Trajectory tracking system and method for four-wheel independent steering vehicle under ice and snow covered pavement

Abstract

The invention discloses a trajectory tracking system and method for a four-wheel independent steering vehicle under an ice and snow covered pavement, and the method comprises the steps: collecting ice and snow covered pavement information data and vehicle driving state parameter data in the vehicle driving process, and obtaining the adhesion coefficients of four wheels of the four-wheel independent steering vehicle; performing four-wheel tire cornering stiffness estimation on the four-wheel independent steering vehicle; establishing an actual system model, and determining an input quantity and an output quantity of trajectory tracking control; and combining the optimal nominal system model control law with the pipeline control law to form final control input of an actual system model, thereby realizing trajectory tracking of the four-wheel independent steering vehicle on the ice and snow covered pavement. By combining the optimal nominal system model control law and the pipeline control law, the trajectory tracking control of the four-wheel independent steering vehicle is realized under the uncertainty that the snow depth degree of the four-wheel independent steering vehicle is not uniform on the road surface.

Description

Technical Field

[0001] The invention belongs to the technical field of automobile wire-controlled chassis, and in particular relates to a trajectory tracking system and method for a four-wheel independent steering vehicle on an icy and snowy road. Background Art

[0002] Four-wheel independent steering (4WIS) vehicles can independently control the angle of each wheel through electrical signals, providing a new optimal steering platform for intelligent driving. The vehicle's trajectory tracking control is not only of great significance to improving vehicle safety and passenger comfort, but also helps to maintain the stability of the vehicle, enabling the vehicle to make adaptive adjustments to the dynamic changes in the driving environment. With the popularization of autonomous driving and advanced driver assistance systems (ADAS), it has become an inevitable trend for four-wheel independent steering vehicles to become the mainstream steering platform. Compared with traditional steering vehicles, four-wheel independent steering vehicles have the characteristic of being able to individually control the turning angle of each wheel. They can not only accurately control the vehicle's motion trajectory to the greatest extent, but also cope with the dynamic changes of various driving environments and improve the accuracy of trajectory tracking.

[0003] Under icy and snowy road conditions, the trajectory tracking performance of the four-wheel independent steering vehicle is reduced due to the uncertainty of the road conditions, including the uncertainty of the adhesion coefficient of the four wheels and the uncertainty caused by the uneven depth of snow on the road. Therefore, it is urgent to carry out trajectory tracking control of four-wheel independent steering vehicles under icy and snowy roads.

[0004] The Chinese invention patent application number is CN202310480148.9, and the name is "Vehicle trajectory tracking control system based on parameter uncertainty and yaw stability". It proposes a method that combines commonly used low-cost vehicle-mounted sensors with mathematical models to estimate the vehicle's yaw angular velocity and longitudinal velocity. After applying yaw stability control in the lateral LQR controller, the path tracking accuracy is greatly improved; but this patent only considers its own modeling uncertainty, ignores the uncertainty of the external environment, and increases the trajectory tracking error. The Chinese invention patent application number is CN201710146567.3, and the name is "An unmanned vehicle extreme dynamics trajectory tracking control system". An unmanned vehicle extreme dynamics trajectory tracking control system is proposed, and the control system includes: a sensor module, a speed file solving module, and a calculation control module. For the trajectory tracking problem of a known path, the extreme driving behavior of the unmanned vehicle can be realized, so that it can complete the trajectory tracking process at the fastest speed; this patent only considers the extreme nature of its own model, and does not combine it with the driving environment, which increases the danger of vehicle driving.

[0005] The existing trajectory tracking control often ignores the influence of road conditions in the driving environment, especially under icy and snowy road conditions. Due to the structural characteristics of the four-wheel independent steering vehicle, each wheel is a separate control unit, so the icy and snowy road causes uncertainty in the adhesion coefficient of the four wheels, which brings uncertainty in the cornering stiffness of the four-wheel tires, as well as uncertainty caused by the uneven depth of snow on the road, affecting the accuracy of vehicle trajectory tracking. Therefore, the trajectory tracking method that copes with the uncertainty of road conditions on icy and snowy roads has a good application prospect. Summary of the invention

[0006] In view of the above-mentioned deficiencies in the prior art, an object of the present invention is to provide a trajectory tracking system and method for a four-wheel independently steered vehicle on icy and snowy roads, so as to solve the problem that the prior art ignores the driving environment of the vehicle on icy and snowy roads, resulting in uncertainty in the lateral stiffness of the four-wheel tires of the four-wheel independently steered vehicle, as well as the uncertainty caused by the uneven depth of snow on the road, thus making it impossible to accurately track the trajectory of the four-wheel independently steered vehicle.

[0007] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0008] A trajectory tracking system for a four-wheel independent steering vehicle on an icy and snowy road of the present invention comprises: a four-wheel tire cornering stiffness estimation unit and a trajectory tracking control unit;

[0009] The four-wheel tire cornering stiffness estimation unit includes: an ice and snow road environment data acquisition module, a vehicle driving state parameter acquisition module and an estimation module;

[0010] The icy and snowy road environment data acquisition module is used to collect icy and snowy road information data and obtain the adhesion coefficients of the four wheels of the four-wheel independent steering vehicle;

[0011] A vehicle driving state parameter acquisition module is used to collect vehicle driving state parameter data;

[0012] An estimation module, used to estimate the cornering stiffness of the four-wheel tires by using the adhesion coefficients of the four wheels and the vehicle driving state parameter data;

[0013] The trajectory tracking control unit includes: a nominal system module, an actual system module, a pipeline construction module and a control module;

[0014] A nominal system module is used to establish a nominal system model according to the estimated results of the cornering stiffness of the four-wheel tires and output the control law of the nominal system model;

[0015] The actual system module is used to establish the actual system model based on the nominal system model and the uncertainty caused by the uneven depth of snow on the road surface;

[0016] The pipeline construction module is used to generate a pipeline with the trajectory of the nominal system model as the center and combined with the uncertainty of the icy and snowy road conditions to ensure that the trajectory of the actual system model remains within the pipeline under the influence of the uncertainty caused by the uneven depth of snow on the road surface, and output the pipeline control law;

[0017] The control module is used to form the final control input of the actual system model according to the nominal system model control law and the pipeline control law to minimize the trajectory tracking error.

