WO2024045741A1

WO2024045741A1 - Vehicle yaw angle prediction method and device and computer readable storage medium

Info

Publication number: WO2024045741A1
Application number: PCT/CN2023/098393
Authority: WO
Inventors: 高延熹; 顾原; 庞竹吟; 陈博; 吕颖; 韩佳琪; 王艺蒙
Original assignee: 中国第一汽车股份有限公司
Priority date: 2022-08-31
Filing date: 2023-06-05
Publication date: 2024-03-07
Also published as: CN115257782A

Abstract

Disclosed in embodiments of the present disclosure are a vehicle yaw angle prediction method and device and a computer readable storage medium. The method comprises: on the basis of a vehicle center of mass traveling speed and yaw angle sensing data of a target vehicle, determining a vehicle yaw angle of the target vehicle at the current moment; determining a turning radius and a tire sideslip angle of wheels of the target vehicle; on the basis of the equivalent velocity, turning radius and tire sideslip angle of the wheels of the target vehicle in a wheel traveling direction, determining the actual speed of the wheels in a vehicle traveling direction; determining a vehicle yaw angle weighted angular velocity of the wheels on the basis of the actual speed of the wheels of the target vehicle; and on the basis of the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheels, determining a target vehicle yaw angle of the target vehicle at a predetermined prediction moment.

Description

Vehicle yaw angle prediction method, device and computer-readable storage medium

cross-citation

This disclosure claims priority to the Chinese patent application filed with the China Patent Office on August 31, 2022, with application number 202211062092.7 and the application title "Vehicle yaw angle prediction method, device and computer-readable storage medium", the entire content of which is incorporated by reference. incorporated in this disclosure.

Technical field

The present disclosure relates to the field of data processing, and specifically to a vehicle yaw angle prediction method, device and computer-readable storage medium.

Background technique

In the related art, there is a technical problem of inaccurate vehicle yaw angle estimation.

In response to the above problems, no effective solution has yet been proposed.

Contents of the invention

Embodiments of the present disclosure provide a vehicle yaw angle prediction method, device and computer-readable storage medium to at least solve the technical problem of inaccurate vehicle yaw angle estimation.

According to one aspect of an embodiment of the present disclosure, a vehicle yaw angle prediction method is provided, including: determining the vehicle yaw angle of the target vehicle at the current moment based on the vehicle center of mass traveling speed and yaw angle sensing data of the target vehicle; determining The turning radius and tire slip angle of the target vehicle's wheels; based on the equivalent speed of the target vehicle's wheels in the wheel's traveling direction, the turning radius and the tire slip angle, determine the actual speed of the wheels in the vehicle's traveling direction; based on the target vehicle's wheels The actual speed of the vehicle is determined to determine the vehicle yaw angle weighted angular velocity of the wheel; based on the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheel, the target vehicle yaw angle of the target vehicle at the predetermined prediction time is determined.

Optionally, determine the actual speed of the wheels in the vehicle's traveling direction based on the equivalent speed, turning radius and tire slip angle of the target vehicle's wheels in the vehicle's traveling direction, including: using the wheel speed sensor in the target vehicle to obtain respectively The first equivalent speed of the wheel; obtain the rotation angular velocity and wheel radius of the wheel respectively, and calculate the second equivalent speed of the wheel based on the rotation angular velocity and wheel radius; according to a predetermined ratio, calculate the first equivalent speed of the wheel The speed and the second equivalent speed are combined to obtain the comprehensive equivalent speed of the wheel; based on the comprehensive equivalent speed of the wheel, the turning radius and the tire slip angle, the actual speed of the wheel is calculated.

Optionally, determining the vehicle yaw angle weighted angular velocity of the wheels based on the actual speed of the wheels of the target vehicle includes: determining the vehicle yaw angle weighted angular velocity of the wheels based on the actual speed of the wheels, the vehicle center of mass traveling speed and the turning radius.

