A method for calculating rear wheel turning angle of intelligent vehicles considering driving style

Abstract

The present invention discloses a method for calculating the rear wheel angle of an intelligent vehicle that takes driving style into account. The method comprises a driving information acquisition module, a driving style judgment module, a loss function calculation module, and a rear wheel angle calculation module. The driving information acquisition module is used to obtain vehicle driving state information and driver physiological signal information; the driving style judgment module is used to calculate the driver's driving style factor; the loss function calculation module is used to calculate the loss function of the neural network in the rear wheel angle calculation module; and the rear wheel angle calculation module is used to calculate the ratio of the rear wheel angle to the front wheel angle using a deep neural network.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent vehicle control and safe driving, relates to intelligent vehicle steering control technology, and specifically relates to a method for calculating the rear wheel steering angle of an intelligent vehicle taking driving style into consideration. Background Art

[0002] With the development of intelligent driving technology, smart vehicles are becoming an important direction for future mobility. One of the core technologies of smart vehicles is precise vehicle dynamic control, and rear-wheel steering angle control, as a key means of improving vehicle handling stability and safety, has received widespread attention. Existing steering control systems are typically based on fixed parameters or preset models, using vehicle dynamics formulas to calculate the optimal steering angle. These methods do not consider the driver's driving style, resulting in significant differences in control strategies between different drivers. This can lead to control hysteresis or over-response under different driving styles, seriously affecting the driving experience and driving safety.

[0003] While some research has attempted to assess driver fatigue and stress by sensing physiological signals, most studies focus primarily on the classification and identification of driving styles, lacking deep integration with rear-wheel steering angle calculation, making dynamic adjustment difficult. Therefore, a driving style-informed rear-wheel steering angle calculation method is urgently needed, capable of adapting to different drivers' control habits and optimizing the dynamic control performance of intelligent vehicles. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for calculating the rear wheel turning angle of an intelligent vehicle taking driving style into consideration, so as to solve the problems faced in the above-mentioned background technology.

[0005] In order to achieve the above object, the present invention provides the following solutions:

[0006] The driving information acquisition module is used to obtain vehicle driving state information and driver's physiological signal information, including vehicle longitudinal speed V x , vehicle lateral acceleration a y , front wheel turning angle δ f , vehicle roll angle φ, front axle slip angle α f , rear axle slip angle α r , vehicle yaw angular velocity ω r , driver's eye movement frequency f eye , pupil diameter d pupil , heart rate variability HRV, skin electrode activity EDA, electromyographic signal EMG, head angle θ head ;

[0007] The driving style judgment module is based on the driving behavior factor and biological data factors Calculate the driver's driving style factor S d , the driver style factor refers to the driver's driving proficiency, where when When the driver is defined as a novice driver, When the driver is defined as an ordinary driver, When the driver is defined as a skilled driver, the specific calculation formula is:

[0008]

[0009] Where, is the driving behavior factor, is the biological data factor;

[0010] The loss function calculation module is based on the driver's operating burden loss function L busy , vehicle rollover risk loss function L roll , Vehicle skidding risk loss function L slip , physical loss function L physics Get the total loss function L of the rear wheel angle calculation module total , the calculation formula is as follows:

[0011]

[0012] Where ξ1, ξ2, and ξ3 are the loss functions L busy 、L roll 、L slip The weighting factor of is calculated by the loss function weighting factor attention mechanism, and the value range is 0 to 1; physicis is the weighting factor of the physical loss function, when λ physicis When it approaches 0, the proportion of the physical loss function increases, improving the ability to learn physical laws. physicis When it approaches 1, the proportion of the physical loss function decreases, reducing the ability to learn physical laws; L busy is the driver's control burden loss function, L roll is the vehicle rollover risk loss function, L slip is the vehicle sideslip risk loss function, L physics is the physical loss function;

[0013] The rear wheel angle calculation module calculates the total loss function L according to the calculation total , a deep neural network algorithm is used to determine the ratio R of the vehicle's rear wheel angle to the front wheel angle. When R < 0, the front and rear wheels turn in the same direction; when R > 0, the front and rear wheels turn in opposite directions. The calculation formula is as follows:

[0014] δr =δ f ·R

[0015] Where, δ f is the front wheel turning angle, R is the ratio of the rear wheel turning angle to the front wheel turning angle;

[0016] The input layer contains 5 nodes, corresponding to the vehicle longitudinal speed V x , vehicle lateral acceleration a y , yaw angular velocity w r , center of mass side slip angle β, front wheel turning angle δ f The hidden layer adopts a three-layer structure, including the first hidden layer, the second hidden layer, and the third hidden layer; the first hidden layer contains 64 neurons, the second hidden layer contains 32 neurons, and the third hidden layer contains 16 neurons; the output layer contains 1 node, and the output is the ratio R of the rear wheel and front wheel steering angles of the vehicle;

[0017] The calculation formula of the rear wheel angle calculation module is:

[0018]

[0019] Where V x is the vehicle's longitudinal speed, a y Vehicle lateral acceleration, w r is the yaw rate, β is the sideslip angle of the center of mass, δ f is the front wheel angle; h1 is the output of the first hidden layer, h2 is the output of the second hidden layer; Swish is the activation of the first hidden layer; ReLU is the activation function of the second hidden layer and the third hidden layer; W1, W2, W3, W4 are weight matrices, all determined through training; b1, b2, b3, b4 are bias terms, all determined through training, W s is the weight matrix from the input layer to the dynamic scaling factor S, b s is the bias term from the input layer to the dynamic scaling factor S; S is the dynamic scaling factor, τ is the scaling weight control factor, and its value range is 0 to 1; Tanh is the output layer activation function; Sigmoid is the dynamic scaling factor layer activation function.

