k , as follows:

[0080] (19);

[0081] (56) Input the context vector obtained in step (55) into the GRU decoding network, and circularly calculate the prediction results of the vehicle-road state parameters at time k+n to obtain the prediction data of the vehicle-road state parameters within n / 10 seconds, completing the long-time domain prediction of the vehicle-road state parameters. The circular calculation formula is as follows:

[0082] (20)

[0083] In the formula, rd k+n and zd k+n are the output of the reset gate and the update gate of the GRU decoding network at time k+n respectively; W rd , U rd and b rd are the input weight matrix, state weight matrix and bias matrix of the reset gate; W zd , U zd and b zd are the input weight matrix, state weight matrix and bias matrix of the update gate; W H , U H and b H are the input weight matrix, state weight matrix and bias matrix when calculating the candidate hidden state; is the candidate hidden state at time k+n; W o is the weight matrix of the fully connected layer output by the GRU network; n is the prediction time domain.

[0084] Advantages of the present invention:

[0085] Through the strong tracking estimation of vehicle state parameters, the present invention can actively enhance the perception accuracy and real-time performance of the drive-by-wire chassis for vehicle state parameters; by using on-vehicle image information to replace the original chassis passive excitation state information to actively identify road state parameters, the initiative and real-time performance of the drive-by-wire chassis for perceiving road state parameters are actively enhanced.

[0086] Based on enhancing the accuracy and real-time performance of vehicle-road state perception, the present invention predicts the changes of vehicle-road state parameters in the future time domain, and long-time domain prediction data of vehicle-road state parameters can be obtained, actively enhancing the perception time domain range of the drive-by-wire chassis for vehicle-road state parameters.

[0087] The present invention can effectively improve the perception accuracy, real-time performance and time domain range of the drive-by-wire chassis system for vehicle-road states, endow the drive-by-wire chassis system with stronger perception ability, effectively improve the chassis information acquisition ability, and further support the development of intelligent functions of the drive-by-wire chassis, having strong practicality and engineering significance. Brief Description of the Drawings

[0088] Figure 1 is the flowchart of the method of the present invention;

[0089] Figure 2 is the schematic diagram of the three-degree-of-freedom vehicle dynamics model constructed in the present invention. Detailed Embodiment

[0090] For the convenience of understanding by those skilled in the art, the present invention will be further described below in conjunction with embodiments and drawings. The content mentioned in the embodiments does not limit the present invention.

[0091] Referring to Figure 1 and Figure 2 shown, a method for actively enhancing the perception of vehicle-road state parameters of a drive-by-wire chassis system of the present invention is as follows:

[0092] (1) Construct a three-degree-of-freedom vehicle dynamics model including vehicle yaw motion, lateral motion and longitudinal motion;

[0093] The modeling process of the three-degree-of-freedom vehicle dynamics model is as follows:

[0094] (11) Combine the components of the absolute acceleration of the vehicle center of mass on each axis of the vehicle coordinate system to obtain the vehicle longitudinal and lateral kinematic equations:

[0095] (1)

[0096] In the formula, and are the absolute longitudinal acceleration and absolute lateral acceleration of the vehicle respectively; and are the longitudinal speed and lateral speed of the vehicle in the vehicle coordinate system, respectively; and are the longitudinal acceleration and lateral acceleration of the vehicle in the vehicle coordinate system, respectively; is the yaw angular velocity of the vehicle;

[0097] (12) Analyze the vehicle dynamic characteristics and combine with D'Alembert's principle and Newton's second law to obtain the vehicle longitudinal dynamic equation as follows:

[0098] (2)

[0099] In the formula, m is the vehicle mass, F x-i is the longitudinal force acting on the vehicle on the x-axis of the vehicle coordinate system oxy; F l-i are the longitudinal tire forces of each wheel of the vehicle, i = fl, fr, rl, rr, fl represents the left front wheel, fr represents the right front wheel, rl represents the left rear wheel, and rr represents the right rear wheel; is the longitudinal tire force of the left front wheel, is the longitudinal tire force of the right front wheel, is the longitudinal tire force of the left rear wheel, is the longitudinal tire force of the right rear wheel; F c-fl is the lateral tire force of the left front wheel, F c-fr is the lateral tire force of the right front wheel; is the front wheel steering angle;

