Intelligent semitrailer trajectory tracking control method, system and equipment based on type-2 fuzzy control

Abstract

The invention discloses an intelligent semitrailer trajectory tracking control method, system and equipment based on type-2 fuzzy control, and the method comprises the steps: building a dynamic model of a semitrailer through a Lagrange method, enabling the dynamic model to precisely simulate a vehicle state, and building a trajectory tracking model; a type-2 fuzzy controller is designed, and uncertain interference suffered by trailer tracking errors is covered while the tractor tracking errors are processed. The double-layer uncertainty processing improves the adaptability and robustness of the fuzzy control system in a complex environment. Parameters of the type-2 fuzzy controller are optimized by using a particle swarm optimization algorithm, so that the precision of the controller is effectively improved, and the parameter design difficulty of the controller is remarkably reduced. In the actual driving process of the intelligent commercial semitrailer, the trajectory tracking precision is remarkably improved, and the safety of the intelligent commercial semitrailer under the conditions of large load and high speed is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of automatic driving of intelligent commercial vehicles, and in particular to a trajectory tracking control method, system and equipment for commercial intelligent semi-trailers. Background Art

[0002] Commercial semi-trailers have become one of the important means in the field of transportation with their low transportation costs and high transportation efficiency. However, the cost of drivers has increased year by year, and fatigue driving can easily cause safety accidents, which increases transportation costs and reduces transportation efficiency. With the development of high-level autonomous driving technology and advanced driver assistance technology, new ideas have been brought to commercial semi-trailers to reduce costs and increase efficiency. During high-speed driving, the intelligent semi-trailer is tracked and controlled on the premise that the driving trajectory is pre-set. Automatic driving of intelligent commercial semi-trailers can be achieved.

[0003] The study found that when only the front wheel steering of the tractor's front axle is used, the direction of the trailer's movement is determined by the front wheel steering device and the articulation device, and its movement is completely dependent on the traction of the tractor. Therefore, the difficulty and focus of the research on semi-trailer trajectory tracking control is to improve the trajectory tracking capabilities of the tractor and trailer while reducing costs. In addition, in practical applications, the articulation is susceptible to uncertainty interference caused by changes such as the trailer's center of mass transfer and load transfer, resulting in the trailer's trajectory tracking control being unable to keep consistent with the tractor. This characteristic will become more obvious as the vehicle speed and load change.

[0004] The problem faced in actual control system design is that a single control variable is difficult to coordinate and regulate multiple control targets, and too many control inputs increase the difficulty of controller design and reduce the controller design accuracy. On the other hand, if only a single trajectory tracking control target is considered, the trajectory tracking control accuracy of the semi-trailer tractor and trailer body cannot be guaranteed. Summary of the invention

[0005] In view of the above problems, the present invention provides an intelligent semi-trailer trajectory tracking control method based on type II fuzzy logic control, which effectively solves the problem that when the semi-trailer is traveling on a large curvature trajectory, the center of mass transfer and load transfer of the trailer cause uncertainty deviations in the driving trajectories of the rear and front bodies, and it is difficult to take into account the tracking effects of both bodies during trajectory tracking. It mainly includes the nonlinear dynamics modeling part of the semi-trailer vehicle, the construction of the trajectory tracking model, the construction of the main body of the type II fuzzy controller, and the parameter optimization of the type II fuzzy controller.

[0006] The vehicle nonlinear dynamics modeling part establishes a vehicle physical model through some simplifications and assumptions, and this model will serve as the carrier for the controller.

[0007] The main controller part of the type-II fuzzy controller is built to cover the uncertainty interference of the trailer tracking error in addition to processing the tractor tracking error. This two-level uncertainty processing improves the adaptability and robustness of the fuzzy control system in complex environments. The particle swarm optimization algorithm is introduced to solve the problem of many parameters and complex design of the type-II fuzzy logic controller, while ensuring the coverage of uncertainty interference and improving the controller accuracy. The improved type-II fuzzy logic controller enables the semi-trailer to handle the interference of center of mass transfer and load transfer under different vehicle speeds and different loads, and can handle the trajectory tracking control under large curvature or curvature mutation conditions.