[0020]

[0021] Where, L busy is the driver's control burden loss function, L roll is the vehicle rollover risk loss function, L slip is the vehicle sideslip risk loss function; k1 is the adjustment factor of the driver's control burden loss function, k2 is the adjustment factor of the vehicle rollover risk loss function, and k3 is the adjustment factor of the vehicle sideslip risk loss function, which is used to control the sensitivity of each loss item. The specific value is selected according to specific needs; is the normalized biological signal characteristic value, is the eigenvalue calculated using exponentially weighted moving average, The eigenvalues ​​obtained by using Sigmoid nonlinear transformation are used to enhance the stability of biological data factors.

[0022] The driving style judgment module, the normalized biological signal characteristic value Eigenvalues ​​after exponentially weighted moving average calculation Eigenvalues ​​obtained using Sigmoid nonlinear transformation The specific calculation process is as follows:

[0023] First, for different physiological signals, core features are extracted. The specific calculation process is as follows:

[0024] Eye movement frequency f eye The core feature of the eye movement frequency is the instantaneous change rate Δf of the driver eye , information entropy H eye , when the driver's driving behavior is proficient, the information entropy H eye , instantaneous rate of change Δf eye The value of will be smaller, and the information entropy H will be smaller when the driver's driving behavior is unfamiliar. eye , instantaneous rate of change Δf eye The value of will be larger; the calculation formula is as follows:

[0025]

[0026] p i =|FFT(f eye )| 2

[0027] H eye =-∑p i logp i

[0028] Where f eye is the driver's eye movement frequency, FFT(x) is Fourier transform, where x = f eye 、p i is the eye movement frequency f eye The power spectral density of

[0029] Pupil diameter d pupil The core feature is the coefficient of variation CV of pupil diameter pupil , the energy of the high-frequency component of the pupil diameter signal D pupil The pupil diameter of experienced drivers is more stable, and the high-frequency component energy D of the pupil diameter signal in a short period of time pupil , pupil diameter d pupilThe fluctuation is small, the pupil diameter of novice drivers changes more dramatically, and the high-frequency component energy D of the pupil diameter signal in a short period of time pupil , pupil diameter d pupil The fluctuation is large, and the calculation formula is as follows:

[0030]

[0031] Where σ pupil is the standard deviation of pupil diameter, μ pupil is the mean pupil diameter, d pupil is the pupil diameter; FFT(x) is the Fourier transform, where x = d pupil 、f c is the lower limit of the high frequency range obtained by Fourier transform, f max The upper limit of the high-frequency range obtained by Fourier transform, the specific value is determined through experiments;

[0032] Standard deviation of pupil diameter σ pupil and the mean pupil diameter μ pupil The calculation formula is as follows:

[0033]

[0034] Where d pupil,i is the pupil diameter at the i-th moment, N is the number of pupil diameter samples collected;

[0035] The core characteristic of heart rate variability (HRV) is the ratio of low-frequency to high-frequency power of heart rate variability (HRV). LF / HF , low frequency high frequency power ratio HRV LF / HF When it is higher, the driver's driving behavior is relatively unfamiliar, and the low-frequency and high-frequency power is higher than HRV. LF / HF When it is lower, the driver's driving behavior is more skilled. The calculation formula is as follows:

[0036]

[0037] Where, P LF is the low-frequency power of heart rate variability, P HF is the high frequency power of heart rate variability, HRV is the heart rate variability;

[0038] The core feature of skin electrical activity (EDA) is the skin electrical energy attenuation factor (EDA). decay , skin electrical energy attenuation factor EDA decay When it is larger, the driver is in a state of high tension and high pressure, and the driving behavior is relatively unfamiliar. The skin electrical energy attenuation factor EDA decay When it is small, the driver is in a relaxed state and the driver's driving behavior is relatively skilled. The calculation formula is as follows:

[0039]

[0040] Where EDA(t) is the skin electrical signal value at time t, EDA(t-1) is the skin electrical signal value at time t-1, and λ EDA is the exponential attenuation factor of skin electrical activity, which is used to amplify the drastic changes in skin electrical activity in a short period of time; T is the current sampling time;

[0041] The core feature of the electromyographic signal EMG is the electromyographic signal adaptive power exponential root mean square value EMG adaptive , EMG adaptive power exponential root mean square value adaptive When it is larger, the driver is in a state of high tension and high pressure, and the driving behavior is relatively unfamiliar. The EMG adaptive power exponent root mean square value adaptive When it is small, the driver is in a relaxed state and the driver's driving behavior is relatively skilled. The calculation formula is as follows:

[0042]

[0043] Where, EMG t is the skin electrical signal value at time t, z is the electromyographic signal adaptive power index, σ EMG is the standard deviation of the EMG signal, N is the number of EMG signal samples collected;

[0044] Head angle θ head The characteristic value of the head angle change rate θ stability , head angle change rate θ stability When it is larger, the driver is in a state of high tension and high pressure, and the driving behavior is relatively unfamiliar. The head angle change rate θ stability When it is small, the driver is in a relaxed state and the driver's driving behavior is relatively skilled. The calculation formula is as follows:

[0045]

[0046] Where θ head (t) is the head angle at time t, μ θ (t) is the sliding mean at time t, ζ1 is the sliding window size, σ θ (t) is the sliding standard deviation at time t, μ θ (t) is the mean value of the driver’s head angle;

[0047] Normalized biological signal feature value Eigenvalues ​​after exponentially weighted moving average calculation Sigmoid nonlinear transformation eigenvalue The instantaneous rate of change of eye movement frequency Δf eye , eye movement frequency feye Information entropy H eye , coefficient of variation of pupil diameter CV pupil , the energy of the high-frequency component of the pupil diameter signal D pupil , heart rate variability low frequency high frequency power ratio HRV LF / HF , skin electrical energy attenuation factor EDA decay , head angle change rate θ stability Calculated, where X i =[Δf eye ,H eye ,CV pupil ,D pupil ,HRV LF / HF ,EDA decay ,θ stability ], the specific calculation process is as follows:

[0048] Normalized biological signal feature value The biological signal feature value X i Mapping to [0,1] avoids dimensionality issues and ensures comparability between different features. The calculation formula is as follows:

[0049]

[0050] Where, max(X i ) is the biological signal characteristic value X i The maximum value, min(X i ) is the biological signal characteristic value X i The minimum value of

[0051] Eigenvalues ​​after exponentially weighted moving average calculation Use exponential weighted moving average to smooth and reduce the noise effect on the eigenvalue X i To avoid the impact of sharp fluctuations in a short period of time and cause misjudgment, the calculation formula is as follows:

[0052]

[0053] In the formula, ε is the smoothing coefficient, which controls the balance between new data and historical data. When ε is close to 1, it is more dependent on current data and has a faster response speed. When ε is close to 0, it is more dependent on historical data and has a higher degree of smoothing.

