Vehicle path tracking control method and device, storage medium and electronic equipment

Abstract

The present disclosure provides a vehicle path tracking control method and device, a storage medium and an electronic device; and relates to the technical field of vehicle automatic control. The method comprises: acquiring a lateral position deviation of a target vehicle relative to a planned driving path, the lateral position deviation comprising a historical lateral position deviation and a current lateral position deviation; obtaining a target front-view distance of the target vehicle based on the historical lateral position deviation through a particle swarm optimization algorithm; calculating a front wheel deflection angle of the target vehicle according to the target front-view distance and the current lateral position deviation, so as to control the target vehicle to drive according to the front wheel deflection angle. The present disclosure can improve the robustness of vehicle lateral motion control by adaptively adjusting the front-view distance of the vehicle, so as to meet the control requirements under different road conditions and different vehicle speeds.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle automatic control technology, and more specifically, to a vehicle path tracking control method, a vehicle path tracking control device, a computer-readable storage medium, and an electronic device. Background Technology

[0002] Autonomous driving technology, as a current hot topic in automotive technology development, has a profound impact on the automotive industry and even on national welfare and people's livelihoods. In the future, autonomous driving technology may revolutionize human travel and industrial production methods.

[0003] The control of autonomous vehicles mainly includes two parts: lateral control and longitudinal control. Lateral control refers to the control of the vehicle's steering system. For example, path tracking is a major application of lateral control in intelligent vehicles. Path tracking means that, given a desired path, the vehicle uses its position information in the geodetic coordinate system and a certain control strategy to ensure that the vehicle's actual driving path matches the planned path.

[0004] Currently, developing stable path tracking control methods to ensure that autonomous vehicles can stably track target paths in complex road traffic environments is crucial for the driving performance and safety of autonomous vehicles.

[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this disclosure is to provide a vehicle path tracking control method, a vehicle path tracking control device, a computer-readable storage medium, and an electronic device, thereby overcoming to some extent the problem of poor robustness of lateral motion control of unmanned vehicles under different road conditions and vehicle speeds due to the limitations and defects of related technologies.

[0007] According to a first aspect of this disclosure, a vehicle path tracking control method is provided, comprising:

[0008] The lateral position deviation of the target vehicle relative to the planned driving path is obtained, and the lateral position deviation includes the historical lateral position deviation and the current lateral position deviation.

[0009] Based on the historical lateral position deviation, the target forward-looking distance of the target vehicle is obtained through particle swarm optimization algorithm;

[0010] The front wheel deflection angle of the target vehicle is calculated based on the forward sight distance and the current lateral position deviation, so as to control the driving of the target vehicle according to the front wheel deflection angle.

[0011] In one exemplary embodiment of this disclosure, obtaining the target forward-looking distance of the target vehicle based on the historical lateral position deviation using a particle swarm optimization algorithm includes:

[0012] Construct an adaptive degree function based on the historical lateral position deviation;

[0013] Based on the adaptive degree function, the target forward-looking distance of the target vehicle is obtained through particle swarm optimization algorithm.

[0014] In one exemplary embodiment of this disclosure, constructing the adaptive degree function based on the historical lateral position deviation includes:

[0015] Calculate the average and maximum lateral position deviations of the target vehicle based on the historical lateral position deviations;

[0016] The adaptive function is constructed based on the average lateral position deviation and the maximum lateral position deviation of the target vehicle.

[0017] In one exemplary embodiment of this disclosure, the adaptive function is:

[0018]

[0019] in, This represents the calculated average lateral position deviation of the target vehicle. e represents the permissible standard lateral position deviation of the target vehicle. max E represents the calculated maximum lateral position deviation of the target vehicle. max This indicates the maximum permissible lateral position deviation of the target vehicle.

[0020] In one exemplary embodiment of this disclosure, obtaining the target forward-looking distance of the target vehicle based on the adaptive degree function using a particle swarm optimization algorithm includes:

[0021] The parameters of the preset particle swarm optimization algorithm include the range of inertia weight, acceleration factor, and forward look-ahead distance;

[0022] The position and velocity of each particle are randomly initialized within the preset forward look-ahead distance;

[0023] The position and velocity of each particle are updated using the inertial weight and acceleration factor to obtain the current position and current velocity of each particle;

[0024] Based on the current position and current velocity of each particle, the fitness value of each particle is calculated using the adaptive function;

[0025] Update the individual optimal position and the global optimal position of the particle swarm based on the fitness value of each particle;

[0026] When the optimal position of an individual particle swarm and the optimal position of the global particle swarm satisfy a preset convergence condition, the target forward-looking distance of the target vehicle is obtained.

[0027] In one exemplary embodiment of this disclosure, updating the individual optimal position and the global optimal position of the particle swarm based on the fitness value of each particle includes:

[0028] The fitness value of each particle is compared with the historical best fitness value of each particle, and the optimal position of each particle is updated.

[0029] The fitness value of each particle is compared with the historical best fitness value of the particle swarm, and the global best position of the particle swarm is updated.

[0030] In one exemplary embodiment of this disclosure, calculating the front wheel deflection angle of the target vehicle based on the target forward-looking distance and the current lateral position deviation includes:

[0031] Obtain the attribute information of the target vehicle, including the wheelbase of the target vehicle;

[0032] The current front wheel deflection angle of the target vehicle is calculated based on the wheelbase of the target vehicle, the forward sight distance of the target, and the current lateral position deviation.

[0033] According to a second aspect of this disclosure, a vehicle path tracking control device is provided, comprising:

[0034] The lateral position deviation acquisition module is used to acquire the lateral position deviation of the target vehicle relative to the planned driving path. The lateral position deviation includes historical lateral position deviation and current lateral position deviation.

