Kinematic model adaptive method, device and equipment in vehicle positioning and medium

Abstract

The application provides a kinematic model adaptive method, device, equipment and medium for vehicle positioning, and the method comprises the following steps: acquiring speed information of a current vehicle body during vehicle driving; selecting the most suitable kinematic model from multiple preset kinematic models, including a constant rotation rate and speed model, a constant rotation rate and acceleration model and a constant acceleration model, based on the speed information; and performing positioning prediction on the current vehicle in different motion states through the kinematic model. Compared with the single model of the kinematic model used for prediction in the positioning scheme based on filtering in the prior art, the application is suitable for the scene of short-time positioning prediction through the kinematic model, and the most suitable kinematic model can be adaptively selected in the scene of different motion states of the vehicle by acquiring the speed information of the motion state of the vehicle, so that the optimal position prediction is provided, and higher positioning precision is obtained than that of the single kinematic model.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to an adaptive method, apparatus, device, and medium for kinematic model in vehicle positioning. Background Technology

[0002] In object tracking, we need to predict the object's position and motion state at the next moment. Predictions are always based on certain rules. For vehicles, kinematic models include CV (constant velocity), CA (constant acceleration), CTRV (constant turn rate and velocity), CTRA (constant turn rate and acceleration), IMM (Interacting Multiple Model), and so on. After each prediction, we need to use an appropriate filtering algorithm to update the predicted value with the measured value to obtain more accurate motion information. Commonly used filtering algorithms include Kalman filtering, particle filtering, and Bayesian filtering.

[0003] In positioning systems based on filters and other methods, short-term prediction using kinematic models is an indispensable step. However, due to factors such as sensor noise, the optimal performance of different kinematic models varies in different scenarios. For example, when the yaw rate observed by the vehicle's inertial measurement unit (IMU) is very small, possibly due to noise interference, the CA model will be more accurate than the CTRA model.

[0004] Currently, in filtering-based localization schemes, the predicted kinematic models are mostly single models. However, a single kinematic model cannot provide more accurate predictions for localization in different scenarios. Summary of the Invention

[0005] To address the problems existing in the prior art, the present invention provides a method, device, equipment, and medium for adaptive kinematic model in vehicle positioning, which can adaptively select a more suitable kinematic model in different scenarios to obtain higher positioning accuracy.

[0006] This invention provides an adaptive kinematic model method for vehicle positioning, comprising:

[0007] Obtain the speed information of the vehicle in the current vehicle coordinate system while it is in motion;

[0008] Based on the velocity information, the most suitable kinematic model is selected from multiple preset kinematic models, wherein the multiple preset kinematic models include: a constant rate of rotation and velocity model, a constant rate of rotation and acceleration model, and a constant acceleration model;

[0009] The selected kinematic model is used to predict the location of the current vehicle under different motion states.

[0010] According to the present invention, a kinematic model adaptive method for vehicle positioning is provided, wherein the velocity information includes: the current angular velocity of the vehicle body; correspondingly,

[0011] The step of selecting the most suitable kinematic model from multiple preset kinematic models based on the velocity information specifically includes:

[0012] The angular increment is calculated based on the angular velocity and the predetermined prediction duration.

[0013] Determine whether the angle increment is greater than or equal to a preset first threshold. If so, then the constant rotation rate and speed model is adopted.

[0014] Otherwise, it is determined whether the angular velocity is less than a preset second threshold. If it is, the constant acceleration model is used; otherwise, the constant rotation and acceleration model is used.

[0015] According to the vehicle positioning kinematic model adaptive method provided by the present invention, the method further includes: acquiring road information of lane lines during vehicle driving, and determining, based on the road information and the speed information, whether to add a sideslip compensation model to the selected kinematic model to perform position compensation prediction for vehicle sideslip when the vehicle is turning.

[0016] According to the present invention, a kinematic model adaptive method for vehicle positioning includes determining, when the vehicle is turning, whether to add a sideslip compensation model to the selected kinematic model to predict the vehicle's sideslip position based on the road information and the speed information.