[0018] Furthermore, the icy and snowy road environment data acquisition module is a road detection sensor.

[0019] Furthermore, the vehicle driving state parameter acquisition module includes: a lateral acceleration sensor, a yaw angular acceleration sensor, a wheel angle sensor, a longitudinal velocity sensor, a center of mass sideslip angle sensor and a yaw angular velocity sensor.

[0020] Furthermore, the vehicle driving state parameter data includes: vehicle lateral acceleration, yaw angular acceleration, wheel angle, longitudinal speed, center of mass sideslip angle, yaw angular velocity, wherein the wheel angle includes left front wheel angle, left rear wheel angle, right front wheel angle, and right rear wheel angle.

[0021] Furthermore, the nominal system module establishes a nominal system model, and based on the established nominal system model, establishes a cost function with the goal of minimizing the tracking error, obtains the optimal nominal system model control sequence, takes the first item of the sequence, and outputs the optimal nominal system model control law.

[0022] Furthermore, the actual system module establishes an actual system model. Compared with the nominal system model, the actual system model includes the uncertainty of uneven snow depth on the road surface. The input and output of the trajectory tracking control are determined through the actual system model.

[0023] Furthermore, the pipeline construction module is used to define the uncertainty of icy and snowy road conditions and generate pipelines, and output pipeline control laws.

[0024] Furthermore, the uncertainty definition of the icy and snowy road condition describes the possible range of deviations from the nominal system model, representing the uncertainty of uneven snow depth on the road surface.

[0025] Further, the generation of the pipeline represents the allowable deviation range centered on the trajectory of the nominal system model.

[0026] Furthermore, the pipeline construction module ensures that the trajectory of the actual system model remains within the generated pipeline under the influence of the uncertainty of uneven snow depth on the road surface through the pipeline control law output.

[0027] Furthermore, the control module combines the optimal nominal system model control law and the pipeline control law to form a final control input of the actual system model for trajectory tracking of a four-wheel independent steering vehicle on icy and snowy roads.

[0028] A trajectory tracking method for a four-wheel independent steering vehicle on an icy and snowy road of the present invention is based on the above system and comprises the following steps:

[0029] 1) Collecting icy and snowy road information data and vehicle driving status parameter data during vehicle driving, and using the icy and snowy road information data to obtain the adhesion coefficients of the four wheels of the four-wheel independent steering vehicle;

[0030] 2) The adhesion coefficients of the four wheels and the vehicle driving state parameter data are used as the input of the bidirectional long short-term memory neural network to estimate the cornering stiffness of the four-wheel tires of the four-wheel independent steering vehicle;

[0031] 3) A nominal system model is established based on the estimation results of the cornering stiffness of the four-wheel tires, and the optimal nominal system model control law is output. Based on the nominal system model and the uncertainty of the uneven depth of snow on the road during vehicle driving, an actual system model is established to determine the input and output of trajectory tracking control;

[0032] 4) Taking the trajectory of the nominal system model as the center and combining the uncertainty of icy and snowy road conditions, a pipeline is generated and the pipeline control law is output; the optimal nominal system model control law and the pipeline control law are combined to form the final control input of the actual system model, thus realizing the trajectory tracking of the four-wheel independent steering vehicle on icy and snowy roads.

[0033] Furthermore, the vehicle driving state parameter data in step 1) includes: vehicle lateral acceleration, yaw angular acceleration, wheel angle, longitudinal speed, center of mass sideslip angle, yaw angular velocity, wherein the wheel angle includes left front wheel angle, left rear wheel angle, right front wheel angle, and right rear wheel angle.

[0034] Furthermore, in the step 1), a road detection sensor is used to take a picture to obtain image information of the road ahead, and the image information is used to compare road conditions under different adhesion coefficients to obtain the adhesion coefficients of the four wheels.

[0035] Furthermore, the bidirectional long short-term memory neural network in step 2) includes: an input gate, a forget gate, and an output gate; the input gate includes a forward input gate and a reverse input gate;

[0036] The forward input gate combines the immediate impact of the current icy and snowy road conditions on the cornering stiffness of the four-wheel tires with the impact of the icy and snowy road conditions over a longer period of time on the cornering stiffness of the four-wheel tires, adds or deletes the information on the changes in the cornering stiffness of the four-wheel tires, and adds a reverse input gate to obtain the missed adhesion coefficient or driving status parameter data under icy and snowy roads; the forget gate is used to control the deletion of the redundant adhesion coefficient or driving status parameter data of the four wheels, and finally outputs them through the output gate.

[0037] Furthermore, the specific steps of estimating the cornering stiffness of the four-wheel tires in step 2) are as follows:

[0038] 21) When the conditions of the icy and snowy road surface change during the vehicle's driving, the forget gate forgets the adhesion coefficients of the four wheels or the vehicle's driving state parameter data at the previous moment, re-inputs the current adhesion coefficients and driving state parameter data of the four wheels, and updates the output of the forget gate;

[0039] 22) The forward input gate uses the adhesion coefficients of the four wheels to adjust the influence weights of the adhesion coefficients and driving state parameter data of the four wheels, and obtains the adhesion coefficient data or driving state parameter data missed on the icy and snowy road through the reverse input gate to update the input of the bidirectional long short-term memory neural network;

[0040] 23) According to the input of the forget gate and the bidirectional long short-term memory neural network, the adhesion coefficient and driving state parameter data accumulation of the four wheels estimated by the four-wheel tire cornering stiffness at the current moment are updated;

[0041] 24) Update the current output of the output gate, combine the adhesion coefficient and driving state parameter data accumulation of the four wheels at the current moment, and output the memory and processing state of the four-wheel tire cornering stiffness at the current moment;

[0042] 25) The bidirectional long short-term memory neural network outputs the cornering stiffness of the four-wheel tires of a four-wheel independent steering vehicle.