[0035] The target forward-looking distance determination module is used to obtain the target forward-looking distance of the target vehicle based on the historical lateral position deviation using a particle swarm optimization algorithm.

[0036] The front wheel deflection angle determination module is used to calculate the front wheel deflection angle of the target vehicle based on the target forward viewing distance and the current lateral position deviation, so as to control the driving of the target vehicle according to the front wheel deflection angle.

[0037] According to a third aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the preceding claims.

[0038] According to a fourth aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method described in any of the preceding methods by executing the executable instructions.

[0039] The exemplary embodiments disclosed herein may have some or all of the following beneficial effects:

[0040] In the vehicle path tracking control method provided in the exemplary embodiments of this disclosure, the lateral position deviation of the target vehicle relative to the planned driving path is obtained, including historical lateral position deviation and current lateral position deviation. Based on the historical lateral position deviation, the target forward sight distance of the target vehicle is obtained through a particle swarm optimization algorithm. The front wheel deflection angle of the target vehicle is calculated based on the target forward sight distance and the current lateral position deviation, so as to control the driving of the target vehicle according to the front wheel deflection angle. This disclosure improves the robustness of vehicle lateral motion control by adaptively adjusting the vehicle's forward sight distance through a particle swarm optimization algorithm, enabling the vehicle to stably track the planned driving path, thereby meeting the control requirements under different road conditions and vehicle speeds.

[0041] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0043] Figure 1 A schematic diagram of an exemplary system architecture for a vehicle path tracking control method and apparatus to which embodiments of the present disclosure can be applied is shown;

[0044] Figure 2 A flowchart illustrating a vehicle path tracking control method according to an embodiment of the present disclosure is shown schematically.

[0045] Figure 3 A geometrical schematic diagram of pure tracking control according to an embodiment of the present disclosure is shown schematically;

[0046] Figure 4 A flowchart illustrating the determination of target forward look-ahead distance according to an embodiment of the present disclosure is shown schematically.

[0047] Figure 5 A flowchart illustrating the determination of target forward look-ahead distance using a particle swarm optimization algorithm according to an embodiment of the present disclosure is shown schematically.

[0048] Figure 6 A flowchart illustrating a vehicle path tracking control method based on a particle swarm optimization algorithm according to an embodiment of the present disclosure is shown schematically.

[0049] Figure 7 A block diagram of a vehicle path tracking control device according to an embodiment of the present disclosure is shown schematically;

[0050] Figure 8 The schematic diagram illustrates a structural schematic of a computer system suitable for implementing an electronic device according to embodiments of the present disclosure. Detailed Implementation

[0051] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0052] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0053] Figure 1 A schematic diagram of an exemplary system architecture for a vehicle path tracking control method and apparatus to which embodiments of the present disclosure can be applied is shown.

[0054] like Figure 1 As shown, system architecture 100 may include one or more of terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables. Terminal devices 101, 102, and 103 may be various electronic devices with displays, including but not limited to desktop computers, laptops, smartphones, and tablets. It should be understood that... Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, there can be any number of terminal devices, networks, and servers. For example, server 105 could be a server cluster consisting of multiple servers.

[0055] This disclosure can be illustrated using the lateral control of an autonomous vehicle as an example. The autonomous vehicle can interact with the server 105 via network 104 using terminals 101, 102, and 103 to receive or send messages. For example, when the autonomous vehicle sends a data processing request to the server via terminal 101 (or terminal 102 or 103), the server 105 can obtain the lateral position deviation of the vehicle relative to the planned driving path, including historical and current lateral position deviations. Based on the historical lateral position deviation, the server uses a particle swarm optimization algorithm to obtain the target forward-looking distance of the vehicle. Then, it can calculate the front wheel deflection angle of the vehicle based on the target forward-looking distance and the current lateral position deviation. Finally, the server 105 can display the data processing result of the vehicle, i.e., the front wheel deflection angle, on terminal 101 or other terminals, and simultaneously generate corresponding lateral control commands based on the calculated front wheel deflection angle to control the vehicle's stable driving. It is understood that the vehicle path tracking control method in this disclosure is applicable to, but not limited to, lateral control scenarios of autonomous vehicles. For example, it can be applied to any movable device that requires trajectory tracking, and this disclosure does not limit it.

[0056] The vehicle path tracking control method provided in this embodiment is generally executed by server 105. Correspondingly, the vehicle path tracking control device is generally installed in server 105. The server can send the front wheel deflection angle of the vehicle to the terminal device, and the terminal device can display it to the user. However, it is readily understood by those skilled in the art that the vehicle path tracking control method provided in this embodiment can also be executed by terminal devices 101, 102, and 103. Correspondingly, the vehicle path tracking control device can also be installed in terminal devices 101, 102, and 103. For example, after execution by the terminal device, the front wheel deflection angle of the vehicle can be directly displayed on the display screen of the terminal device. This exemplary embodiment does not impose any special limitations on this.

[0057] The technical solutions of the embodiments of this disclosure are described in detail below:

[0058] Pure tracking control is a method for controlling the lateral motion of a vehicle. It is derived from a vehicle kinematic model and is well-suited for vehicles with Ackermann steering systems. The basic idea of ​​pure tracking control is to guide the current steering wheel movement at a point on the target trajectory ahead in each control cycle, causing the vehicle to move towards the target point.

[0059] Forward sight distance is a crucial parameter in pure tracking control, and its selection directly impacts tracking performance. For example, a shorter forward sight distance can cause instability or even oscillations in vehicle control, while setting a longer forward sight distance to ensure vehicle stability can result in significant tracking errors. Therefore, with a fixed forward sight distance, it is difficult to meet the required precision for lateral motion control under different road conditions and vehicle speeds. This may lead to poor robustness in lateral motion control, such as erratic maneuvers during high-speed control or cutting inside circles during turns.

