Vehicle hinge angle estimation method and system and vehicle

Abstract

The invention discloses a vehicle hinge angle estimation method and system and a vehicle. The method for estimating the hinging angle of the vehicle comprises the steps of obtaining a first hinging angle of the vehicle according to a pre-established hinging vehicle model; a second hinge angle, measured by a vehicle-mounted sensor, of the vehicle is obtained; and the first hinge angle and the second hinge angle are fused, and the final hinge angle of the vehicle is estimated. By the adoption of the control system for accurately estimating the hinge angle and automatic driving, the dynamic characteristics of the vehicle can be adjusted in real time, particularly, in the turning or emergency operation process, the vehicle is prevented from being out of control or overturning, and in the scenes of automatic driving truck queue or automatic parking and the like, accurate vehicle body posture information can be provided through hinge angle estimation; more accurate control can be realized under different road conditions, and the safety and controllability of the automatic driving vehicle can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of electric vehicles, and in particular to a method and system for estimating an articulation angle of a vehicle and a vehicle. Background Art

[0002] The articulation angle, in the automobile transportation industry, usually refers to the angle between the tractor-oriented axis of an articulated vehicle and the tractor-oriented axis of the follower trailer. The tractor-oriented trailer of an articulated vehicle is connected by bearings. Although they are inseparable, they can still move relative to each other by rotating. The articulation angle is a physical quantity that reflects this movement. Different from the autonomous driving technology of general passenger vehicles, the double-body articulation feature of commercial articulated vehicles brings new challenges to the perception, planning and control technology of autonomous driving.

[0003] High-precision articulation angle estimation results can significantly improve the safety of commercial articulated vehicles' autonomous driving trajectory planning and the accuracy of motion control. In the past, the measurement of articulation angles was mainly measured by installing angle sensors at the articulations. However, due to the diversity of saddle structures and sizes at the articulations of semi-trailer trains, it is difficult to install them uniformly and the dynamic response is also slow, which seriously affects the measurement results. The current articulation angle measurement algorithms mostly install sensors (lidar, millimeter-wave radar) at the rear of the tractor and install tags at the front of the trailer. The above method has a large change to the original vehicle and is more effective for measuring box trailers. Due to the variety of trailer types, it is not generally applicable to flatbed trucks, barn-type trailers, and tank trucks.

[0004] The following technical problems exist: the method of installing the articulation angle sensor increases the cost of the whole vehicle and requires redesigning the sensor for different trailers; the method of installing the sensor at the rear of the tractor increases the cost of the whole vehicle and is not applicable to different types of trailers. Summary of the invention

[0005] Based on this, it is necessary to provide a method, system and vehicle for estimating the articulation angle of a vehicle in response to the above-mentioned technical problems, which improves the accuracy of articulation angle estimation and avoids the situation where a single method fails and cannot estimate the articulation angle. It does not require any hardware to be installed on the tractor, reduces the cost of the entire vehicle and is applicable to various types of tractors. It does not require any signs to be placed on the trailer and is adaptable to various types of trailers.

[0006] In a first aspect, a method for estimating an articulation angle of a vehicle is provided, comprising:

[0007] Obtaining a first articulation angle of the vehicle according to a pre-established articulated vehicle model;

[0008] Obtaining a second articulation angle of the vehicle measured by an onboard sensor;

[0009] The first articulation angle and the second articulation angle are integrated to estimate a final articulation angle of the vehicle.

[0010] In some examples, before estimating a final articulation angle of the vehicle, the method further includes:

[0011] Estimate the mass of the vehicle to obtain the mass of the vehicle;

[0012] Determining whether the vehicle is equipped with a trailer according to the vehicle mass;

[0013] If yes, then the estimation of the final articulation angle of the vehicle is performed, otherwise the estimation of the final articulation angle of the vehicle is terminated,

[0014] The estimation of the vehicle mass includes:

[0015] When the vehicle's operating condition meets the mass estimation requirements, the vehicle mass is estimated by combining longitudinal dynamics and lateral dynamics. When the operating condition continues to fail to meet the mass estimation requirements, the vehicle's intelligent driving system manipulates the vehicle to perform corresponding acceleration, deceleration or steering actions in appropriate scenarios to make the vehicle's operating condition meet the mass estimation requirements.