[0043] Furthermore, in step 21), the lateral acceleration a of the vehicle is selected y , yaw angular acceleration Left

[0044] Front wheel turning angle δ lf 、Left rear wheel turning angle δ lr , right front wheel turning angle δ rf , right rear wheel turning angle δ rr , longitudinal speed v x , sideslip angle β, yaw rate ω, left front wheel adhesion coefficient u lf , left rear wheel adhesion coefficient u lr , right front wheel adhesion coefficient u rf and the right rear wheel adhesion coefficient u rr, as the input of the bidirectional long short-term memory neural network, the expression is as follows:

[0045]

[0046] The output of the forget gate is expressed as:

[0047] f (t) =σ(W f h (t-1) +U f x0 (t) +b f )

[0048] Among them, f (t) is the output of the forget gate, σ is the activation function, h (t-1) is the memory and processing state of the adhesion coefficient data and driving state parameter data of the four wheels at time t-1, x0 (t) is the input of the positive input gate at time t, W f , U f is the weight coefficient of the forget gate, b f is the bias value of the forget gate.

[0049] Furthermore, in step 22), the adhesion coefficient data or driving state parameter data missing on the icy and snowy road are obtained through the reverse input gate, x (t) is the input of the bidirectional long short-term memory neural network at time t, and the expression is as follows:

[0050] x (t) =x0 (t) +x n (t)

[0051] Among them, x n (t) represents the missing adhesion coefficient or driving state parameter data, which is the input of the reverse input gate at time t.

[0052] Furthermore, the input of updating the bidirectional long short-term memory neural network in step 22) includes two parts. The first part is outputting i through the activation function σ (t) The second part is to output the temporary estimated value a of the four-wheel tire cornering stiffness through the activation function tanh (t) , the input of the bidirectional long short-term memory neural network is expressed as:

[0053]

[0054] Among them, i (t) Represents the first part of the input, a (t) represents the temporary estimated value of the four-wheel tire cornering stiffness, W i is the weight coefficient of the adhesion coefficient of the four wheels, U iis the weight coefficient of the driving state parameter data, by adjusting W i and U i Update input, W a , U a is the weight coefficient of feature extraction, b i is the input bias value, b a is the bias value for feature extraction.

[0055] Furthermore, in step 23), the adhesion coefficient and driving state parameter data accumulation C of the four wheels are updated. (t) , C (t) Determined by the forget gate and the input, the expression is as follows:

[0056] C (t) =C (t-1) ⊙f (t) +i (t) ⊙a (t)

[0057] Where ⊙ is the Hadamard product.

[0058] Furthermore, in step 24), the current output O of the output gate is updated. (t) The memory and processing state h of the adhesion coefficient data and driving state parameter data of the four wheels at time t-1 (t-1) and the input x of the bidirectional long short-term memory neural network at time t (t) Obtained through the activation function σ, the output of the output gate is expressed as:

[0059] O (t) =σ(W o h (t-1) +U o x (t) +b o )

[0060] Among them, W o , U o is the weight coefficient of the output gate, b o is the bias value of the output gate.

[0061] Furthermore, the memory and processing state h of the adhesion coefficient data and driving state parameter data of the four wheels at the current moment are output in step 24). (t) ,h (t) It is determined by the product of two parts. The first part is the output O of the output gate obtained by the activation function σ (t) The second part is C obtained by the activation function tanh (t) , expressed as:

[0062] h (t) =O (t)⊙tanh(C t ).

[0063] Furthermore, the output of the four-wheel tire cornering stiffness Output of the four-wheel independent steering vehicle in step 25) is expressed as:

[0064] Output:{C lf ,C lr ,C rf ,C rr}=σ(Vh (t) +c)

[0065] Among them, V is the weight matrix that connects the memory and processing state and output of the adhesion coefficient data and driving state parameter data of the four wheels, c is the bias term added to the weighted sum, and C lf is the cornering stiffness of the left front wheel, C lr is the cornering stiffness of the left rear wheel, C rf is the cornering stiffness of the right front wheel, C rr is the cornering stiffness of the right rear wheel.

[0066] Furthermore, the specific steps of step 3) are as follows:

[0067] 31) Establish a nominal system model based on the estimation results of the cornering stiffness of the four-wheel tires, obtain the optimal nominal system model control sequence by generating a cost function, take the first item of the sequence, and output the optimal nominal system model control law;

[0068] 32) Based on the nominal system model and the uncertainty of the uneven depth of snow on the road, the actual system model is established to determine the input and output of trajectory tracking control.

[0069] Furthermore, the nominal system model in step 31) is as follows:

[0070]

[0071] in, is the trajectory of the nominal system model, is the deviation between the nominal system model output and the actual system model output, is the deviation between the nominal system model input and the actual system model input, A is the state matrix containing the cornering stiffness of the four-wheel tires, and B is the input matrix containing the cornering stiffness of the four-wheel tires.