Optionally, based on the weighted angular velocity of the vehicle yaw angle and the vehicle yaw angle of the wheels at the current moment, determining the target vehicle yaw angle of the target vehicle at the predetermined prediction time includes: based on the vehicle yaw angle at the current moment and the vehicle yaw angle of the wheels. The yaw angle weighted angular velocity uses the target prediction model to determine the yaw angle of the target vehicle at the predetermined prediction time. The target prediction model is built based on the particle filter algorithm and is obtained after training with multiple sets of sample data.

Optionally, according to the method of claim 1, based on the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheels, determining the target vehicle yaw angle of the target vehicle at the predetermined predicted time includes:

Among them, ψ _K+1 is the target vehicle yaw angle at the predetermined prediction time, ψ _K is the vehicle yaw angle at the current moment, is the weighted angular velocity of the vehicle yaw angle at the current moment, is the weighted angular acceleration of the vehicle yaw angle at the current moment, and T is the duration from the current moment to the predetermined predicted moment.

Optionally, based on the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheels, determine the target vehicle yaw angle of the target vehicle at the predetermined prediction time, including: obtaining the measurement noise of the sensor in the target vehicle; based on the measurement The noise, the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheels are used to determine the target vehicle yaw angle of the target vehicle at the predetermined prediction time.

According to another aspect of the embodiment of the present disclosure, a vehicle yaw angle prediction device is also provided, including: a first determination module configured to determine the target vehicle based on the vehicle center of mass traveling speed and yaw angle sensing data of the target vehicle. The vehicle yaw angle at the current moment; the second determination module is configured to determine the turning radius and tire slip angle of the target vehicle wheels; the third determination module is configured to determine the turning radius based on the equivalent speed of the target vehicle wheels in the wheel traveling direction. radius and tire slip angle to determine the actual speed of the wheel in the direction of vehicle travel; the fourth determination module is set to determine the vehicle yaw angle weighted angular velocity of the wheel based on the actual speed of the wheel of the target vehicle; the fifth determination module is set to The target vehicle yaw angle of the target vehicle at a predetermined predicted time is determined based on the weighted angular velocity of the vehicle yaw angle at the current time and the vehicle yaw angle of the wheels.

Optionally, the third determination module includes: an acquisition unit, configured to obtain the first equivalent speed of the wheel using the wheel speed sensor in the target vehicle; a first calculation unit, configured to obtain the rotation angular velocity and The wheel radius calculates the second equivalent speed of the wheel based on the rotational angular velocity and the wheel radius; the synthesis unit is set to synthesize the first equivalent speed and the second equivalent speed of the wheel according to a predetermined ratio to obtain the comprehensive value of the wheel. Equivalent speed; the second calculation unit is set to calculate the actual speed of the wheel based on the comprehensive equivalent speed of the wheel, turning radius and tire slip angle.

According to another aspect of the embodiment of the present disclosure, a computer-readable storage medium is also provided. The computer-readable storage medium includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to perform any of the above. vehicle yaw angle prediction method.

According to another aspect of the embodiment of the present disclosure, a computer device is also provided, including: a memory and a processor, the memory stores a computer program; the processor is configured to execute the computer program stored in the memory, and when the computer program is run, the processing The device performs any of the above vehicle yaw angle prediction methods.

In the embodiment of the present disclosure, particle filtering is used to obtain the driving sensing data of the vehicle from different sensors of the target vehicle, and these sensing data are fused to determine the vehicle yaw angle of the target vehicle at the current moment, based on The turning radius, tire slip angle, equivalent speed of the wheel in the direction of wheel travel, and the actual speed of the wheel in the direction of vehicle travel are iteratively determined to determine the vehicle yaw angle weighted angular velocity of the wheel, and then based on the current moment of the target vehicle The yaw angle and the vehicle yaw angle weighted angular velocity of the wheels determine the target vehicle yaw angle of the target vehicle at the predetermined prediction time, achieving the purpose of determining the target vehicle yaw angle of the target vehicle based on multiple vehicle sensing data. This achieves the technical effect of improving the accuracy of vehicle yaw angle prediction, thereby solving the technical problem of inaccurate vehicle yaw angle estimation.