[0017] Establish a cubic polynomial equation for lane line detection and calculate the curvature of the lane where the current vehicle is located;

[0018] Determine whether the curvature is greater than or equal to a preset third threshold. If so, add a sideslip compensation model to the selected kinematic model.

[0019] Otherwise, based on the speed information and the weight of the vehicle trailer, it is determined whether to add a sideslip compensation model to the selected kinematic model.

[0020] According to the vehicle positioning kinematic model adaptation method provided by the present invention, the speed information further includes: the current longitudinal speed of the vehicle body. Correspondingly, the step of determining whether to add a sideslip compensation model based on the speed information and the vehicle-mounted weight includes:

[0021] Determine whether the difference between the angular velocity and the average angular velocity within the time window is within a range of several times the variance of the angular velocity within the time window. If so, then, if the longitudinal velocity is greater than or equal to the fourth threshold and the vehicle-mounted weight is greater than or equal to the fifth threshold, add a sideslip compensation model based on the selected kinematic model.

[0022] According to the adaptive kinematic model method for vehicle positioning provided by the present invention, after obtaining the speed information of the current vehicle coordinate system during vehicle movement, the method further includes: using the maximum movement frequency of the vehicle controlled by the vehicle control system as the threshold for low-pass filtering to perform low-pass filtering on the speed information, and adding the processed speed information into multiple time windows for information statistics to process noise data.

[0023] The present invention also provides a kinematic model adaptive device for vehicle positioning, comprising:

[0024] The acquisition module is used to acquire the speed information of the vehicle's current motion coordinate system during vehicle movement;

[0025] The kinematic model adaptive module is used to select the most suitable kinematic model from multiple preset kinematic models based on the velocity information, wherein the multiple preset kinematic models include: a constant rate of rotation and velocity model, a constant rate of rotation and acceleration model, and a constant acceleration model;

[0026] The vehicle positioning prediction module is used to predict the positioning of the current vehicle under different motion states using the selected kinematic model.

[0027] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the vehicle positioning kinematic model adaptive method as described above.

[0028] The present invention also provides a vehicle capable of assisted driving and / or autonomous driving, the vehicle including the electronic devices described above.

[0029] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the vehicle positioning kinematic model adaptive method as described above.

[0030] This invention provides a method, apparatus, device, and medium for adaptive kinematic modeling in vehicle positioning. It acquires the vehicle's current speed information during movement; based on this speed information, it selects the most suitable kinematic model from multiple preset kinematic models, such as a constant rev and velocity model, a constant rev and acceleration model, and a constant acceleration model; and uses this kinematic model to predict the vehicle's positioning under different motion states. Compared to existing filtering-based positioning schemes that often use a single kinematic model, this invention adaptively selects a more suitable kinematic model under different vehicle motion states, providing optimal position prediction and achieving higher positioning accuracy than using a single kinematic model overall. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0032] Figure 1 This is a flowchart illustrating an adaptive kinematic model method for vehicle positioning provided by the present invention.

[0033] Figure 2 This is a flowchart illustrating the specific steps of the vehicle adaptive selection of kinematics model in the method provided in this embodiment of the invention;

[0034] Figure 3 This is a flowchart illustrating the specific steps of adding a sideslip compensation model to an existing kinematic model in the method provided in this embodiment of the invention.

[0035] Figure 4 This is a schematic diagram of the structure of an adaptive kinematic model device for vehicle positioning provided by the present invention;

[0036] Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention.

[0037] Figure label:

[0038] 21: Acquisition module; 22: Kinematic model adaptive module; 23: Vehicle positioning prediction module. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described clearly and completely below with reference to specific embodiments and accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0040] It should be noted that those skilled in the art will understand, explicitly and implicitly, that the embodiments described in this invention can be combined with other embodiments without conflict. Unless otherwise defined, the technical or scientific terms used in this invention should be understood in their ordinary sense by those skilled in the art. The terms "a," "an," "an," "the," etc., used in this invention do not indicate quantity limitation and can represent singular or plural. The terms "comprising," "including," "having," and any variations thereof used in this invention are intended to cover non-exclusive inclusion; the terms "first," "second," "third," etc., used in this invention are merely to distinguish similar objects and do not represent a specific ordering of objects.

