WO2024066943A1

WO2024066943A1 - Intelligent-parking vehicle positioning method applied to vehicle

Info

Publication number: WO2024066943A1
Application number: PCT/CN2023/116862
Authority: WO
Inventors: 姜辉; 杜建宇; 李超; 黄显晴; 王皓南; 王恒凯; 李佳骏; 曹天书; 宋新丽; 吴岗岗
Original assignee: 中国第一汽车股份有限公司
Priority date: 2022-09-30
Filing date: 2023-09-05
Publication date: 2024-04-04
Also published as: CN115900695A

Abstract

An intelligent-parking vehicle positioning method applied to a vehicle. The intelligent-parking vehicle positioning method applied to a vehicle comprises: collecting a rear-wheel speed, a course angle and a front-wheel steering angle; determining a first vehicle state variable and a first system state equation; determining a first Jacobian matrix and a second Jacobian matrix; determining the current estimated value according to the rear-wheel speed, the course angle, the first Jacobian matrix and a historical estimated value; determining an estimated value of an error covariance matrix according to estimation process noise and the first Jacobian matrix; determining a Kalman filtering gain matrix; determining the current estimation error according to the second Jacobian matrix and a historical estimation error; determining an estimated value of a state variable and an error covariance matrix according to the current estimation error, the Kalman filtering gain matrix, the second Jacobian matrix, the current estimated value and the estimated value of the error covariance matrix; and adjusting control parameters to determine a parking location of a target vehicle.

Description

Method for positioning vehicle in intelligent parking system

This application claims priority to the Chinese patent application filed with the China Patent Office on September 30, 2022, with application number 202211231764.2, the entire contents of which are incorporated by reference into this application.

Technical Field

The present application relates to the field of intelligent vehicle driving, for example, to a method for positioning a vehicle for intelligent parking of a vehicle.

Background technique

With the rapid development of vehicle intelligent driving technology, smart parking has become an indispensable vehicle assistance function.

However, when a vehicle is performing intelligent parking, the vehicle's large steering and insufficient body rigidity cause changes in parameters such as the vehicle's track and wheelbase, making it impossible for traditional dead reckoning algorithms to meet the requirements for high-precision positioning of the vehicle during automatic parking.

Summary of the invention

The present application provides a method for intelligent parking vehicle positioning applied to a vehicle to improve the accuracy of vehicle positioning, thereby improving the accuracy of automatic parking and enhancing the user experience.

According to one aspect of the present application, a method for intelligent parking vehicle positioning applied to a vehicle is provided, comprising:

Collect the rear wheel speed, heading angle and front wheel steering angle corresponding to the target vehicle at the current moment;

Determining a first vehicle state variable and a first system state equation corresponding to the current moment based on the rear wheel speed, the heading angle, and the front wheel steering angle;

Determine the observed variable equation corresponding to the current moment according to the target feature position point and the rear wheel center point at the current moment;

Determine a first Jacobian matrix according to the first system state equation; and determine a second Jacobian matrix according to the observation variable equation;

Determine the current estimated value at the current moment according to the rear wheel speed, the heading angle, the first Jacobian matrix and the historical estimated value at the previous moment; wherein the previous moment is a moment before the current moment and the time interval with the current moment is a preset time length;

Determine the error coordination matrix according to the estimation process noise at the previous moment and the first Jacobian matrix. Variance matrix estimation value; wherein the estimation process noise is determined based on a preset adaptive factor and the historical estimation error of the previous moment;

Determine a Kalman filter gain matrix according to the error covariance matrix estimate, the second Jacobian matrix and the observation noise at the previous moment;

Determine the current estimation error at the current moment according to the second Jacobian matrix and the historical estimation error;

Determine the state variable estimate and the error covariance matrix at the current moment according to the current estimated error, the Kalman filter gain matrix, the second Jacobian matrix, the current estimate and the error covariance matrix estimate;

Based on the state variable estimation value and the error covariance matrix, the control parameters corresponding to the current moment are adjusted to determine the parking position of the target vehicle at the current moment based on the control parameters.

According to another aspect of the present application, a device for intelligent parking vehicle positioning applied to a vehicle is provided, comprising:

A target vehicle information collection module, configured to collect the rear wheel speed, heading angle and front wheel steering angle corresponding to the target vehicle at the current moment;

a vehicle state information determination module, configured to determine a first vehicle state variable and a first system state equation corresponding to the current moment based on the rear wheel speed, the heading angle, and the front wheel steering angle;

an observation variable equation determination module, configured to determine the observation variable equation corresponding to the current moment according to the target feature position point and the rear wheel center point at the current moment;