[0072] Furthermore, the cost function in step 31) is defined as:

[0073]

[0074] Among them, the objective function constraint is U is the constraint of the function, As an additional mandatory constraint, the constant N p and N c represents the prediction range and control range; k represents the time, and are the weighted diagonal matrices of state variables and input variables, respectively, is the state dimension, is the input dimension; the relaxation factor ε and the weighting coefficient κ are used to balance the constraints and avoid infeasible optimization problems caused by the constraints; when the constraints are exceeded, the relaxation variable ε becomes positive and expands the nominal system model input constraints otherwise, the slack variable ε is set to 0.

[0075] Furthermore, the optimal nominal system model control law in step 31) is expressed as:

[0076]

[0077] Among them, U * (k) is the optimal nominal system model control sequence, is the optimal control law of the nominal system model; the corresponding optimal trajectory of the nominal system model is The cost function is J * (k).

[0078] Furthermore, the actual system model in step 32) is expressed as:

[0079]

[0080] Where μ is the input of trajectory tracking control, μ=(δ lf ,δ lr ,δ rf ,δ rr ) T , is the output of trajectory tracking control, is the heading angle of the four-wheel independent steering vehicle, Y is the lateral position of the four-wheel independent steering vehicle, v x is the longitudinal velocity of the four-wheel independent steering vehicle, ω is the yaw angular velocity of the four-wheel independent steering vehicle, Represents the uncertainty impact of uneven snow depth on the road.

[0081] Furthermore, the specific steps of step 4) are as follows:

[0082] 41) Define the uncertainty caused by uneven snow depth on the road surface;

[0083] 42) generating a pipeline centered on the trajectory of the nominal system model based on the uncertainty;

[0084] 43) Design the pipeline control law, and output the pipeline control law so that the trajectory of the actual system model remains within the generated pipeline;

[0085] 44) Combine the optimal nominal system model control law and the pipeline control law to form the final control input of the actual system model.

[0086] Furthermore, the uncertainty caused by the uneven depth of snow on the road surface in step 41) The expression is as follows:

[0087]

[0088] Among them, ∈(k) is the error between the nominal system model and the actual system model, and η(k) represents the pipeline control law.

[0089] Furthermore, in step 42), the pipeline Ω centered on the trajectory of the nominal system model tube The expression is as follows:

[0090]

[0091] Among them, C e is a constant matrix, The maximum range representing the uncertainty of uneven snow depth on the road.

[0092] Furthermore, the pipeline control law expression in step 43) is as follows:

[0093]

[0094] Where η(k) is the pipeline control law; t represents the current moment; represents the uncertainty of the uneven snow depth on the road surface; λ represents the pipeline parameter, which determines the range of deviation from the nominal system model.

[0095] Furthermore, the final control input expression of the actual system model in step 44) is:

[0096]

[0097] in, is the optimal nominal system model control law, η(k) is the pipeline control law, It is the final control input of the actual system model.

[0098] Beneficial effects of the present invention:

[0099] The present invention aims at the characteristic of independent wheel states of four-wheel independent steering vehicles, estimates the adhesion coefficients of the four wheels, accurately judges the change of road surface information through the information forgetting of the forgetting gate of the long-short time memory neural network, and obtains the adhesion coefficient or driving state parameter data missed on icy and snowy roads by adding a bidirectional long-short time memory neural network, avoids the road surface information retained by the forgetting gate, ensures the accurate capture of the adhesion coefficient information of icy and snowy roads, prevents the estimated road surface information from being missed due to the uncertainty of the adhesion coefficients of the four wheels, and effectively improves the estimation result of the cornering stiffness of the four-wheel tires.

[0100] The present invention establishes a nominal system model through the estimation results of the cornering stiffness of the four-wheel tires, and obtains the optimal control law of the nominal system model, so that the four-wheel independent steering vehicle can achieve accurate trajectory tracking under the uncertainty of the adhesion coefficient of the four wheels on icy and snowy roads; a pipeline is constructed to minimize the difference between the trajectory of the actual system model and the trajectory of the nominal system model, helping the actual system model to keep up with the nominal system model, which not only achieves robustness but also effectively improves the trajectory tracking accuracy.

[0101] The present invention combines the optimal nominal system model control law and the pipeline control law to enable the four-wheel independent steering vehicle to achieve trajectory tracking control under the uncertainty of uneven snow depth on the road surface. BRIEF DESCRIPTION OF THE DRAWINGS

[0102] Figure 1 It is a structural diagram of the system of the present invention.

[0103] Figure 2 Flow chart of the method of the present invention.

[0104] Figure 3 The figure is a flow chart of estimating the cornering stiffness of four-wheel tires in the present invention. DETAILED DESCRIPTION

[0105] In order to facilitate the understanding of those skilled in the art, the present invention is further described below in conjunction with embodiments and drawings. The contents mentioned in the implementation modes are not intended to limit the present invention.

[0106] Reference Figure 1 As shown, a trajectory tracking system for a four-wheel independent steering vehicle on an icy and snowy road of the present invention comprises: a four-wheel tire cornering stiffness estimation unit and a trajectory tracking control unit;

[0107] The four-wheel tire cornering stiffness estimation unit includes: an icy and snowy road environment data acquisition module, a vehicle driving state parameter acquisition module and an estimation module; the icy and snowy road environment data acquisition module is a road detection sensor.

[0108] The icy and snowy road environment data acquisition module is used to collect icy and snowy road information data and obtain the adhesion coefficients of the four wheels of the four-wheel independent steering vehicle;

[0109] A vehicle driving state parameter acquisition module is used to collect vehicle driving state parameter data; the vehicle driving state parameter acquisition module includes: a lateral acceleration sensor, a yaw angular acceleration sensor, a wheel angle sensor, a longitudinal velocity sensor, a center of mass sideslip angle sensor and a yaw angular velocity sensor;

[0110] Among them, the vehicle driving state parameter data include: vehicle lateral acceleration, yaw angular acceleration, wheel angle, longitudinal speed, center of mass sideslip angle, yaw angular velocity, and the wheel angle includes the left front wheel angle, left rear wheel angle, right front wheel angle, and right rear wheel angle.