[0016] In some examples, obtaining the first articulation angle of the vehicle according to a pre-established articulated vehicle model includes:

[0017] Establishing an articulated vehicle model of a tractor-trailer, wherein the articulated vehicle model is used to describe the relative motion between the tractor-trailer through the geometric structure of the tractor-trailer and its motion parameters;

[0018] According to the articulated vehicle model, the first articulation angle between the tractor and the semi-trailer is derived.

[0019] The articulated vehicle model includes one or both of a kinematics module and a dynamics model.

[0020] In some examples, deriving a first articulation angle between a tractor and a semi-trailer according to the articulated vehicle model includes:

[0021] Define the vehicle's wheelbase, speed, and initial articulation angle;

[0022] Obtain the speed, turning angle and relative motion of the tractor;

[0023] The change of the articulation angle at each moment is calculated through the kinematic model;

[0024] The real-time articulation angle is obtained through numerical integration;

[0025] A filtering algorithm is applied to smooth the variation of the articulation angle to obtain the first articulation angle.

[0026] In some examples, obtaining the second articulation angle of the vehicle measured by an onboard sensor includes:

[0027] The vehicle-mounted sensor is used to detect a second articulation angle of the vehicle, wherein the vehicle-mounted sensor includes at least one of the following:

[0028] Side laser radar, side 4D millimeter-wave radar, side camera and 360-degree fisheye camera.

[0029] Among them, when using lateral laser radar for articulation angle detection, the sides of different types of trailers can be fitted.

[0030] In some examples, fusing the first articulation angle and the second articulation angle to estimate a final articulation angle of the vehicle includes:

[0031] The first articulation angle and the second articulation angle are fused by using algorithms such as Kalman filtering to obtain a final articulation angle of the vehicle.

[0032] In some examples, after estimating the final articulation angle of the vehicle, the method further includes:

[0033] The articulation angle is corrected by an offline correction method or an online correction method. The offline correction method is used for vehicles in the development process and the test process to correct the weight parameters in the estimation algorithm, and the online correction method is used for mass-produced vehicles to improve the estimation accuracy of the articulation angle.

[0034] In a second aspect, a vehicle articulation angle estimation system is provided, comprising:

[0035] An acquisition module, configured to obtain a first articulation angle of the vehicle according to a pre-established articulated vehicle model;

[0036] A measuring module, used for obtaining a second articulation angle of the vehicle measured by an on-board sensor;

[0037] An estimation module is used to fuse the first articulation angle and the second articulation angle to estimate a final articulation angle of the vehicle.

[0038] According to a third aspect, a vehicle is provided, comprising: an articulation angle estimation system for a vehicle according to the second aspect.

[0039] In a fourth aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the vehicle articulation angle estimation method of the first aspect and any possible implementation method of the first aspect are implemented.

[0040] In a fifth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the steps of the vehicle articulation angle estimation method of the above-mentioned first aspect and any possible implementation method of the first aspect are implemented.

[0041] In a sixth aspect, a computer program product is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of the vehicle articulation angle estimation method of the above-mentioned first aspect and any possible implementation method of the first aspect are implemented.

[0042] According to the embodiment of the present application, the first articulation angle of the vehicle is obtained according to the pre-established articulated vehicle model, and then the second articulation angle of the vehicle measured by the vehicle-mounted sensor is obtained. Finally, the first articulation angle and the second articulation angle are integrated to estimate the final articulation angle of the vehicle. The accuracy of the articulation angle estimation is improved, and the failure of a single method to estimate the articulation angle is avoided. There is no need to install any hardware on the tractor, which reduces the cost of the whole vehicle and is applicable to various types of tractors. There is no need to arrange any signs on the trailer, and it is adaptable to various types of trailers. By accurately estimating the articulation angle, the control system of the autonomous driving can adjust the dynamic characteristics of the vehicle in real time, especially when turning or in emergency operations, to prevent the vehicle from losing control or overturning. In scenarios such as autonomous driving truck queues or automatic parking, the articulation angle estimation can provide accurate vehicle posture information, help achieve more precise control under different road conditions, and improve the safety and controllability of autonomous driving vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0044] Figure 1 A flow chart of a method for estimating the articulation angle of a vehicle provided in an embodiment of the present application;