[0041] The following is an explanation of relevant terms in the art in the embodiments of this invention:

[0042] Kalman filtering: Kalman filtering is an algorithm that uses the state equations of a linear system to optimally estimate the system state using observed input and output data. Since the observed data includes noise and interference from the system, the optimal estimation can also be viewed as a filtering process. In other words, Kalman filtering essentially fuses the values ​​measured by sensors with values ​​derived from a mathematical model to approximate the actual values; therefore, it is often called a sensor fusion algorithm. Kalman filtering is commonly used for state estimation, such as vehicle position estimation (vehicle tracking) and pose estimation for mobile robots.

[0043] Kinematic models: Based on the complexity (number of times) of the kinematic model, they are divided into first-order motion models (also known as linear motion models) and second-order motion models. First-order motion models include: constant velocity model (CV) and constant acceleration model (CA). These linear motion models assume that the target is moving in a straight line and do not consider the turning of the object.

[0044] The secondary motion models include: the Constant Turn Rate and Velocity (CTRV) model and the Constant Turn Rate and Acceleration (CTRA) model.

[0045] Example 1

[0046] Reference Figure 1 As shown in this embodiment, an adaptive kinematic model method for vehicle positioning includes:

[0047] Step S1: Obtain the speed information of the vehicle in the current vehicle coordinate system while the vehicle is moving;

[0048] In this step, the vehicle speed information in the current vehicle coordinate system is obtained through the vehicle speed sensor.

[0049] Step S2: Select the most suitable kinematic model from multiple preset kinematic models based on velocity information. The multiple preset kinematic models include: constant rotation and velocity model, constant rotation and acceleration model, and constant acceleration model.

[0050] Figure 2 The flowchart illustrates the specific steps of the vehicle adaptive selection of the kinematic model in this embodiment. In this embodiment, the acquired velocity information includes the current angular velocity of the vehicle body. Step S2 specifically includes:

[0051] Step S201: Calculate the angular increment based on the angular velocity and the predetermined prediction duration;

[0052] Step S202: Determine whether the angular increment is greater than or equal to a preset first threshold. If so, proceed to step S203: Use a constant rotation rate and speed model.

[0053] Otherwise, proceed to step S204: determine whether the angular velocity is less than the preset second threshold. If yes, proceed to step S205: adopt the constant acceleration model. If no, proceed to step S206: adopt the constant rotation and acceleration model.

[0054] Specifically, theoretically, when modeling a problem, the more parameters and the more refined the model, the higher the computational accuracy. However, in reality, all sensors contain noise, so a more complex model with more variables does not necessarily yield higher accuracy. The technical solution of this invention uses the angular increment parameter in modeling to determine the appropriate kinematic model. The angular increment is obtained by integrating the angular velocity over a predetermined prediction duration. Based on the kinematic model used in the positioning filter, the prediction duration can be the time difference between the current time and the time of the last filter state update, or it can be a fixed duration, such as tens of milliseconds. Therefore, during modeling, if the angular increment is greater than or equal to a first threshold (in this embodiment, the first threshold is set to 0.2 rad, i.e., the absolute value of the angular increment ≥ 0.2 rad), we consider that the vehicle has indeed turned to some extent, and a turn rate needs to be added to make the model predict a more accurate position. Therefore, when the angular increment is ≥ 0.2 rad, the CTRV model is used. This model is suitable for predicting vehicle position at large angles, and its prediction result has a small error. If the angular increment is less than 0.2 rad, the angular velocity is further determined to be greater than or equal to the second threshold. If the angular velocity is greater than or equal to the second threshold (i.e., the absolute value of the angular velocity is ≥ 0.01 rad / s), the CTRA model is used. The CTRA model is used when the vehicle's cornering angle is not large because it is an approximation of Taylor expansion, typically a first-order Taylor expansion. This model is suitable for predicting vehicle position at small angles, and its prediction error is small. If the angular velocity is less than the second threshold (in this embodiment, the second threshold is set to 0.01 rad / s, i.e., the absolute value of the angular velocity is < 0.01 rad / s), the CA model is used. This case assumes the vehicle is not turning, but the data in this case contains noise. If a model with a turn rate is used, its prediction accuracy is not as high as the CA model. Therefore, the CA model is used when the angular velocity is relatively small, and its prediction accuracy is accurate. The values ​​of the first and second thresholds mentioned above are not limited to the limitations of this embodiment and can be adjusted according to the actual situation. Therefore, by obtaining the velocity information expressing the vehicle's motion state, adaptive selection of the vehicle kinematics model is achieved.