[0008] The technical solution of the present invention is:

[0009] Semi-trailer vehicle nonlinear dynamics modeling part: Semi-trailer consists of a tractor and a trailer connected by an articulated device, in which the tractor usually has two axles and the trailer has three axles, which are simplified to a single axle during the modeling process. In addition, the vehicle model also makes the following assumptions: 1. Ignore the influence of aerodynamics; 2. The coaxial left and right wheels are merged into one equivalent wheel; 3. Assume that the articulation angle is small; 4. Ignore the rolling resistance of the tire; 5. Ignore the roll and pitch of the vehicle; Use the 7-degree-of-freedom dynamic model as the reference model in the controller, according to the characteristics of the semi-trailer, and consider the influence of the longitudinal speed change of the vehicle on the vehicle, and establish a vehicle model with seven degrees of freedom considering the lateral, longitudinal, and yaw of the tractor, the lateral, longitudinal, yaw of the trailer, and the relative rotation at the articulation angle.

[0010] The Lagrangian method is used to obtain partial derivatives of the tractor variables to achieve the requirements of the simplified model, and the sources of uncertainty at the articulation are analyzed. The specific Lagrangian equation expression is shown in the following formula:

[0011] The Lagrange equation is expressed as follows:

[0012]

[0013] In the formula, It is the Lagrangian, defined as L = TV, where T is the kinetic energy of the system, V is the potential energy of the system, q is the generalized velocity, t is the time variable, and Q is the generalized force.

[0014] The coordinates of the trailer relative to the tractor can be expressed as:

[0015]

[0016] Select As a generalized coordinate, the generalized coordinate is a function of time, and the kinetic energy is expressed as:

[0017]

[0018] Where: m1 is the mass of the tractor, m2 is the mass of the trailer, x1 is the longitudinal displacement of the tractor, x2 is the longitudinal displacement of the trailer, is the longitudinal speed of the tractor, is the longitudinal velocity of the trailer, y1 is the lateral displacement of the tractor, y2 is the lateral displacement of the trailer, is the lateral speed of the tractor, is the lateral speed of the trailer, and Represent the yaw angles of the tractor and trailer, I1 and I2 represent the rotational inertia of the tractor and trailer, respectively, f is the distance between the center of mass of the tractor and the hinge point, where the potential energy V = 0, so L = T. The present invention only considers the partial derivative of the Lagrangian equation L with respect to the longitudinal velocity, lateral velocity, yaw angular velocity of the tractor and the yaw angle of the trailer, and the Lagrangian term can be obtained:

[0019]

[0020] The generalized force expression for each state is as follows:

[0021] Q x1 =F xf +F xr +F xs -F yf δ+F ys γ

[0022] Q y1 =F yf +F yr +F ys +F xf Delta-F xs γ

[0023]

[0024] Q x1 , Q y1 , They respectively represent the longitudinal generalized force, lateral generalized force, yaw direction generalized force of the tractor and the yaw direction generalized force of the trailer.

[0025] From the above formula we can infer:

[0026]

[0027] Define the intermediate variable matrix:

[0028]

[0029] Therefore, the state equation is expressed as follows:

[0030]

[0031]

[0032] F x,i =Ka*S

[0033] F yi =Ca*α

[0034] In the formula, a1 and b1 are the distances between the front axle and rear axle of the tractor and the center of mass, a2 and b2 are the distances between the front axle and rear axle of the trailer and the center of mass, γ is the articulation angle, δ represents the front wheel turning angle of the tractor, S is the slip rate of the wheel, and α represents the side slip angle of the wheel, which can be obtained by Trucksim software. Ka and Ca are the longitudinal slip stiffness and side slip stiffness of the tire, respectively, which are proportional to the load size in the linear region. V x1 is the longitudinal velocity of the tractor, V y1 represents the lateral velocity of the tractor, ω1 represents the yaw angular velocity of the tractor, and x represents the state vector.