A Jacobian matrix determination module, configured to determine a first Jacobian matrix according to the first system state equation; and determine a second Jacobian matrix according to the observation variable equation;

a current estimated value determination module, configured to determine the current estimated value at the current moment according to the rear wheel speed, the heading angle, the first Jacobian matrix and the historical estimated value at the previous moment; wherein the previous moment is a moment before the current moment and the time interval with the current moment is a preset time length;

An error covariance matrix estimation value determination module is configured to determine an error covariance matrix estimation value according to the estimation process noise at the previous moment and the first Jacobian matrix; wherein the estimation process noise is determined based on a preset adaptive factor and the historical estimation error at the previous moment;

A Kalman filter gain matrix determination module, configured to determine a Kalman filter gain matrix according to the error covariance matrix estimate, the second Jacobian matrix and the observation noise at the previous moment;

a current estimation error determination module, configured to determine the current estimation error at the current moment according to the second Jacobian matrix and the historical estimation error;

An error covariance matrix determination module is configured to determine the state variable estimate and the error covariance matrix at the current moment according to the current estimated error, the Kalman filter gain matrix, the second Jacobian matrix, the current estimate and the error covariance matrix estimate;

The parking position determination module is configured to adjust the control parameters corresponding to the current moment based on the state variable estimation value and the error covariance matrix, so as to determine the parking position of the target vehicle at the current moment based on the control parameters.

According to another aspect of the present application, an electronic device is provided, the electronic device comprising:

at least one processor; and

a memory communicatively connected to the at least one processor; wherein,

The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned method for intelligent parking vehicle positioning applied to a vehicle.

According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions for causing a processor to execute the above-mentioned method for intelligent parking vehicle positioning applied to a vehicle.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a flow chart of a method for positioning a vehicle in intelligent parking provided in Embodiment 1 of the present application;

FIG2 is a schematic diagram of a vehicle intelligent parking system provided in Example 1 of the present application;

FIG3 is a flow chart of a method for positioning a vehicle for intelligent parking provided in Embodiment 2 of the present application;

FIG4 is a schematic diagram of the structure of a device for positioning a vehicle for intelligent parking provided in Embodiment 3 of the present application;

FIG5 is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. The described embodiments are only embodiments of a part of the present application.

The terms "first", "second", etc. in the specification and claims of this application and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be used in addition to In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

Embodiment 1

FIG1 is a flow chart of a method for positioning a vehicle in intelligent parking applied to a vehicle according to the first embodiment of the present application. The present embodiment is applicable to the case of intelligent parking of a vehicle. The method can be executed by a device for positioning a vehicle in intelligent parking applied to a vehicle. The device for positioning a vehicle in intelligent parking applied to a vehicle can be implemented in the form of hardware and/or software. The device for positioning a vehicle in intelligent parking applied to a vehicle can be configured in an electronic device. As shown in FIG1 , the method includes:

S101, collecting the rear wheel speed, heading angle and front wheel steering angle corresponding to the target vehicle at the current moment.

The technology provided in the embodiment of the present application can be applied to vehicles with intelligent parking functions, and the vehicle performing intelligent parking can be determined as the target vehicle. During the intelligent parking process of the target vehicle, the target vehicle can collect multiple parameter information of the target vehicle at the corresponding moment according to the preset duration, and the control parameters of the target vehicle can be determined according to the multiple parameter information of the target vehicle, and the target vehicle can be controlled to perform intelligent parking according to the control parameters. In order to introduce the technical solution of the embodiment of the present application, the embodiment of the present application takes a moment in the process of intelligent parking of the target vehicle as an example for explanation, and the moment can be determined as the current moment.

In an embodiment of the present application, the method of collecting the rear wheel speed, heading angle and front wheel steering angle corresponding to the target vehicle at the current moment can be: determining the heading angle of the target vehicle in the global coordinate system; collecting the rear wheel speed of the target vehicle based on the speed sensor; determining the front wheel steering angle of the target vehicle in the vehicle coordinate system; wherein the vehicle coordinate system is established in the global coordinate system.

As shown in Figure 2, a global coordinate system XOY is established based on the current position of the target vehicle and the target feature position point. Based on the global coordinate system XOY and the current position of the target vehicle, a vehicle coordinate system X`O`Y` is established under the global coordinate system XOY. The center line of the target vehicle is determined based on the body direction and vehicle width of the target vehicle, and the angle between the center line of the target vehicle and the X-axis of the global coordinate system is determined, and the angle is determined as the heading angle θ. The rear wheel speed of the rear wheel of the target vehicle is collected by the speed sensor of the target vehicle. According to the center line of the target vehicle and the front wheel angle of the target vehicle, the angle between the center line of the target vehicle and the front wheel of the target vehicle is determined, and the angle is determined as the front wheel steering angle δ.

S102: Determine a first vehicle state variable and a first system state equation corresponding to the current moment based on the rear wheel speed, the heading angle, and the front wheel steering angle.