[0055] Step S3: Predict the location of the current vehicle under different motion states using the selected kinematic model.

[0056] In this step, in a positioning system based on filters and other methods, the Kalman filter uses the aforementioned adaptively selected kinematic model to predict the positioning of the current vehicle under different motion states.

[0057] In summary, this embodiment provides an adaptive kinematic model method for vehicle positioning, suitable for scenarios requiring short-term positioning prediction using kinematic models. It acquires the vehicle's current speed information during movement; based on this speed information, it selects the most suitable kinematic model from multiple preset kinematic models, such as constant rev and velocity models, constant rev and acceleration models, and constant acceleration models; and uses this kinematic model to predict the vehicle's positioning under different motion states. Compared to existing filtering-based positioning schemes that often use single kinematic models, this invention, by acquiring the vehicle's speed information, can adaptively select a more suitable kinematic model under different vehicle motion states, providing optimal position prediction and achieving higher positioning accuracy than using a single kinematic model overall.

[0058] The vehicle positioning kinematic model adaptive method provided in this embodiment further includes: step S4: obtaining road information of lane lines during vehicle driving, and determining whether to add a sideslip compensation model to the selected kinematic model to perform position compensation prediction for vehicle sideslip based on road information and speed information when the vehicle turns.

[0059] Figure 3 This embodiment shows a flowchart illustrating the specific steps of adding a sideslip compensation model to an existing kinematic model in the method described in this embodiment; in this embodiment, step S4 specifically includes:

[0060] Step S401: Establish the cubic polynomial equation for lane line detection;

[0061] Step S402: Calculate the curvature of the lane where the vehicle is currently located;

[0062] Step S403: Determine whether the curvature is greater than or equal to the preset third threshold. If so, proceed to step S404: Add a sideslip compensation model to the selected kinematic model.

[0063] Otherwise, based on the speed information and the weight of the vehicle and trailer, determine whether to add a sideslip compensation model to the selected kinematic model. That is, execute step S405: determine whether the difference between the angular velocity and the average angular velocity within the time window is within the variance range of the angular velocity of several times the time window. If so, and if the longitudinal velocity is greater than or equal to the fourth threshold and the weight of the vehicle and trailer is greater than or equal to the fifth threshold, add a sideslip compensation model to the selected kinematic model. That is, execute step S406: determine whether the longitudinal velocity is greater than or equal to the fourth threshold. If so, execute step S407: determine whether the weight of the vehicle and trailer carried by the front of the vehicle is greater than or equal to the fifth threshold. If so, execute step S404: add a sideslip compensation model to the selected kinematic model.