Description of drawings

The drawings described here are used to provide a further understanding of the present disclosure and constitute a part of the present application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the attached picture:

Figure 1 is a flow chart of a vehicle yaw angle prediction method according to an embodiment of the present disclosure;

Figure 2 is a schematic diagram of a radius of curvature provided according to an optional embodiment of the present disclosure;

Figure 3 is a schematic diagram of side slip angle calculation provided according to an optional embodiment of the present disclosure;

Figure 4 is a structural block diagram of a vehicle yaw angle prediction device provided according to an embodiment of the present disclosure.

Detailed ways

In order to enable those skilled in the art to better understand the present disclosure, the technical solutions in the present disclosure embodiments will be clearly and completely described below in conjunction with the accompanying drawings in the present disclosure embodiments. Obviously, the described embodiments These are part of the embodiments of this disclosure, not all of them. Based on the embodiments in this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts should fall within the scope of protection of this disclosure.

It should be noted that the terms "first", "second", etc. in the description and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances so that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, e.g., a process, method, system, product, or apparatus that encompasses a series of steps or units and need not be limited to those explicitly listed. Those steps or elements may instead include other steps or elements not expressly listed or inherent to the process, method, product or apparatus.

Terminology

Particle filtering is a process that approximates the probability density function by finding a group of random samples propagating in the state space, replacing the integral operation with the sample mean, and then obtaining the minimum variance estimate of the system state. These samples are vividly called "particles" ", so it is called particle filtering.

Turning radius refers to the distance from the steering center to the contact point between the front outer steering wheel and the ground when the car is driving.

According to an embodiment of the present disclosure, an embodiment of a vehicle yaw angle prediction method is provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and ,Although a logical sequence is shown in the flowcharts, in some cases, the steps shown or described may be performed in a sequence different from that herein.

Figure 1 is a flow chart of a vehicle yaw angle prediction method according to an embodiment of the present disclosure. As shown in Figure 1, the method includes the following steps:

Step S102, determine the vehicle yaw angle of the target vehicle at the current moment based on the vehicle center of mass traveling speed and yaw angle sensing data of the target vehicle;

Step S104, determine the turning radius and tire slip angle of the target vehicle wheels;

Step S106, determine the actual speed of the wheels in the vehicle traveling direction based on the equivalent speed of the target vehicle wheels in the wheel traveling direction, the turning radius and the tire slip angle;

Step S108, based on the actual speed of the wheels of the target vehicle, determine the vehicle yaw angle weighted angular velocity of the wheels;

Step S110: Determine the target vehicle yaw angle of the target vehicle at the predetermined predicted time based on the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheels.

Through the above steps, particle filtering is used to obtain the vehicle's driving sensing data from different sensors of the target vehicle, and these sensing data are fused to determine the vehicle yaw angle of the target vehicle at the current moment. Based on the turning radius, The tire slip angle, the equivalent speed of the wheel in the direction of wheel travel, and the actual speed of the wheel in the direction of vehicle travel, iteratively determine the vehicle yaw angle weighted angular velocity of the wheel, and then based on the current vehicle yaw angle of the target vehicle The angular velocity is weighted by the vehicle yaw angle of the vehicle and the wheels to determine the target vehicle yaw angle of the target vehicle at the predetermined prediction time, achieving the purpose of determining the target vehicle yaw angle of the target vehicle based on multiple vehicle sensing data, thereby achieving The technical effect is to improve the accuracy of vehicle yaw angle prediction, thereby solving the technical problem of inaccurate vehicle yaw angle estimation.

As an optional embodiment, based on the equivalent speed of the target vehicle wheels in the wheel traveling direction, the turning radius and the tire slip angle, determining the actual speed of the wheels in the vehicle traveling direction includes: using the wheels in the target vehicle The speed sensor obtains the first equivalent speed of the wheel respectively; obtains the rotation angular velocity and wheel radius of the wheel respectively, and calculates the second equivalent speed of the wheel based on the rotation angular velocity and wheel radius; according to a predetermined ratio, the first equivalent speed of the wheel is calculated The effective speed and the second equivalent speed are combined to obtain the comprehensive equivalent speed of the wheel; based on the comprehensive equivalent speed of the wheel, the turning radius and the tire slip angle, the actual speed of the wheel is calculated.