[0111] An estimation module, used to estimate the cornering stiffness of the four-wheel tires by using the adhesion coefficients of the four wheels and the vehicle driving state parameter data;

[0112] The trajectory tracking control unit includes: a nominal system module, an actual system module, a pipeline construction module and a control module;

[0113] A nominal system module is used to establish a nominal system model according to the estimated results of the cornering stiffness of the four-wheel tires and output the control law of the nominal system model;

[0114] The actual system module is used to establish the actual system model based on the nominal system model and the uncertainty caused by the uneven depth of snow on the road surface;

[0115] The pipeline construction module is used to generate a pipeline with the trajectory of the nominal system model as the center and combined with the uncertainty of the icy and snowy road conditions to ensure that the trajectory of the actual system model remains within the pipeline under the influence of the uncertainty caused by the uneven depth of snow on the road surface, and output the pipeline control law;

[0116] The control module is used to form the final control input of the actual system model according to the nominal system model control law and the pipeline control law to minimize the trajectory tracking error.

[0117] Among them, the nominal system module establishes a nominal system model, and according to the established nominal system model, establishes a cost function with the goal of minimizing the tracking error, obtains the optimal nominal system model control sequence, takes the first item of the sequence, and outputs the optimal nominal system model control law.

[0118] Among them, the actual system module establishes an actual system model. Compared with the nominal system model, the actual system model contains the uncertainty of uneven snow depth on the road surface. The input and output of trajectory tracking control are determined through the actual system model.

[0119] The pipeline construction module is used to define the uncertainty of icy and snowy road conditions and generate pipelines, and output pipeline control laws.

[0120] The uncertainty definition of icy and snowy road conditions describes the possible range of deviations from the nominal system model, and represents the uncertainty of uneven snow depth on the road surface.

[0121] The generation of the pipeline represents the allowable deviation range centered on the trajectory of the nominal system model.

[0122] The pipeline construction module outputs the pipeline control law to ensure that the trajectory of the actual system model remains within the generated pipeline under the influence of the uncertainty of uneven snow depth on the road surface.

[0123] The control module combines the optimal nominal system model control law and the pipeline control law to form the final control input of the actual system model for trajectory tracking of a four-wheel independent steering vehicle on icy and snowy roads.

[0124] Reference Figure 2 As shown, a trajectory tracking method of a four-wheel independent steering vehicle on an icy and snowy road of the present invention is based on the above system, and the steps are as follows:

[0125] 1) Collecting icy and snowy road information data and vehicle driving status parameter data during vehicle driving, and using the icy and snowy road information data to obtain the adhesion coefficients of the four wheels of the four-wheel independent steering vehicle;

[0126] The vehicle driving status parameter data include: vehicle lateral acceleration, yaw angular acceleration, wheel angle, longitudinal speed, center of mass sideslip angle, yaw angular velocity, among which the wheel angle includes left front wheel angle, left rear wheel angle, right front wheel angle, and right rear wheel angle.

[0127] Wherein, in said step 1), a road detection sensor is used to take a picture to obtain image information of the road ahead, and the image information is used to compare the road surface conditions under different adhesion coefficients to obtain the adhesion coefficients of the four wheels.

[0128] 2) The adhesion coefficients of the four wheels and the vehicle driving state parameter data are used as the input of the bidirectional long short-term memory neural network to estimate the cornering stiffness of the four-wheel tires of the four-wheel independent steering vehicle;

[0129] The bidirectional long short-term memory neural network includes: an input gate, a forget gate, and an output gate; the input gate includes a forward input gate and a reverse input gate;

[0130] The forward input gate combines the immediate impact of the current icy and snowy road conditions on the cornering stiffness of the four-wheel tires with the impact of the icy and snowy road conditions over a longer period of time on the cornering stiffness of the four-wheel tires, adds or deletes the information on the changes in the cornering stiffness of the four-wheel tires, and adds a reverse input gate to obtain the missed adhesion coefficient or driving status parameter data under icy and snowy roads; the forget gate is used to control the deletion of the redundant adhesion coefficient or driving status parameter data of the four wheels, and finally outputs them through the output gate.

[0131] Reference Figure 3 As shown, the specific steps of estimating the cornering stiffness of four-wheel tires in step 2) are as follows:

[0132] 21) When the conditions of the icy and snowy road surface change during the vehicle's driving, the forget gate forgets the adhesion coefficients of the four wheels or the vehicle's driving state parameter data at the previous moment, re-inputs the current adhesion coefficients and driving state parameter data of the four wheels, and updates the output of the forget gate;

[0133] 22) The forward input gate uses the adhesion coefficients of the four wheels to adjust the influence weights of the adhesion coefficients and driving state parameter data of the four wheels, and obtains the adhesion coefficient data or driving state parameter data missed on the icy and snowy road through the reverse input gate to update the input of the bidirectional long short-term memory neural network;

[0134] 23) According to the input of the forget gate and the bidirectional long short-term memory neural network, the adhesion coefficient and driving state parameter data accumulation of the four wheels estimated by the four-wheel tire cornering stiffness at the current moment are updated;

[0135] 24) Update the current output of the output gate, combine the adhesion coefficient and driving state parameter data accumulation of the four wheels at the current moment, and output the memory and processing state of the four-wheel tire cornering stiffness at the current moment;

[0136] 25) The bidirectional long short-term memory neural network outputs the cornering stiffness of the four-wheel tires of a four-wheel independent steering vehicle.

