Vehicle trajectory tracking method, system and device and computer readable storage medium

Abstract

A vehicle trajectory tracking method, system and device and a computer readable storage medium belong to the field of automatic driving, and the method comprises the steps: collecting a plurality of groups of vehicle historical driving records, including a rear axle axis distance difference, a yaw angle difference, a rear axle axis speed and a yaw angle speed between a front moment and a rear moment; dividing all the rear axle center distance differences, the yaw angle differences, the rear axle center speeds and the yaw angle speeds into a plurality of grades according to numerical values to obtain a plurality of distance difference grades, angle difference grades, speed grades and angular speed grades; and obtaining a vehicle trajectory tracking model based on the level training, and performing vehicle trajectory tracking. When the rear axle axis speed and the yaw angle speed are controlled according to the rear axle axis distance difference and the yaw angle difference, the control model is trained after all the data are divided according to the grades, so that fuzzy control is achieved, frequent change of the control quantity caused by frequent change of the state quantity is avoided, and driving safety and comfort are improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving, and specifically to a vehicle trajectory tracking method, system, device and computer-readable storage medium. Background Art

[0002] The most widely used autonomous driving control algorithms are the Proportional Integral Derivative (PID) algorithm, the Linear Quadratic Regulator (LQR) algorithm, the Model Predictive Control (MPC) algorithm, and the Sliding Mode Control (SMC) algorithm.

[0003] PID control method is widely used, but the selection of traditional PID controller parameters mainly depends on repeated experiments and experience, and it is impossible to change the control parameters in time according to the change of state.

[0004] The LQR control method is a stable control method that has high requirements on system dynamics and is sensitive to system noise.

[0005] The MPC control method considers the nonlinear dynamic model of the control system and predicts the output behavior of the system in the future, which requires high computing power.

[0006] The SMC control method is a variable structure control method that has high requirements on the system stability and noise interference suppression capability and is prone to chattering problems.

[0007] The existing autonomous driving control algorithms each have various problems. In general, the commonly used trajectory tracking algorithms now all establish accurate mathematical models in advance, collect state quantities during vehicle driving, and input the state quantities into the mathematical model for solution to obtain the control quantity, and control the vehicle's driving in real time according to the control quantity. Since the mathematical model for controlling the vehicle has parameters set in advance, the model parameters will not change according to different driving conditions during driving. Each set of state quantity data collected will obtain a set of control quantity data, which requires a large amount of calculation and high computing power. In addition, the change of state quantity will affect the control quantity in real time and continuously. If the control quantity keeps changing, the vehicle will be in a state of constant adjustment, and the stability of the vehicle's trajectory tracking will be affected, which in turn affects the ride comfort of the vehicle. When the state quantity jumps, especially abnormal jumps, the vehicle state will change suddenly, which will seriously affect the vehicle safety. Summary of the invention

[0008] The present application provides a vehicle trajectory tracking method, system, device and computer-readable storage medium, which can solve the technical problems of poor stability and safety of vehicle trajectory tracking in the prior art.

[0009] In a second aspect, an embodiment of the present application provides a vehicle trajectory tracking method, characterized in that the method comprises:

[0010] Collecting multiple groups of vehicle historical driving records, each group of vehicle historical driving records includes vehicle historical input and vehicle historical output, the vehicle historical input is the rear axle axis center distance difference and the yaw angle difference between two adjacent moments, and the vehicle historical output is the rear axle axis center speed and the yaw angle speed between two adjacent moments;

[0011] According to the numerical level classification strategy, the rear axle axis distance difference, yaw angle difference, rear axle axis speed, and yaw angle velocity in all vehicle historical driving records are divided into multiple levels according to the numerical values, thereby obtaining multiple distance difference levels, angle difference levels, speed levels, and angular velocity levels;

[0012] The distance difference level and the angle difference level are used as input quantities, and the speed level and the angular velocity level are used as output quantities for model training to obtain a vehicle trajectory tracking model for vehicle trajectory tracking.