[0035] Therefore, the longitudinal force and lateral force should actually be:

[0036] F xi =(Ka+△Ka)*S

[0037] F yi =(Ca+△Ca)*α

[0038] In the formula, the subscript x of F represents the longitudinal direction, y represents the lateral direction, and i=f,r,s, which represent the front, middle and rear axles of the semitrailer respectively.

[0039] Build a trajectory tracking model: The trajectory tracking model is to establish the relationship between the vehicle coordinate system and the global coordinate system. The above dynamic model can be used to obtain the state quantities such as the lateral and longitudinal speeds and yaw angular velocity of the tractor, so as to obtain the lateral position coordinates of the tractor. It is worth noting that although the tractor is also affected by the articulation, due to the short wheelbase of the tractor, the lateral position coordinate Y1 of the tractor is less affected and can still be expressed as:

[0040] Y1=∫V y1 dt

[0041] The trailer is long and is not rigidly connected to the tractor. It is affected by the load transfer and center of mass change related to vehicle speed and load. Therefore, the trailer cannot obtain the Y1 lateral position corresponding to the tractor X1 position. At this time, the actual trailer lateral position coordinate Y2 is:

[0042] Y2=Y1+△y

[0043] △y represents the lateral position deviation between the tractor and the trailer.

[0044] The kinematic model of trajectory tracking is expressed as follows:

[0045]

[0046] Where: ρ is the road curvature, Y r is the expected ordinate, e y1 is the lateral error between the tractor and the track, is the heading angle deviation of the tractor, e y2 is the lateral error between the trailer and the track.

[0047] Build a dual-input single-output type II fuzzy logic controller: Let the input variable domain x = (x1, x2) T , there are P rules (p=1,…,P), defined as follows:

[0048]

[0049] Above and is the antecedent of the type II fuzzy logic controller, Represents the output item of the type II fuzzy logic controller, which is set as a Gaussian membership function in the present invention, including the upper membership function and the membership function of the lower layer The clear input is fuzzified through the upper and lower membership functions to enhance its fuzzy characteristics.

[0050] The upper-level membership function corresponding to each input is:

[0051]

[0052] Where, m = 1, 2, 3, …, M; M represents the number of controller inputs.

[0053] The lower layer membership function is:

[0054]

[0055] in c p,m and Represent the centers of the Gaussian lower and upper membership functions, σ p,m and is the standard deviation of the Gaussian lower and upper membership functions, and h is the height of the lower membership function.

[0056] is the output term of the type II fuzzy logic controller, see Figure 2 The output layer shown contains the fuzzy upper layer output and blur the lower output y(x). The fuzzified factors trigger the fuzzy rules The rule post-item output corresponding to this rule After the operation, the fuzzy output is obtained, in which the triggering rule f p , They are:

[0057]

[0058] ∩ represents the algebraic product.

[0059] The present invention uses TS type II fuzzy logic controller, and the rule consequent is designed as a constant type rule consequent, that is, Fuzzy upper layer output and blur the lower output y (x) is expressed as:

[0060]

[0061] The final clarified output y(x) is:

[0062]

[0063] Establish the fuzzy rule table of type II fuzzy controller:

[0064] The type II fuzzy logic controller uses the lateral deviation and heading angle deviation as control inputs, and the tractor front wheel turning angle as control output. The control principle is that when the lateral deviation is negative, the vehicle position is biased to the right in the global coordinate system, and a left turning angle is required. When the heading angle error is negative or zero, a larger left turning angle is required, and the control amount should be positive (PL). When the lateral deviation is positive, the vehicle position is biased to the left in the global coordinate system, and a right turning angle is required. When the heading angle error is positive or zero, a larger right turning angle is required, and the control amount should be negative (NL). By analogy, the fuzzy rules can be summarized in Table 1.