[0045] Figure 2 It is a schematic diagram of a coordinate system with the centerline point of the front of the vehicle as the origin, the x-axis to the left and the y-axis to the rear;

[0046] Figure 3 It is a top view of the trailer;

[0047] Figure 4 This is a schematic diagram of the vehicle's hardware configuration;

[0048] Figure 5 It is a schematic diagram of the position of the articulation angle between the tractor trailer;

[0049] Figure 6 It is a cross-sectional view similar to a tanker truck;

[0050] Figure 7A structural block diagram of an articulation angle estimation system for a vehicle provided in an embodiment of the present application;

[0051] Figure 8 A structural block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The present application is further described in detail below in conjunction with the embodiments and drawings. It is to be understood that the specific embodiments described herein are only used to explain the relevant application, rather than to limit the application. It is also necessary to explain that, for ease of description, only the parts related to the application are shown in the drawings.

[0053] It should be noted that, in the absence of conflict, the embodiments of the present application, that is, the features of the embodiments, can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0054] The following describes in detail the articulation angle estimation method, system and vehicle of a vehicle according to an embodiment of the present application in conjunction with the accompanying drawings.

[0055] Figure 1 FIG. 1 is a flow chart of a method for estimating the articulation angle of a vehicle according to an embodiment of the present application. Figure 1 As shown, the method for estimating the articulation angle of a vehicle according to an embodiment of the present application includes the following steps:

[0056] S101: Obtaining a first articulation angle of the vehicle according to a pre-established articulated vehicle model.

[0057] In one embodiment of the present application, it is first necessary to determine whether to estimate the articulation angle, that is: estimate the mass of the entire vehicle to obtain the mass of the entire vehicle; determine whether the vehicle is equipped with a trailer based on the mass of the entire vehicle; if so, estimate the final articulation angle of the vehicle, otherwise terminate the estimation of the final articulation angle of the vehicle.

[0058] Among them, estimating the mass of the whole vehicle includes: when the working condition of the vehicle meets the mass estimation requirements, estimating the mass of the whole vehicle by combining longitudinal dynamics and lateral dynamics, wherein, when the working condition continues to fail to meet the mass estimation requirements, the intelligent driving system of the vehicle manipulates the vehicle to perform corresponding acceleration, deceleration or steering actions in appropriate scenarios, so that the working condition of the vehicle meets the mass estimation requirements. That is: if the working condition of the vehicle does not meet the mass estimation requirements all the time, the intelligent driving system of the vehicle manipulates the vehicle to perform corresponding acceleration, deceleration or steering actions in appropriate scenarios, thereby, the working condition of the vehicle usually meets the mass estimation requirements.

[0059] For example: if it is a tractor-trailer, the articulation angle is estimated, otherwise it is not necessary to estimate the articulation angle.

[0060] In one embodiment of the present application, according to a pre-established articulated vehicle model, obtaining the first articulation angle of the vehicle includes: establishing an articulated vehicle model of a tractor-trailer, wherein the articulated vehicle model is used to describe the relative motion between the tractor-trailer, through the geometric structure of the tractor-trailer and its motion parameters; according to the articulated vehicle model, deriving the first articulation angle between the tractor-trailer. The articulated vehicle model includes one or both of a kinematics module or a dynamics model.

[0061] In this example, the first articulation angle between the tractor and the semi-trailer is derived based on the articulated vehicle model, including: defining the wheelbase, speed and initial articulation angle of the vehicle; obtaining the speed, turning angle and relative motion of the tractor; calculating the change of the articulation angle at each moment through a kinematic model; obtaining the real-time articulation angle through numerical integration; and applying a filtering algorithm to smooth the change of the articulation angle to obtain the first articulation angle.

[0062] Specifically, the mass value estimated by the mass estimation module can be greater than a certain threshold (the weight of the tractor) to determine whether the train is equipped with a trailer. If the train is equipped with a trailer, the articulation angle is estimated in real time. Otherwise, if the train is not equipped with a trailer, there is no need to estimate the articulation angle.