[0100] (13) According to the dynamic characteristic analysis in step (12), obtain the vehicle lateral dynamic equation as follows:

[0101] (3)

[0102] In the formula, F y-i is the lateral force acting on the vehicle on the y-axis of the vehicle coordinate system oxy; is the lateral tire force of the left rear wheel; is the lateral tire force of the right rear wheel;

[0103] (14) According to the dynamic characteristic analysis in step (12), obtain the vehicle yaw motion equation as follows:

[0104] (4)

[0105] In the formula, M z-i is the yaw moment generated by the forces on each wheel of the vehicle around the z-axis of the vehicle coordinate system oxy; I z is the moment of inertia of the vehicle around the z-axis; l f and l r are the distances from the vehicle center of mass to the front axle and rear axle, respectively; Bv is the vehicle track width;

[0106] (15) Construct the longitudinal and lateral force expression equations of the whole vehicle as follows:

[0107] (5)

[0108] In the formula, C cf , C cr are the cornering stiffness of the front wheels and the cornering stiffness of the rear wheels respectively; , are the front wheel cornering angle and the rear wheel cornering angle respectively;

[0109] (16) Combine the equations in steps (11)-(15) to construct a three-degree-of-freedom whole vehicle dynamics model as follows:

[0110] (6)

[0111] In the formula, is the vehicle yaw angular acceleration, and are the sideslip angle of the vehicle center of mass and the sideslip angular acceleration of the center of mass respectively.

[0112] (2) Based on the whole vehicle dynamics model in step (1), construct a state equation and a measurement equation for estimating vehicle state parameters. The vehicle state parameters include: yaw angular velocity, sideslip angle of the center of mass, and longitudinal and lateral vehicle speeds; and use the Kalman filter method to estimate the vehicle state parameters in real time; specifically including:

[0113] (21) Use the yaw angular velocity, sideslip angle of the center of mass, and longitudinal vehicle speed as state variables, and use the vehicle front wheel steering angle and the vehicle absolute longitudinal acceleration as system input variables to construct a state equation and a measurement equation for estimating vehicle state parameters as follows:

[0114] (7)

[0115] In the formula, f is the system state equation function; h is the measurement equation function; x(t)=[ω r , β, v x is the system state vector at time t; is the rate of change of the system state vector at time t with respect to time; z(t)=[a y is the system measurement vector at time t; u(t)=[δ f , a x is the system input vector at time t; w(t) and v(t) are the system inherent noise and measurement noise at time t respectively; Q is the system inherent noise variance; R is the measurement noise variance; G represents a normal distribution;

[0116] (22) Discretize the equation in step (21) using the forward Euler method as follows:

[0117] (8)

[0118] where A and B are the Jacobian matrices obtained by taking the partial derivatives of f and h with respect to the system state vector x, respectively; x(k) and x(k + 1) are the system state vectors at times k and k + 1, respectively; u(k) and z(k) are the system input vector and the system measurement vector at time k, respectively; w(k) and are the system inherent noise and the measurement noise at time k, respectively;

[0119] (23) Perform a one-step prediction of the system state as follows:

[0120] (9)

[0121] where is the state prediction value obtained by performing a one-step prediction on the estimated value at time k - 1; is the state estimate value at time k - 1;

[0122] (24) Combine the orthogonality principle and introduce a decay factor to calculate the system prediction covariance matrix at time k as follows:

[0123] (10)

[0124] where P k-1 is the covariance matrix of the estimated value at time k - 1; is the transpose matrix of matrix A; is the decay factor used to adjust the Kalman filter gain K k such that the estimation residual satisfies orthogonality, expressed as:

[0125] (11)

[0126] where is the covariance matrix of the output difference; is the transpose matrix of matrix B;

[0127] (25) Solve for the decay factor as follows:

[0128] (12)

[0129] where is the function for finding the trace of a matrix;

[0130] (26) Calculate the system state at time k, which is the estimated value of the vehicle state parameters, as follows:

[0131] (13)

[0132] Wherein, is the estimated value of the vehicle state parameters at time k, including yaw rate, sideslip angle of the center of mass, and longitudinal vehicle speed. The lateral vehicle speed v y = v x β; z k is the system measurement value at time k, which is the measured value of the absolute lateral acceleration;

[0133] (27) Calculate the covariance matrix of the estimated value at time k , as follows:

[0134] (14)

[0135] Wherein, I is the identity matrix.