[0065] Table 1 Fuzzy rules table

[0066]

[0067] In the table: NL represents negative large, NS represents negative small, ZE represents zero, PS represents positive small, and PL represents positive large.

[0068] The lateral error of the tractor e y1 Heading angle error As the input variable of the type-II fuzzy logic controller, the front wheel steering angle δ of the tractor is solved.

[0069] Parameter optimization of type-2 fuzzy controller:

[0070] The inspiration for the particle swarm optimization algorithm (PSO) comes from the observation of the behavior of bird flocks migrating and fish schools foraging. These groups show a collaborative behavior when looking for food or migrating, that is, individuals cooperate with each other and move in the most favorable direction to obtain better results. The essence of this group behavior is information sharing and collaboration between individuals to achieve the overall optimization goal.

[0071] The following are the basic steps of the PSO algorithm conceived by the present invention in combination with the application object of the semi-trailer tractor:

[0072] step1. Initialization:

[0073] The parameters of the type-II fuzzy logic controller are randomly generated as particles in the particle swarm, and the position and velocity of each particle are randomly generated, and the individual optimal solution (initial position) and the group optimal solution of each particle are initialized.

[0074] Step 2. Iteration process: For each iteration, perform the following steps:

[0075] 1. Update particle speed and position according to the formula;

[0076] 2. Evaluate fitness: Calculate the fitness value of each particle, which is determined by the objective cost function defined by the problem;

[0077] 3. Update individual and global optimal solutions: For each particle, compare the fitness value based on the current position and the individual optimal solution, and update the individual optimal solution. At the same time, update the global optimal solution based on the fitness value comparison of all particles.

[0078] Step 3. Termination conditions:

[0079] The algorithm is terminated when the predetermined number of iterations is reached or the expected state is met.

[0080] Based on the above control method, the present invention also proposes an intelligent semi-trailer trajectory tracking control system based on type II fuzzy control, comprising:

[0081] A nonlinear dynamics model part of a semi-trailer vehicle, which is a nonlinear dynamics model of a semi-trailer vehicle established by the above method;

[0082] Trajectory tracking model part, which is the trajectory tracking model established above;

[0083] The type-II fuzzy logic controller part is a type-II fuzzy logic controller established according to the above method, and the parameters are optimized according to the above optimization method. The optimal front wheel steering angle of the tractor is calculated and output based on the optimized parameters to achieve trajectory tracking.

[0084] The present invention also proposes a control device for an intelligent semi-trailer, comprising a processor and a memory, wherein the memory is used to store instruction codes, and the processor is used to read instructions from the memory and execute the instructions. When executing the instructions, the processor can implement the above-mentioned trajectory tracking control method.

[0085] Beneficial effects of the present invention:

[0086] 1) The present invention establishes a dynamic model of a semi-trailer through the Lagrangian method. This dynamic model accurately simulates the vehicle state and builds a trajectory tracking model. It analyzes and explains why the trajectory tracking accuracy of the intelligent commercial semi-trailer is affected when facing uncertainty.

[0087] 2) Semi-trailers have two bodies, the tractor and the trailer. Due to the influence of uncertainty factors, it is difficult to take into account the tracking accuracy of both. A type II fuzzy controller is designed to cover the uncertainty interference of the trailer tracking error in addition to processing the tractor tracking error. This two-level uncertainty processing improves the adaptability and robustness of the fuzzy control system in complex environments.

[0088] 3) Considering that the type-II fuzzy controller has many parameters and complex design, the particle swarm optimization algorithm is used to optimize the parameters, which effectively improves the controller accuracy and significantly reduces the difficulty of controller parameter design. In the actual driving process of the intelligent commercial semi-trailer, the trajectory tracking accuracy is significantly improved, ensuring the safety of the intelligent commercial semi-trailer under heavy load and high speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 A schematic diagram of a semitrailer dynamics model provided by an embodiment of the present invention;

[0090] Figure 2 A detailed flow chart of a semitrailer trajectory tracking control method provided in an embodiment of the present invention.