[0137] Specifically, in step 21), the lateral acceleration a of the vehicle is selected y , yaw angular acceleration Left front wheel turning angle δ lf 、Left rear wheel turning angle δ lr , right front wheel turning angle δ rf , right rear wheel turning angle δ rr , longitudinal speed v x , sideslip angle β, yaw rate ω, left front wheel adhesion coefficient u lf , left rear wheel adhesion coefficient u lr , right front wheel adhesion coefficient u rf and the right rear wheel adhesion coefficient u rr, as the input of the bidirectional long short-term memory neural network, the expression is as follows:

[0138]

[0139] The output of the forget gate is expressed as:

[0140] f (t) =σ(W f h (t-1) +U f x0 (t) +b f )

[0141] Among them, f (t) is the output of the forget gate, σ is the activation function, h (t-1) is the memory and processing state of the adhesion coefficient data and driving state parameter data of the four wheels at time t-1, x0 (t) is the input of the positive input gate at time t, W f , U f is the weight coefficient of the forget gate, b f is the bias value of the forget gate.

[0142] Specifically, in step 22), the missing adhesion coefficient data or driving state parameter data on the icy and snowy road are obtained through the reverse input gate, x (t) is the input of the bidirectional long short-term memory neural network at time t, and the expression is as follows:

[0143] x (t) =x0 (t) +x n (t)

[0144] Among them, x n (t) represents the missing adhesion coefficient or driving state parameter data, which is the input of the reverse input gate at time t.

[0145] Specifically, the input of the bidirectional long short-term memory neural network updated in step 22) includes two parts. The first part is the output i through the activation function σ (t) The second part is to output the temporary estimated value a of the four-wheel tire cornering stiffness through the activation function tanh (t) , the input of the bidirectional long short-term memory neural network is expressed as:

[0146]

[0147] Among them, i (t) Represents the first part of the input, a (t) represents the temporary estimated value of the four-wheel tire cornering stiffness, W i is the weight coefficient of the adhesion coefficient of the four wheels, U iis the weight coefficient of the driving state parameter data, by adjusting W i and U i Update input, W a , U a is the weight coefficient of feature extraction, b i is the input bias value, b a is the bias value for feature extraction.

[0148] Specifically, in step 23), the adhesion coefficient and driving state parameter data accumulation C of the four wheels are updated. (t) , C (t) Determined by the input of the forget gate and the bidirectional long short-term memory neural network, the expression is as follows:

[0149] C (t) =C (t-1) ⊙f (t) +i (t) ⊙a (t)

[0150] Where ⊙ is the Hadamard product.

[0151] Specifically, in step 24), the current output O of the output gate is updated. (t) The memory and processing state h of the adhesion coefficient data and driving state parameter data of the four wheels at time t-1 (t-1) and the input x at time t (t) Obtained through the activation function σ, the output of the output gate is expressed as:

[0152] O (t) =σ(W o h (t-1) +U o x (t) +b o )

[0153] Among them, W o , U o is the weight coefficient of the output gate, b o is the bias value of the output gate.

[0154] The memory and processing state h of the adhesion coefficient data and driving state parameter data of the four wheels at the current moment are output in step 24). (t) ,h (t) It is determined by the product of two parts. The first part is the output O of the output gate obtained by the activation function σ (t) The second part is C obtained by the activation function tanh (t) , expressed as:

[0155] h (t) =O (t) ⊙tanh(Ct ).

[0156] Specifically, the output of the four-wheel tire cornering stiffness Output of the four-wheel independent steering vehicle in step 25) is expressed as:

[0157] Output:{C lf ,C lr ,C rf ,C rr}=σ(Vh (t) +c)

[0158] Among them, V is the weight matrix that connects the memory and processing state and output of the adhesion coefficient data and driving state parameter data of the four wheels, c is the bias term added to the weighted sum, and C lf is the cornering stiffness of the left front wheel, C lr is the cornering stiffness of the left rear wheel, C rf is the cornering stiffness of the right front wheel, C rr is the cornering stiffness of the right rear wheel.

[0159] 3) A nominal system model is established based on the estimation results of the cornering stiffness of the four-wheel tires, and the optimal nominal system model control law is output. Based on the nominal system model and the uncertainty of the uneven depth of snow on the road during vehicle driving, an actual system model is established to determine the input and output of trajectory tracking control.

[0160] Wherein, the specific steps of step 3) are as follows:

[0161] 31) Establish a nominal system model based on the estimation results of the cornering stiffness of the four-wheel tires, obtain the optimal nominal system model control sequence by generating a cost function, take the first item of the sequence, and output the optimal nominal system model control law;

[0162] 32) Based on the nominal system model and the uncertainty of the uneven depth of snow on the road, the actual system model is established to determine the input and output of trajectory tracking control.

[0163] Specifically, the nominal system model in step 31) is as follows:

[0164]

[0165] in, is the trajectory of the nominal system model, is the deviation between the nominal system model output and the actual system model output, is the deviation between the nominal system model input and the actual system model input, A is the state matrix containing the cornering stiffness of the four-wheel tires, and B is the input matrix containing the cornering stiffness of the four-wheel tires.

[0166] Specifically, the cost function in step 31) is defined as:

[0167]

[0168] Among them, the objective function constraint is U is the constraint of the function, As an additional mandatory constraint, the constant N p and N c represents the prediction range and control range, k represents the time, and are the weighted diagonal matrices of state variables and input variables, respectively, is the state dimension, is the input dimension; the relaxation factor ε and the weighting coefficient κ are used to balance the constraints and avoid infeasible optimization problems caused by the constraints; when the constraints are exceeded, the relaxation variable ε becomes positive and expands the nominal system model input constraints otherwise, the slack variable ε is set to 0.