[0064] Specifically, lane line pixels are acquired using radar or vehicle-mounted cameras. A cubic polynomial equation (curve fitting equation) for lane line detection is established based on these pixels. The radius of curvature is obtained by solving the cubic polynomial equation to determine the curvature of the lane currently occupied by the vehicle. It is then determined whether the curvature is greater than or equal to a third threshold (in this embodiment, the third threshold is set to 0.001, i.e., curvature ≥ 0.001). If so, a sideslip compensation model is added to the selected kinematic model; otherwise, it is determined whether the difference between the angular velocity and the average angular velocity within the time window is within the variance range of the angular velocity over three times the time window (three times the time window). The time window is 3 frames (choosing a 3x time window minimizes the error in angular velocity observed within this window). If so, it further checks whether the longitudinal velocity in the preceding vehicle's coordinate system is greater than or equal to the fourth threshold (in this embodiment, the fourth threshold is set to 50 km / h, i.e., longitudinal velocity ≥ 50 km / h). If so, it continues to check whether the weight of the trailer currently carried by the truck is greater than or equal to the fifth threshold (in this embodiment, the fifth threshold is set to 20T, i.e., trailer weight ≥ 20T). If so, a sideslip compensation model is added to the selected kinematic model. If none of the above conditions are met, no sideslip compensation model is added. The values ​​of the third, fourth, and fifth thresholds are not limited to those of this embodiment and can be adjusted according to actual conditions. This embodiment is compatible with heavy trucks and provides the ability to add a sideslip compensation model to further improve prediction accuracy in different scenarios. Therefore, through the above steps, optimal position prediction can be provided based on different vehicle motion states and road information. By adding another sideslip compensation model to the selected kinematic model, more accurate position prediction of heavy trucks under high dynamic conditions can be achieved.

[0065] In this embodiment, after obtaining the speed information of the current vehicle coordinate system during vehicle movement in step S1, the method further includes: using the maximum movement frequency of the vehicle controlled by the vehicle control system as the threshold for low-pass filtering to perform low-pass filtering on the speed information, and adding the processed speed information into multiple time windows for information statistics to process noise data.

[0066] Specifically, the angular velocity, longitudinal velocity, and lateral velocity of the vehicle body in the current vehicle coordinate system are obtained. The vehicle control system uses the maximum movement frequency that can control the vehicle as the threshold of the low-pass filter to perform low-pass filtering on these velocity information. The processed values ​​are then added to multiple time windows (10-frame time windows) for information statistics. This method of using long-time window information statistics is used to process noise data and improve the accuracy of the sensor data.

[0067] Example 2

[0068] Based on the same inventive concept as the above method, and referring to... Figure 4As shown, this embodiment provides a kinematic model adaptive device for vehicle positioning, including:

[0069] Module 21 is used to acquire the speed information of the current vehicle body motion coordinate system during vehicle movement;

[0070] The kinematic model adaptation module 22 is used to select the most suitable kinematic model from multiple preset kinematic models based on velocity information. The multiple preset kinematic models include: a constant rate of rotation and velocity model, a constant rate of rotation and acceleration model, and a constant acceleration model.

[0071] The vehicle positioning prediction module 23 is used to predict the positioning of the current vehicle under different motion states using the selected kinematic model.

[0072] Specifically, the acquisition module 21 includes: a coordinate system establishment unit for establishing the motion coordinate system of the current vehicle; and a speed acquisition unit for acquiring real-time speed information of the vehicle during its movement based on the current motion coordinate system.

[0073] The kinematic model adaptive module 22 specifically includes: an angular increment calculation unit, used to calculate the angular increment based on the angular velocity and the predetermined prediction duration; a first judgment unit, used to judge whether the angular increment is greater than or equal to a preset first threshold; a second judgment unit, used to further judge whether the angular velocity is less than a preset second threshold if the angular increment is less than the first threshold; and a kinematic model adaptive selection unit, used to select the corresponding kinematic model based on the judgment results of the first and second judgment units, that is, when the angular increment is greater than or equal to the first threshold, a constant rotation rate and velocity model is used, or when the angular increment is less than the first threshold and the angular velocity is greater than the second threshold, a constant rotation rate and acceleration model is used, or when the angular increment is less than the first threshold and the angular velocity is less than the second threshold, a constant acceleration model is used.