The first vehicle state variable may include the position information of the rear wheel center point of the target vehicle, the target feature The feature point coordinates and heading angle of the position point in the global coordinate system.

In the implementation of the present application, based on the rear wheel speed, the heading angle and the front wheel steering angle, the first vehicle state variable and the first system state equation corresponding to the current moment are determined, including: based on the rear wheel speed and the heading angle, determining the position information of the rear wheel center point; determining the first vehicle state variable at the current moment according to the position information, the feature point coordinates of the target feature position point in the global coordinate system and the heading angle; based on the rear wheel speed and the front wheel steering angle, determining the heading angle change rate; based on the heading angle change rate and the position information, determining the first system state equation.

The position information of the rear wheel center point may refer to the position information of the rear axle center point between the two rear wheels of the target vehicle. The target feature position point may refer to a fixed position, such as a parking position such as an intersection of a parking space and a final parking position point. The heading angle change rate may refer to the increment of the heading angle of the target vehicle based on the current heading angle of the front wheel and the heading angle at the previous moment.

According to the rear wheel speed and heading angle of the target vehicle, the position information of the rear wheel center point can be determined. For example, as shown in FIG2 , the horizontal coordinate of the rear wheel center point of the target vehicle can be: x=v*cosθ.

The ordinate of the rear wheel center point of the target vehicle may be: y=v*sinθ.

According to the position information of the center point, the feature point coordinates and the heading angle of the known target feature position point in the global coordinate system, the first vehicle state variable at the current moment can be determined.

For example, the first vehicle state variable may be: J=[x, y, θ, x _A , y _A ].

(x, y) is the position information of the rear wheel center point of the target vehicle, θ is the heading angle, and (x _A , y _A ) is the feature point coordinates of the known target feature position point in the global coordinate system.

The heading angle change rate can be determined based on the rear wheel speed v and the front wheel steering angle δ.

For example, as shown in FIG2 , the heading angle change rate θ=v*tanδ.

According to the heading angle change rate θ and the position information of the rear wheel center point of the target vehicle, the first system state equation can be determined.

For example, the first system state equation can be:

Among them, k can refer to the current moment, ω _k is the process noise, υ _k is the observation noise, and T can refer to the time interval between the previous moment and the current moment.

S103. Determine the observation variable equation corresponding to the current moment according to the target feature position point and the rear wheel center point at the current moment.

According to the target feature position point and the rear wheel center point at the current moment, determine the distance between the target feature position point and the rear wheel center point at the current moment. According to the target feature position point and the rear wheel center point at the current moment, determine the angle between the straight line between the rear wheel center point and the target feature position point and the vehicle coordinate system in the X'-axis direction. According to the distance between the target feature position point and the rear wheel center point at the current moment, and the angle between the straight line between the rear wheel center point and the target feature position point and the vehicle coordinate system in the X'-axis direction, determine the observation variable equation corresponding to the current moment.

In the embodiment of the present application, the observed variable equation may be:

As shown in Figure 2, r is the distance between the intersection of the rear wheel center point and the target feature position point A; _φk is the angle between the line between the rear wheel center point and the target feature position point A and the vehicle coordinate system in the X'-axis direction, _ωk is the process noise, _υk is the observation noise, and k represents the time.

S104. Determine a first Jacobian matrix according to the first system state equation; and determine a second Jacobian matrix according to the observation variable equation.

In an embodiment of the present application, determining the first Jacobian matrix according to the first system state equation may include: performing partial division based on the first system state equation to obtain the first Jacobian matrix. Performing partial division processing on the first system state equation may obtain the first Jacobian matrix.

For example, the first Jacobian matrix can be:

T may refer to the time interval between the previous moment and the current moment.

In an embodiment of the present application, determining the second Jacobian matrix according to the observed variable equation may include: calculating a partial division based on the observed variable equation to obtain the second Jacobian matrix.

By taking partial division of the observed variable equation, the second Jacobian matrix can be obtained.

For example, the second Jacobian matrix can be:

Δx＝x _A -x, Δy＝y _A -y, r is the distance between the intersection of the rear wheel center point and the target feature position point A.

S105: Determine a current estimated value at a current moment according to the rear wheel speed, the heading angle, the first Jacobian matrix, and the historical estimated value at a previous moment.

The previous moment may refer to a moment before the current moment and separated from the current moment by a preset time length.

Based on the extended Kalman filter algorithm, the current estimated value at the current moment can be determined according to the rear wheel speed, heading angle, first Jacobian matrix and the historical estimated value at the previous moment.

For example, the current estimate at the current moment could be:

Where u = [v, θ], It can refer to the historical estimation value at the previous moment, A can refer to the position coordinates of the target feature position point A, and F can refer to the first Jacobian matrix.

S106: Determine an error covariance matrix estimate according to the estimation process noise at the previous moment and the first Jacobian matrix.