[0060] Based on one or more of the above-mentioned problems, this exemplary embodiment provides a vehicle path tracking control method. This method can be applied to the server 105, or to one or more of the terminal devices 101, 102, and 103, and this exemplary embodiment does not impose any special limitations on it. (See reference) Figure 2 As shown, the vehicle path tracking control method may include the following steps S210 to S230:

[0061] Step S210. Obtain the lateral position deviation of the target vehicle relative to the planned driving path, wherein the lateral position deviation includes the historical lateral position deviation and the current lateral position deviation;

[0062] Step S220. Based on the historical lateral position deviation, the target forward-looking distance of the target vehicle is obtained through particle swarm optimization algorithm;

[0063] Step S230. Calculate the front wheel deflection angle of the target vehicle based on the target forward viewing distance and the current lateral position deviation, so as to control the driving of the target vehicle according to the front wheel deflection angle.

[0064] In the vehicle path tracking control method provided in the exemplary embodiments of this disclosure, the lateral position deviation of the target vehicle relative to the planned driving path is obtained, including historical lateral position deviation and current lateral position deviation. Based on the historical lateral position deviation, the target forward sight distance of the target vehicle is obtained through a particle swarm optimization algorithm. The front wheel deflection angle of the target vehicle is calculated based on the target forward sight distance and the current lateral position deviation, so as to control the driving of the target vehicle according to the front wheel deflection angle. This disclosure improves the robustness of vehicle lateral motion control by adaptively adjusting the vehicle's forward sight distance through a particle swarm optimization algorithm, enabling the vehicle to stably track the planned driving path, thereby meeting the control requirements under different road conditions and vehicle speeds.

[0065] The steps described above in this example implementation will now be explained in more detail.

[0066] In step S210, the lateral position deviation of the target vehicle relative to the planned driving path is obtained, and the lateral position deviation includes the historical lateral position deviation and the current lateral position deviation.

[0067] In this example implementation, the target vehicle is the autonomous vehicle whose driving is to be controlled. The target vehicle can travel according to the planned driving path. Typically, based on a certain environmental model, given the starting point and target point of the autonomous vehicle, an effective path that is collision-free and can safely reach the target point can be planned according to the performance indicators of the autonomous vehicle. This effective path is the planned driving path of the autonomous vehicle. It should be noted that the planned driving path of the autonomous vehicle consists of multiple discrete points, each of which can be used as a control point. Correspondingly, controlling the target vehicle can be understood as controlling the target vehicle to reach each discrete point on the planned driving path within a preset time.

[0068] For example, when obtaining the lateral position deviation of a target vehicle relative to a planned driving path, the planned driving path of the target vehicle can be obtained first, and the lateral position deviation of the target vehicle can be determined based on the planned driving path. For example, the lateral position deviation of the target vehicle can be determined based on the target vehicle's positioning information and the planned driving path. The lateral position deviation refers to the distance deviation between the lateral position of the target vehicle and the planned position in the planned driving path, and can include the current lateral position deviation and historical lateral position deviation. For example, the current lateral position deviation can be the deviation between the lateral position of the target vehicle at the current moment and the planned position in the planned driving path at the current moment. The historical lateral position deviation can be the deviation between the lateral position of the target vehicle at a historical moment and the planned position at the corresponding historical moment in the planned driving path. There can be multiple historical moments, and the historical moments can be set according to the actual application scenario; this disclosure does not impose specific limitations on this. For example, a time point within a certain time interval from the current moment can be obtained as a historical moment, or a travel time point within a certain distance from the current position can be obtained as a historical moment.

[0069] It should be noted that when driving, drivers often pay attention to a distance ahead in the direction the car is traveling in order to determine the vehicle's next position (i.e., the driver's forward-looking point). The distance between the current position and the next position is the driver's forward-looking (pre-aiming) distance, and the corresponding next position is the pre-aiming point. Generally, to better simulate the driving process of a driver, when performing lateral control on an autonomous vehicle, a distance can be selected ahead of the autonomous vehicle's driving path as the forward-looking distance. In the example implementation of this disclosure, after determining the forward-looking distance, a pure tracking control method can be used to calculate the front wheel deflection angle of the autonomous vehicle based on the forward-looking distance and the lateral position deviation, and then the autonomous vehicle can be controlled to drive stably based on the front wheel deflection angle.

[0070] refer to Figure 3 The diagram shows a geometric schematic of the pure tracking control method. The lateral position deviation can be calculated using the rear axle center of the target vehicle as a reference point. Figure 3 In the diagram, position ① is the current aiming point. Position ② is the actual position of the target vehicle. (x, y) is the rear axle center of the target vehicle, and (X, Y) is the next aiming point determined based on the target's forward sight distance, the current aiming point, and the planned driving path. The next aiming point is located on the planned driving path. Currently, it is necessary to control the target vehicle's rear axle to pass through this aiming point (X, Y):

[0071] According to the Law of Sines:

[0072]

[0073] In equation (1), l is the forward sight distance of the target, R is the turning radius, and α is the heading angle of the target vehicle at the current aiming point.

[0074] From equation (1), the turning radius of the target vehicle can be obtained as:

[0075]

[0076] And:

[0077]

[0078] In equation (3), Δp is the lateral position deviation of the target vehicle, which is the distance deviation between the actual lateral position of the target vehicle at a certain moment and the planned position corresponding to that moment in the planned driving path.