[0091] Figure 3 A schematic diagram of a type II fuzzy controller provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0092] The present invention will be further described below in conjunction with the accompanying drawings.

[0093] like Figure 1 As shown, the dynamic model of the semi-trailer is established

[0094] The vehicle's roll, pitch, and vertical motion are not considered, and the vehicle only moves in the xoy plane. The vehicle is a tractor with front wheel steering, and the body coordinate system is in the left-right symmetric plane of the vehicle. The origin of the vehicle's center of mass is o, the x-axis is the vehicle's longitudinal axis, the positive direction is the direction of the front of the vehicle, the z-axis is perpendicular to the upward direction, and the y-axis points to the side of the vehicle body, and its positive direction satisfies the right-hand rule.

[0095] The Lagrange equation is expressed as follows:

[0096]

[0097] In the formula, It is the Lagrangian, defined as L = TV, where T is the kinetic energy of the system, V is the potential energy of the system, q is the generalized velocity, and Q is the generalized force.

[0098] The coordinates of the trailer relative to the tractor can be expressed as:

[0099]

[0100] Select As a generalized coordinate system, the generalized coordinates are a function of time, and the kinetic energy is expressed as:

[0101]

[0102] Where m1 is the mass of the tractor, m2 is the mass of the trailer, is the longitudinal speed of the tractor, is the longitudinal velocity of the trailer, is the lateral speed of the tractor, is the lateral velocity of the trailer, γ is the articulation angle, and Represent the yaw angles of the tractor and trailer, I1 and I2 represent the rotational inertia of the tractor and trailer, respectively, f is the distance between the center of mass of the tractor and the hinge point, where the potential energy V=0, so L=T. The present invention only considers the partial derivatives of the Lagrangian equation L with respect to the longitudinal and transverse speeds, yaw angles of the tractor and the yaw angles of the trailer, and the Lagrangian term can be obtained:

[0103]

[0104] The generalized force expression for each state is as follows:

[0105] Q x =F xf +F xr +F xs -F yf δ+F ys γ

[0106] Q y1 =F yf +F yr +F ys +F xf Delta-F xs γ

[0107]

[0108] From the above formula, we can infer that

[0109]

[0110] F x,i =Ka*S

[0111] F yi =Ca*α

[0112] Where a1 and b1 are the distances between the front and rear axles and the center of mass of the tractor, a2 and b2 are the distances between the front and rear axles and the center of mass of the trailer, S is the slip rate of the wheel, α is the sideslip angle of the wheel, Ka and Ca are the longitudinal slip stiffness and lateral stiffness of the tire, respectively, which are proportional to the load size in the linear region.

[0113] Therefore, the longitudinal and lateral forces should actually be:

[0114] F xi =(Ka+△Ka)*S

[0115] F yi =(Ca+△Ca)*α

[0116] The trajectory tracking model is to establish the relationship between the vehicle coordinate system and the global coordinate system. The state quantities such as the lateral and longitudinal speeds and yaw angular velocity of the tractor can be obtained from the above dynamic model, so as to obtain the lateral coordinate position of the tractor. It is worth noting that although the tractor is also affected by the articulation, due to the short wheelbase of the tractor, the lateral position coordinate of the tractor is less affected and can still be expressed as:

[0117] Y1=∫V y1 dt

[0118] At this time, the actual lateral position of the trailer is:

[0119] Y2=Y1+△y

[0120] The kinematic model of trajectory tracking is expressed as follows:

[0121]

[0122] Where: ρ is the road curvature, Y r is the expected vertical coordinate, is the yaw angle of the tractor, e y1 is the lateral error between the tractor and the track, is the yaw angle deviation of the tractor, e y2 is the lateral error between the trailer and the track.