[0054] Sigmoid nonlinear transformation eigenvalue Use Sigmoid nonlinear transformation to enhance the stability of data and avoid eigenvalue X i The impact caused by being too large or too small is uneven. The calculation formula is as follows:

[0055]

[0056] Where, is the normalized biological signal feature value.

[0057] The loss function calculation module calculates the driver's control burden loss function L by the following formula: busy , vehicle rollover risk loss function L roll , Vehicle skidding risk loss function L slip and the physical loss function L physics :

[0058] Driver's control burden loss function L busy The frequency and amplitude of the driver's steering wheel operation are measured to assess the driver's driving burden. The calculation formula is as follows:

[0059]

[0060] Where, δ f [i] is the steering wheel angle at time i, Δt is the time step; ψ i is a weight factor used to measure the importance of different data nodes. The specific value is obtained by experiment and ranges from 0 to 1; busy is the driver burden loss function weight factor, which is used to measure the weight of the driver's steering wheel operation frequency and amplitude. The specific value is obtained by experiment and ranges from 0 to 1; N is the total number of data samples; Softplus is a soft regularization function that makes the loss function smooth and differentiable;

[0061] Vehicle rollover risk loss function L roll Measure the lateral acceleration a y As well as the exceeding of the vehicle roll angle φ, the rollover risk of the vehicle is assessed. The specific calculation formula is as follows:

[0062]

[0063] Where a y [i] is the lateral acceleration at time i, φ[i] is the vehicle roll angle at time i, a y,max is the maximum value of the vehicle's lateral acceleration, φ max is the maximum value of the vehicle roll angle, a y,th is the vehicle's lateral acceleration threshold, φ th is the vehicle roll angle threshold; ψ i is a weight factor used to measure the importance of different data nodes. The specific value is obtained by experiment and ranges from 0 to 1; roll,1 ,λ roll,2 is the weight factor of the vehicle rollover risk loss function, which is used to adjust the vehicle rollover risk loss function Lroll The weight of each item in the equation ranges from 0 to 1; N is the total number of data samples; Softplus is a soft regularization function that makes the loss function smooth and differentiable;

[0064] Vehicle skidding risk loss function L slip Measure the front and rear wheel slip angle α f and α r The over-limit situation is used to assess the side slip risk of the vehicle. The specific calculation formula is as follows:

[0065]

[0066] Where, α f [i] is the front wheel slip angle at time i, α r [i] is the rear wheel slip angle at time i, is the linear interval threshold of the front wheel slip angle, is the linear interval threshold of the rear wheel slip angle, α max is the linear interval threshold of the tire slip angle; ψ i is a weight factor used to measure the importance of different data nodes. The specific value is obtained by experiment and ranges from 0 to 1; slip,1 and λ slip,2 is the vehicle skidding risk loss function L slip Weight factor, used to adjust the vehicle sideslip risk loss function L slip The weight of each item ranges from 0 to 1; N is the total number of data samples; Softplus is a soft regularization function that makes the loss function smooth and differentiable;

[0067] Physical loss function L physics Measure the ratio of the front and rear wheel angles predicted by the neural network x NN and x model The difference between them ensures the basic physical law of the composite mechanism model. The specific calculation formula is as follows:

[0068]

[0069] Where x NN [i] is the predicted value at time i obtained by the neural network, x model [i] is the ideal value of the front and rear wheel angle ratio at time i calculated by the mechanism model, and N is the total number of data samples.

[0070] The loss function calculation module calculates the loss function weighting factor w according to the attention mechanism i , the specific calculation process is as follows:

[0071] First, the driver's driving style factor S dPerform nonlinear mapping to obtain the driving style factor S′ after nonlinear mapping d and high-order transformation driving style factors The specific calculation formula is as follows:

[0072]

[0073]

[0074] Where, is the weight matrix, all obtained through training; is the bias term, all obtained through training; ReLU is the activation function of the first hidden layer, SiLU is the activation function of the second hidden layer, and tanh is the activation function of the third hidden layer; S d is the driver's driving style factor;

[0075] Then the temperature coefficient τ is calculated. The specific calculation formula is as follows:

[0076]

[0077] Where λ1, λ2, and λ3 are weighting coefficients, whose specific values ​​are obtained by experiments and range from 0 to 1; W τ1 、W τ2 is the weight matrix, obtained through training; b τ1 、b τ2 is the bias term, which is obtained through training; SiLU and tanh are activation functions; S′ d is the driving style factor obtained after nonlinear mapping, S d is the driver's driving style factor, It is a high-level driving style factor;

[0078] Then the attention weight The specific calculation formula is as follows:

[0079]

[0080] Where S′ d is the driving style factor obtained after nonlinear mapping, ξ initial is the initial weighting factor of the loss function, and its specific value is obtained based on experiments; Q is the query vector of driving style, which is used to calculate the matching degree between the current driver style and the driving behavior factor; K is the driving behavior characteristic factor, which provides information on historical driving behavior; V is the value vector of the weighting factor of the loss function, which provides the basic weight for dynamic adjustment; W Q 、W K 、W V 、 is the weight matrix, the specific value is obtained according to the experiment, b Q 、b K 、b V 、 is the bias term, and its specific value is obtained according to the experiment. is the attention weight, d k is the normalization factor, τ is the temperature coefficient to prevent the gradient from disappearing; SiLU is the activation function, and Softmax is the normalization function;

[0081] The final loss weighting factor ξ can be calculated from the calculated attention weight i , the calculation formula is as follows:

[0082]

[0083] Where, is the attention weight, and V is the loss function weighting factor value vector.