[0169] Specifically, the optimal nominal system model control law in step 31) is expressed as:

[0170]

[0171] Among them, U * (k) is the optimal nominal system model control sequence, is the optimal control law of the nominal system model; the corresponding optimal trajectory of the nominal system model is The cost function is J * (k).

[0172] Specifically, the actual system model in step 32) is expressed as:

[0173]

[0174] Where, μ is the input of trajectory tracking control, μ= ( δ lf ,δ lr ,δ rf ,δ rr ) T , is the output of trajectory tracking control, is the heading angle of the four-wheel independent steering vehicle, Y is the lateral position of the four-wheel independent steering vehicle, v x is the longitudinal velocity of the four-wheel independent steering vehicle, ω is the yaw angular velocity of the four-wheel independent steering vehicle, Represents the uncertainty impact of uneven snow depth on the road.

[0175] 4) Taking the trajectory of the nominal system model as the center and combining the uncertainty of icy and snowy road conditions, a pipeline is generated and the pipeline control law is output; the optimal nominal system model control law and the pipeline control law are combined to form the final control input of the actual system model, realizing the trajectory tracking of the four-wheel independent steering vehicle on icy and snowy roads;

[0176] Wherein, the specific steps of step 4) are as follows:

[0177] 41) Define the uncertainty caused by uneven snow depth on the road surface;

[0178] 42) generating a pipeline centered on the trajectory of the nominal system model based on the uncertainty;

[0179] 43) Design the pipeline control law, and output the pipeline control law so that the trajectory of the actual system model remains within the generated pipeline;

[0180] 44) Combine the optimal nominal system model control law and the pipeline control law to form the final control input of the actual system model.

[0181] Specifically, the uncertainty caused by the uneven depth of snow on the road surface in step 41) The expression is as follows:

[0182]

[0183] Among them, ∈(k) is the error between the nominal system model and the actual system model, and η(k) represents the pipeline control law.

[0184] Specifically, in step 42), the pipeline Ω centered on the trajectory of the nominal system model tube The expression is as follows:

[0185]

[0186] Among them, C e is a constant matrix, The maximum range representing the uncertainty of uneven snow depth on the road.

[0187] Specifically, the pipeline control law expression in step 43) is as follows:

[0188]

[0189] Among them, η(k) is the pipeline control law, t represents the current moment, represents the uncertainty of the uneven snow depth on the road surface, and λ represents the pipeline parameter, which determines the range of deviation from the nominal system model.

[0190] Specifically, the final control input expression of the actual system model in step 44) is:

[0191]

[0192] in, is the optimal nominal system model control law, η(k) is the pipeline control law, It is the final control input of the actual system model.

[0193] The present invention has many specific application paths. The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements can be made without departing from the principle of the present invention. These improvements should also be regarded as the protection scope of the present invention.

Claims

1. A trajectory tracking system for a four-wheel independent steering vehicle on an icy or snowy road, characterized in that: include: Four-wheel tire cornering stiffness estimation unit and trajectory tracking control unit; The four-wheel tire cornering stiffness estimation unit includes: an ice and snow road environment data acquisition module, a vehicle driving state parameter acquisition module and an estimation module; The icy and snowy road environment data acquisition module is used to collect icy and snowy road information data and obtain the adhesion coefficients of the four wheels of the four-wheel independent steering vehicle; A vehicle driving state parameter acquisition module is used to collect vehicle driving state parameter data; An estimation module, used to estimate the cornering stiffness of the four-wheel tires by using the adhesion coefficients of the four wheels and the vehicle driving state parameter data; The trajectory tracking control unit includes: a nominal system module, an actual system module, a pipeline construction module and a control module; A nominal system module is used to establish a nominal system model according to the estimated results of the cornering stiffness of the four-wheel tires and output the control law of the nominal system model; The actual system module is used to establish the actual system model based on the nominal system model and the uncertainty caused by the uneven depth of snow on the road surface; The pipeline construction module is used to generate a pipeline with the trajectory of the nominal system model as the center and combined with the uncertainty of the icy and snowy road conditions to ensure that the trajectory of the actual system model remains within the pipeline under the influence of the uncertainty caused by the uneven depth of snow on the road surface, and output the pipeline control law; The control module is used to form the final control input of the actual system model according to the nominal system model control law and the pipeline control law to minimize the trajectory tracking error.

2. The trajectory tracking system for a four-wheel independent steering vehicle on an icy and snowy road according to claim 1, characterized in that: The nominal system module establishes a nominal system model, and according to the established nominal system model, establishes a cost function with the goal of minimizing the tracking error, obtains the optimal nominal system model control sequence, takes the first item of the sequence, and outputs the optimal nominal system model control law.

3. The trajectory tracking system for a four-wheel independent steering vehicle on an icy and snowy road according to claim 1, characterized in that: The actual system module establishes an actual system model. Compared with the nominal system model, the actual system model includes the uncertainty of uneven snow depth on the road surface. The input and output of the trajectory tracking control are determined through the actual system model.

4. A method for tracking the trajectory of a four-wheel independent steering vehicle on an icy and snowy road, based on the system described in any one of claims 1 to 3, characterized in that: The steps are as follows: 1) Collecting icy and snowy road information data and vehicle driving status parameter data during vehicle driving, and using the icy and snowy road information data to obtain the adhesion coefficients of the four wheels of the four-wheel independent steering vehicle; 2) The adhesion coefficients of the four wheels and the vehicle driving state parameter data are used as the input of the bidirectional long short-term memory neural network to estimate the cornering stiffness of the four-wheel tires of the four-wheel independent steering vehicle; 3) A nominal system model is established based on the estimation results of the cornering stiffness of the four-wheel tires, and the optimal nominal system model control law is output. Based on the nominal system model and the uncertainty of the uneven depth of snow on the road during vehicle driving, an actual system model is established to determine the input and output of trajectory tracking control; 4) Taking the trajectory of the nominal system model as the center and combining the uncertainty of icy and snowy road conditions, a pipeline is generated and the pipeline control law is output; the optimal nominal system model control law and the pipeline control law are combined to form the final control input of the actual system model, thus realizing the trajectory tracking of the four-wheel independent steering vehicle on icy and snowy roads.