[0123] like Figure 2 , 3 As shown, Figure 2It is an overall flow chart of the implementation of the present invention, Figure 3 This is a schematic diagram of a type II fuzzy controller. The present invention uses the deviation between the planned path trajectory and the current position of the vehicle body as the controller input, and optimizes the controller parameters through a particle swarm algorithm. Finally, the optimized type II fuzzy controller is used for trajectory tracking control.

[0124] The specific process is:

[0125] The upper membership of the type II fuzzy controller is:

[0126]

[0127] The lower level membership is:

[0128]

[0129] in c p,m and Represent the centers of the Gaussian lower and upper membership functions, σ p,m and is the standard deviation of the Gaussian lower and upper membership functions, and h is the height of the lower membership function.

[0130]

[0131] ∩ represents the algebraic product.

[0132] The fuzzy upper layer output is obtained through the above triggering rules and blur the lower output y (x) is expressed as:

[0133]

[0134] The final clarified output y(x) is:

[0135]

[0136] Design of PSO optimization algorithm

[0137] The parameters of the type-2 fuzzy controller are randomly generated as particles in the particle swarm, and the initial position and velocity are randomly set for each particle. In addition, the individual optimal solution (initial position) of each particle and the group optimal solution are initialized.

[0138] In each iteration, do the following:

[0139] Update the particle's velocity and position;

[0140] Evaluate fitness: Calculate the fitness value of each particle, which is equal to the defined target cost function value;

[0141] After the controller is built, the particle swarm algorithm is used to optimize the controller parameters to achieve the trajectory tracking accuracy of the semi-trailer under the influence of uncertain factors, including the following:

[0142] Building the cost function

[0143] The cost function of the optimization algorithm is:

[0144] J=k1J1 2 +k2J2 2 +k3J3 2

[0145] k1, k2, and k3 represent weighting coefficients.

[0146] The above formula takes into account the lateral displacement deviation and heading angle deviation of the entire vehicle body at the same time, where:

[0147] J1=e y =n1e y1 +n2e y2

[0148] J1 is the lateral displacement deviation of the tractor y1 and the lateral displacement deviation of the trailer e y2 The sum of the errors added in proportion is used as the lateral displacement deviation of the vehicle body, and n1 and n2 represent the two deviations e respectively. y1 and e y2 The weighting coefficient of .

[0149]

[0150] Indicates the yaw angle of the tractor.

[0151]

[0152] In the formula, set In order to obtain an 85% uncertainty coverage, the x q The lateral displacement error of the tractor is used as the first lateral deviation input of the controller e y1 , x g Indicates the first lateral deviation of the trailer as a controller e y2 , is the fuzzy output, and y Represent the fuzzy upper and lower layer outputs respectively.

[0153] Update individual and global optimal solutions: For each particle, compare the fitness value of its individual optimal solution based on its current position to update the individual optimal solution. At the same time, compare the fitness values ​​of all particles to update the global optimal solution.

[0154] The algorithm terminates when the set number of iterations is reached or a specific stopping condition is met.

[0155] Finally, the optimized parameters will be obtained through the particle swarm optimization algorithm. c p,m and use σ p,m , and h are assigned to the Type-2 fuzzy controller, which outputs the optimal front wheel steering angle of the tractor based on the optimized parameters to achieve trajectory tracking.

[0156] The series of detailed descriptions listed above are only specific descriptions of feasible implementation methods of the present invention. They are not intended to limit the scope of protection of the present invention. All equivalent methods or changes that do not deviate from the technical creation of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent semi-trailer trajectory tracking control method based on type-II fuzzy control, characterized in that: include: S1. Establish a nonlinear dynamic model of a semitrailer vehicle; S2, establish trajectory tracking model; S3, establish a type II fuzzy logic controller; S4, the parameters of the type II fuzzy logic controller are optimized, and the optimal front wheel steering angle of the tractor is output based on the optimized parameters to achieve trajectory tracking.