The estimation process noise may be determined based on a preset adaptive factor and a historical estimation error at a previous moment.

Compute an estimate of the error covariance matrix based on the estimated process noise and the first Jacobian matrix at the previous time step.

In the embodiment of the present application, the calculation method for determining the error covariance matrix estimate may be:

Among them, _Fk can be the first Jacobian matrix, Pk _-1 can be the error covariance matrix estimate at the previous moment, is the estimation process noise at the previous moment.

S107, determining a Kalman filter gain matrix according to the error covariance matrix estimate, the second Jacobian matrix, and the observation noise at the previous moment.

The Kalman filter gain matrix at the current moment is calculated based on the error covariance matrix estimate, the second Jacobian matrix, and the observation noise at the previous moment.

In the embodiment of the present application, in S107, the Kalman filter gain matrix may be:

The error covariance matrix estimate, is the observation noise of the previous moment, H is the second Jacobian matrix, and K _k is the Kalman filter gain matrix.

S108. Determine the current estimation error at the current moment according to the second Jacobian matrix and the historical estimation error.

According to the second Jacobian matrix and the historical estimation error, the current estimation error at the current moment can be calculated.

In an embodiment of the present application, the current estimation error at the current moment is determined based on the second Jacobian matrix and the historical estimation error, including: determining the estimated value of the observed variable based on the second Jacobian matrix and the current estimated value; determining the current estimation error at the current moment based on the estimated value of the observed variable.

Based on the second Jacobian matrix and the current estimate, the observed variable estimate can be calculated.

For example, the observed variable estimates can be:

Where H can refer to the second Jacobian matrix, Can refer to current estimates.

The current estimation error at the current moment is calculated based on the estimated value of the observed quantity and the observed variable, wherein the observed variable can be calculated by substituting the position coordinates of the target feature position point A and the position coordinates of the rear wheel center point into the observed variable equation.

For example, the current estimated error can be:

Among them, Z _k can refer to the observed variable, Can refer to the estimated value of an observed variable.

S109, determining the state variable estimate and the error covariance matrix at the current moment according to the current estimated error, the Kalman filter gain matrix, the second Jacobian matrix, the current estimate and the error covariance matrix estimate.

The current state variable estimate is calculated based on the current estimation error, the current estimate value and the Kalman filter gain matrix. The error covariance matrix is determined based on the error covariance matrix estimate, the second Jacobian matrix and the Kalman filter gain matrix.

In the embodiment of the present application, the estimated value of the state variable may be:

The error covariance matrix can be:

in, represents the estimated value of the state variable, P _k represents the error covariance matrix, e _k represents the current estimation error, and E is the unit matrix.

S110 . Adjust the control parameters corresponding to the current moment based on the estimated values of the state variables and the error covariance matrix, so as to determine the parking position of the target vehicle at the current moment based on the control parameters.

According to the obtained state variable estimation value and the error covariance matrix, the control parameters corresponding to the target vehicle at the current moment are adjusted so that the target vehicle determines the parking position at the current moment according to the control parameters.

The technical solution of the embodiment of the present application collects the rear wheel speed, heading angle and front wheel steering angle corresponding to the target vehicle at the current moment. Based on the rear wheel speed, heading angle and front wheel steering angle, determine the The first vehicle state variable and the first system state equation corresponding to the current moment. According to the target feature position point and the rear wheel center point at the current moment, determine the observation variable equation corresponding to the current moment. According to the first system state equation, determine the first Jacobian matrix; and, according to the observation variable equation, determine the second Jacobian matrix. According to the rear wheel speed, heading angle, the first Jacobian matrix and the historical estimated value at the previous moment, determine the current estimated value at the current moment. According to the estimation process noise at the previous moment and the first Jacobian matrix, determine the error covariance matrix estimate. According to the error covariance matrix estimate, the second Jacobian matrix and the observation noise at the previous moment, determine the Kalman filter gain matrix. According to the second Jacobian matrix and the historical estimation error, determine the current estimation error at the current moment. According to the current estimation error, the Kalman filter gain matrix, the second Jacobian matrix, the current estimated value and the error covariance matrix estimate, determine the state variable estimate and the error covariance matrix at the current moment. Based on the estimated value of the state variable and the error covariance matrix, the control parameters corresponding to the current moment are adjusted to determine the parking position of the target vehicle at the current moment based on the control parameters. This solves the problem of inaccurate estimation of the vehicle's posture due to the failure to adjust the control parameters corresponding to the parking according to changes in parameters such as the vehicle's wheelbase and track during the parking process. This improves the accuracy of vehicle positioning during the parking process, thereby improving the accuracy of automatic parking and enhancing the user experience.

On the basis of the above-mentioned embodiment, the method for intelligent parking vehicle positioning applied to the vehicle also includes: processing the error covariance matrix estimate and the current estimated error based on a preset adaptive factor, determining the process noise and observation noise at the current moment, and determining the error covariance matrix estimate and the Kalman filter gain matrix at the next moment based on the updated process noise and observation noise.