[0013] In conjunction with the second aspect, in one implementation, the plurality of distance difference levels include a no difference level, a relatively close level, a very close level, a far level, and a very far level;

[0014] The upper limit of the numerical range of the no-difference level is smaller than the lower limit of the numerical range of the relatively close level, the upper limit of the numerical range of the relatively close level is smaller than the lower limit of the numerical range of the very close level, the upper limit of the numerical range of the very close level is smaller than the lower limit of the numerical range of the far level, and the upper limit of the numerical range of the far level is smaller than the lower limit of the numerical range of the very far level.

[0015] In conjunction with the second aspect, in one implementation, the plurality of angle difference levels include a first negative major level, a first negative minor level, a first zero level, a first positive minor level, and a first positive major level;

[0016] The upper limit of the numerical range of the first negative major level is smaller than the lower limit of the numerical range of the first negative minor level, the upper limit of the numerical range of the first negative minor level is smaller than the lower limit of the numerical range of the first zero level, the upper limit of the numerical range of the first zero level is smaller than the lower limit of the numerical range of the first positive minor level, and the upper limit of the numerical range of the first positive minor level is smaller than the lower limit of the numerical range of the first positive major level.

[0017] In conjunction with the second aspect, in one embodiment, the plurality of speed levels include a slow level, a very slow level, a fast level, a very fast level, and a very fast level;

[0018] The upper limit of the numerical range of the slow level is less than the lower limit of the numerical range of the very slow level, the upper limit of the numerical range of the very slow level is less than the lower limit of the numerical range of the fast level, the upper limit of the numerical range of the fast level is less than the lower limit of the numerical range of the very fast level, and the upper limit of the numerical range of the very fast level is less than the lower limit of the numerical range of the very fast level.

[0019] In conjunction with the second aspect, in one implementation, the plurality of angular velocity levels include a second negative large level, a second negative small level, a second zero level, a second positive small level, and a second positive large level;

[0020] The upper limit of the numerical range of the second negative major level is smaller than the lower limit of the numerical range of the second negative minor level, the upper limit of the numerical range of the second negative minor level is smaller than the lower limit of the numerical range of the second zero level, the upper limit of the numerical range of the second zero level is smaller than the lower limit of the numerical range of the second positive minor level, and the upper limit of the numerical range of the second positive minor level is smaller than the lower limit of the numerical range of the second positive major level.

[0021] In conjunction with the second aspect, in one implementation, the rear axle axis center distance difference, yaw angle difference, rear axle axis center speed, and yaw angle speed are all based on a geodetic coordinate system;

[0022] When the vehicle travels along the positive direction of the X-axis, if the current vehicle real-time position is on the left side of the vehicle target position at the next moment, the yaw angle difference and the yaw angle velocity are both positive.

[0023] In conjunction with the second aspect, in one implementation, the performing vehicle trajectory tracking according to the vehicle trajectory tracking model specifically includes the following steps:

[0024] Collect the real-time location information of the vehicle at the current moment and the target location information of the vehicle at the next moment;

[0025] Calculate the rear axle center distance difference and yaw angle difference at the next moment relative to the current moment according to the vehicle real-time position information and the vehicle target position information;

[0026] The distance difference level corresponding to the rear axle axis center distance difference and the angle difference level corresponding to the yaw angle difference are used as input quantities and input into the vehicle trajectory tracking model to obtain the speed level and the angular velocity level;

[0027] Determine whether the current speed level and angular velocity level are the same as the speed level and angular velocity level obtained according to the model. If so, continue to control the vehicle according to the current rear axle axis speed and yaw angle velocity. If not, switch the current rear axle axis speed and / or yaw angle velocity to the speed level and / or angular velocity level obtained according to the model and continue to control the vehicle.

[0028] In a second aspect, an embodiment of the present application provides a vehicle trajectory tracking system, the vehicle trajectory tracking system comprising:

[0029] A data acquisition module, which is used to collect multiple groups of vehicle historical driving records, each group of vehicle historical driving records includes vehicle historical input and vehicle historical output, the vehicle historical input is the rear axle axis center distance difference and yaw angle difference between two adjacent moments, and the vehicle historical output is the rear axle axis center speed and yaw angle speed between two adjacent moments;

[0030] A data processing module is used to classify the rear axle axis distance difference, yaw angle difference, rear axle axis speed, and yaw angle velocity in all historical driving records of the vehicle into multiple levels according to the numerical value, and obtain multiple distance difference levels, angle difference levels, speed levels, and angular velocity levels;

[0031] The tracking control module is used to perform model training with the distance difference level and the angle difference level as input quantities and the speed level and the angular velocity level as output quantities to obtain a vehicle trajectory tracking model for vehicle trajectory tracking.