[0084] The beneficial effects of the present invention are:

[0085] This invention combines a neural network with an attention mechanism to comprehensively analyze vehicle driving status and driver physiological signal data, achieving intelligent vehicle rear wheel steering angle calculation that takes driving style into account, thereby improving vehicle control stability and driving safety. By calculating a driving style factor, this method can classify driver proficiency, enabling more personalized rear wheel steering angle adjustment. Furthermore, the invention incorporates multiple loss functions, including driver operational burden, vehicle rollover risk, vehicle sideslip risk, and physical losses, and uses an attention mechanism to dynamically adjust loss weights. This optimizes rear wheel steering angle calculation under different driving styles and operating conditions, ensuring vehicle safety and comfort in complex driving environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] The present invention will be further described below in conjunction with the accompanying drawings:

[0087] Figure 1 This is a framework diagram of a method for calculating the rear wheel angle of an intelligent vehicle taking driving style into consideration, as proposed by the present invention. DETAILED DESCRIPTION

[0088] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0089] See Figure 1 The method for calculating the rear wheel turning angle of an intelligent vehicle considering driving style according to the present invention includes a driving information collection module, a driving style judgment module, a loss function calculation module, and a rear wheel turning angle calculation module;

[0090] The driving information acquisition module is used to obtain vehicle driving state information and driver's physiological signal information, including vehicle longitudinal speed V x , vehicle lateral acceleration a y , front wheel turning angle δ f , vehicle roll angle φ, front axle slip angle α f , rear axle slip angle α r , vehicle yaw angular velocity ω r , driver's eye movement frequency f eye , pupil diameter d pupil , heart rate variability HRV, skin electrode activity EDA, electromyographic signal EMG, head angle θ head ;

[0091] The driving style judgment module is based on the driving behavior factor and biological data factors Calculate the driver's driving style factor S d , the driver style factor refers to the driver's driving proficiency, where when When the driver is defined as a novice driver, When the driver is defined as an ordinary driver, When the driver is defined as a skilled driver, the specific calculation formula is:

[0092]

[0093] Where, is the driving behavior factor, is the biological data factor;

[0094] The loss function calculation module is based on the driver's operating burden loss function L busy , vehicle rollover risk loss function L roll , Vehicle skidding risk loss function L slip , physical loss function L physics Get the total loss function L of the rear wheel angle calculation module total , the calculation formula is as follows:

[0095]

[0096] Where ξ1, ξ2, and ξ3 are the loss functions L busy 、L roll 、L slip The weighting factor of is calculated by the loss function weighting factor attention mechanism, and the value range is 0 to 1; physicis is the weighting factor of the physical loss function, when λ physicisWhen it approaches 0, the proportion of the physical loss function increases, improving the ability to learn physical laws. physicis When it approaches 1, the proportion of the physical loss function decreases, reducing the ability to learn physical laws; L busy is the driver's control burden loss function, L roll is the vehicle rollover risk loss function, L slip is the vehicle sideslip risk loss function, L physics is the physical loss function;

[0097] The rear wheel angle calculation module calculates the total loss function L according to the calculation total , a deep neural network algorithm is used to determine the ratio R of the vehicle's rear wheel angle to the front wheel angle. When R < 0, the front and rear wheels turn in the same direction; when R > 0, the front and rear wheels turn in opposite directions. The calculation formula is as follows:

[0098] δ r =δ f ·R

[0099] Where, δ f is the front wheel turning angle, R is the ratio of the rear wheel turning angle to the front wheel turning angle;

[0100] The input layer contains 5 nodes, corresponding to the vehicle longitudinal speed V x , vehicle lateral acceleration a y , yaw angular velocity w r , center of mass side slip angle β, front wheel turning angle δ f The hidden layer adopts a three-layer structure, including the first hidden layer, the second hidden layer, and the third hidden layer; the first hidden layer contains 64 neurons, the second hidden layer contains 32 neurons, and the third hidden layer contains 16 neurons; the output layer contains 1 node, and the output is the ratio R of the rear wheel and front wheel steering angles of the vehicle;

[0101] The calculation formula of the rear wheel angle calculation module is:

[0102]

[0103] Where V x is the vehicle's longitudinal speed, a y Vehicle lateral acceleration, w r is the yaw rate, β is the sideslip angle of the center of mass, δ f is the front wheel angle; h1 is the output of the first hidden layer, h2 is the output of the second hidden layer; Swish is the activation of the first hidden layer; ReLU is the activation function of the second hidden layer and the third hidden layer; W1, W2, W3, W4 are weight matrices, all determined through training; b1, b2, b3, b4 are bias terms, all determined through training, W sis the weight matrix from the input layer to the dynamic scaling factor S, b s is the bias term from the input layer to the dynamic scaling factor S; S is the dynamic scaling factor, τ is the scaling weight control factor, and its value range is 0 to 1; tanh is the output layer activation function; Sigmoid is the dynamic scaling factor layer activation function.

[0104]

[0105] Where, L busy is the driver's control burden loss function, L roll is the vehicle rollover risk loss function, L slip is the vehicle sideslip risk loss function; k1 is the adjustment factor of the driver's control burden loss function, k2 is the adjustment factor of the vehicle rollover risk loss function, and k3 is the adjustment factor of the vehicle sideslip risk loss function, which is used to control the sensitivity of each loss item. The specific value is selected according to specific needs; is the normalized biological signal characteristic value, is the eigenvalue calculated using exponentially weighted moving average, The eigenvalues ​​obtained by using Sigmoid nonlinear transformation are used to enhance the stability of biological data factors.