2. The intelligent semi-trailer trajectory tracking control method based on type-II fuzzy control according to claim 1 is characterized in that: The nonlinear dynamic model of the semitrailer vehicle in S1 adopts a seven-degree-of-freedom model, which is realized by taking partial derivatives of the tractor variables using the Lagrangian method.

3. The intelligent semi-trailer trajectory tracking control method based on type-II fuzzy control according to claim 1 or 2, characterized in that: The specific modeling method of the nonlinear dynamics model is as follows: The established Lagrange equation expression is shown as follows: Where L is the Lagrangian, defined as L = TV, where T is the system kinetic energy, V is the system potential energy, q is the generalized velocity, t is the time variable, and Q is the generalized force; The coordinates of the trailer relative to the tractor are expressed as: Select As a generalized coordinate system, the generalized coordinates are a function of time, and the kinetic energy is expressed as: Where m1 is the mass of the tractor, m2 is the mass of the trailer, is the longitudinal speed of the tractor, is the longitudinal velocity of the trailer, is the lateral speed of the tractor, is the lateral speed of the trailer, and Represent the yaw angles of the tractor and trailer, I1 and I2 represent the rotational inertia of the tractor and trailer, respectively, f is the distance between the center of mass of the tractor and the articulation point, where the potential energy V = 0, so L = T,; Taking partial derivatives of the Lagrangian equation L with respect to the longitudinal velocity, lateral velocity, yaw angle of the tractor and the yaw angle of the trailer, the Lagrangian term can be obtained: The generalized force expression for each state is as follows: Q x =F xf +F xr +F xs -F yf δ+F ys γ Q y1 =F yf +F yr +F ys +F xf δ-F xs γ Define intermediate matrix variables: F x,i =The*S F yi =Ca*α Where a1 and b1 are the distances between the front and rear axles and the center of mass of the tractor, a2 and b2 are the distances between the front and rear axles and the center of mass of the trailer, γ is the articulation angle, S is the slip rate of the wheel, α is the side slip angle of the wheel, Ka and Ca are the longitudinal slip stiffness and side slip stiffness of the tire, respectively, which are proportional to the load size in the linear region; V x1 is the longitudinal velocity of the tractor, V y1 represents the lateral velocity of the tractor, ω1 represents the yaw angular velocity of the tractor, and x represents the state vector; The longitudinal force and lateral force are: F xi =(Ka+△Ka)*S F yi =(Ca+△Ca)*α The subscript x of F represents the longitudinal direction, y represents the lateral direction, and i=f,r,s, which represent the front, middle and rear axles of the semitrailer respectively.

4. The intelligent semi-trailer trajectory tracking control method based on type-II fuzzy control according to claim 3 is characterized in that: The S2 trajectory tracking model is to establish the relationship between the vehicle coordinate system and the global coordinate system. The lateral speed, longitudinal speed and yaw rate of the tractor are obtained from the above vehicle dynamics model, so that the lateral position coordinates of the tractor can be obtained: Y1=∫V y1 dt; The lateral position coordinates of the trailer are: Y2=Y1+△y Therefore, the trajectory tracking model is expressed as follows: Where: ρ is the road curvature, Y r is the expected ordinate, e y1 is the lateral error between the tractor and the track, is the heading angle deviation of the tractor, e y2 is the lateral error between the trailer and the track.