[0032] In a third aspect, an embodiment of the present application provides a vehicle trajectory tracking device, which includes a processor, a memory, and a vehicle trajectory tracking program stored in the memory and executable by the processor, wherein when the vehicle trajectory tracking program is executed by the processor, the steps of the vehicle trajectory tracking method are implemented.

[0033] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a vehicle trajectory tracking program is stored, wherein when the vehicle trajectory tracking program is executed by a processor, the steps of the vehicle trajectory tracking method are implemented.

[0034] The beneficial effects brought by the technical solution provided by the embodiments of the present application include:

[0035] When controlling the rear axle axis speed and yaw angle velocity according to the rear axle axis distance difference and yaw angle difference, each data is divided into levels and the control model is trained to realize fuzzy control, avoid frequent changes in control quantity caused by frequent changes in state quantity, and improve driving safety and comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of establishing a vehicle kinematic model based on active front wheel steering in this application;

[0037] Figure 2 A schematic diagram of a flow chart of an embodiment of a vehicle trajectory tracking method of the present application;

[0038] Figure 3This is a schematic diagram of the functional modules of an embodiment of the vehicle trajectory tracking system of the present application;

[0039] Figure 4 This is a schematic diagram of the hardware structure of the vehicle trajectory tracking device involved in the embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0041] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0042] In a second aspect, an embodiment of the present application provides a vehicle trajectory tracking method.

[0043] In one embodiment, referring to Figure 2 , Figure 2 This is a flow chart of the second embodiment of the vehicle trajectory tracking method of this application. Figure 2 As shown, the vehicle trajectory tracking method includes:

[0044] Step S1, collecting multiple groups of vehicle historical driving records, each group of vehicle historical driving records includes vehicle historical input and vehicle historical output, the vehicle historical input is the rear axle axis center distance difference and the yaw angle difference between two adjacent moments, and the vehicle historical output is the rear axle axis center speed and the yaw angle speed between two adjacent moments;

[0045] Step S2, according to the numerical level classification strategy, the rear axle axis distance difference, yaw angle difference, rear axle axis speed, and yaw angle velocity in all vehicle historical driving records are divided into multiple levels according to the numerical values, so as to obtain multiple distance difference levels, angle difference levels, speed levels, and angular velocity levels;

[0046] Step S3: using the distance difference level and the angle difference level as input quantities and the speed level and the angular velocity level as output quantities to perform model training, thereby obtaining a vehicle trajectory tracking model for vehicle trajectory tracking.

[0047] In this embodiment, considering that the vehicle does not need to consider too much about dynamic issues such as vehicle stability control when the vehicle is running at a low speed, the following can be established: Figure 1The vehicle kinematic model is established based on the active steering of the vehicle front wheels, the x-axis is the horizontal coordinate of the geodetic coordinate system, and the y-axis is the vertical coordinate of the geodetic coordinate system. Figure 1 The vehicle travels along the positive direction of the X axis. O is the origin of the coordinate system. is the yaw angle of the vehicle, δ f is the front wheel deflection angle of the vehicle, v f and v r refers to the front and rear axle speeds of the vehicle, l is the wheelbase, R is the turning radius of the rear wheels of the vehicle, point P is the instantaneous rotation center of the vehicle, point N and point M are the front and rear axle centers of the vehicle, respectively. The kinematic constraints of the front and rear axles of the vehicle are as follows:

[0048]

[0049] The calculation formula for the speed at the center of the vehicle's rear axle is as follows (2):

[0050]

[0051] The geometric relationship between the front and rear wheels is shown in the following formula (3):

[0052]

[0053] The calculation formula of the vehicle's yaw rate is as follows (4):

[0054]

[0055] Combining the above formulas (1) to (4), the kinematic model of the vehicle can be transformed into the following formula (5):

[0056]

[0057] It can be seen from this model that by calculating the vehicle rear axle velocity v r By controlling the yaw angle and angular velocity w, the vehicle can be moved in different positions in the geodetic coordinate system.