[0106] The driving style judgment module, the normalized biological signal characteristic value Eigenvalues ​​after exponentially weighted moving average calculation Eigenvalues ​​obtained using Sigmoid nonlinear transformation The specific calculation process is as follows:

[0107] First, for different physiological signals, core features are extracted. The specific calculation process is as follows:

[0108] Eye movement frequency f eye The core feature of the eye movement frequency is the instantaneous change rate Δf of the driver eye , information entropy H eye , when the driver's driving behavior is proficient, the information entropy H eye , instantaneous rate of change Δf eye The value of will be smaller, and the information entropy H will be smaller when the driver's driving behavior is unfamiliar. eye , instantaneous rate of change Δf eye The value of will be larger; the calculation formula is as follows:

[0109]

[0110] p i =|FFT(f eye )| 2

[0111] Heye =-∑p i logp i

[0112] Where f eye is the driver's eye movement frequency, FFT(x) is Fourier transform, where x = f eye 、p i is the eye movement frequency f eye The power spectral density of

[0113] Pupil diameter d pupil The core feature is the coefficient of variation CV of pupil diameter pupil , the energy of the high-frequency component of the pupil diameter signal D pupil The pupil diameter of experienced drivers is more stable, and the high-frequency component energy D of the pupil diameter signal in a short period of time pupil , pupil diameter d pupil The fluctuation is small, the pupil diameter of novice drivers changes more dramatically, and the high-frequency component energy D of the pupil diameter signal in a short period of time pupil , pupil diameter d pupil The fluctuation is large, and the calculation formula is as follows:

[0114]

[0115] Where σ pupil is the standard deviation of pupil diameter, μ pupil is the mean pupil diameter, d pupil is the pupil diameter; FFT(x) is the Fourier transform, where x = d pupil 、f c is the lower limit of the high frequency range obtained by Fourier transform, f max The upper limit of the high-frequency range obtained by Fourier transform, the specific value is determined through experiments;

[0116] Standard deviation of pupil diameter σ pupil and the mean pupil diameter μ pupil The calculation formula is as follows:

[0117]

[0118]

[0119] Where d pupil,i is the pupil diameter at the i-th moment, N is the number of pupil diameter samples collected;

[0120] The core characteristic of heart rate variability (HRV) is the ratio of low-frequency to high-frequency power of heart rate variability (HRV). LF / HF , low frequency high frequency power ratio HRV LF / HF When it is higher, the driver's driving behavior is relatively unfamiliar, and the low-frequency and high-frequency power is higher than HRV.LF / HF When it is lower, the driver's driving behavior is more skilled. The calculation formula is as follows:

[0121]

[0122] Where, P LF is the low-frequency power of heart rate variability, P HF is the high frequency power of heart rate variability, HRV is the heart rate variability;

[0123] The core feature of skin electrical activity (EDA) is the skin electrical energy attenuation factor (EDA). decay , skin electrical energy attenuation factor EDA decay When it is larger, the driver is in a state of high tension and high pressure, and the driving behavior is relatively unfamiliar. The skin electrical energy attenuation factor EDA decay When it is small, the driver is in a relaxed state and the driver's driving behavior is relatively skilled. The calculation formula is as follows:

[0124]

[0125] Where EDA(t) is the skin electrical signal value at time t, EDA(t-1) is the skin electrical signal value at time t-1, and λ EDA is the exponential attenuation factor of skin electrical activity, which is used to amplify the drastic changes in skin electrical activity in a short period of time; T is the current sampling time;

[0126] The core feature of the electromyographic signal EMG is the electromyographic signal adaptive power exponential root mean square value EMG adaptive , EMG adaptive power exponential root mean square value adaptive When it is larger, the driver is in a state of high tension and high pressure, and the driving behavior is relatively unfamiliar. The EMG adaptive power exponent root mean square value adaptive When it is small, the driver is in a relaxed state and the driver's driving behavior is relatively skilled. The calculation formula is as follows:

[0127]

[0128] Where, EMG t is the skin electrical signal value at time t, z is the electromyographic signal adaptive power index, σ EMG is the standard deviation of the EMG signal, N is the number of EMG signal samples collected;

[0129] Head angle θ head The characteristic value of the head angle change rate θ stability , head angle change rate θ stability When it is larger, the driver is in a state of high tension and high pressure, and the driving behavior is relatively unfamiliar. The head angle change rate θ stabilityWhen it is small, the driver is in a relaxed state and the driver's driving behavior is relatively skilled. The calculation formula is as follows:

[0130]

[0131] Where θ head (t) is the head angle at time t, μ θ (t) is the sliding mean at time t, ζ1 is the sliding window size, σ θ (t) is the sliding standard deviation at time t, μ θ (t) is the mean value of the driver’s head angle;

[0132] Normalized biological signal feature value Eigenvalues ​​after exponentially weighted moving average calculation Sigmoid nonlinear transformation eigenvalue The instantaneous rate of change of eye movement frequency Δf eye , eye movement frequency f eye Information entropy H eye , coefficient of variation of pupil diameter CV pupil , the energy of the high-frequency component of the pupil diameter signal D pupil , heart rate variability low frequency high frequency power ratio HRV LF / HF , skin electrical energy attenuation factor EDA decay , head angle change rate θ stability Calculated, where X i =[Δf eye ,H eye ,CV pupil ,D pupil ,HRV LF / HF ,EDA decay ,θ stability ], the specific calculation process is as follows:

[0133] Normalized biological signal feature value The biological signal feature value X i Mapping to [0,1] avoids dimensionality issues and ensures comparability between different features. The calculation formula is as follows:

[0134]

[0135] Where, max(X i ) is the biological signal characteristic value X i The maximum value, min(X i ) is the biological signal characteristic value X i The minimum value of

[0136] Eigenvalues ​​after exponentially weighted moving average calculation Use exponential weighted moving average to smooth and reduce the noise effect on the eigenvalue X i To avoid the impact of sharp fluctuations in a short period of time and cause misjudgment, the calculation formula is as follows:

[0137]

[0138] In the formula, ε is the smoothing coefficient, which controls the balance between new data and historical data. When ε is close to 1, it is more dependent on current data and has a faster response speed. When ε is close to 0, it is more dependent on historical data and has a higher degree of smoothing.