[0074] This device also includes: a position prediction and compensation module, specifically comprising: a lane detection equation establishment unit, used to establish a cubic polynomial equation for lane detection; a curvature calculation module, used to solve the cubic polynomial equation to calculate the curvature of the lane currently occupied by the vehicle; a third judgment unit, used to determine whether the curvature is greater than or equal to a preset third threshold; a fourth judgment unit, used to determine whether the difference between the angular velocity and the average angular velocity within a time window is within a range of the variance of the angular velocity within a certain number of time windows; a fifth judgment unit, used to determine whether the longitudinal velocity is greater than or equal to a preset fourth threshold; and a sixth judgment unit, used to determine whether the vehicle's front end carries... Whether the weight of the trailer carried is greater than or equal to the preset fifth threshold; the sideslip compensation model adds a unit, which is used to add a sideslip compensation model to the selected kinematic model based on the judgment results of the third judgment unit, the fourth judgment unit, the fifth judgment unit and the sixth judgment unit. That is, when the curvature is greater than or equal to the third threshold, the sideslip compensation model is added to the selected kinematic model, or when the curvature is less than the third threshold and the longitudinal speed is greater than or equal to the fourth threshold and the weight of the trailer carried by the front of the vehicle is greater than or equal to the fifth threshold, the sideslip compensation model is added to the selected kinematic model.

[0075] The specific implementation process of the functions and roles of each module in the above device can be found in the implementation process of the corresponding steps in the above method. Therefore, relevant parts can be referred to in the description of the method embodiment, and will not be repeated here.

[0076] The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division. In actual implementation, there may be other division methods. In the embodiments, each functional module can be integrated into a processor, or each module can be a separate device, or two or more modules can be integrated into a device. Each functional module in each embodiment can be implemented in hardware or in the form of hardware plus software functional units.

[0077] Example 3

[0078] Reference Figure 5 As shown, this embodiment provides an electronic device, which includes: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. The processor 310, communication interface 320, and memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions from the memory 330. The processor 310 executes the vehicle positioning kinematic model adaptive method described in the above method embodiment, which includes:

[0079] Obtain the speed information of the vehicle in the current vehicle coordinate system while it is in motion;

[0080] The most suitable kinematic model is selected from multiple preset kinematic models based on velocity information. These preset kinematic models include: constant rotation and velocity model, constant rotation and acceleration model, and constant acceleration model.

[0081] The selected kinematic model is used to predict the location of the current vehicle under different motion states.

[0082] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0083] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program that can be stored on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, the computer is able to execute the vehicle positioning kinematic model adaptive method described in the above method embodiments, the method comprising:

[0084] Obtain the speed information of the vehicle in the current vehicle coordinate system while it is in motion;

[0085] The most suitable kinematic model is selected from multiple preset kinematic models based on velocity information. These preset kinematic models include: constant rotation and velocity model, constant rotation and acceleration model, and constant acceleration model.

[0086] The selected kinematic model is used to predict the location of the current vehicle under different motion states.

[0087] Example 4

[0088] This embodiment provides a vehicle capable of assisted driving and / or autonomous driving, including the electronic equipment described above. This enables the vehicle to adaptively select a more suitable kinematic model in different motion states, providing optimal position prediction through this kinematic model, achieving higher positioning accuracy than using a single kinematic model overall.

[0089] Example 5

[0090] This embodiment provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the vehicle positioning kinematic model adaptive method described in the above method embodiment. The method includes:

[0091] Obtain the speed information of the vehicle in the current vehicle coordinate system while it is in motion;

[0092] The most suitable kinematic model is selected from multiple preset kinematic models based on velocity information. These preset kinematic models include: constant rotation and velocity model, constant rotation and acceleration model, and constant acceleration model.

[0093] The selected kinematic model is used to predict the location of the current vehicle under different motion states.