[0058] Assume that there is a planned trajectory in the geodetic coordinate system, and the coordinates of the vehicle at the current moment are point E (x N ,y N ), the target position coordinates at the next moment are point F (x N+1 ,y N+1 ), the difference between the current angle and the ideal angle is θ, and the distance between the rear axle center at two moments is d. Therefore, in the design of the fuzzy controller, θ and d are used as the input of the controller, and the rear axle center speed v is used as the input of the controller. r and yaw angular velocity w as the output of the controller.

[0059] Preferably, the above-mentioned multiple distance difference levels include no difference level, relatively close level, very close level, far level, and very far level; accordingly, all rear axle axis distance differences d are divided into 5 fuzzy sets: no difference (ZO), relatively close (BJJ), very close (HJ), far (Y), and very far (HY). The membership function of each variable is defined by the above fuzzification.

[0060] The upper limit of the numerical range of the no-difference level is smaller than the lower limit of the numerical range of the relatively close level, the upper limit of the numerical range of the relatively close level is smaller than the lower limit of the numerical range of the very close level, the upper limit of the numerical range of the very close level is smaller than the lower limit of the numerical range of the far level, and the upper limit of the numerical range of the far level is smaller than the lower limit of the numerical range of the very far level.

[0061] Preferably, the above-mentioned multiple angle difference levels include the first negative large level, the first negative small level, the first zero level, the first positive small level, and the first positive large level; accordingly, all yaw angle differences are also divided into 5 fuzzy sets: the first negative large (NB), the first negative small (NS), the first zero (ZO), the first positive small (PS), and the first positive large (PB). The membership function of each variable is defined by the above fuzzification.

[0062] The upper limit of the numerical range of the first negative major level is smaller than the lower limit of the numerical range of the first negative minor level, the upper limit of the numerical range of the first negative minor level is smaller than the lower limit of the numerical range of the first zero level, the upper limit of the numerical range of the first zero level is smaller than the lower limit of the numerical range of the first positive minor level, and the upper limit of the numerical range of the first positive minor level is smaller than the lower limit of the numerical range of the first positive major level.

[0063] Preferably, the multiple speed levels include slow, very slow, fast, very fast, and very fast; correspondingly, all rear axle axis speeds are also divided into five fuzzy sets: slow speed (M), very slow speed (HM), fast speed (K), very fast speed (HK), and very fast speed (FCK). The membership function of each variable is defined by the above fuzzification.

[0064] The upper limit of the numerical range of the slow level is less than the lower limit of the numerical range of the very slow level, the upper limit of the numerical range of the very slow level is less than the lower limit of the numerical range of the fast level, the upper limit of the numerical range of the fast level is less than the lower limit of the numerical range of the very fast level, and the upper limit of the numerical range of the very fast level is less than the lower limit of the numerical range of the very fast level.

[0065] Preferably, the above-mentioned multiple angular velocity levels include the second negative large level, the second negative small level, the second zero level, the second positive small level, and the second positive large level; accordingly, all yaw angular velocities are also divided into 5 fuzzy sets: the second negative large (NB'), the second negative small (NS'), the second zero (ZO'), the second positive small (PS'), and the second positive large (PB'). The membership function of each variable is defined by the above fuzzification.

[0066] The upper limit of the numerical range of the second negative major level is smaller than the lower limit of the numerical range of the second negative minor level, the upper limit of the numerical range of the second negative minor level is smaller than the lower limit of the numerical range of the second zero level, the upper limit of the numerical range of the second zero level is smaller than the lower limit of the numerical range of the second positive minor level, and the upper limit of the numerical range of the second positive minor level is smaller than the lower limit of the numerical range of the second positive major level.

[0067] Further, in one embodiment, the rear axle axis center distance difference, yaw angle difference, rear axle axis center speed, and yaw angle speed are all based on a geodetic coordinate system;

[0068] When the vehicle travels along the positive direction of the X-axis, if the current vehicle real-time position is on the left side of the vehicle target position at the next moment, the yaw angle difference and the yaw angle velocity are both positive.