[0139] Sigmoid nonlinear transformation eigenvalue Use Sigmoid nonlinear transformation to enhance the stability of data and avoid eigenvalue X i The impact caused by being too large or too small is uneven. The calculation formula is as follows:

[0140]

[0141] Where, is the normalized biological signal feature value.

[0142] The loss function calculation module calculates the driver's control burden loss function L by the following formula: busy , vehicle rollover risk loss function L roll , Vehicle skidding risk loss function L slip and the physical loss function L physics :

[0143] Driver's control burden loss function L busy The frequency and amplitude of the driver's steering wheel operation are measured to assess the driver's driving burden. The calculation formula is as follows:

[0144]

[0145] Where, δ f [i] is the steering wheel angle at time i, Δt is the time step; ψ i is a weight factor used to measure the importance of different data nodes. The specific value is obtained by experiment and ranges from 0 to 1; busy is the driver burden loss function weight factor, which is used to measure the weight of the driver's steering wheel operation frequency and amplitude. The specific value is obtained by experiment and ranges from 0 to 1; N is the total number of data samples; Softplus is a soft regularization function that makes the loss function smooth and differentiable;

[0146] Vehicle rollover risk loss function L roll Measure the lateral acceleration a yAs well as the exceeding of the vehicle roll angle φ, the rollover risk of the vehicle is assessed. The specific calculation formula is as follows:

[0147]

[0148] Where a y [i] is the lateral acceleration at time i, φ[i] is the vehicle roll angle at time i, a y,max is the maximum value of the vehicle's lateral acceleration, φ max is the maximum value of the vehicle roll angle, a y,th is the vehicle's lateral acceleration threshold, φ th is the vehicle roll angle threshold; ψ i is a weight factor used to measure the importance of different data nodes. The specific value is obtained by experiment and ranges from 0 to 1; roll,1 ,λ roll,2 is the weight factor of the vehicle rollover risk loss function, which is used to adjust the vehicle rollover risk loss function L roll The weight of each item in the equation ranges from 0 to 1; N is the total number of data samples; Softplus is a soft regularization function that makes the loss function smooth and differentiable;

[0149] Vehicle skidding risk loss function L slip Measure the front and rear wheel slip angle α f and α r The over-limit situation is used to assess the side slip risk of the vehicle. The specific calculation formula is as follows:

[0150]

[0151] Where, α f [i] is the front wheel slip angle at time i, α r [i] is the rear wheel slip angle at time i, is the linear interval threshold of the front wheel slip angle, is the linear interval threshold of the rear wheel slip angle, α max is the linear interval threshold of the tire slip angle; ψ i is a weight factor used to measure the importance of different data nodes. The specific value is obtained by experiment and ranges from 0 to 1; slip,1 and λ slip,2 is the vehicle skidding risk loss function L slip Weight factor, used to adjust the vehicle sideslip risk loss function L slip The weight of each item ranges from 0 to 1; N is the total number of data samples; Softplus is a soft regularization function that makes the loss function smooth and differentiable;

[0152] Physical loss function L physicsMeasure the ratio of the front and rear wheel angles predicted by the neural network x NN and x model The difference between them ensures the basic physical law of the composite mechanism model. The specific calculation formula is as follows:

[0153]

[0154] Where x NN [i] is the predicted value at time i obtained by the neural network, x model [i] is the ideal value of the front and rear wheel angle ratio at time i calculated by the mechanism model, and N is the total number of data samples.

[0155] The loss function calculation module calculates the loss function weighting factor w according to the attention mechanism i , the specific calculation process is as follows:

[0156] First, the driver's driving style factor S d Perform nonlinear mapping to obtain the driving style factor S after nonlinear mapping d ′ and high-order transformation driving style factors The specific calculation formula is as follows:

[0157]

[0158] Where, is the weight matrix, all obtained through training; is the bias term, all obtained through training; ReLU is the activation function of the first hidden layer, SiLU is the activation function of the second hidden layer, and tanh is the activation function of the third hidden layer; S d is the driver's driving style factor;

[0159] Then the temperature coefficient τ is calculated. The specific calculation formula is as follows:

[0160]

[0161] Where λ1, λ2, and λ3 are weighting coefficients, whose specific values ​​are obtained by experiments and range from 0 to 1; W τ1 、W τ2 is the weight matrix, obtained through training; b τ1 、b τ2 is the bias term, which is obtained through training; SiLU and tanh are activation functions; S d ′ is the driving style factor obtained after nonlinear mapping, S d is the driver's driving style factor, It is a high-level driving style factor;

[0162] Then the attention weight The specific calculation formula is as follows:

[0163]

[0164] Where S d ′ is the driving style factor obtained after nonlinear mapping, ξ initial is the initial weighting factor of the loss function, and its specific value is obtained based on experiments; Q is the query vector of driving style, which is used to calculate the matching degree between the current driver style and the driving behavior factor; K is the driving behavior characteristic factor, which provides information on historical driving behavior; V is the value vector of the weighting factor of the loss function, which provides the basic weight for dynamic adjustment; W Q 、W K 、W V 、 is the weight matrix, the specific value is obtained according to the experiment, b Q 、b K 、b V 、 is the bias term, and its specific value is obtained according to the experiment. is the attention weight, d k is the normalization factor, τ is the temperature coefficient to prevent the gradient from disappearing; SiLU is the activation function, and Softmax is the normalization function;

[0165] The final loss weighting factor ξ can be calculated from the calculated attention weight i , the calculation formula is as follows:

[0166]

[0167] Where, is the attention weight, and V is the loss function weighting factor value vector.