[0094] The various embodiments in this invention are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are relatively simple in description because they are fundamentally similar to the method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0095] The devices, media, and methods provided in the embodiments of the present invention are one-to-one correspondences. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0096] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process method or product that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process method or product. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process method or product that includes that element.

[0097] The above are merely embodiments of the present invention and are not intended to limit the invention. Although the present invention has been described in detail above with general descriptions and specific embodiments, modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

Claims

1. An adaptive kinematic model method for vehicle positioning, characterized in that, include: Obtain the speed information of the vehicle in the current vehicle coordinate system while it is in motion; Based on the velocity information, the most suitable kinematic model is selected from multiple preset kinematic models, wherein the multiple preset kinematic models include: a constant rate of rotation and velocity model, a constant rate of rotation and acceleration model, and a constant acceleration model; The selected kinematic model is used to predict the location of the current vehicle under different motion states. Obtain road information about lane lines while the vehicle is in motion, establish a cubic polynomial equation for lane line detection, and calculate the curvature of the lane where the vehicle is currently located. If the curvature is less than the preset third threshold, it is determined whether the difference between the angular velocity and the average angular velocity within the time window is within the variance range of the angular velocity within a certain number of time windows. If so, a sideslip compensation model is added to the selected kinematic model, provided that the longitudinal velocity is greater than or equal to the fourth threshold and the vehicle weight is greater than or equal to the fifth threshold.

2. The adaptive kinematic model method for vehicle positioning according to claim 1, characterized in that, The speed information includes: the current angular velocity of the vehicle body; correspondingly, The step of selecting the most suitable kinematic model from multiple preset kinematic models based on the velocity information specifically includes: The angular increment is calculated based on the angular velocity and the predetermined prediction duration. Determine whether the angle increment is greater than or equal to a preset first threshold. If so, then the constant rotation rate and speed model is adopted. Otherwise, it is determined whether the angular velocity is less than a preset second threshold. If it is, the constant acceleration model is used; otherwise, the constant rotation and acceleration model is used.

3. The adaptive kinematic model method for vehicle positioning according to claim 1, characterized in that, The method further includes: If the curvature is greater than or equal to a preset third threshold, then a sideslip compensation model is added to the selected kinematic model.

4. The adaptive kinematic model method for vehicle positioning according to claim 1, characterized in that, After acquiring the speed information of the current vehicle coordinate system during vehicle movement, the method further includes: using the maximum movement frequency of the vehicle controlled by the vehicle control system as the threshold for low-pass filtering to perform low-pass filtering on the speed information, and adding the processed speed information into multiple time windows for information statistics to process noise data.

5. An adaptive kinematic model device for vehicle positioning, characterized in that, include: The acquisition module is used to acquire the speed information of the vehicle's current motion coordinate system during vehicle movement; The kinematic model adaptive module is used to select the most suitable kinematic model from multiple preset kinematic models based on the velocity information, wherein the multiple preset kinematic models include: a constant rate of rotation and velocity model, a constant rate of rotation and acceleration model, and a constant acceleration model; The vehicle positioning prediction module is used to predict the positioning of the current vehicle under different motion states using the selected kinematic model. The position prediction and compensation module is used to obtain road information of lane lines while the vehicle is driving, establish a cubic polynomial equation for lane line detection, and calculate the curvature of the lane where the vehicle is currently located. If the curvature is less than the preset third threshold, it is determined whether the difference between the angular velocity and the average angular velocity within the time window is within the variance range of the angular velocity within a certain number of time windows. If so, a sideslip compensation model is added to the selected kinematic model, provided that the longitudinal velocity is greater than or equal to the fourth threshold and the vehicle weight is greater than or equal to the fifth threshold.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the kinematic model adaptation method for vehicle positioning as described in any one of claims 1-4.

7. A vehicle capable of assisted driving and / or autonomous driving, characterized in that, The vehicle includes the electronic equipment as described in claim 6.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the kinematic model adaptive method for vehicle positioning as described in any one of claims 1-4.

Images