[0069] The above vehicle trajectory tracking is performed according to the vehicle trajectory tracking model, and specifically includes the following steps:

[0070] Collect the real-time location information of the vehicle at the current moment and the target location information of the vehicle at the next moment;

[0071] Calculate the rear axle center distance difference and yaw angle difference at the next moment relative to the current moment according to the vehicle real-time position information and the vehicle target position information;

[0072] The distance difference level corresponding to the rear axle axis center distance difference and the angle difference level corresponding to the yaw angle difference are used as input quantities and input into the vehicle trajectory tracking model to obtain the speed level and the angular velocity level;

[0073] Determine whether the current speed level and angular velocity level are the same as the speed level and angular velocity level obtained according to the model. If so, continue to control the vehicle according to the current rear axle axis speed and yaw angle velocity. If not, switch the current rear axle axis speed and / or yaw angle velocity to the speed level and / or angular velocity level obtained according to the model and continue to control the vehicle.

[0074] In this embodiment, the rear axle axis distance difference and yaw angle difference obtained according to the actual collected vehicle real-time position information and vehicle target position information are divided into different levels to realize input fuzzification. After the level rather than the specific value is input into the model, the model makes a fuzzy decision and the output is also a level. If any one of the rear axle axis speed and yaw angle velocity at the current moment is not within the level range of the model output, the control target is to adjust it to the level range of the model output. If both are within the level range of the model output, the rear axle axis speed and yaw angle velocity at the current moment can be maintained.

[0075] In a specific embodiment, the input and output are divided into 5 subsets, so 25 fuzzy control rules as shown in Table 1 below can be formulated.

[0076] Table 1 25 fuzzy control rules

[0077] d θ <![CDATA[v r ]]> w ZO ZO HM ZO' ZO NS HM NS' ZO NB HM NB' ZO PS HM P.S. ZO PB HM PB' HJ ZO M <![CDATA[ ZO ’]]> HJ NS M <![CDATA[ NS ’]]> HJ NB M <![CDATA[ NB ’]]> HJ PS M <![CDATA[ PS ’]]> HJ PB M <![CDATA[ PB ’]]> BJJ ZO K <![CDATA[ ZO ’]]> BJJ NS K <![CDATA[ NS ’]]> BJJ NB K <![CDATA[ NB ’]]> BJJ PS K <![CDATA[ PS ’]]> BJJ PB K <![CDATA[ PB ’]]> Y ZO HK <![CDATA[ ZO ’]]> Y NS HK <![CDATA[ NS ’]]> Y NB HK <![CDATA[ NB ’]]> Y PS HK <![CDATA[ PS ’]]> Y PB HK <![CDATA[ PB ’]]> HY ZO FCK <![CDATA[ ZO ’]]> HY NS FCK <![CDATA[ NS ’]]> HY NB FCK <![CDATA[ NB ’]]> HY PS FCK <![CDATA[ PS ’]]> HY PB FCK <![CDATA[ PB ’]]>

[0078] When the fluctuations of d and θ in the input are small, that is, the values ​​after the change and the values ​​before the change are still within the same level range, then when the target output and the current output take several levels as input and output, the model calculation amount is reduced, the control stability is improved, and frequent changes in output caused by frequent small changes in input are avoided, thereby achieving precise adjustment of the steering angle and speed, ensuring that the vehicle travels stably along the planned path, while balancing the calculation speed and the stability of the tracking process, ensuring the vehicle's driving safety and ride comfort.

[0079] In a second aspect, an embodiment of the present application also provides a vehicle trajectory tracking system.

[0080] In one embodiment, referring to Figure 3 , Figure 3 This is a functional module diagram of an embodiment of the vehicle trajectory tracking system of the present application. Figure 3 As shown, the vehicle trajectory tracking device includes:

[0081] A data acquisition module 1 is used to collect multiple groups of vehicle historical driving records, each group of vehicle historical driving records includes vehicle historical input and vehicle historical output, the vehicle historical input is the rear axle axis center distance difference and yaw angle difference between two adjacent moments, and the vehicle historical output is the rear axle axis center speed and yaw angle speed between two adjacent moments;

[0082] The data processing module 2 is used to classify the rear axle axis distance difference, yaw angle difference, rear axle axis speed, and yaw angle velocity in all historical driving records of the vehicle into multiple levels according to the numerical value, and obtain multiple distance difference levels, angle difference levels, speed levels, and angular velocity levels;

[0083] The tracking control module 3 is used to perform model training with the distance difference level and the angle difference level as input quantities and the speed level and the angular velocity level as output quantities to obtain a vehicle trajectory tracking model for vehicle trajectory tracking.