[0063] The vehicle mass estimation module estimates the mass of the vehicle by combining longitudinal dynamics and lateral dynamics;

[0064] The vehicle mass is estimated using the longitudinal dynamics method by the following formula;

[0065] m*ax=F1-F2;

[0066] Where m is the vehicle mass (to be estimated); ax is the longitudinal acceleration of the vehicle; F1- is the driving force of the vehicle, and F2 is the resistance of the vehicle. The use of longitudinal dynamics estimation requires that the acceleration of the vehicle cannot be too small, that is, the absolute value of ax is greater than a certain threshold as an entry condition.

[0067] However, if the vehicle is always in a constant speed condition, resulting in the estimation result not converging; then: the vehicle's intelligent driving system controls the vehicle to perform a certain degree of acceleration and deceleration in appropriate scenarios, thereby shortening the estimation convergence time.

[0068] Estimate the mass using the transverse dynamics method using the following formula:

[0069] m*ay=Fy;

[0070] Where m is the vehicle mass, ay is the lateral acceleration of the vehicle, and Fy is the lateral force of the vehicle. The lateral force Fy of the tire is usually related to the tire's sideslip angle, the vehicle's sideslip angle, and the vehicle speed, and can be described by a tire model.

[0071] Select a suitable working condition, such as a working condition on a curve, when the absolute value of ay is greater than a certain threshold; if the working condition is always on a straight road, then: the vehicle's intelligent driving system controls the vehicle to change lanes to the left or right in a suitable scenario to enter a scenario estimated using lateral dynamics.

[0072] Vehicle weight identification does not need to be calculated all the time. It is only calculated at the beginning of the program. Once the set termination condition is reached, the system identification algorithm is terminated to save computing power.

[0073] Calculate the articulation angle using an articulated vehicle model:

[0074] The kinematic model of the tractor-trailer is established and the articulation angle is calculated according to the model.

[0075] The kinematic model of the tractor-trailer is established. The core is to describe the relative motion between the tractor and the trailer. The articulation angle between the two is derived through the geometric structure of the vehicle and its motion parameters.

[0076] The kinematic equations of the tractor and the semi-trailer. By analyzing the kinematic relationship between the tractor and the semi-trailer, the rate of change of the articulation angle can be obtained.

[0077]

[0078] where v t is the tractor speed, v s is the speed of the semitrailer, R t is the turning radius of the tractor, R s It is the turning radius of the semi-trailer.

[0079] The motion of the tractor follows the following kinematic relationship:

[0080]

[0081] L t is the wheelbase of the tractor, delta_t is the front wheel turning angle;

[0082]

[0083] Kinematic equations of a semitrailer:

[0084] ν s =v t ·cos(ψ)

[0085]

[0086] Theta_s is the turning angle of the semi-trailer, L s It is the wheelbase of the semi-trailer.

[0087] In order to obtain a continuous articulation angle, the rate of change of the articulation angle can be Perform numerical integration. Assuming that the articulation angle at time t0 is ψ0, then the articulation angle ψ(t) at subsequent times is:

[0088]

[0089] By discretizing this equation and updating the articulation angle at each moment, the articulation angle of the vehicle during the entire driving process can be obtained.

[0090] The implementation steps are as follows:

[0091] Initialization parameters: Define the vehicle's wheelbase, speed, and initial articulation angle.

[0092] Real-time data update: Get the speed, turning angle and relative movement of the tractor based on sensor data (such as GPS, wheel speed sensor).

[0093] Calculate the articulation angle change rate: Calculate the articulation angle change rate at each moment through the kinematic model.

[0094] Integrate to solve the articulation angle: Get the real-time articulation angle through numerical integration.

[0095] Filtering and smoothing: To eliminate noise, a filtering algorithm (such as Kalman filtering) can be applied to smooth the changes in the articulation angle.

[0096] By building a dynamic model of the tractor-trailer, the articulation angle is calculated based on the model. The rate of change of the articulation angle is directly related to the yaw rate of the tractor and the semitrailer. The rate of change of the articulation angle can be expressed as:

[0097]

[0098] where w t is the yaw rate of the tractor, w s is the yaw rate of the semitrailer;

[0099] The kinematic equation of tractor yaw is:

[0100]

[0101] The kinematic equation of the semitrailer yaw:

[0102]

[0103] Based on the dynamic equation and the articulation angle change rate equation, the numerical integration method can be used to gradually calculate the articulation angle change at each time step:

[0104]

[0105] S102: Obtain a second articulation angle of the vehicle measured by a vehicle-mounted sensor.