[0079] Combining equations (2) and (3), the turning radius of the target vehicle can be obtained as follows:

[0080]

[0081] The turning radius of the target vehicle can also be calculated based on its wheelbase and front wheel deflection angle. Specifically, it can be calculated based on:

[0082]

[0083] Where w is the wheelbase of the target vehicle, and δ is the front wheel deflection angle of the target vehicle.

[0084] Finally, by combining equations (4) and (5), the relationship between the vehicle's front wheel deflection angle δ, lateral position deviation Δp, target forward sight distance l, and wheelbase w can be obtained as follows:

[0085]

[0086] As can be seen from equation (6), when the wheelbase of the vehicle and the forward sight distance of the target are constant, the current front wheel deflection angle of the target vehicle can be determined based on the current lateral position deviation of the target vehicle.

[0087] In step S220, based on the historical lateral position deviation, the target forward-looking distance of the target vehicle is obtained through a particle swarm optimization algorithm.

[0088] In the exemplary embodiments of this disclosure, the forward-looking distance of the target vehicle can be changed in real time according to the operating conditions to improve the accuracy of the lateral motion control of the target vehicle. For example, the target forward-looking distance of the target vehicle can be obtained using the particle swarm optimization (PSO) algorithm. The target forward-looking distance can be a preset distance between two adjacent aiming points in the planned driving path, or it can be close to the preset distance. Based on the target forward-looking distance, the target vehicle can be controlled to drive stably according to the planned driving path.

[0089] Particle swarm optimization (PSO) refers to the algorithm that leverages the information sharing among individuals within a swarm to drive the overall movement of the swarm from disorder to order within the problem space, thereby obtaining the optimal solution. In the initialization phase, PSO generates a swarm of random particles, each representing a potential solution to the problem, and then iterates to find the optimal solution. In each iteration, a particle updates its state by tracking two "extremes." The first extreme is the historical best solution found by the particle itself, called the individual extreme (pBest), and the second extreme is the historical best solution found by the entire swarm, called the global extreme (gBest). In PSO, each particle has three attributes: its position, velocity, and fitness value determined by an adaptive function for that state. Updating the particle's state means dynamically adjusting its velocity based on its own and other particles' movement experience, thus achieving optimization within the solvable space. In other words, the particle's velocity is updated based on the difference between its current position and the individual and swarm extremes.

[0090] Correspondingly, in the example implementation of this disclosure, the target vehicle is a particle, and target vehicles at different positions are different particles. The position of the target vehicle at a certain moment is a solution in the search space. Each solution can be evaluated using an adaptive function, that is, each position corresponds to a fitness value, and the position with the highest fitness value is the global optimal solution. This position is also the target forward sight distance of the target vehicle. The front wheel deflection angle of the target vehicle is determined based on the target forward sight distance to control the target vehicle to drive stably according to the planned driving path.

[0091] In one example implementation, reference Figure 4 As shown, the target forward-looking distance of the target vehicle can be determined according to steps S410 and S420.

[0092] In step S410, an adaptive degree function is constructed based on the historical lateral position deviation.

[0093] In vehicle lateral motion control, the main control parameters are the target vehicle's average lateral position deviation and maximum lateral position deviation. For example, when constructing the adaptive function, the target vehicle's average and maximum lateral position deviations can be calculated based on historical lateral position deviations, thus enabling the construction of the adaptive function. For instance, the historical lateral position deviations of the target vehicle at various time points within a certain time interval can be obtained, and the average and maximum lateral position deviations can be calculated based on these historical deviations. For example, if the historical lateral position deviations at various time points within a certain time interval are 3cm, 5cm, 8cm, 11cm, and 15cm, averaging these five historical lateral position deviations yields an average lateral position deviation of 8.4cm for the target vehicle. Comparing these five historical lateral position deviations, the maximum lateral position deviation of the target vehicle can be determined to be 15cm.

[0094] Since the average lateral position deviation and maximum lateral position deviation of the target vehicle are two main control indicators in the lateral motion control of the vehicle, in the example implementation of this disclosure, an adaptive function can be constructed based on the average lateral position deviation and maximum lateral position deviation of the target vehicle. The forward sight distance can be optimized according to the adaptive function, which can improve the control accuracy of the target vehicle.

[0095] For example, the adaptive function in the particle swarm optimization algorithm can be set as:

[0096]

[0097] in, This represents the calculated average lateral position deviation of the target vehicle. e represents the standard permissible lateral position deviation of the target vehicle. max E represents the calculated maximum lateral position deviation of the target vehicle. max This represents the maximum permissible lateral position deviation of the target vehicle. As can be seen from equation (7), the smaller the value of the adaptive function, that is, the smaller the ratio of the average lateral position deviation of the target vehicle to the standard permissible lateral position deviation of the target vehicle, and the smaller the ratio of the maximum lateral position deviation of the target vehicle to the maximum permissible lateral position deviation of the target vehicle, the smaller the distance of the target vehicle from the planned driving path, indicating that the control accuracy of the target vehicle is higher.

[0098] In particle swarm optimization (PSO) algorithms, to more intuitively represent the quality of individuals within the swarm, the adaptive function can be further set as:

[0099] F = -f (8)

[0100] This indicates that the higher the fitness value, the higher the control accuracy of the target vehicle. Equation (8) can also be expressed as:

[0101]

[0102] in, and E max The value can be set according to the actual performance of the target vehicle, for example... E max =20cm, this disclosure is for and E max The specific value is not limited.

[0103] In this example, an adaptive function is constructed based on the average and maximum lateral position deviations of the target vehicle. This adaptive function can be used to calculate the fitness value of the target vehicle at each aiming point. An optimal forward look distance is then determined based on the aiming point with the highest fitness value, thereby improving the control accuracy of the target vehicle.