According to the preset adaptive factor and Kalman filter gain matrix, the process noise at the current moment can be calculated. According to the preset adaptive factor and estimated error, the observation noise at the current moment can be calculated. According to the process noise and observation noise at the current moment, the error covariance matrix estimate and Kalman filter gain matrix at the next moment are calculated.

In the embodiment of the present application, the preset adaptive factor may be:

Where d is the forgetting factor, and its value range is [0,1]. The process noise can be:

The observation noise can be:

Among them, _Kk is the Kalman filter gain matrix, q is the adaptive factor, and _ek represents the current estimation error.

The technical solution of the embodiment of the present application can calculate the error covariance matrix estimation value and the Kalman filter gain matrix at the next moment through the process noise and the observation noise at the current moment, and the control parameters at the next moment can be determined based on the error covariance matrix estimation value and the Kalman filter gain matrix at the next moment, so that the target vehicle determines the position of the target vehicle during the parking process according to the control parameters, thereby improving the automatic Improve the accuracy of automatic parking and enhance the user experience.

Embodiment 2

Fig. 3 is a flow chart of a method for intelligent parking vehicle positioning applied to a vehicle provided in the second embodiment of the present application. As an embodiment of the above embodiments, the manner of determining the error covariance matrix estimation value and the Kalman filter gain matrix can be shown in Fig. 3 .

S210, based on the initial value X ₀ of the first system state equation, the first Jacobian matrix F _k , and the historical estimated value of the previous moment The position coordinates of the target feature point A and the input value u _k (where u = [v, θ]) can be used to obtain the current estimated value at the current moment. According to the initial error covariance matrix estimate P ₀ , the initial estimated process noise Q ₀ , and the first Jacobian matrix F _k , the error covariance matrix estimate can be obtained:

S220, according to the second Jacobian matrix H and the current estimated value The estimated value of the observed variable can be calculated

S230 . According to the initial error covariance matrix estimate P ₀ , the second Jacobian matrix H , and the initial observation noise R ₀ , a Kalman filter gain matrix K _k may be calculated.

S240, estimate value based on observation and observed variables Z _k , and calculate the current estimation error e _k at the current moment.

According to the current estimation error e _k and the Kalman filter gain matrix K _k at the current moment, the process noise Q _k at the current moment and the observation noise R _k at the current moment can be obtained. Through the process noise at the current moment and the observation noise at the current moment, the error covariance matrix estimate and the Kalman filter gain matrix at the next moment can be calculated, and the control parameters at the next moment can be determined based on the error covariance matrix estimate and the Kalman filter gain matrix at the next moment.

S250, according to the current estimation error e _k , the Kalman filter gain matrix K _k and the current estimation value at the current moment The estimated value of the state variable at the current moment can be obtained by calculation According to the initial error covariance matrix estimate P ₀ , the second Jacobian matrix H and the Kalman filter gain matrix K _k , the error covariance matrix P _k can be determined.

S260. According to the obtained estimated values of the state variables and the error covariance matrix, the control parameters corresponding to the target vehicle at the current moment are adjusted so that the target vehicle determines the parking position at the current moment according to the control parameters.

Through the technical solution of the embodiment of the present application, the vehicle position of the target vehicle at each moment can be determined, which solves the problem that the control parameters corresponding to the parking are not adjusted according to the changes in parameters such as the wheelbase and wheelbase of the vehicle during the parking process, resulting in inaccurate estimation of the vehicle posture, thereby improving the accuracy of vehicle positioning during the parking process, thereby improving the accuracy of automatic parking, improving user experience, and at the same time improving the target vehicle. The safety of smart parking.

Embodiment 3

FIG4 is a schematic diagram of the structure of a device for intelligent parking vehicle positioning provided in the third embodiment of the present application. This embodiment is applicable to the case of automatic parking of vehicles. As shown in FIG4 , the device includes: a target vehicle parameter information acquisition module 401, a vehicle state information determination module 402, an observation variable equation determination module 403, a Jacobian matrix determination module 404, a current estimated value determination module 405, an error covariance matrix estimated value determination module 406, a Kalman filter gain matrix determination module 407, a current estimated error determination module 408, an error covariance matrix determination module 409 and a parking position determination module 410. Among them,