In the embodiment of the present disclosure, the equivalent speed of the wheel obtained by the wheel speed sensor can be directly used to calculate the actual vehicle speed of the wheel, or the equivalent speed of the wheel can be calculated by using the rotation angular velocity of the wheel and the wheel radius. Speed, the first equivalent speed and the second equivalent speed of the wheel can also be determined respectively through the above two methods, and then the first equivalent speed and the second equivalent speed are combined according to a predetermined comprehensive ratio (for example, 0.4:0.6) speed to obtain a more accurate comprehensive equivalent speed, thereby improving the accuracy of the actual speed calculated based on the equivalent speed. The predetermined comprehensive ratio can be set according to the actual situation. For example, the sensitivity of the wheel speed sensor can be considered, Measurement errors in angular velocity of rotation and wheel radius, etc.

As an optional embodiment, determining the vehicle yaw angle weighted angular velocity of the wheel based on the actual speed of the wheel of the target vehicle includes: determining the vehicle yaw angle of the wheel based on the actual speed of the wheel, the vehicle center of mass traveling speed and the turning radius. Angle weighted angular velocity.

After determining the actual speed of the wheels, the vehicle center of mass traveling speed and the turning radius, the vehicle yaw angle weighted angular velocity of the wheels can be calculated according to the following formula:

Among them, one of the above two formulas can be selected to calculate the vehicle yaw angle weighted angular velocity. Among them, v _WFL,x and v _WFL,y are the speed components of the actual wheel speed in the preset x and y directions respectively, v _G,x and v _G,y are the velocity components of the vehicle's center of mass traveling speed in the preset x and y directions, respectively. is the vehicle yaw angle weighted angular velocity, r _FL is the distance from the wheel center of mass to the vehicle center of mass, γ _FL is the angle between the wheel traveling direction and the vehicle traveling direction.

As an optional embodiment, determining the target vehicle yaw angle of the target vehicle at a predetermined predicted time based on the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheels includes: based on the vehicle yaw angle at the current moment The target vehicle yaw angle is weighted with the vehicle yaw angle of the wheels and the target prediction model is used to determine the target vehicle yaw angle at the predetermined prediction time. The target prediction model is built based on the particle filter algorithm and is obtained after training with multiple sets of sample data. In the embodiment of the present disclosure, a prediction model for the vehicle yaw angle can be constructed based on the particle filter algorithm, and the prediction model is trained using multiple sets of sample data, and the prediction model is continuously adjusted and optimized to obtain the target prediction model. The prediction accuracy and/or accuracy can also be evaluated for the prediction model, and when the prediction result of the prediction model for the vehicle yaw angle reaches the required prediction accuracy and/or accuracy, the prediction model is determined as Target prediction model.

As an optional embodiment, based on the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheels, determining the target vehicle yaw angle of the target vehicle at a predetermined predicted time includes:

Among them, ψ _K+1 is the target vehicle yaw angle at the predetermined prediction time, ψ _K is the vehicle yaw angle at the current moment, Vehicle yaw angle weighted angular velocity at the current moment, is the weighted angular acceleration of the vehicle yaw angle at the current moment, and T is the duration from the current moment to the predetermined predicted moment.

As an optional embodiment, determining the target vehicle yaw angle of the target vehicle at a predetermined predicted time based on the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheels includes: obtaining the yaw angle of the sensor in the target vehicle. Measure noise; based on the measurement noise, the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheels, determine the target vehicle yaw angle of the target vehicle at the predetermined prediction time. Considering that when using the sensor of the target vehicle to obtain transmission data, there may be different levels of measurement noise in the measurement data depending on the actual performance of the sensor. For this measurement noise, a unified sensor measurement that applies to all sensors can be preset. Noise parameter, use this measurement noise parameter to process all data obtained by the sensor, you can also determine different measurement noise parameters for different sensors, and then use the measurement noise parameters corresponding to different sensors to process the corresponding sensing data. Processing to eliminate vehicle yaw angle prediction errors caused by sensor measurement noise as much as possible.