[0104] In step S420, the target forward-looking distance of the target vehicle is obtained by using a particle swarm optimization algorithm based on the adaptive degree function.

[0105] After constructing the adaptive function based on the average and maximum lateral position deviations of the target vehicle, a basic range of forward sight distance can be set, within which the target forward sight distance of the target vehicle can be determined using the particle swarm optimization algorithm.

[0106] In one example implementation, reference Figure 5 As shown, step S420 may further include steps S510 to S560, which use particle swarm optimization algorithm to determine the target forward-looking distance of the target vehicle.

[0107] In step S510, the parameters of the particle swarm optimization algorithm are preset, including the range of inertia weight, acceleration factor and forward look-ahead distance.

[0108] The parameters of the particle swarm optimization algorithm can be initialized, including the particle swarm size N, particle dimension D, inertia weight w, acceleration factors c1 and c2, and the range of the forward distance l. Here, particle dimension D represents the spatial dimension of the particle search, i.e., the number of independent variables. The inertia weight w reflects the influence of the particle's past motion state on its current behavior, and its value is between [0, 1]. A larger w indicates stronger global optimization ability and weaker local optimization ability; conversely, a larger w indicates stronger local optimization ability. In practical applications, an adaptive value method can usually be adopted. For example, the initial value of the inertia weight w can be preset to 0.9, making the global optimization ability of the particle swarm optimization algorithm strong. As the iteration progresses, w continuously decreases, giving the particle swarm optimization algorithm a strong local optimization ability. When the iteration ends, w = 0.1. Acceleration factor c1 represents the acceleration weight that propels a particle to its individual optimal position, and acceleration factor c2 represents the acceleration weight that propels a particle to its group optimal position. For example, c1 = c2 = 2, or c1 = 1.6, c2 = 2. Acceleration factors c1 and c2 have different values ​​for different problems. This disclosure does not make specific restrictions on the value of acceleration factors.

[0109] For example, in a D-dimensional search space, a population X = (x1, x2, ..., xn) consisting of n particles. n ), where the i-th particle can be represented as a D-dimensional vector x. i =(x i1 x i2 , ..., x iD Let represent the position of the i-th particle in the D-dimensional search space, and also represent a solution to the problem. The fitness value corresponding to each particle's position can be calculated based on the constructed fitness function. The velocity of the i-th particle can be expressed as v. i =(v i1 v i2 , ..., v iD Its individual extreme value can be P. i =(P i1 P i2 , ..., P iD Let P(i) represent the position with the best fitness among all positions experienced by the i-th particle. The population extremum can be P(i). g =(P g1 P g2 , ..., P gD ), which represents the position with the best fitness found by all particles.

[0110] For example, the particle swarm has a dimension D of 20, and the preset forward range is (3, 10), i.e., X min =3,X max =3. Each particle can be represented as a 20-dimensional vector x.i And x i Satisfy X min <x i <X max Among them, X min X max They can be represented as follows:

[0111]

[0112]

[0113] In step S520, the position and velocity of each particle are randomly initialized within the preset forward look-ahead distance.

[0114] Given a range of forward-looking distances, the velocity and position of each particle can be randomly initialized in the search space, i.e., each particle's velocity and position can be assigned values. For example, the initial velocity of the particle swarm can be set to 0. This disclosure does not impose specific limitations on the initial velocity and starting position of the particles. The corresponding fitness value can be calculated based on the initial velocity and starting position of each particle to obtain the current optimal position of each particle and the current optimal position of the swarm.

[0115] For example, in equation (9) E max When =20cB, equation (9) can be written as:

[0116]

[0117] When calculating a particle's fitness value, the lateral position deviation of each particle can be obtained based on its initial position and its planned position within the planned path. For example, if the initial position and the planned position are the same, The calculated fitness value of the particle after initialization is 0. When e max The larger the value, the smaller the calculated fitness value of the particle.

[0118] By calculating the fitness value of each particle, the historical best position of each particle and the historical best position of the swarm can be updated. For example, during the initialization process, i.e., the first iteration, the current best position of the particle and the current best position of the swarm are the historical best positions of the particle and the swarm, respectively. After multiple iterations, the historical best position of each particle can be set as its current position, and the historical best position of the swarm can be set as the position of the best particle in the initial swarm. This allows for updating the position and velocity of each particle by tracking its historical best position and the swarm's historical best position.

[0119] In step S530, the position and velocity of each particle are updated using the inertial weight and acceleration factor to obtain the current position and current velocity of each particle.

[0120] For example, the velocity and position of each particle can be updated using inertial weights and acceleration factors based on the particle's own historical best position and the group's historical best position.

[0121] For example, when iterating the velocity and position of a particle, we can use the following:

[0122] v i =w*v0+c1*rand(P i -x0)+c2*rand(P g -x0) (11)

[0123] x i =x0+v i (12)

[0124] Update the particle's velocity and position; in equation (11), v i Let w*v0 be the particle's current velocity. The first term, w*v0, is called the memory term, representing the influence of the previous velocity. w is the inertia weight, and v0 is the particle's velocity in the previous iteration. The second term, r2nd(P) i -x i The term ) is called the self-cognition term, representing a vector pointing from the current position to the particle's own historical best position. c1 is the acceleration factor, r2nd is a random number distributed between [0, 1], used to increase the randomness of the search. P i x is the particle's own historical optimal position. i This represents the current position of the particle. The third term, c2*rand(P) g -x i The term ) is called the group cognition term, representing a vector pointing from the current position to the group's historical best position. It reflects the cooperation and knowledge sharing among particles. c2 is the acceleration factor, and P g This represents the historical optimal position of the swarm. For example, in the example implementation of this disclosure, w = 1, c1 = c2 = 2. It should be noted that the specific values ​​of w, c1, and c2 are not limited in this disclosure. In other examples, w can also be a dynamic value. For example, w can change linearly during the search process of particle swarm optimization, or it can be dynamically changed according to the test function of particle swarm optimization performance. In equation (12), x i x is the particle's current position, and x0 is the particle's position in the previous iteration.