[0084] In this embodiment, when controlling the rear axle axis speed and yaw angle velocity according to the rear axle axis distance difference and yaw angle difference, each data is divided into levels and the control model is trained to realize fuzzy control, thereby avoiding frequent changes in control quantity caused by frequent changes in state quantity and improving driving safety and comfort.

[0085] Among them, the functional implementation of each module in the above-mentioned vehicle trajectory tracking system corresponds to the various steps in the above-mentioned vehicle trajectory tracking method embodiment, and its functions and implementation processes are no longer repeated here one by one.

[0086] In a third aspect, an embodiment of the present application provides a vehicle trajectory tracking device, which may be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0087] Reference Figure 4 , Figure 4 The hardware structure diagram of the vehicle trajectory tracking device involved in the embodiment of the present application is shown in FIG. In the embodiment of the present application, the vehicle trajectory tracking device may include a processor, a memory, a communication interface, and a communication bus.

[0088] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0089] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to realize the interconnection of devices inside the vehicle trajectory tracking device, and the interface used to realize the interconnection of the vehicle trajectory tracking device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0090] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0091] The processor may be a general-purpose processor, and the general-purpose processor may call the vehicle trajectory tracking program stored in the memory and execute the vehicle trajectory tracking method provided by the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the vehicle trajectory tracking program is called may refer to the various embodiments of the vehicle trajectory tracking method of the present application, which will not be repeated here.

[0092] Those skilled in the art will understand that Figure 4 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0093] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0094] A vehicle trajectory tracking program is stored on the computer-readable storage medium of the present application, wherein when the vehicle trajectory tracking program is executed by a processor, the steps of the vehicle trajectory tracking method as described above are implemented.

[0095] Among them, the method implemented when the vehicle trajectory tracking program is executed can refer to the various embodiments of the vehicle trajectory tracking method of the present application, and will not be repeated here.

[0096] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0097] The terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "second", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence of precedence, nor do they limit "second", "second" and "third" to different types.

[0098] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0099] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0100] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0101] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0102] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A vehicle trajectory tracking method, characterized in that: The method comprises: Collecting multiple groups of vehicle historical driving records, each group of vehicle historical driving records includes vehicle historical input and vehicle historical output, the vehicle historical input is the rear axle axis center distance difference and the yaw angle difference between two adjacent moments, and the vehicle historical output is the rear axle axis center speed and the yaw angle speed between two adjacent moments; According to the numerical level classification strategy, the rear axle axis distance difference, yaw angle difference, rear axle axis speed, and yaw angle velocity in all vehicle historical driving records are divided into multiple levels according to the numerical values, thereby obtaining multiple distance difference levels, angle difference levels, speed levels, and angular velocity levels; The distance difference level and the angle difference level are used as input quantities, and the speed level and the angular velocity level are used as output quantities for model training to obtain a vehicle trajectory tracking model for vehicle trajectory tracking.

2. The vehicle trajectory tracking method according to claim 1, characterized in that: The plurality of distance difference levels include no difference, relatively close, very close, far, and very far; The upper limit of the numerical range of the no-difference level is smaller than the lower limit of the numerical range of the relatively close level, the upper limit of the numerical range of the relatively close level is smaller than the lower limit of the numerical range of the very close level, the upper limit of the numerical range of the very close level is smaller than the lower limit of the numerical range of the far level, and the upper limit of the numerical range of the far level is smaller than the lower limit of the numerical range of the very far level.

3. The vehicle trajectory tracking method according to claim 1, characterized in that: The plurality of angle difference levels include a first negative major level, a first negative minor level, a first zero level, a first positive minor level, and a first positive major level; The upper limit of the numerical range of the first negative major level is smaller than the lower limit of the numerical range of the first negative minor level, the upper limit of the numerical range of the first negative minor level is smaller than the lower limit of the numerical range of the first zero level, the upper limit of the numerical range of the first zero level is smaller than the lower limit of the numerical range of the first positive minor level, and the upper limit of the numerical range of the first positive minor level is smaller than the lower limit of the numerical range of the first positive major level.