It should be noted that in the embodiment of the present disclosure, the model process noise can also be set for the target prediction model. parameters to improve the precision and accuracy of model calculations.

It should be noted that in the embodiment of the present disclosure, the target vehicle may be equipped with different sensors, wherein the sensors may include at least two of the following sensors: wheel speed sensor, combined inertial navigation sensor, and braking system inertial sensor.

It should be noted that in the embodiment of the present disclosure, the turning radius, tire slip angle, equivalent speed in the wheel traveling direction, actual speed in the vehicle traveling direction, and vehicle can be measured for each wheel of the target vehicle. The calculation of the yaw angle weighted angular velocity can also be done by calculating only the above data of a certain wheel or part of the wheels, and then based on the calculation results combined with the vehicle yaw angle of the target vehicle at the current moment, the target vehicle yaw angle of the target vehicle at the predetermined prediction time is calculated. The swing angle is predicted.

Based on the above embodiments and optional embodiments, the present disclosure proposes an optional implementation, which will be described below.

The vehicle yaw rate signal is an important signal used in autonomous driving system software. This signal represents the driving attitude of the vehicle in the preset XY plane. This signal is used by autonomous vehicles when driving in the center on a curve or changing lanes. .

However, in related technologies, when estimating vehicle yaw angle based on sensors, there are usually zero drift (that is, there is a corresponding deviation in the inertial navigation signal when the vehicle is stationary) and temperature drift (that is, it is sensitive to temperature, and the signal error will increase at high temperatures). question.

In response to the above technical problems, optional embodiments of the present disclosure perform data fusion on GPS information, inertial navigation information, and vehicle wheel speed information, and use particle filtering methods to solve the problems of zero drift and temperature drift of the yaw angular velocity signal, and improve the yaw rate. The accuracy of the angular velocity signal.

Optional implementations of the present disclosure can be applied under the following conditions:

1. The vehicle is equipped with a wheel speed sensor, a combined inertial navigation sensor, and a braking system inertial sensor (compared to the combined inertial navigation sensor, this sensor can provide acceleration and yaw angular velocity signals in the X-axis and Y-axis directions in the center-of-mass coordinate system)

2. The vehicle is driving on a level road

3. The center of mass of the vehicle is at a fixed position, which is measured by the vehicle test.

Figure 2 is a schematic diagram of the radius of curvature provided according to an optional embodiment of the present disclosure. As shown in Figure 2, the optional embodiment of the present disclosure involves the calculation of the following items:

1. Radius at the center of mass of the vehicle

Among them, ω _G is the vehicle center of mass yaw angular velocity signal, which can be directly measured by combined inertial navigation or braking system inertial sensors. v _G is the velocity of the center of mass of the vehicle. This signal can be obtained by converting the speed information and attitude information of the combined inertial navigation. The output speed information of the combined inertial navigation is the speed signal of the north-east-ground coordinate system. Combined with the attitude information of the inertial navigation, through the rotation matrix The speed signal in the XYZ axis direction in the vehicle coordinate system can be obtained; this signal can also be obtained by integrating the inertial sensor of the braking system. By discretely integrating the acceleration signals of the X-axis and Y-axis, the speed signal of the corresponding axis can be obtained. Finally, The resultant speed signal and center-of-mass side slip angle signal are obtained according to the vector addition formula.

2. Vehicle center of mass side slip angle

Among them, v _G,x and v _G,y are the velocity components of the vehicle center of mass traveling speed in the preset x and y directions respectively.

3. Wheel turning radius (take the wheel on the left side of the vehicle's front axle (subscript FL) as an example)

Among them, r _FL is the distance from the center of mass to the center of rotation of the wheel on the left side of the front axle, which is a fixed value. θ _FL is related to the side slip angle of the center of mass, which is equal to the sum of the fixed angle value and the side slip angle of the center of mass.