[0136] (3) Offline collect road image information including different adhesion coefficients and slopes, extract road image features, label road type and road slope data, construct a road state parameter recognition data set, and train a graph convolutional neural network based on the data set; specifically including:

[0137] (31) Offline collect road images with different adhesion coefficients, perform semantic segmentation on the images to extract road features in the images. For the road adhesion coefficient μ, divide the road types into asphalt road, concrete road surface, gravel road, dirt road, snow-covered road, and icy road, and the corresponding adhesion coefficients μ are 0.75, 0.75, 0.6, 0.55, 0.25, and 0.15 respectively; at the same time, further subdivide asphalt roads, concrete roads, gravel roads, and dirt roads, including wet and waterlogged conditions, and the corresponding adhesion coefficients μ are 0.65 for wet asphalt road, 0.6 for waterlogged asphalt road, 0.65 for wet concrete road, 0.6 for waterlogged concrete road, 0.5 for wet gravel road, 0.45 for waterlogged gravel road, 0.45 for wet dirt road, 0.3 for waterlogged dirt road. Denote wet asphalt road as type 1, waterlogged asphalt road as type 2, wet concrete road as type 3, waterlogged concrete road as type 4, wet gravel road as type 5, waterlogged gravel road as type 6, wet dirt road as type 7, waterlogged dirt road as type 8, snow-covered road as type 9, and icy road as type 10, and construct a data set including road images, road adhesion coefficient labels, and road types;

[0138] (32) Offline collect road images with different slopes, perform semantic segmentation on the images to extract road features in the images, divide the road slopes into lateral slope and longitudinal slope , and label the road slope s of the image in degrees, and construct a data set including different road images and road slope labels;

[0139] (33) The ResNet network is used to identify the road adhesion coefficient, and a fully connected layer and a Softmax layer are connected after the network. Using the dataset constructed in the step (31) as the training set, 80% of the data is used as the training set, and the remaining 20% of the data is used as the validation set. Using the road image data as the input and the road type as the output, the graph convolutional neural network is trained, and the trained network model is denoted as the adhesion coefficient recognition network model;

[0140] (34) The lightweight MobileNetv3 network is used to identify the road slope, and a fully connected layer is connected after the network. Using the dataset constructed in the step (32) as the training set, 80% of the data is used as the training set, and the remaining 20% of the data is used as the validation set. Using the road image data as the input and the road transverse slope and longitudinal slope as the output, the graph convolutional neural network is trained, and the trained network model is denoted as the road slope recognition network model.

[0141] (4) Real-time collect the road image information during vehicle operation and input it into the network model trained in step (3), and real-time output the road state parameter recognition result; specifically includes:

[0142] (41) Real-time collect the road image information in front of the vehicle during operation;

[0143] (42) Input the road image information collected in step (41) into the trained adhesion coefficient recognition network model and road slope recognition network model respectively, and output the road type and road transverse and longitudinal slope information 、 ;

[0144] (43) Based on the road type and road transverse and longitudinal slope information output in step (42) 、 , convert the road type into the corresponding road adhesion coefficient μ information, and output the real-time road adhesion coefficient and road transverse and longitudinal slope information in real time.