Claims

1. A method for calculating rear wheel turning angle of an intelligent vehicle considering driving style, characterized in that: It includes driving information collection module, driving style judgment module, loss function calculation module, and rear wheel angle calculation module; The driving information acquisition module is used to obtain vehicle driving state information and driver's physiological signal information, including vehicle longitudinal speed , vehicle lateral acceleration , front wheel angle , the vehicle's roll angle , front axle slip angle , rear axle slip angle , vehicle yaw rate , driver's eye movement frequency , pupil diameter , heart rate variability , electrodermal activity , electromyographic signals , head angle ; The driving style judgment module is based on the driving behavior factor and biological data factors Calculate the driver's driving style factor , the driver style factor refers to the driver's driving proficiency, where ,when When the driver is defined as a novice driver, When the driver is defined as an ordinary driver, When the driver is defined as a skilled driver, the specific calculation formula is: ， Where, is the driving behavior factor, is the biological data factor; The loss function calculation module is based on the driver's operating burden loss function , Vehicle rollover risk loss function , Vehicle skidding risk loss function , physical loss function Get the total loss function of the rear wheel angle calculation module , the calculation formula is as follows: ， Where, 、 、 The loss functions are 、 、 The weighting factor of is calculated by the loss function weighting factor attention mechanism, and the value range is arrive ; is the weighting factor of the physical loss function, when When it approaches 0, the proportion of physical loss function increases, which improves the learning ability of physical laws. When it approaches 1, the proportion of the physical loss function decreases, reducing the ability to learn physical laws; is the driver's control burden loss function, is the vehicle rollover risk loss function, is the vehicle sideslip risk loss function, is the physical loss function; The loss function calculation module calculates the loss function weighting factor based on the attention mechanism. The specific calculation process is as follows: First, the driver's driving style factor Perform nonlinear mapping to obtain the driving style factor after nonlinear mapping and high-order transformation driving style factors , the specific calculation formula is as follows: ， ， Where, 、 、 is the weight matrix, all obtained through training; 、 、 is the bias term, all obtained through training; is the activation function of the first hidden layer, is the activation function of the second hidden layer, is the activation function of the third hidden layer; is the driver's driving style factor; Then the temperature coefficient The specific calculation formula is as follows: ， Where, 、 、 is the weighting coefficient, the specific value is obtained by experiment, and the value range is arrive ; 、 is the weight matrix, obtained through training; 、 is the bias term, all obtained through training; 、 is the activation function; is the driving style factor obtained after nonlinear mapping, is the driver's driving style factor, It is a high-level driving style factor; Then the attention weight The specific calculation formula is as follows: ， Where, is the driving style factor obtained after nonlinear mapping, is the initial weighting factor of the loss function, and its specific value is obtained based on experiments; is the query vector of driving style, which is used to calculate the matching degree between the current driver style and driving behavior factors. It is a driving behavior characteristic factor, providing historical driving behavior information, A vector of weighted factor values ​​for the loss function, providing basic weights for dynamic adjustment; 、 、 、 is the weight matrix, and its specific value is obtained according to the experiment. 、 、 、 is the bias term, and its specific value is obtained according to the experiment. is the attention weight, is the normalization factor, is the temperature coefficient, which prevents the gradient from disappearing; is the activation function, is the normalization function; The final loss weighting factor can be calculated from the calculated attention weight , the calculation formula is as follows: ， Where, is the attention weight, is the loss function weighting factor value vector; The rear wheel angle calculation module calculates the total loss function according to the calculation , using a deep neural network algorithm to determine the ratio of the vehicle's rear wheel angle to the front wheel angle ,in When the front and rear wheels turn in the same direction, When the front and rear wheels turn in opposite directions, the calculation formula is as follows: ， Where, is the front wheel angle, is the ratio of the rear wheel angle to the front wheel angle; The input layer contains 5 nodes, corresponding to the longitudinal speed of the vehicle , vehicle lateral acceleration , yaw angular velocity , center of mass side slip angle , front wheel angle The hidden layer adopts a three-layer structure, including the first hidden layer, the second hidden layer, and the third hidden layer; the first hidden layer contains 64 neurons, the second hidden layer contains 32 neurons, and the third hidden layer contains 16 neurons; the output layer contains 1 node, and the output is the ratio of the vehicle's rear wheel to front wheel steering angle ; The calculation formula of the rear wheel angle calculation module is: ， In the formula is the vehicle's longitudinal speed, Vehicle lateral acceleration, is the yaw angular velocity, is the sideslip angle of the center of mass, is the front wheel turning angle; is the output of the first hidden layer, is the output of the second hidden layer; Activation for the first hidden layer; Activation functions for the second and third hidden layers; 、 、 、 is the weight matrix, which is determined through training; 、 、 、 is the bias term, which is determined through training. The dynamic scaling factor for the input layer The weight matrix, The dynamic scaling factor for the input layer The bias term; is the dynamic scaling factor, is the scaling weight control factor, and its value range is arrive ; is the output layer activation function; is the dynamic scaling factor layer activation function.

2. The method for calculating rear wheel turning angle of an intelligent vehicle considering driving style according to claim 1, characterized in that: The driving style judgment module calculates the driving behavior factor by the following formula and biological data factors : ， ， Where, is the driver's control burden loss function, is the vehicle rollover risk loss function, is the vehicle sideslip risk loss function; is the adjustment factor of the driver's control burden loss function, is the adjustment factor of the vehicle rollover risk loss function, It is the adjustment factor of the vehicle sideslip risk loss function, which is used to control the sensitivity of each loss item. The specific value is selected according to specific needs; is the normalized biological signal characteristic value, is the eigenvalue calculated using exponentially weighted moving average, To adopt The eigenvalues ​​obtained by nonlinear transformation enhance the stability of biological data factors.