[0106] In one embodiment of the present application, obtaining the second articulation angle of the vehicle measured by a vehicle-mounted sensor includes: applying the vehicle-mounted sensor to detect the second articulation angle of the vehicle, wherein the vehicle-mounted sensor includes but is not limited to at least one of the following: a lateral laser radar, a lateral 4D millimeter-wave radar, a lateral camera, and a 360-degree surround fisheye camera.

[0107] Specifically, the articulation angle is measured in real time by sensors:

[0108] The articulation angle is estimated using one or more of a variety of sensors installed in the autonomous vehicle; the sensors include but are not limited to side lidar, side 4D millimeter-wave radar, side camera and 360-degree surround fisheye camera, etc.

[0109] The articulation angle is calculated based on the vehicle's lateral LiDAR.

[0110] Original point cloud data acquisition: The laser beam emitted by the side laser radar measures the distance to surrounding objects and can generate high-precision three-dimensional point cloud data. Through these point cloud data, the outline of the vehicle body and the relative position of the tractor and trailer can be detected.

[0111] Target trailer recognition and feature surface extraction.

[0112] Use point cloud data to identify the outlines of the tractor and trailer, especially the key areas near the articulation points. Clustering or shape recognition algorithms can be used to extract feature points related to the tractor and trailer. Feature points usually include the edges and corners of the vehicle body. Abnormal data is removed and the center axis of the trailer y=ax+b is fitted to calculate the angle between the trailer axis and the tractor axis.

[0113] Articulation angle calculation:

[0114] Establish as Figure 2 The coordinate system shown is a coordinate system with the center line of the front of the vehicle as the origin, the x-axis to the left and the y-axis to the rear, wherein the fitted center axis of the trailer is y=ax+b. Then the estimated articulation angle alpha is arctan(1 / a).

[0115] Filtering and smoothing. Since LiDAR data may be affected by noise, a filtering algorithm (such as Kalman filtering or low-pass filtering) is used to smooth the articulation angle to reduce transient errors and jitter and provide a stable angle output.

[0116] The trailer point cloud data collected by the lateral lidar is processed, and the lidar point cloud results are processed to fit the point cloud results of different types of trailers into a relatively flat plane.

[0117] For example, for a box trailer, since its side is relatively flat, only smoothing filtering is needed to obtain a better ground plane.

[0118] For example: If the plane has a large area of ​​unevenness, the top view is as follows: Figure 3 , then the abnormal points away from the center plane are proposed and the side plane is fitted;

[0119] For example, similar to a tanker truck, take the protruding points in it for fitting to get an approximate plane.

[0120] The articulation angle is calculated based on the vehicle's side-view cameras.

[0121] Object detection and feature point tracking. Using images captured by the camera, use computer vision techniques (such as convolutional neural networks or traditional feature point detection algorithms) to identify specific parts of the vehicle, such as the edges, corners, or other significant features of the vehicle body. Once the key points of the vehicle are detected, the movement of these points in the image can be tracked using optical flow or other tracking algorithms.

[0122] Articulation angle calculation,

[0123] Once the different parts of the vehicle body are identified and tracked, the next step is to calculate the articulation angle by geometric methods. The articulation angle is the relative rotation angle between the tractor and the trailer, usually calculated by the vector between two key points. The angle in the camera coordinate system can be estimated by trigonometric functions:

[0124]

[0125] Among them, (x1, y1) and (x2, y2) are the coordinates of the two feature points of the tractor and trailer in the image plane.

[0126] Multi-frame data fusion and smoothing:

[0127] Since the images collected by the camera may be affected by noise or jitter, the articulation angle needs to be smoothed through time series data. A filter (such as a Kalman filter) can be used to fuse and optimize the estimated articulation angle to improve accuracy.

[0128] S103: Fusing the first articulation angle and the second articulation angle to estimate a final articulation angle of the vehicle.