5. The intelligent semi-trailer trajectory tracking control method based on type-II fuzzy control according to claim 4 is characterized in that: The S3 type II fuzzy logic controller is a dual-input single-output TS type II fuzzy logic controller. y and heading angle deviation As the control input, the tractor front wheel angle δ is the control output; let the input variable domain x=(x1,x2) T , there are P rules (p=1,…,P), defined as follows: Above and For the first term of the type II fuzzy logic controller, the present invention is set to a Gaussian membership function, including the upper membership function and the membership function of the lower layer The clear input is fuzzified through the upper and lower membership functions to enhance its fuzzy characteristics; The upper-level membership corresponding to each input is: The lower level membership is: where c p,m and Represent the center of the Gaussian lower and upper membership functions, σ p,m and is the standard deviation of the Gaussian lower and upper membership functions, and h is the height of the lower membership function; is the output item of the type II fuzzy logic controller, including the fuzzy upper layer output And the fuzzy lower layer output y(x), the fuzzified factor triggers the fuzzy rule The rule post-item output corresponding to this rule After operation, the fuzzy output is obtained, and the fuzzy rules are: ∩ represents the algebraic product; The rule consequent is designed as a constant rule consequent, that is, Fuzzy upper layer output And the fuzzy lower layer output y(x) is expressed as: The final clarified output y(x) is:

6. The intelligent semi-trailer trajectory tracking control method based on type-II fuzzy control according to claim 5 is characterized in that: The rule table establishment method of the type II fuzzy logic controller is as follows: The control principle of the type II fuzzy logic controller is: when the lateral deviation is negative, the vehicle position is biased to the right in the global coordinate system, and a left turn is required. When the heading angle error is negative or zero, a larger left turn is required, and the control amount should be positive (PL); when the lateral deviation is positive, the vehicle position is biased to the left in the global coordinate system, and a right turn is required. When the heading angle error is positive or zero, a larger right turn is required, and the control amount should be negative (NL). By analogy, fuzzy rules are established. The fuzzy rules are shown in Table 1: Table 1 Fuzzy rules table 7. The intelligent semi-trailer trajectory tracking control method based on type-II fuzzy control according to claim 6 is characterized in that: The parameter optimization of the S4 type II fuzzy controller is implemented using a particle swarm algorithm, which includes the following steps: step1. Initialization: The parameters of the type-II fuzzy logic controller are randomly generated as particles in the particle swarm, and the position and velocity of each particle are randomly generated, and the individual optimal solution (initial position) and the group optimal solution of each particle are initialized; Step 2. Iteration process: For each iteration, perform the following steps: step2.1, update particle speed and position according to the formula; Step 2.2, evaluate fitness: calculate the fitness value of each particle, which is equal to the defined target cost function value; Step 2.3, Update individual and global optimal solutions: For each particle, compare the fitness value based on the current position and the individual optimal solution, and update the individual optimal solution; at the same time, update the global optimal solution based on the fitness value comparison of all particles; Step 3. Iteration termination: When the predetermined number of iterations is reached or the stopping condition is met, the iteration is terminated.

8. The intelligent semi-trailer trajectory tracking control method based on type-II fuzzy control according to claim 7 is characterized in that: The cost function in step 2.2 is as follows: <h2 style=";text-align:left;direction:ltr">J=k1J1<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> +k2J2<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> +k3J3<h2 style=";text-align:left;direction:ltr"> 2 The above formula takes into account the lateral displacement deviation and heading angle deviation of the entire vehicle body at the same time, where: J1=e y =n1e y1 +n2e y2 J1 is the error sum of the lateral displacement deviation of the tractor and the lateral displacement deviation of the trailer added in proportion, which is taken as the lateral displacement deviation of the vehicle body; Used to describe the yaw angle of the tractor; in:

9. An intelligent semi-trailer trajectory tracking control system based on type II fuzzy control, characterized in that: include: A nonlinear dynamics model of a semi-trailer vehicle, which is the model established by S1 in claim 1; A trajectory tracking model part, which is the model established by S2 in claim 1; The type II fuzzy logic controller part adopts the type II fuzzy logic controller established by the method of S3 described in claim 1, and realizes parameter optimization according to the method of S4, calculates the optimal front wheel turning angle of the output tractor based on the optimized parameters, and realizes trajectory tracking.

10. A control device for an intelligent semi-trailer, characterized in that: It comprises a processor and a memory, wherein the memory is used to store instructions, and the processor is used to read the instructions in the memory and execute the instructions. When executing the instructions, the processor can implement the trajectory tracking control method of claim 1.

Images