3. The method for calculating rear wheel angle of an intelligent vehicle considering driving style according to claim 1, characterized in that: The driving style judgment module, the normalized biological signal characteristic value , the eigenvalue after exponentially weighted moving average calculation ,use Eigenvalues ​​obtained by nonlinear transformation , the specific calculation process is as follows: First, for different physiological signals, core features are extracted. The specific calculation process is as follows: Eye movement frequency The core feature of the eye movement frequency is the instantaneous rate of change of the driver's eye movement frequency. , information entropy The calculation formula is as follows: ， ， ， In the formula is the driver's eye movement frequency, is the Fourier transform, where 、 Eye movement frequency The power spectral density of pupil diameter The core feature is the coefficient of variation of pupil diameter , pupil diameter signal high frequency component energy ; The calculation formula is as follows: ， In the formula is the standard deviation of pupil diameter, is the mean pupil diameter, is the pupil diameter; is the Fourier transform, where 、 is the lower limit of the high frequency range obtained by Fourier transform, The upper limit of the high-frequency range obtained by Fourier transform, the specific value is determined through experiments; Standard deviation of pupil diameter and the mean pupil diameter The calculation formula is as follows: ， ， In the formula For the Pupil diameter at the moment, is the number of pupil diameter samples collected; Heart rate variability The core feature is the low-frequency and high-frequency power ratio of heart rate variability , the calculation formula is as follows: ， ， ， Where, is the low-frequency power of heart rate variability, is the high frequency power of heart rate variability, is heart rate variability; Electrodermal activity The core feature is the skin electrical energy attenuation factor , the calculation formula is as follows: ， Where, for Skin electrical signal value at the moment, for Skin electrical signal value at the moment, is the exponential attenuation factor of skin electrical activity, which is used to amplify the drastic changes in skin electrical activity in a short period of time. is the current sampling time; electromyographic signals The core feature is the root mean square value of the adaptive power exponent of the electromyographic signal , the calculation formula is as follows: ， ， Where, is the skin electrical signal value at time t, is the adaptive power exponent of the electromyographic signal, is the standard deviation of the electromyographic signal, is the number of collected EMG signal samples; Head angle The characteristic value of the head angle change rate , the calculation formula is as follows: ， ， Where, for Head angle at the moment, for The sliding mean of the time is the sliding window size, for The sliding standard deviation of the moment, is the mean of the driver’s head angle; Normalized biological signal feature value , the eigenvalue after exponentially weighted moving average calculation 、 Nonlinear transformation eigenvalue The instantaneous rate of change of eye movement frequency , eye movement frequency Information entropy , coefficient of variation of pupil diameter , pupil diameter signal high frequency component energy , heart rate variability low frequency high frequency power ratio , Skin electrical energy attenuation factor , head angle change rate Calculated, where , the specific calculation process is as follows: Normalized biological signal feature value , the biological signal feature value Map to To avoid dimensionality problems and ensure comparability between different features, the calculation formula is as follows: ， Where, is the biological signal characteristic value The maximum value of is the biological signal characteristic value The minimum value of Eigenvalues ​​after exponentially weighted moving average calculation , use exponential weighted moving average to smooth and reduce the noise impact on the eigenvalue To avoid the impact of sharp fluctuations in a short period of time and cause misjudgment, the calculation formula is as follows: ， Where, is the smoothing coefficient, which controls the balance between new data and historical data. , When it is close to 1, it is more dependent on the current data and responds faster. When it is close to 0, it is more dependent on historical data and has a higher degree of smoothing; Nonlinear transformation eigenvalue ,use Nonlinear transformation, enhance data stability, avoid eigenvalue The impact caused by being too large or too small is uneven. The calculation formula is as follows: ， Where, is the normalized biological signal feature value.

4. The method for calculating rear wheel angle of an intelligent vehicle considering driving style according to claim 1, characterized in that: The loss function calculation module calculates the driver's control burden loss function by the following formula: , Vehicle rollover risk loss function , Vehicle skidding risk loss function and physical loss function : Driver's control burden loss function The frequency and amplitude of the driver's steering wheel operation are measured to assess the driver's driving burden. The calculation formula is as follows: ， Where, for Steering wheel angle at the moment, is the time step; is a weight factor used to measure the importance of different data nodes. The specific value is obtained by experiment and the value range is arrive ; is the driver burden loss function weight factor, which is used to measure the weight of the driver's steering wheel operation frequency and amplitude. The specific value is obtained by experiment and the value range is arrive ; is the total number of data samples; is a soft regularization function that makes the loss function smooth and differentiable; Vehicle rollover risk loss function Measuring lateral acceleration and vehicle roll angle The overload situation of the vehicle is evaluated to assess the rollover risk of the vehicle. The specific calculation formula is as follows: ， Where, for The lateral acceleration at the moment for The vehicle roll angle at the moment is the maximum value of the vehicle's lateral acceleration, is the maximum value of the vehicle roll angle, is the vehicle's lateral acceleration threshold, is the vehicle roll angle threshold; is a weight factor used to measure the importance of different data nodes. The specific value is obtained by experiment and the range is arrive ; 、 is the weight factor of the vehicle rollover risk loss function, which is used to adjust the vehicle rollover risk loss function The weight of each item in the range is arrive ; is the total number of data samples; is a soft regularization function that makes the loss function smooth and differentiable; Vehicle skidding risk loss function Measure the front and rear wheel slip angles and The over-limit situation is used to assess the side slip risk of the vehicle. The specific calculation formula is as follows: ， Where, for The front wheel slip angle at the moment for The rear wheel slip angle at the moment is the linear interval threshold of the front wheel slip angle, is the linear interval threshold of the rear wheel slip angle, is the linear interval threshold of the tire slip angle; is a weight factor used to measure the importance of different data nodes. The specific value is obtained by experiment and the range is arrive ; and is the vehicle skidding risk loss function Weight factor, used to adjust the vehicle skidding risk loss function The weight of each item ranges from arrive ; is the total number of data samples; is a soft regularization function that makes the loss function smooth and differentiable; Physical loss function Measures the ratio of the front and rear wheel angles predicted by the neural network and The difference between them ensures the basic physical law of the composite mechanism model. The specific calculation formula is as follows: ， Where, Predicted by the neural network Time prediction value, is calculated by the mechanism model The ideal value of the front and rear wheel angle ratio at the moment, is the total number of data samples.

Images