[0125] In step S540, the fitness value of each particle is calculated using the adaptive function based on the current position and current velocity of each particle.

[0126] After obtaining the current position and velocity of each particle, the fitness value of each particle can be calculated using the adaptive function, i.e., equation (9). It can be understood that the fitness of a particle can be evaluated based on the adaptive function each time its position and velocity are iterated, i.e., the fitness value is calculated. For example, when calculating the fitness value of a particle after the nth iteration, the lateral position deviation of the particle in each previous iteration can be obtained, i.e., the historical lateral position deviation of the particle can be obtained, and the fitness value of the particle can be calculated based on the historical lateral position deviation. e max Then, the corresponding fitness value is calculated according to equation (9).

[0127] In step S550, the individual optimal position and the global optimal position of the particle swarm are updated according to the fitness value of each particle.

[0128] For example, the fitness value of each particle can be compared with its historical best fitness value to update the optimal position of each particle. The fitness value of each particle can also be compared with the historical best fitness value of the particle swarm to update the global optimal position of the particle swarm. Specifically, for each particle, its current position's fitness value can be compared with the fitness value of the best position it has passed through; if the current position's fitness value is higher, then its current position is taken as the individual's optimal position, and the individual's optimal forward distance is determined based on its current position and its starting position. Similarly, for each particle, its current position's fitness value can be compared with the fitness value of the best position the particle swarm has passed through; if the current position's fitness value is higher, then its current position is taken as the swarm's optimal position, and the global optimal forward distance can also be determined based on the swarm's optimal position.

[0129] For example, after the nth iteration, the fitness of each particle is... After the (n+1)th iteration, the position of the particle with the highest fitness value is P. i Then P i It can be written as:

[0130]

[0131] According to Equation (13), the optimal position of individual particles and the optimal position of the global particle swarm can be continuously updated iteratively until the particle swarm meets the iteration termination condition. Then, the target forward sight distance of the target vehicle is obtained based on the position of the particle with the highest fitness value.

[0132] Step S560. When the optimal position of an individual particle swarm and the optimal position of the global particle swarm satisfy the preset convergence condition, the target forward-looking distance of the target vehicle is obtained.

[0133] The convergence condition can be that the fitness value of the optimal position searched by the particle swarm meets a preset fitness threshold, the particle swarm reaches a preset number of iterations, or the fitness difference between two iterations meets a preset difference threshold; this disclosure does not specifically limit this. After iteration, the target forward look-ahead distance, i.e., the optimal forward look-ahead distance, can be obtained from the position of the particle with the highest fitness value. Each time the particle swarm iterates to obtain an optimal forward look-ahead distance, a pure tracking control algorithm can be used to calculate the lateral control command of the target vehicle at the optimal forward look-ahead distance.

[0134] In this example, the vehicle's forward look-ahead distance is adaptively adjusted using a particle swarm optimization algorithm, improving the robustness of the vehicle's lateral motion control. This allows the vehicle to stably track the planned driving path, thus meeting control requirements under different road conditions and vehicle speeds. Specifically, designing an adaptive degree function based on the average and maximum lateral position deviations, and optimizing the forward look-ahead distance using this function, improves the control accuracy of the target vehicle.

[0135] In step S230, the front wheel deflection angle of the target vehicle is calculated based on the target forward viewing distance and the current lateral position deviation, so as to control the driving of the target vehicle according to the front wheel deflection angle.

[0136] As shown in equation (6), when the vehicle's wheelbase and target forward viewing distance are constant, the current front wheel deflection angle of the target vehicle can be determined based on the target vehicle's current lateral position deviation. Therefore, after determining the target forward viewing distance of the target vehicle, the target vehicle's attribute information, such as its wheelbase, can be obtained. Then, the current front wheel deflection angle of the target vehicle can be calculated according to equation (6), that is, the current front wheel deflection angle of the target vehicle can be calculated based on the target vehicle's wheelbase, target forward viewing distance, and current lateral position deviation. After determining the target vehicle's front wheel deflection angle, the target vehicle can be controlled to move based on this angle. For example, if it is determined that the front wheels need to deflect by 5°, a control command to deflect the front wheels by 5° can be generated to control the front wheel deflection.

[0137] refer to Figure 6 As shown, a vehicle path tracking control method is schematically illustrated, which includes steps S601 to S603:

[0138] Step S601: Determine the forward sight distance using a particle swarm optimization algorithm. The vehicle's average lateral position deviation and historical lateral position deviation can be obtained. An adaptive function is constructed based on these two deviations. The adaptive function is used to evaluate the particles in the particle swarm iteratively, determining the position of the particle with the highest fitness value after iteration, thereby determining the vehicle's forward sight distance.

[0139] Step S602: Calculate the front wheel deflection angle using a pure tracking control algorithm. In the pure tracking control algorithm, the front wheel deflection angle can be calculated based on the vehicle's forward sight distance, distance to other vehicles, and current lateral position deviation.

[0140] Step S603: Perform lateral control of the vehicle based on the front wheel deflection angle. Generate lateral control commands for the vehicle based on the calculated front wheel deflection angle to control the vehicle to travel along the planned driving path.