The target vehicle parameter information acquisition module 401 is configured to acquire the rear wheel speed, heading angle and front wheel steering angle corresponding to the target vehicle at the current moment; the vehicle state information determination module 402 is configured to determine the first vehicle state variable and the first system state equation corresponding to the current moment based on the rear wheel speed, the heading angle and the front wheel steering angle; the observation variable equation determination module 403 is configured to determine the observation variable equation corresponding to the current moment according to the target feature position point and the rear wheel center point at the current moment; the Jacobian matrix determination module 404 is configured to determine the first Jacobian matrix according to the first system state equation; and, according to the observation variable equation, determine the second Jacobian matrix; the current estimated value determination module 405 is configured to determine the current estimated value at the current moment according to the rear wheel speed, the heading angle, the first Jacobian matrix and the historical estimated value at the previous moment; wherein the previous moment is before the current moment and the time interval with the current moment is a preset time length; the error covariance matrix estimated value determination module 406 is configured to determine the error covariance matrix estimated value according to the The estimation process noise at the previous moment and the first Jacobian matrix are used to determine the error covariance matrix estimate; wherein the estimation process noise is determined based on a preset adaptive factor and the historical estimation error at the previous moment; a Kalman filter gain matrix determination module 407 is configured to determine the Kalman filter gain matrix according to the error covariance matrix estimate, the second Jacobian matrix and the observation noise at the previous moment; a current estimation error determination module 408 is configured to determine the current estimation error at the current moment according to the second Jacobian matrix and the historical estimation error; an error covariance matrix determination module 409 is configured to determine the state variable estimate and the error covariance matrix at the current moment according to the current estimation error, the Kalman filter gain matrix, the second Jacobian matrix, the current estimate and the error covariance matrix estimate; a parking position determination module 410 is configured to adjust the control parameters corresponding to the current moment based on the state variable estimate and the error covariance matrix, so as to determine the parking position of the target vehicle at the current moment based on the control parameters.

The technical solution of the embodiment of the present application collects the rear wheel speed, heading angle and front wheel steering angle corresponding to the target vehicle at the current moment. According to the target feature position point and the rear wheel center point at the current moment, the observation variable equation corresponding to the current moment is determined. According to the first system state equation, a first Jacobian matrix is determined; and, according to the observation variable equation, a second Jacobian matrix is determined. According to the rear wheel speed, the heading angle, the first Jacobian matrix and the historical estimation value at the previous moment, the current estimation value at the current moment is determined. According to the estimation process noise at the previous moment and the first Jacobian matrix, an error covariance matrix estimation value is determined. According to the error covariance matrix estimation value, the second Jacobian matrix and the observation noise at the previous moment, a Kalman filter gain matrix is determined. According to the second Jacobian matrix and the historical estimation error, the current estimation error at the current moment is determined. According to the current estimation error, the Kalman filter gain matrix, the second Jacobian matrix, the current estimation value and the error covariance matrix estimation value, the state variable estimation value and the error covariance matrix estimation value at the current moment are determined. Based on the estimated value of the state variable and the error covariance matrix, the control parameters corresponding to the current moment are adjusted to determine the parking position of the target vehicle at the current moment based on the control parameters, thereby solving the problem of inaccurate estimation of the vehicle posture due to failure to adjust the control parameters corresponding to parking according to changes in parameters such as the vehicle's wheelbase and wheelbase during the parking process. This improves the accuracy of vehicle positioning during the parking process, thereby improving the accuracy of automatic parking and enhancing the user experience.

Based on the above embodiment, the target vehicle parameter information acquisition module 401 can be set to: determine the heading angle of the target vehicle in the global coordinate system; collect the rear wheel speed of the target vehicle based on the speed sensor; determine the front wheel steering angle of the target vehicle in the vehicle coordinate system; wherein the vehicle coordinate system is established in the global coordinate system.

Based on the above embodiment, the vehicle state information determination module 402 may be configured as follows:

Based on the rear wheel speed and the heading angle, determine the position information of the rear wheel center point; determine the first vehicle state variable at the current moment according to the position information, the feature point coordinates of the target feature position point in the global coordinate system and the heading angle; based on the rear wheel speed and the front wheel steering angle, determine the heading angle change rate; based on the heading angle change rate and the position information, determine the first system state equation.

Based on the above embodiment, the observed variable equation is:

Among them, r is the distance between the intersection of the rear wheel center point and the target feature position point A; _φk is the angle between the line between the rear wheel center point and the target feature position point A and the vehicle coordinate system in the X'-axis direction, _ωk is the process noise, _υk is the observation noise, and k represents the time.

Based on the above embodiment, the Jacobian matrix determination module 404 is configured to: obtain the first Jacobian matrix by partial division based on the first system state equation; and obtain the second Jacobian matrix by partial division based on the observation variable equation.

Based on the above embodiment, the error covariance matrix estimation value includes:

Among them, _Fk is the first Jacobian matrix, Pk _-1 is the error covariance matrix estimate at the previous moment, is the estimation process noise at the previous moment.

Based on the above embodiment, the Kalman filter gain matrix may include:

in, The error covariance matrix estimate, is the observation noise of the previous moment, H is the second Jacobian matrix, and K _k is the Kalman filter gain matrix.