[0145] (5) Use an encoder-decoder network to perform long-time domain prediction on the current vehicle state parameters in step (2) and the current road state parameters in step (4), and obtain the change information of the vehicle-road state parameters in the future time domain; specifically includes:

[0146] (51) Select a bidirectional GRU network as the encoding network and a GRU network as the decoding network, and perform offline training. The encoding network uses the historical data sequence of the vehicle-road state parameters with a length of 2 seconds and a sampling interval of 0.1 second as the network input, expressed as:

[0147] (15)

[0148] In the formula, N in is the network input, representing the historical sequence of vehicle-road state parameters; S i is the vehicle-road state parameter vector corresponding to the i-th moment, and each element in the vector represents the value of the corresponding vehicle-road state parameter at the i-th moment, where i = k - 19, k - 18, …, k; are respectively the vehicle yaw rate, the centroid side slip angle, the vehicle longitudinal speed in the vehicle coordinate system, the vehicle lateral speed in the vehicle coordinate system, the road adhesion coefficient, the road cross slope, and the road longitudinal slope at the i-th moment;

[0149] (52) After the historical data sequence of the vehicle-road state parameters is input into the bidirectional GRU encoding network, the final output result of the bidirectional GRU encoding network is as follows:

[0150] (16)

[0151] In the formula, h is the hidden state output by the bidirectional GRU encoding network; hf i is the hidden state output by the forward GRU encoding network in the bidirectional GRU encoding network at the i-th moment; hb i is the hidden state output by the backward GRU encoding network in the bidirectional GRU encoding network at the i-th moment;

[0152] (53) Perform time encoding on the hidden state obtained in step (52) to obtain the time encoding vector as follows:

[0153] (17)

[0154] In the formula, is the time encoding vector at the k-th moment; is the weight of the hidden state of the encoding network at the i-th moment; is the correlation score between the hidden state of the encoding network at the i-th moment and the hidden state of the decoding network at the k - 1-th moment ; V α 、W α and U α are the weight matrices of the scoring network; h i is the hidden state output by the bidirectional GRU encoding network at the i-th moment;

[0155] (54) Perform feature encoding on all feature vectors of the hidden state obtained in step (52) to obtain the feature encoding vector as follows:

[0156] (18)

[0157] In the formula, is the feature encoding vector at the k-th moment; d is the dimension of the hidden state feature vector; is the weight of the p-dimensional feature vector; is the correlation score between the p-dimensional feature vector and the decoder hidden state at time k-1 ; V ℓ , W ℓ and U ℓ are the weight matrices of the scoring network; f p is the feature vector of the p-th dimension, representing the numerical combination of the p-th dimension of all hidden states;

[0158] (55) Concatenate the time encoding vector and the feature encoding vector to obtain the context vector C output by the encoding network at time k k , as follows:

[0159] (19);

[0160] (56) Input the context vector obtained in step (55) into the GRU decoding network, and cyclically calculate the prediction results of the vehicle-road state parameters at time k+n to obtain the prediction data of the vehicle-road state parameters within n / 10 seconds, completing the long-time-domain prediction of the vehicle-road state parameters. The cyclic calculation formula is as follows:

[0161] (20)

[0162] In the formula, rd k+n and zd k+n are the output of the reset gate and the update gate of the GRU decoding network at time k+n, respectively; W rd , U rd and b rd are the input weight matrix, state weight matrix and bias matrix of the reset gate; W zd , U zd and b zd are the input weight matrix, state weight matrix and bias matrix of the update gate; W H , U H and b H are the input weight matrix, state weight matrix and bias matrix when calculating the candidate hidden state; is the candidate hidden state at time k+n; W o is the weight matrix of the fully connected layer output by the GRU network; n is the prediction time domain.

[0163] (6) Send the current vehicle state parameters in step (2), the current road state parameters in step (4), and the vehicle-road state parameters in the future time domain in step (5) to the by-wire chassis control system to complete the active enhanced perception of the vehicle-road state parameters by the by-wire chassis system.

[0164] The specific application ways of the present invention are numerous. The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements can be made, and these improvements should also be regarded as the protection scope of the present invention.