[0141] In the vehicle path tracking control method provided in the exemplary embodiments of this disclosure, the lateral position deviation of the target vehicle relative to the planned driving path is obtained, including historical lateral position deviation and current lateral position deviation. Based on the historical lateral position deviation, the target forward sight distance of the target vehicle is obtained through a particle swarm optimization algorithm. The front wheel deflection angle of the target vehicle is calculated based on the target forward sight distance and the current lateral position deviation, so as to control the driving of the target vehicle according to the front wheel deflection angle. This disclosure improves the robustness of vehicle lateral motion control by adaptively adjusting the vehicle's forward sight distance through a particle swarm optimization algorithm, enabling the vehicle to stably track the planned driving path, thereby meeting the control requirements under different road conditions and vehicle speeds.

[0142] It should be noted that although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0143] Furthermore, this example embodiment also provides a vehicle path tracking control device, which can be applied to a server or terminal device. (See reference) Figure 7 As shown, the vehicle path tracking control device 700 may include a lateral position deviation acquisition module 710, a target forward viewing distance determination module 720, and a front wheel deflection angle determination module 730, wherein:

[0144] The lateral position deviation acquisition module 710 is used to acquire the lateral position deviation of the target vehicle relative to the planned driving path, wherein the lateral position deviation includes historical lateral position deviation and current lateral position deviation.

[0145] The target forward-looking distance determination module 720 is used to obtain the target forward-looking distance of the target vehicle based on the historical lateral position deviation through a particle swarm optimization algorithm.

[0146] The front wheel deflection angle determination module 730 is used to calculate the front wheel deflection angle of the target vehicle based on the target forward viewing distance and the current lateral position deviation, so as to control the driving of the target vehicle based on the front wheel deflection angle.

[0147] In one optional implementation, the target forward-looking distance determination module 720 includes:

[0148] An adaptive function construction unit is used to construct an adaptive function based on the historical lateral position deviation.

[0149] The target forward-looking distance determination unit is used to obtain the target forward-looking distance of the target vehicle based on the adaptive degree function and through a particle swarm optimization algorithm.

[0150] In one alternative implementation, the adaptive function construction unit includes:

[0151] The deviation calculation subunit is used to calculate the average lateral position deviation and the maximum lateral position deviation of the target vehicle based on the historical lateral position deviation.

[0152] The function construction sub-unit is used to construct an adaptive function based on the average lateral position deviation and the maximum lateral position deviation of the target vehicle.

[0153] In an alternative implementation, the adaptive function in the function constructing subunit is configured as follows:

[0154]

[0155] in, This represents the calculated average lateral position deviation of the target vehicle. e represents the permissible standard lateral position deviation of the target vehicle. max E represents the calculated maximum lateral position deviation of the target vehicle. max This indicates the maximum permissible lateral position deviation of the target vehicle.

[0156] In one optional implementation, the target forward-looking distance determination module 720 includes:

[0157] The parameter preset unit is used to preset the parameters of the particle swarm optimization algorithm, including the range of inertia weight, acceleration factor and forward look-ahead distance;

[0158] The particle swarm initialization unit is used to randomly initialize the position and velocity of each particle within a preset forward look-ahead distance.

[0159] The particle swarm update unit is used to update the position and velocity of each particle using the inertia weight and acceleration factor to obtain the current position and current velocity of each particle.

[0160] A fitness calculation unit is used to calculate the fitness value of each particle based on its current position and current velocity using the fitness function.

[0161] The optimal value acquisition unit is used to update the individual optimal position and the global optimal position of the particle swarm based on the fitness value of each particle.

[0162] The target forward-looking distance determination unit is used to obtain the target forward-looking distance of the target vehicle when the optimal position of an individual particle swarm and the optimal position of the global particle swarm satisfy a preset convergence condition.

[0163] In one optional implementation, the optimal value acquisition unit includes:

[0164] The individual optimal value acquisition subunit is used to compare the fitness value of each particle with the historical optimal fitness value of each particle and update the optimal position of each particle.

[0165] The global optimum value acquisition subunit is used to compare the fitness value of each particle with the historical best fitness value of the particle swarm and update the global optimum position of the particle swarm.

[0166] In one alternative implementation, the front wheel deflection angle determination module 730 includes:

[0167] An information acquisition unit is used to acquire attribute information of the target vehicle, including the wheelbase of the target vehicle.

[0168] The front wheel deflection angle determination unit is used to calculate the current front wheel deflection angle of the target vehicle based on the wheelbase of the target vehicle, the forward sight distance of the target vehicle, and the current lateral position deviation.

[0169] The specific details of each module in the above-mentioned vehicle path tracking control device have been described in detail in the corresponding vehicle path tracking control method, so they will not be repeated here.

[0170] The modules in the above-described device can be general-purpose processors, including central processing units (CPUs), network processors, etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. Each module can also be implemented using software, firmware, etc. The processors in the above-described device can be independent processors or integrated together.

[0171] Exemplary embodiments of this disclosure also provide a computer-readable storage medium having a program product stored thereon capable of implementing the methods described above in this specification. In some possible embodiments, various aspects of this disclosure may also be implemented as a program product including program code that, when run on an electronic device, causes the electronic device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. This program product may be a portable compact disc read-only memory (CD-ROM) including program code and may run on an electronic device, such as a personal computer. However, the program product of this disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0172] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0173] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0174] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0175] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0176] Exemplary embodiments of this disclosure also provide an electronic device capable of implementing the above-described method. Referring below... Figure 8 To describe an electronic device 800 according to such an exemplary embodiment of the present disclosure. Figure 8 The electronic device 800 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0177] like Figure 8 As shown, the electronic device 800 can be represented as a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, a bus 830 connecting different system components (including storage unit 820 and processing unit 810), and a display unit 840.