Figure 3 is a schematic diagram for calculating the side slip angle according to an optional embodiment of the present disclosure, where α is the tire side slip angle, v _R is the wheel equivalent speed, v _W is the wheel actual speed, and δ _W is the wheel speed, as shown in Figure As shown in 3, the optional implementation of the present disclosure also involves the calculation of the following items:

4. Vehicle center of mass speed

Among them, v _WFL,x and v _WFL,y are the speed components of the actual wheel speed in the preset x and y directions respectively, v _G,x and v _G,y are the vehicle center of mass driving speed in the preset direction respectively. The velocity components in the x and y directions, is the vehicle yaw angle weighted angular velocity, r _FL is the distance from the wheel center of mass to the vehicle center of mass, γ _FL is the angle between the wheel traveling direction and the vehicle traveling direction.

5. Tire slip angle

Among them, δ _W is the wheel speed.

6. Wheel equivalent speed
v _RFL =ω _RFL *r _stac

Among them, ω _RFL is the wheel rotation angular velocity, which is measured by the wheel speed sensor, and r _stac is the static radius of the wheel, which is obtained by static measurement.

7. The relationship between the equivalent speed of the wheel and the actual speed of the wheel
v _WFL =v _RFL *cos(α _FL )

After calculating the vehicle yaw angle weighted angular velocity through the above formulas, the particle filter algorithm can be used to predict the vehicle yaw angle at the next moment based on the vehicle yaw angle at the current moment.

Among them, the weighting method of vehicle yaw angle weighted angular velocity is:

1. Calculate the wheel equivalent speed through the inertial sensor, and adopt a predetermined proportional relationship (for example, 0.4:0.6) with the equivalent vehicle speed obtained by the wheel speed sensor to obtain the comprehensive equivalent speed;

2. Use the relationship between the above-mentioned equivalent wheel speed and the actual wheel speed to calculate the actual wheel speed;

3. Use the actual wheel speed and calculate the vehicle yaw angle weighted angular velocity based on the vehicle center of mass velocity calculation formula.

In an optional embodiment of the present disclosure, when using the particle filter algorithm to predict the vehicle yaw angle, it includes several steps: particle initialization, particle search, particle correction and particle resampling. Among them, the state equation of the particle filter algorithm can be expressed as:

Among them, the parameters in the particle filter algorithm can also be adjusted. For example, according to the actual performance of the sensor, the measurement noise R=0.16 can be obtained, the model process noise Q=0.15 can be assumed, or the particle filter can be assumed The weight obeys Gaussian distribution, and can also be set to other weight calculation methods. If the method of obeying Gaussian distribution is adopted, the weight calculation formula is as follows:

Among them, the particle resampling method can be random sampling, or other sampling methods can be used according to actual application needs.

The yaw angular velocity signal calculation method provided by the optional embodiment of the present disclosure solves the problem of zero drift of yaw angular velocity when the vehicle is stationary and traveling straight. When turning, compared with the original ordinary signal filtering method, the signal accuracy is improved by 5%.

According to an embodiment of the present disclosure, a vehicle yaw angle prediction device is also provided. Figure 4 is a structural block diagram of a vehicle yaw angle prediction device provided according to an embodiment of the present disclosure. As shown in Figure 4, the device includes: a first The determination module 41, the second determination module 42, the third determination module 43, the fourth determination module 44 and the fifth determination module 45 are described below.

The first determination module 41 is used to determine the vehicle yaw angle of the target vehicle at the current moment based on the vehicle center of mass traveling speed and yaw angle sensing data of the target vehicle; the second determination module 42 is connected to the above-mentioned first determination module 41, Used to determine the turning radius and tire slip angle of the target vehicle wheel; the third determination module 43, connected to the above-mentioned second determination module 42, is used to determine the equivalent speed of the target vehicle wheel in the wheel traveling direction, the turning radius and the tire The slip angle determines the actual speed of the wheel in the direction of vehicle travel; the fourth determination module 44 is connected to the above-mentioned third determination module 43 and is used to determine the vehicle yaw angle weighted angular velocity of the wheel based on the actual speed of the wheel of the target vehicle. ; The fifth determination module 45, connected to the above-mentioned fourth determination module 44, is used to determine the target vehicle yaw angle of the target vehicle at the predetermined predicted time based on the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheels.