[0129] In one embodiment of the present application, the fusing of the first articulation angle and the second articulation angle to estimate the final articulation angle of the vehicle includes: using algorithms such as Kalman filtering to fuse the first articulation angle and the second articulation angle to obtain the final articulation angle of the vehicle.

[0130] Specifically, the Kalman filter and other algorithms are used to fuse the model value and the measured value to output the final articulation angle value, and further calculate the articulation angle acceleration; articulation angle acceleration.

[0131] The vehicle articulation angle estimation method of the embodiment of the present application, after estimating the final articulation angle of the vehicle, further includes: correcting the final articulation angle of the vehicle in real time. For example, the articulation angle is corrected by an offline correction method or an online correction method, wherein the offline correction method is used for vehicles in the development process and the testing process to correct the weight parameters in the estimation algorithm, and the online correction method is used for mass-produced vehicles to improve the estimation accuracy of the articulation angle. Wherein:

[0132] The calibration method can be divided into an online self-calibration module and an offline calibration module.

[0133] On a mass-produced vehicle, the online self-calibration module determines that the vehicle is in a straight-line driving condition with a hitch, and considers that the articulation angle at this time is 0. The subsequent articulation angle information is updated.

[0134] Offline calibration module, on the developed engineering vehicle, install a high-precision angle measurement device near the tractor saddle, directly measure the articulation angle online, and calibrate the fusion result. The high-precision angle measurement device can be a Hall sensor, a magnetic sensor or a photoelectric encoder, which can achieve 0.1 degree or even higher accuracy measurement. The calibration methods of the offline calibration module are divided into static calibration and dynamic calibration.

[0135] For static calibration, the vehicle is parked in place and the tractor and trailer are placed at a certain angle, such as 5°, 10°, 15°, 20°, etc., to calibrate the sensor's measurement results.

[0136] Dynamic calibration involves driving the vehicle to perform various test conditions, such as passing curves of different curvatures at different speeds, changing lanes to the left or right, etc. The estimated articulation angle is calibrated through real-time measurement of high-precision articulation angle data.

[0137] The first embodiment of the present application relates to a method for measuring the articulation angle of a vehicle, which is applied to a device for measuring the articulation angle of a vehicle, such as Figure 4 As shown, the vehicle includes a tractor 1 and a semitrailer 2 articulated with the tractor 1 at an articulation point 3, and one or more side laser radars, side cameras and other sensors are installed on the side of the tractor.

[0138] Figure 5 It is a schematic diagram of the position of the articulation angle between the tractor trailer according to the first embodiment of the present application.

[0139] Specific as Figure 5As shown, in Figure a, the tractor and the trailer are parallel, and the articulation angle is 0; in Figure b, the articulation angle is the angle alpha between the tractor 1 and the semi-trailer 2.

[0140] in, Figure 3 It’s a top view of some kind of trailer; Figure 6 It is similar to half of a tanker truck cross-section.

[0141] According to the vehicle articulation angle estimation method of the embodiment of the present application, the first articulation angle of the vehicle is obtained according to the pre-established articulated vehicle model, and then the second articulation angle of the vehicle measured by the vehicle-mounted sensor is obtained. Finally, the first articulation angle and the second articulation angle are integrated to estimate the final articulation angle of the vehicle. The estimation accuracy of the articulation angle is improved, and the failure of a single method to estimate the articulation angle is avoided. No hardware needs to be installed on the tractor, the cost of the whole vehicle is reduced, and it is applicable to various types of tractors. No signs need to be arranged on the trailer, and it is adaptable to various types of trailers. By accurately estimating the articulation angle, the control system of the autonomous driving can adjust the dynamic characteristics of the vehicle in real time, especially when turning or in emergency operations, to prevent the vehicle from losing control or overturning. In scenarios such as autonomous driving truck queues or automatic parking, the articulation angle estimation can provide accurate vehicle posture information, help achieve more precise control under different road conditions, and improve the safety and controllability of autonomous driving vehicles.

[0142] Figure 7 FIG. 1 is a structural block diagram of a vehicle articulation angle estimation system according to an embodiment of the present application. Figure 7 As shown, the articulation angle estimation system of a vehicle according to one embodiment of the present application includes: an acquisition module 710, a measurement module 720 and an estimation module 730, wherein:

[0143] An acquisition module 710 is used to obtain a first articulation angle of the vehicle according to a pre-established articulated vehicle model;

[0144] A measuring module 720 is used to obtain a second articulation angle of the vehicle measured by a vehicle-mounted sensor;

[0145] The estimation module 730 is used to fuse the first articulation angle and the second articulation angle to estimate a final articulation angle of the vehicle.