Claims

1. A method for actively enhancing perception of vehicle-road state parameters of a drive-by-wire chassis system, characterized in that: Here are the steps: (1) Construct a three-degree-of-freedom vehicle dynamics model that includes vehicle yaw motion, lateral motion, and longitudinal motion; (2) constructing state equations and measurement equations for estimating vehicle state parameters based on the vehicle dynamics model in step (1), wherein the vehicle state parameters include: yaw rate, sideslip angle of center of mass, and lateral and longitudinal vehicle speeds; and using a Kalman filter method to estimate the vehicle state parameters in real time; (3) Offline collection of road image information containing different adhesion coefficients and slopes, extraction of road image features and annotation of road type and road slope data, construction of a road state parameter recognition dataset, and training of a graph convolutional neural network based on the dataset; (4) collecting road image information while the vehicle is running in real time and inputting it into the network model trained in step (3), and outputting the road state parameter recognition results in real time; (5) Using the codec network to perform long-term prediction on the current vehicle state parameters in step (2) and the current road state parameters in step (4), and obtain information on changes in the vehicle-road state parameters in the future time domain; (6) The current vehicle state parameters in step (2), the current road state parameters in step (4), and the vehicle-road state parameters in the future time domain in step (5) are sent to the drive-by-wire chassis control system to complete the active enhanced perception of the vehicle-road state parameters by the drive-by-wire chassis system.

2. The method for actively enhancing the perception of vehicle-road state parameters of a drive-by-wire chassis system according to claim 1, characterized in that: The modeling process of the three-degree-of-freedom vehicle dynamics model in step (1) is as follows: (11) Combining the absolute acceleration of the vehicle's center of mass in each axis of the vehicle coordinate system, the vehicle's lateral and longitudinal kinematic equations are obtained as follows: （1） In the formula, and are the vehicle's absolute longitudinal acceleration and the vehicle's absolute lateral acceleration respectively; and are the longitudinal velocity and lateral velocity of the vehicle in the vehicle coordinate system respectively; and are the longitudinal acceleration and lateral acceleration of the vehicle in the vehicle coordinate system respectively; is the vehicle yaw angular velocity; (12) The vehicle longitudinal dynamics equation is obtained by analyzing the vehicle dynamics characteristics and combining D'Alembert's theorem and Newton's second law as follows: （2） In the formula, m is the vehicle mass, F x-i F is the longitudinal force on the vehicle along the x-axis of the vehicle coordinate system oxy; l-i is the longitudinal force of the tires of each wheel of the vehicle, i=fl, fr, rl, rr, where fl represents the left front wheel, fr represents the right front wheel, rl represents the left rear wheel, and rr represents the right rear wheel; is the tire longitudinal force of the left front wheel, is the tire longitudinal force of the right front wheel, is the tire longitudinal force of the left rear wheel, is the tire longitudinal force of the right rear wheel; F c-fl is the tire lateral force of the left front wheel, F c-fr is the tire lateral force of the right front wheel; is the front wheel turning angle; (13) According to the dynamic characteristics analysis in step (12), the vehicle lateral dynamic equation is as follows: （3） In the formula, F y-i The lateral force on the vehicle along the y-axis of the vehicle coordinate system oxy; is the tire lateral force of the left rear wheel; is the tire lateral force of the right rear wheel; (14) According to the dynamic characteristics analysis in step (12), the vehicle yaw motion equation is as follows: （4） Where M z-i I is the yaw moment generated by the force on each wheel of the vehicle around the z-axis of the vehicle coordinate system oxy; z is the moment of inertia of the vehicle around the z-axis; l f and l r are the distances from the vehicle's center of mass to the front and rear axles, respectively; B v is the vehicle wheelbase; (15) The vehicle longitudinal force and lateral force expression equations are constructed as follows: （5） In the formula, C cf , C cr are the cornering stiffness of the front wheel and the cornering stiffness of the rear wheel respectively; , They are the front wheel slip angle and the rear wheel slip angle respectively; (16) Combine the equations in steps (11)-(15) to construct a three-degree-of-freedom vehicle dynamics model as follows: （6） In the formula, is the vehicle yaw angular acceleration, and are the vehicle's sideslip angle at center of mass and its acceleration at center of mass, respectively.