[0178] Storage unit 820 stores program code that can be executed by processing unit 810, causing processing unit 810 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, processing unit 810 can perform... Figure 2 , Figures 4 to 6 Any one or more of the method steps.

[0179] Storage unit 820 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 821 and / or cache memory 822, and may further include a read-only memory (ROM) 823.

[0180] The storage unit 820 may also include a program / utility 824 having a set (at least one) of program modules 825, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0181] Bus 830 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0182] Electronic device 800 can also communicate with one or more external devices 900 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 800, and / or with any device that enables electronic device 800 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 850. Furthermore, electronic device 800 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 860. As shown, network adapter 860 communicates with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0183] In some embodiments, the vehicle path tracking control method described herein can be executed by the processing unit 810 of the electronic device. In some embodiments, target vehicle attribute information, such as wheelbase and lateral position deviation of the vehicle relative to the planned driving path, can be input through the input interface 850. In some embodiments, the front wheel deflection angle of the vehicle can be output to an external device 900 for user viewing through the output interface 850.

[0184] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the method according to the exemplary embodiments of this disclosure.

[0185] Furthermore, the above figures are merely illustrative representations of the processes included in the methods according to exemplary embodiments of this disclosure, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0186] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0187] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A vehicle path tracking control method characterized by comprising: include: The lateral position deviation of the target vehicle relative to the planned driving path is obtained. The lateral position deviation includes historical lateral position deviation and current lateral position deviation. The lateral position deviation refers to the distance deviation between the lateral position of the target vehicle and the planned position in the planned driving path. Based on the historical lateral position deviation, the target forward sight distance of the target vehicle is obtained through particle swarm optimization algorithm; the historical lateral position deviation is the deviation between the lateral position of the target vehicle at a historical moment and the planned position at the corresponding historical moment in the planned driving path; the historical moment can be multiple moments. The front wheel deflection angle of the target vehicle is calculated based on the forward sight distance and the current lateral position deviation, so as to control the driving of the target vehicle according to the front wheel deflection angle; The step of obtaining the target forward-looking distance of the target vehicle based on the historical lateral position deviation using a particle swarm optimization algorithm includes: Calculate the average and maximum lateral position deviations of the target vehicle based on the historical lateral position deviations; An adaptive function is constructed based on the average and maximum lateral position deviations of the target vehicle. Based on the adaptive degree function, the target forward-looking distance of the target vehicle is obtained through particle swarm optimization algorithm.

2. The vehicle path tracking control method according to claim 1, characterized by, The adaptive function is: wherein, represents a calculated average lateral position deviation of the target vehicle, represents a standard lateral position deviation allowed for the target vehicle, represents a calculated maximum lateral position deviation of the target vehicle, represents a maximum lateral position deviation allowed for the target vehicle.

3. The vehicle path tracking control method according to claim 1, characterized by, The step of obtaining the target forward-looking distance of the target vehicle based on the adaptive degree function using a particle swarm optimization algorithm includes: The parameters of the preset particle swarm optimization algorithm include the range of inertia weight, acceleration factor, and forward look-ahead distance; The position and velocity of each particle are randomly initialized within the preset forward look-ahead distance; The position and velocity of each particle are updated using the inertial weight and acceleration factor to obtain the current position and current velocity of each particle; Based on the current position and current velocity of each particle, the fitness value of each particle is calculated using the adaptive function; Update the individual optimal position and the global optimal position of the particle swarm based on the fitness value of each particle; When the optimal position of an individual particle swarm and the optimal position of the global particle swarm satisfy a preset convergence condition, the target forward-looking distance of the target vehicle is obtained.

4. The vehicle path tracking control method according to claim 3, characterized by, The step of updating the individual optimal position and the global optimal position of the particle swarm based on the fitness value of each particle includes: The fitness value of each particle is compared with the historical best fitness value of each particle, and the optimal position of each particle is updated. The fitness value of each particle is compared with the historical best fitness value of the particle swarm, and the global best position of the particle swarm is updated.

5. The vehicle path tracking control method according to claim 1, characterized by, The step of calculating the front wheel deflection angle of the target vehicle based on the forward sight distance and the current lateral position deviation includes: Obtain the attribute information of the target vehicle, including the wheelbase of the target vehicle; The current front wheel deflection angle of the target vehicle is calculated based on the wheelbase of the target vehicle, the forward sight distance of the target, and the current lateral position deviation.

6. A vehicle path tracking control device, characterized in that, include: The lateral position deviation acquisition module is used to acquire the lateral position deviation of the target vehicle relative to the planned driving path. The lateral position deviation includes historical lateral position deviation and current lateral position deviation. The lateral position deviation refers to the distance deviation between the lateral position of the target vehicle and the planned position in the planned driving path. The target forward-looking distance determination module is used to obtain the target forward-looking distance of the target vehicle based on the historical lateral position deviation using a particle swarm optimization algorithm; the historical lateral position deviation is the deviation between the lateral position of the target vehicle at a historical moment and the planned position at the corresponding historical moment in the planned driving path; the historical moments are multiple moments. The front wheel deflection angle determination module is used to calculate the front wheel deflection angle of the target vehicle based on the target forward viewing distance and the current lateral position deviation, so as to control the driving of the target vehicle based on the front wheel deflection angle; The target forward-looking distance determination module is specifically used for: Calculate the average and maximum lateral position deviations of the target vehicle based on the historical lateral position deviations; An adaptive function is constructed based on the average and maximum lateral position deviations of the target vehicle. Based on the adaptive degree function, the target forward-looking distance of the target vehicle is obtained through particle swarm optimization algorithm.

7. A computer readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-5.

8. An electronic device, comprising: include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the method of any one of claims 1-5 by executing the executable instructions.

Images