[0146] According to the vehicle articulation angle estimation system of the embodiment of the present application, the first articulation angle of the vehicle is obtained according to the pre-established articulated vehicle model, and then the second articulation angle of the vehicle measured by the vehicle-mounted sensor is obtained. Finally, the first articulation angle and the second articulation angle are integrated to estimate the final articulation angle of the vehicle. The articulation angle estimation accuracy is improved, and the failure of a single method to estimate the articulation angle is avoided. No hardware needs to be installed on the tractor, the cost of the whole vehicle is reduced, and it is applicable to various types of tractors. No signs need to be arranged on the trailer, and it is adaptable to various types of trailers. By accurately estimating the articulation angle, the control system of the autonomous driving can adjust the dynamic characteristics of the vehicle in real time, especially when turning or emergency operations, to prevent the vehicle from losing control or overturning. In scenarios such as autonomous driving truck queues or automatic parking, the articulation angle estimation can provide accurate vehicle posture information, help achieve more precise control under different road conditions, and improve the safety and controllability of autonomous driving vehicles.

[0147] For the specific definition of the vehicle's articulation angle estimation system, please refer to the definition of the vehicle's articulation angle estimation method mentioned above, which will not be repeated here. The various modules of the above-mentioned vehicle's articulation angle estimation system can be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0148] In one embodiment, a vehicle is provided, comprising: an articulation angle estimation system for a vehicle according to the above embodiment, wherein the vehicle obtains a first articulation angle of the vehicle according to a pre-established articulated vehicle model, then obtains a second articulation angle of the vehicle measured by an onboard sensor, and finally, fuses the first articulation angle and the second articulation angle to estimate the final articulation angle of the vehicle. The articulation angle estimation accuracy is improved, and the failure of a single method to estimate the articulation angle is avoided. No hardware is required to be installed on the tractor, the cost of the whole vehicle is reduced, and the vehicle is applicable to various types of tractors. No signs are required to be arranged on the trailer, and the vehicle is adaptable to various types of trailers. By accurately estimating the articulation angle, the control system of the autonomous driving can adjust the dynamic characteristics of the vehicle in real time, especially when turning or in emergency operation, to prevent the vehicle from losing control or overturning. In scenarios such as autonomous driving truck platoons or automatic parking, the articulation angle estimation can provide accurate vehicle posture information, help achieve more precise control under different road conditions, and improve the safety and controllability of the autonomous driving vehicle.

[0149] In one embodiment, a computer device is provided. Figure 8 This is a block diagram of the computer device provided in the embodiment of the present application, refer to Figure 8The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the embodiment of the method for estimating the articulation angle of the vehicle is implemented. For example, the method includes: obtaining a first articulation angle of the vehicle according to a pre-established articulated vehicle model;

[0150] Obtaining a second articulation angle of the vehicle measured by an onboard sensor;

[0151] The first articulation angle and the second articulation angle are integrated to estimate a final articulation angle of the vehicle.

[0152] The embodiment of the present application further provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and the processor executes the computer program to implement the above-mentioned vehicle articulation angle estimation method embodiment. For example, the following steps are performed: according to a pre-established articulated vehicle model, a first articulation angle of the vehicle is obtained;

[0153] Obtaining a second articulation angle of the vehicle measured by an onboard sensor;

[0154] The first articulation angle and the second articulation angle are fused to estimate a final articulation angle of the vehicle.

[0155] The present application embodiment provides a computer program product, which includes instructions. When the instructions are executed, the method described in the embodiment of the present application is executed. For example, it can be executed Figure 1 The various steps of the vehicle articulation angle estimation method shown are, for example, performed as follows: obtaining a first articulation angle of the vehicle according to a pre-established articulated vehicle model;

[0156] Obtaining a second articulation angle of the vehicle measured by an onboard sensor;

[0157] The first articulation angle and the second articulation angle are fused to estimate a final articulation angle of the vehicle.