3. The method for actively enhancing the perception of vehicle-road state parameters of a drive-by-wire chassis system according to claim 2, characterized in that: The step (2) specifically includes: (21) The state equation and measurement equation for vehicle state parameter estimation are constructed with yaw rate, center of mass sideslip angle and longitudinal vehicle speed as state variables, and vehicle front wheel steering angle and vehicle absolute longitudinal acceleration as system input variables, as follows: （7） Where, f is the system state equation function; h is the measurement equation function; x(t)=[ , β, ] is the system state vector at time t; is the rate of change of the system state vector at time t; z(t)=[a y ] is the system measurement vector at time t; u(t)=[δ f , a x ] is the system input vector at time t; w(t) and v(t) are the system inherent noise and measurement noise at time t, respectively; Q is the system inherent noise variance; R is the measurement noise variance; G represents normal distribution; (22) The forward Euler method is used to discretize the equation in step (21) as follows: （8） Where A and B are the Jacobian matrices obtained by taking the partial derivatives of f and h with respect to the system state vector x; x(k) and x(k+1) are the system state vectors at time k and k+1, respectively; u(k) and z(k) are the system input vector and system measurement vector at time k, respectively; w(k) and are the system inherent noise and measurement noise at time k respectively; (23) One-step prediction of the system state is as follows: （9） In the formula, The state prediction value obtained by one-step prediction of the estimated value at time k-1; is the estimated value of the state at time k-1; (24) Combining the orthogonality principle and introducing the attenuation factor to calculate the system prediction covariance matrix at time k ,as follows: （10） Where P k-1 is the estimated value covariance matrix at time k-1; is the transposed matrix of matrix A; is the attenuation factor, used to adjust the Kalman filter gain K k So that the estimated residuals satisfy orthogonality, expressed as: （11） In the formula, is the covariance matrix of the output difference; is the transposed matrix of matrix B; (25) Solve for the attenuation factor ,as follows: （12） In the formula, To find the function of matrix trace; (26) Calculate the system state at time k, which is the estimated value of the vehicle state parameter, as follows: （13） In the formula, is the estimated value of the vehicle state parameters at time k, including yaw rate, sideslip angle of center of mass and longitudinal speed, lateral speed v y =v x β; z k is the system measurement value at time k, is the measurement value of the absolute lateral acceleration; (27) Calculate the estimated value covariance matrix at time k ,as follows: （14） Where I is the unit matrix.

4. The method for actively enhancing the perception of vehicle-road state parameters of a drive-by-wire chassis system according to claim 3, characterized in that: The step (3) specifically includes: (31) Offline collection of road images with different adhesion coefficients, semantic segmentation of the images was performed to extract road features in the images. According to the road adhesion coefficient μ, the road types were divided into asphalt roads, concrete roads, gravel roads, dirt roads, snowy roads, and icy roads. The corresponding adhesion coefficients μ were 0.75, 0.75, 0.6, 0.55, 0.25, and 0.15, respectively. At the same time, asphalt roads, concrete roads, gravel roads, and dirt roads were further subdivided, including wet and waterlogged conditions. The corresponding adhesion coefficients μ were 0.65 for wet asphalt roads and 0.65 for waterlogged asphalt roads. 0.6, wet concrete road 0.65, waterlogged concrete road 0.6, wet gravel road 0.5, waterlogged gravel road 0.45, wet soil road 0.45, waterlogged soil road 0.3, and record wet asphalt road as type 1, waterlogged asphalt road as type 2, wet concrete road as type 3, waterlogged concrete road as type 4, wet gravel road as type 5, waterlogged gravel road as type 6, wet soil road as type 7, waterlogged soil road as type 8, snowy road as type 9, and icy road as type 10, and build a dataset containing road images, road adhesion coefficient annotations, and road types; (32) Offline collection of road images with different slopes, and semantic segmentation of the images to extract road features in the images, and to divide the road slope into transverse slope and horizontal slope. and longitudinal slope , annotate the image with the road slope s in degrees, and construct a dataset containing different road images and road slope annotations; (33) Using a ResNet network to identify the road adhesion coefficient, and accessing a fully connected layer and a Softmax layer after the network, using the data set constructed in step (31) as a training set, using 80% of the data as a training set, and the remaining 20% ​​of the data as a validation set, using road image data as input and road type as output to train the graph convolutional neural network, and the trained network model is recorded as an adhesion coefficient recognition network model; (34) A lightweight MobileNetv3 network is used to identify the road slope, and a fully connected layer is connected to the back of the network. The data set constructed in step (32) is used as the training set, 80% of the data is used as the training set, and the remaining 20% ​​of the data is used as the validation set. The graph convolutional neural network is trained with the road image data as input and the road transverse slope and longitudinal slope as output. The trained network model is recorded as the road slope recognition network model.