5. The method for tracking the trajectory of a four-wheel independent steering vehicle on an icy and snowy road according to claim 4, characterized in that: In the step 1), a road detection sensor is used to take a picture to obtain image information of the road ahead, and the image information is used to compare the road surface conditions under different adhesion coefficients to obtain the adhesion coefficients of the four wheels.

6. The method for tracking the trajectory of a four-wheel independent steering vehicle on an icy and snowy road according to claim 4, characterized in that: The bidirectional long short-term memory neural network in step 2) comprises: an input gate, a forget gate, and an output gate; the input gate comprises a forward input gate and a reverse input gate; The forward input gate combines the immediate impact of the current icy and snowy road conditions on the cornering stiffness of the four-wheel tires with the impact of the icy and snowy road conditions over a longer period of time on the cornering stiffness of the four-wheel tires, adds or deletes the information on the changes in the cornering stiffness of the four-wheel tires, and adds a reverse input gate to obtain the missed adhesion coefficient or driving status parameter data under icy and snowy roads; the forget gate is used to control the deletion of the redundant adhesion coefficient or driving status parameter data of the four wheels, and finally outputs them through the output gate.

7. The method for tracking the trajectory of a four-wheel independent steering vehicle on an icy and snowy road according to claim 6, characterized in that: The specific steps of estimating the cornering stiffness of four-wheel tires in step 2) are as follows: 21) When the conditions of the icy and snowy road surface change during the vehicle's driving, the forget gate forgets the adhesion coefficients of the four wheels or the vehicle's driving state parameter data at the previous moment, re-inputs the current adhesion coefficients and driving state parameter data of the four wheels, and updates the output of the forget gate; 22) The forward input gate uses the adhesion coefficients of the four wheels to adjust the influence weights of the adhesion coefficients and driving state parameter data of the four wheels, and obtains the adhesion coefficient data or driving state parameter data missed on the icy and snowy road through the reverse input gate to update the input of the bidirectional long short-term memory neural network; 23) According to the input of the forget gate and the bidirectional long short-term memory neural network, the adhesion coefficient and driving state parameter data accumulation of the four wheels estimated by the four-wheel tire cornering stiffness at the current moment are updated; 24) Update the current output of the output gate, combine the adhesion coefficient and driving state parameter data accumulation of the four wheels at the current moment, and output the memory and processing state of the four-wheel tire cornering stiffness at the current moment; 25) The bidirectional long short-term memory neural network outputs the cornering stiffness of the four-wheel tires of a four-wheel independent steering vehicle.

8. The method for tracking the trajectory of a four-wheel independent steering vehicle on an icy and snowy road according to claim 4, characterized in that: The specific steps of step 3) are as follows: 31) Establish a nominal system model based on the estimation results of the cornering stiffness of the four-wheel tires, obtain the optimal nominal system model control sequence by generating a cost function, take the first item of the sequence, and output the optimal nominal system model control law; 32) Based on the nominal system model and the uncertainty of the uneven depth of snow on the road, the actual system model is established to determine the input and output of trajectory tracking control.

9. The method for tracking the trajectory of a four-wheel independent steering vehicle on an icy and snowy road according to claim 8, characterized in that: The nominal system model in step 31) is as follows: in, is the trajectory of the nominal system model, is the deviation between the nominal system model output and the actual system model output, is the deviation between the nominal system model input and the actual system model input, A is the state matrix containing the cornering stiffness of the four-wheel tires, and B is the input matrix containing the cornering stiffness of the four-wheel tires; The cost function in step 31) is defined as: Among them, the objective function constraint is U is the constraint of the function, As an additional mandatory constraint, the constant N p and N c represents the prediction range and control range, k represents the time, and are the weighted diagonal matrices of state variables and input variables, respectively, is the state dimension, is the input dimension; the relaxation factor ε and the weighting coefficient κ are used to balance the constraints and avoid infeasible optimization problems caused by the constraints; when the constraints are exceeded, the relaxation variable ε becomes positive and expands the nominal system model input constraints The feasible range of ; otherwise, the slack variable ε is set to 0; The optimal nominal system model control law in step 31) is expressed as: Among them, U * (k) is the optimal nominal system model control sequence, is the optimal control law of the nominal system model; the corresponding optimal trajectory of the nominal system model is The cost function is J * (k); The actual system model in step 32) is expressed as: Where, μ is the input of trajectory tracking control, μ= ( δ lf ,δ lr ,δ rf ,δrr) T , is the output of trajectory tracking control, is the heading angle of the four-wheel independent steering vehicle, Y is the lateral position of the four-wheel independent steering vehicle, v x is the longitudinal velocity of the four-wheel independent steering vehicle, ω is the yaw angular velocity of the four-wheel independent steering vehicle; Represents the uncertainty impact of uneven snow depth on the road.

10. The method for tracking the trajectory of a four-wheel independent steering vehicle on an icy and snowy road according to claim 4, characterized in that: The specific steps of step 4) are as follows: 41) Define the uncertainty caused by uneven snow depth on the road surface; 42) generating a pipeline centered on the trajectory of the nominal system model based on the uncertainty; 43) Design the pipeline control law, and output the pipeline control law so that the trajectory of the actual system model remains within the generated pipeline; 44) Combine the optimal nominal system model control law and the pipeline control law to form the final control input of the actual system model.

Images