[0158] Those of ordinary skill in the art can understand that all or part of the processes in the methods for implementing the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0159] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0160] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A method for estimating the articulation angle of a vehicle, characterized in that: include: Obtaining a first articulation angle of the vehicle according to a pre-established articulated vehicle model; Obtaining a second articulation angle of the vehicle measured by an onboard sensor; The first articulation angle and the second articulation angle are integrated to estimate a final articulation angle of the vehicle.

2. The method for estimating the articulation angle of a vehicle according to claim 1, characterized in that: Prior to estimating the final articulation angle of the vehicle, it is also included: Estimate the mass of the vehicle to obtain the mass of the vehicle; Determining whether the vehicle is equipped with a trailer according to the vehicle mass; If yes, then the estimation of the final articulation angle of the vehicle is performed, otherwise the estimation of the final articulation angle of the vehicle is terminated, The estimation of the vehicle mass includes: When the vehicle's operating condition meets the mass estimation requirements, the vehicle mass is estimated by combining longitudinal dynamics and lateral dynamics. When the operating condition continues to fail to meet the mass estimation requirements, the vehicle's intelligent driving system manipulates the vehicle to perform corresponding acceleration, deceleration or steering actions in appropriate scenarios to make the vehicle's operating condition meet the mass estimation requirements.

3. The method for estimating the articulation angle of a vehicle according to claim 1 or 2, characterized in that: The step of obtaining a first articulation angle of the vehicle according to a pre-established articulated vehicle model comprises: Establishing an articulated vehicle model of a tractor-trailer, wherein the articulated vehicle model is used to describe the relative motion between the tractor-trailer through the geometric structure of the tractor-trailer and its motion parameters; According to the articulated vehicle model, the first articulation angle between the tractor and the semi-trailer is derived. The articulated vehicle model includes one or both of a kinematics module and a dynamics model.

4. The method for estimating the articulation angle of a vehicle according to claim 3, characterized in that: The step of deriving a first articulation angle between the tractor and the semi-trailer according to the articulated vehicle model comprises: Define the vehicle's wheelbase, speed, and initial articulation angle; Obtain the speed, turning angle and relative motion of the tractor; The change of the articulation angle at each moment is calculated through the kinematic model; The real-time articulation angle is obtained through numerical integration; A filtering algorithm is applied to smooth the variation of the articulation angle to obtain the first articulation angle.

5. The method for estimating the articulation angle of a vehicle according to claim 1 or 2, characterized in that: The obtaining of the second articulation angle of the vehicle measured by the vehicle-mounted sensor comprises: The vehicle-mounted sensor is used to detect a second articulation angle of the vehicle, wherein the vehicle-mounted sensor includes at least one of the following: Side laser radar, side 4D millimeter-wave radar, side camera and 360-degree fisheye camera. Among them, when using lateral laser radar for articulation angle detection, the sides of different types of trailers can be fitted.

6. The method for estimating the articulation angle of a vehicle according to claim 1 or 2, characterized in that: The fusing the first articulation angle and the second articulation angle to estimate a final articulation angle of the vehicle includes: The first articulation angle and the second articulation angle are fused by using algorithms such as Kalman filtering to obtain a final articulation angle of the vehicle.

7. The method for estimating the articulation angle of a vehicle according to claim 1, characterized in that: After estimating the final articulation angle of the vehicle, further comprising: The articulation angle is corrected by an offline correction method or an online correction method. The offline correction method is used for vehicles in the development process and the test process to correct the weight parameters in the estimation algorithm, and the online correction method is used for mass-produced vehicles to improve the estimation accuracy of the articulation angle.

8. A vehicle articulation angle estimation system, characterized in that: include: An acquisition module, configured to obtain a first articulation angle of the vehicle according to a pre-established articulated vehicle model; A measuring module, used for obtaining a second articulation angle of the vehicle measured by an on-board sensor; An estimation module is used to fuse the first articulation angle and the second articulation angle to estimate a final articulation angle of the vehicle.

9. A vehicle, characterized in that: include: The articulation angle estimation system for a vehicle according to claim 8.

10. A computer 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, the articulation angle estimation method for a vehicle according to any one of claims 1 to 7 is implemented.

Images