5. The method for actively enhancing the perception of vehicle-road state parameters of a drive-by-wire chassis system according to claim 4, characterized in that: The step (4) specifically includes: (41) Real-time collection of road image information in front of the vehicle while the vehicle is running; (42) Input the road image information collected in step (41) into the trained adhesion coefficient recognition network model and road slope recognition network model respectively, and output the road type and road transverse and longitudinal slope information. , ; (43) Based on the road type and road transverse and longitudinal slope information output in step (42) , , convert the road type into the corresponding road adhesion coefficient μ information, and output the obtained real-time road adhesion coefficient and road transverse and longitudinal slope information in real time.

6. The method for actively enhancing the perception of vehicle-road state parameters of a drive-by-wire chassis system according to claim 5, characterized in that: The step (5) specifically includes: (51) A bidirectional GRU network is selected as the encoding network, and a GRU network is selected as the decoding network. Offline training is performed. The encoding network uses a historical data sequence of vehicle-road state parameters with a length of 2 seconds and a sampling interval of 0.1 seconds as the network input, which is expressed as: （15） Where N in is the network input, representing the historical sequence of vehicle-road state parameters; S i is the vehicle-road state parameter vector corresponding to time i, and each element in the vector represents the value of the corresponding vehicle-road state parameter at time i, i=k-19,k-18,…,k; are the vehicle yaw rate, center of mass sideslip angle, vehicle longitudinal velocity in the vehicle coordinate system, vehicle lateral velocity in the vehicle coordinate system, road adhesion coefficient, road lateral slope and road longitudinal slope at time i respectively; (52) After the historical data sequence of the vehicle-road state parameters is calculated and input into the bidirectional GRU encoding network, the final output result of the bidirectional GRU encoding network is as follows: （16） Where h is the hidden state output by the bidirectional GRU encoding network; hf i hb is the hidden state of the forward GRU encoding network output in the bidirectional GRU encoding network at time i; i is the hidden state output by the backward GRU encoding network in the bidirectional GRU encoding network at time i; (53) Temporally encode the hidden state obtained in step (52) to obtain the temporal encoding vector as follows: （17） In the formula, is the time encoding vector at time k; is the weight of the hidden state of the encoding network at the i-th moment; is the hidden state of the encoding network at the i-th moment and the hidden state of the decoding network at the k-1 moment The correlation score between α , W α and U α is the weight matrix of the scoring network; h i is the hidden state of the bidirectional GRU encoding network output at time i; (54) Perform feature encoding on all the hidden state feature vectors obtained in step (52) to obtain the feature encoding vector as follows: （18） In the formula, is the feature encoding vector at time k; d is the dimension of the hidden state feature vector; is the weight of the p-th dimension feature vector; is the p-th dimension feature vector and the decoder hidden state at time k-1 The correlation score between ℓ , W ℓ and U ℓ is the weight matrix of the scoring network; f p is the feature vector of the pth dimension, representing the numerical combination of the pth dimension of all hidden states; (55) Concatenate the temporal encoding vector and the feature encoding vector to obtain the context vector C output by the encoding network at time k k ,as follows: （19）； (56) The context vector obtained in step (55) is input into the GRU decoding network, and the prediction results of the vehicle-road state parameters at time k+n are cyclically calculated to obtain the prediction data of the vehicle-road state parameters within n / 10 seconds, thereby completing the long-term prediction of the vehicle-road state parameters. The cyclic calculation is shown as follows: （20） In the formula, rd k+n and k+n are the reset gate and update gate outputs of the GRU decoding network at time k+n respectively; W rd , U rd and b rd is the input weight matrix, state weight matrix and bias matrix of the reset gate; W zd , U zd and b zd is the input weight matrix, state weight matrix and bias matrix of the update gate; W H , U H and b H The input weight matrix, state weight matrix and bias matrix are used to calculate the candidate hidden states; is the candidate hidden state at time k+n; W o The weight matrix of the fully connected layer output by the GRU network; n is the prediction time domain.

Images