As an optional embodiment, the third determination module 43 includes: an acquisition unit, used to obtain the first equivalent speed of the wheel using the wheel speed sensor in the target vehicle; a first calculation unit, used to obtain the wheel respectively. The rotation angular velocity and wheel radius are used to calculate the second equivalent speed of the wheel based on the rotation angular velocity and wheel radius; the synthesis unit is used to synthesize the first equivalent speed and the second equivalent speed of the wheel according to a predetermined ratio, Obtain the comprehensive equivalent speed of the wheel; the second calculation unit is used to calculate the actual speed of the wheel based on the comprehensive equivalent speed of the wheel, turning radius and tire slip angle.

According to an embodiment of the present disclosure, a computer-readable storage medium is also provided. The computer-readable storage medium includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to perform the vehicle yaw of any of the above items. Angle prediction method.

According to an embodiment of the present disclosure, a computer device is also provided, including: a memory and a processor, the memory A computer program is stored; a processor is used to execute the computer program stored in the memory. When the computer program is run, the processor causes the processor to execute any of the above vehicle yaw angle prediction methods.

The above serial numbers of the embodiments of the present disclosure are for description purposes and do not represent the advantages and disadvantages of the embodiments.

In the above-mentioned embodiments of the present disclosure, each embodiment is described with its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are schematic. For example, the division of the units may be a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated. to another system, or some features can be ignored, or not implemented. On the other hand, the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the units or modules may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in various embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above integrated units can be implemented in the form of hardware or software functional units.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to cause a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present disclosure. The aforementioned storage media include: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program code. .

The above is the preferred embodiment of the present disclosure. It should be noted that for those of ordinary skill in the art, several improvements and modifications can be made without departing from the principles of the present disclosure, and these improvements and modifications should also be made. regarded as the scope of protection of this disclosure.

Industrial applicability

The vehicle yaw angle prediction method, device and computer-readable storage medium provided by the embodiments of the present disclosure are applied to vehicles, using particle filtering to obtain the driving sensing data of the vehicle from different sensors of the target vehicle, and then analyze these sensors. Perform data fusion on sensory data to determine the vehicle yaw angle of the target vehicle at the current moment. Based on the turning radius, tire slip angle, equivalent speed of the wheel in the direction of wheel travel, and the actual speed of the wheel in the direction of vehicle travel, iterate The vehicle yaw angle weighted angular velocity of the wheels is determined, and then based on the vehicle yaw angle of the target vehicle at the current moment and the vehicle yaw angle weighted angular velocity of the wheels, the target vehicle yaw angle of the target vehicle at the predetermined prediction time is determined, reaching The purpose of determining the target vehicle yaw angle of the target vehicle based on multiple vehicle sensing data is to achieve the technical effect of improving the accuracy of vehicle yaw angle prediction, thereby solving the technical problem of inaccurate vehicle yaw angle estimation.

Claims

A vehicle yaw angle prediction method, including:

Based on the vehicle center of mass traveling speed and yaw angle sensing data of the target vehicle, determine the vehicle yaw angle of the target vehicle at the current moment;

Determine the turning radius and tire slip angle of the target vehicle wheels;

Based on the equivalent speed of the target vehicle wheel in the wheel traveling direction, the turning radius and the tire slip angle, determine the actual speed of the wheel in the vehicle traveling direction;

determining vehicle yaw angle weighted angular velocities of the wheels based on the actual speeds of the wheels of the target vehicle;

Based on the vehicle yaw angle at the current time and the vehicle yaw angle weighted angular velocity of the wheel, a target vehicle yaw angle of the target vehicle at a predetermined predicted time is determined.
The method according to claim 1, wherein the actual speed of the wheel in the vehicle traveling direction is determined based on the equivalent speed of the target vehicle wheel in the wheel traveling direction, the turning radius and the tire slip angle. Speed, including:

Utilize the wheel speed sensor in the target vehicle to obtain the first equivalent speed of the wheels respectively;