Based on the above embodiment, the current estimation error determination module 408 is configured to: determine the estimated value of the observed variable based on the second Jacobian matrix and the current estimated value; and determine the current estimation error at the current moment based on the estimated value of the observed variable.

Based on the above embodiment, the estimated value of the state variable may be:

The error covariance matrix can be:

in, represents the estimated value of the state variable, P _k represents the error covariance matrix, and e _k represents the current estimation error.

On the basis of the above embodiment, the device for positioning a vehicle for intelligent parking of a vehicle further includes:

The noise determination module is configured to determine the process noise and observation noise at the current moment based on the error covariance matrix estimate and the current estimation error based on a preset adaptive factor, so as to determine the error covariance matrix estimate and the Kalman filter gain matrix at the next moment based on the updated process noise and observation noise.

The device for intelligent parking vehicle positioning applied to a vehicle provided in the embodiments of the present application can execute the method for intelligent parking vehicle positioning applied to a vehicle provided in any embodiment of the present application, and has the functional modules and effects corresponding to the execution method.

Embodiment 4

Fig. 5 shows a block diagram of an electronic device 10 that can be used to implement an embodiment of the present application. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 10 can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and/or required herein.

As shown in FIG5 , the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform a variety of appropriate actions and processes according to the computer program stored in the ROM 12 or the computer program loaded from the storage unit 18 to the RAM 13. In the RAM 13, a variety of programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input/output (I/O) interface 15 is also connected to the bus 14.

A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special processing components with processing and computing capabilities. Some examples of the processor 11 include a central processing unit (CPU), a graphics processing unit (GPU), a variety of dedicated artificial intelligence (AI) computing chips, a variety of processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the multiple methods and processes described above, such as a method for intelligent parking vehicle positioning applied to a vehicle.

In some embodiments, the method for intelligent parking vehicle positioning applied to a vehicle may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed on the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for intelligent parking vehicle positioning applied to a vehicle described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for intelligent parking vehicle positioning applied to a vehicle in any other appropriate manner (e.g., by means of firmware).

Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that are executable and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

The computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer programs are executed by the processor, the functions/operations specified in the flow charts and/or block diagrams are implemented. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

In the context of the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or apparatus. A computer readable storage medium may include an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. Examples of machine readable storage media may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a RAM, a ROM, an Erasable Programmable Read-Only Memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube (CRT) or a liquid crystal display (LCD) monitor) configured to display information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other types of devices can also be configured to provide interaction with a user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN), blockchain network, and the Internet.

A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

The various forms of processes shown above can be used to reorder, add or delete steps. For example, the multiple steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

Claims

A method for positioning a vehicle for intelligent parking, comprising:

Collect the rear wheel speed, heading angle and front wheel steering angle corresponding to the target vehicle at the current moment;

Determining a first vehicle state variable and a first system state equation corresponding to the current moment based on the rear wheel speed, the heading angle, and the front wheel steering angle;

Determine the observed variable equation corresponding to the current moment according to the target feature position point and the rear wheel center point at the current moment;

Determine a first Jacobian matrix according to the first system state equation; and determine a second Jacobian matrix according to the observation variable equation;

Determine the current estimated value at the current moment according to the rear wheel speed, the heading angle, the first Jacobian matrix and the historical estimated value at the previous moment; wherein the previous moment is a moment before the current moment and the time interval with the current moment is a preset time length;

Determine an error covariance matrix estimate based on the estimation process noise at the previous moment and the first Jacobian matrix; wherein the estimation process noise is determined based on a preset adaptive factor and the historical estimation error at the previous moment;

Determine a Kalman filter gain matrix according to the error covariance matrix estimate, the second Jacobian matrix, and the observation noise at the previous moment;

Determine the current estimation error at the current moment according to the second Jacobian matrix and the historical estimation error;

Determine the state variable estimate and the error covariance matrix at the current moment according to the current estimation error, the Kalman filter gain matrix, the second Jacobian matrix, the current estimate and the error covariance matrix estimate;

Based on the state variable estimation value and the error covariance matrix, the control parameters corresponding to the current moment are adjusted to determine the parking position of the target vehicle at the current moment based on the control parameters.
The method according to claim 1, wherein said collecting the rear wheel speed, heading angle and front wheel steering angle corresponding to the target vehicle at the current moment comprises:

Determining the heading angle of the target vehicle in a global coordinate system;

Collecting the rear wheel speed of the target vehicle based on a speed sensor;

Determining a front wheel steering angle of the target vehicle in a vehicle coordinate system;

Wherein, the vehicle coordinate system is established under the global coordinate system.
The method according to claim 1, wherein the first vehicle state variable and the second vehicle state variable corresponding to the current moment are determined based on the rear wheel speed, the heading angle, and the front wheel steering angle. A system state equation, including:

Determining the position information of the center point of the rear wheel based on the rear wheel speed and the heading angle;

Determine the first vehicle state variable at the current moment according to the position information, the feature point coordinates of the target feature position point in the global coordinate system, and the heading angle;

Determining a heading angle change rate based on the rear wheel speed and the front wheel steering angle;

The first system state equation is determined based on the heading angle change rate and the position information.
The method according to claim 1, wherein the observed variable equation is:

Among them, r is the distance between the intersection of the rear wheel center point and the target feature position point; φ k is the angle between the line between the rear wheel center point and the target feature position point and the vehicle coordinate system in the X'-axis direction, ω k is the process noise, υ k is the observation noise, and k represents the time.
The method according to claim 1, wherein determining a first Jacobian matrix according to the first system state equation; and determining a second Jacobian matrix according to the observation variable equation comprises:

Calculate the partial division based on the first system state equation to obtain the first Jacobian matrix;

The second Jacobian matrix is obtained by taking partial derivatives based on the observed variable equation.
The method according to claim 1, wherein determining the error covariance matrix estimate according to the estimation process noise at the previous moment and the first Jacobian matrix comprises:

Wherein, Fk is the first Jacobian matrix, Pk -1 is the error covariance matrix estimate at the previous moment, is the estimated process noise at the previous moment.
The method according to claim 1, wherein the determining the Kalman filter gain matrix according to the error covariance matrix estimate, the second Jacobian matrix, and the observation noise at the previous moment comprises:

in, is the error covariance matrix estimate, is the observation noise at the previous moment, H is the second Jacobian matrix, and K k is the Kalman filter gain matrix.
The method according to claim 1, wherein the second Jacobian matrix and The historical estimation error determines the current estimation error at the current moment, including:

Determining an observed variable estimate based on the second Jacobian matrix and the current estimate;

Based on the observed quantity estimate, a current estimation error at the current moment is determined.
The method according to claim 1, wherein the determining the state variable estimate and the error covariance matrix at the current moment according to the current estimated error, the Kalman filter gain matrix, the second Jacobian matrix, the current estimate, and the error covariance matrix estimate comprises:

in, represents the estimated value of the state variable, P k represents the error covariance matrix, and e k represents the current estimation error.
The method according to claim 1, further comprising:

The error covariance matrix estimate and the current estimated error are processed based on a preset adaptive factor to determine the process noise and observation noise at the current moment, so as to determine the error covariance matrix estimate and the Kalman filter gain matrix at the next moment based on the updated process noise and observation noise.
A device for intelligent parking vehicle positioning applied to a vehicle, comprising:

A target vehicle information collection module, configured to collect the rear wheel speed, heading angle and front wheel steering angle corresponding to the target vehicle at the current moment;

a vehicle state information determination module, configured to determine a first vehicle state variable and a first system state equation corresponding to the current moment based on the rear wheel speed, the heading angle, and the front wheel steering angle;

an observation variable equation determination module, configured to determine the observation variable equation corresponding to the current moment according to the target feature position point and the rear wheel center point at the current moment;

A Jacobian matrix determination module, configured to determine a first Jacobian matrix according to the first system state equation; and determine a second Jacobian matrix according to the observation variable equation;

a current estimated value determination module, configured to determine the current estimated value at the current moment according to the rear wheel speed, the heading angle, the first Jacobian matrix and the historical estimated value at the previous moment; wherein the previous moment is a moment before the current moment and the time interval with the current moment is a preset time length;

An error covariance matrix estimation value determination module is configured to determine an error covariance matrix estimation value according to the estimation process noise at the previous moment and the first Jacobian matrix; wherein the estimation process noise is determined based on a preset adaptive factor and the historical estimation error at the previous moment;

A Kalman filter gain matrix determination module is configured to estimate the error covariance matrix according to the error covariance matrix, The second Jacobian matrix and the observation noise at the previous moment determine the Kalman filter gain matrix;

a current estimation error determination module, configured to determine the current estimation error at the current moment according to the second Jacobian matrix and the historical estimation error;

an error covariance matrix determination module, configured to determine the state variable estimate and the error covariance matrix at the current moment according to the current estimated error, the Kalman filter gain matrix, the second Jacobian matrix, the current estimate and the error covariance matrix estimate;

The parking position determination module is configured to adjust the control parameters corresponding to the current moment based on the state variable estimation value and the error covariance matrix, so as to determine the parking position of the target vehicle at the current moment based on the control parameters.
An electronic device, comprising:

at least one processor; and

a memory communicatively connected to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the method for intelligent parking vehicle positioning applied to a vehicle as described in any one of claims 1-10.
A computer-readable storage medium stores computer instructions, wherein the computer instructions are used to enable a processor to implement the method for intelligent parking vehicle positioning applied to a vehicle as described in any one of claims 1-10 when executed.