4. The vehicle trajectory tracking method according to claim 1, characterized in that: The plurality of speed levels include a slow level, a very slow level, a fast level, a very fast level, and a very fast level; The upper limit of the numerical range of the slow level is less than the lower limit of the numerical range of the very slow level, the upper limit of the numerical range of the very slow level is less than the lower limit of the numerical range of the fast level, the upper limit of the numerical range of the fast level is less than the lower limit of the numerical range of the very fast level, and the upper limit of the numerical range of the very fast level is less than the lower limit of the numerical range of the very fast level.

5. The vehicle trajectory tracking method according to claim 1, characterized in that: The plurality of angular velocity levels include a second negative major level, a second negative minor level, a second zero level, a second positive minor level, and a second positive major level; The upper limit of the numerical range of the second negative major level is smaller than the lower limit of the numerical range of the second negative minor level, the upper limit of the numerical range of the second negative minor level is smaller than the lower limit of the numerical range of the second zero level, the upper limit of the numerical range of the second zero level is smaller than the lower limit of the numerical range of the second positive minor level, and the upper limit of the numerical range of the second positive minor level is smaller than the lower limit of the numerical range of the second positive major level.

6. The vehicle trajectory tracking method according to claim 1, characterized in that: The rear axle axis center distance difference, yaw angle difference, rear axle axis center speed, and yaw angle speed are all based on the geodetic coordinate system; When the vehicle travels along the positive direction of the X-axis, if the current vehicle real-time position is on the left side of the vehicle target position at the next moment, the yaw angle difference and the yaw angle velocity are both positive.

7. The vehicle trajectory tracking method according to claim 1, characterized in that: The vehicle trajectory tracking according to the vehicle trajectory tracking model specifically includes the following steps: Collect the real-time location information of the vehicle at the current moment and the target location information of the vehicle at the next moment; Calculate the rear axle center distance difference and yaw angle difference at the next moment relative to the current moment according to the vehicle real-time position information and the vehicle target position information; The distance difference level corresponding to the rear axle axis center distance difference and the angle difference level corresponding to the yaw angle difference are used as input quantities and input into the vehicle trajectory tracking model to obtain the speed level and the angular velocity level; Determine whether the current speed level and angular velocity level are the same as the speed level and angular velocity level obtained according to the model. If so, continue to control the vehicle according to the current rear axle axis speed and yaw angle velocity. If not, switch the current rear axle axis speed and / or yaw angle velocity to the speed level and / or angular velocity level obtained according to the model and continue to control the vehicle.

8. A vehicle trajectory tracking system, characterized in that: The vehicle trajectory tracking system comprises: A data acquisition module, which is used to collect multiple groups of vehicle historical driving records, each group of vehicle historical driving records includes vehicle historical input and vehicle historical output, the vehicle historical input is the rear axle axis center distance difference and yaw angle difference between two adjacent moments, and the vehicle historical output is the rear axle axis center speed and yaw angle speed between two adjacent moments; A data processing module is used to classify the rear axle axis distance difference, yaw angle difference, rear axle axis speed, and yaw angle velocity in all historical driving records of the vehicle into multiple levels according to the numerical value, and obtain multiple distance difference levels, angle difference levels, speed levels, and angular velocity levels; The tracking control module is used to perform model training with the distance difference level and the angle difference level as input quantities and the speed level and the angular velocity level as output quantities to obtain a vehicle trajectory tracking model for vehicle trajectory tracking.

9. A vehicle trajectory tracking device, characterized in that: The vehicle trajectory tracking device includes a processor, a memory, and a vehicle trajectory tracking program stored in the memory and executable by the processor, wherein when the vehicle trajectory tracking program is executed by the processor, the steps of the vehicle trajectory tracking method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a vehicle trajectory tracking program, wherein when the vehicle trajectory tracking program is executed by a processor, the steps of the vehicle trajectory tracking method according to any one of claims 1 to 7 are implemented.

Images