Obtain the rotation angular velocity and wheel radius of the wheel respectively, and calculate the second equivalent speed of the wheel based on the rotation angular velocity and the wheel radius;

According to a predetermined ratio, the first equivalent speed and the second equivalent speed of the wheel are combined to obtain the comprehensive equivalent speed of the wheel;

Based on the comprehensive equivalent speed of the wheel, the turning radius and the tire slip angle, the actual speed of the wheel is calculated.
The method of claim 1 , wherein said determining a vehicle yaw angle weighted angular velocity of a wheel based on the actual speed of a wheel of the target vehicle includes:

Based on the actual speed of the wheel, the vehicle center of mass travel speed and the turning radius, the vehicle yaw angle weighted angular velocity of the wheel is determined.
The method according to claim 1, wherein the target vehicle yaw angle of the target vehicle at a predetermined predicted time is determined based on the vehicle yaw angle at the current time and the vehicle yaw angle weighted angular velocity of the wheel. Swing angles, including:

Based on the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheel, a target prediction model is used to determine the target vehicle yaw angle of the target vehicle at a predetermined prediction time, wherein the target prediction model is based on The particle filter algorithm is constructed and trained on multiple sets of sample data.
The method according to claim 1, wherein the target vehicle yaw angle of the target vehicle at a predetermined predicted time is determined based on the vehicle yaw angle at the current time and the vehicle yaw angle weighted angular velocity of the wheel. ,include:

Among them, ψ K+1 is the target vehicle yaw angle at the predetermined prediction time, ψ K is the vehicle yaw angle at the current moment, is the weighted angular velocity of the vehicle yaw angle at the current moment, is the weighted angular acceleration of the vehicle yaw angle at the current moment, and T is the duration from the current moment to the predetermined predicted moment.
The method according to any one of claims 1 to 5, wherein the weighted angular velocity of the target vehicle at a predetermined predicted time is determined based on the vehicle yaw angle at the current time and the vehicle yaw angle of the wheel. The target vehicle yaw angle includes:

Obtain the measurement noise of the sensor in the target vehicle;

Based on the measurement noise, the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheel, a target vehicle yaw angle of the target vehicle at a predetermined predicted time is determined.
A vehicle yaw angle prediction device, which includes:

The first determination module is configured to determine the vehicle yaw angle of the target vehicle at the current moment based on the vehicle center of mass driving speed and yaw angle sensing data of the target vehicle;

a second determination module configured to determine the turning radius and tire slip angle of the target vehicle wheels;

A third determination module configured to determine the actual speed of the wheel in the vehicle traveling direction based on the equivalent speed of the target vehicle wheel in the wheel traveling direction, the turning radius and the tire slip angle;

a fourth determination module configured to determine the vehicle yaw angle weighted angular velocity of the wheel based on the actual speed of the wheel of the target vehicle;

The fifth determination module is configured to determine the target vehicle yaw angle of the target vehicle at the predetermined predicted time based on the vehicle yaw angle at the current moment and the vehicle yaw angle weighted angular velocity of the wheel.
The device according to claim 7, wherein the third determining module includes:

An acquisition unit configured to obtain the first equivalent speed of the wheels respectively by using the wheel speed sensor in the target vehicle;

The first calculation unit is configured to obtain the rotation angular velocity and wheel radius of the wheel respectively, and calculate the second equivalent speed of the wheel based on the rotation angular velocity and the wheel radius;

The synthesis unit is configured to synthesize the first equivalent speed and the second equivalent speed of the wheel according to a predetermined ratio to obtain the comprehensive equivalent speed of the wheel;

The second calculation unit is configured to calculate the actual speed of the wheel based on the comprehensive equivalent speed of the wheel, the turning radius and the tire slip angle.
A computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute any one of claims 1 to 6 The vehicle yaw angle prediction method.
A computer device, including: a memory and a processor,

The memory stores a computer program;

The processor is configured to execute a computer program stored in the memory. When the computer program is run, the processor causes the processor to execute the vehicle yaw angle prediction method according to any one of claims 1 to 6.