WO2024098463A1

WO2024098463A1 - Vehicle localization method and apparatus, and vehicle

Info

Publication number: WO2024098463A1
Application number: PCT/CN2022/133346
Authority: WO
Inventors: 刘航; 孟博; 师小五
Original assignee: 北汽福田汽车股份有限公司
Priority date: 2022-11-09
Filing date: 2022-11-21
Publication date: 2024-05-16
Also published as: CN118046890A

Abstract

The present disclosure relates to a vehicle localization method and apparatus, and a vehicle. The method comprises: after a vehicle is powered on, acquiring first localization information of the vehicle and second localization information stored before the vehicle is powered off last time; determining a target localization mode from different localization modes according to a size relationship between a deviation value between the first localization information and the second localization information and a preset deviation threshold value; and determining target localization information of the vehicle according to the target localization mode. In the present disclosure, a deviation value between first localization information acquired after a vehicle is powered on and second localization information stored before the vehicle is powered off serves as a basis for selecting a target localization mode, different localization modes are selected when the sizes of vehicle localization deviations are different, such that the problem of a localization deviation being relatively large after a vehicle is moved when an automatic parking system of the vehicle is not started can be effectively solved, and the localization accuracy of the vehicle in an occlusion scenario is thus improved.

Description

Vehicle positioning method, device and vehicle

Technical Field

The present disclosure relates to the field of vehicle control technology, and in particular, to a vehicle positioning method, device and vehicle.

Background technique

The automatic parking system is a driving assistance system that helps the driver identify available parking spaces and automatically drives the vehicle into the available parking spaces. Automatic parking uses the vehicle's visual sensors or ultrasonic radar to perceive the surrounding environment, plans the parking method and path in the central processor, and controls the vehicle to automatically drive into the parking space.

In the related technology, in the absence of fusion positioning of the Global Navigation Satellite System (GNSS) and RTK (Real-time kinematic), the positioning of the vehicle's automatic parking system in the parking lot relies on the vehicle's own sensors, generally using laser radar for SLAM (simultaneous localization and mapping) to build a parking lot map, and based on the position recorded when the vehicle is parked in the parking lot, this position is used as the initial position of the vehicle in the SLAM map before the vehicle is powered on and driven. After the vehicle is parked and powered off, if the vehicle is moved without the automatic parking system started, the vehicle position recorded by the automatic parking system when it was parked before the power was turned off is inconsistent with the actual position of the vehicle when it was started, resulting in a large deviation in the vehicle positioning.

Summary of the invention

The purpose of the present disclosure is to provide a vehicle positioning method, device and vehicle to solve the problem of large vehicle positioning deviation caused by moving the vehicle when the automatic parking system is not activated.

In order to achieve the above object, the present disclosure provides a vehicle positioning method, the method comprising:

After the vehicle is powered on, obtaining the first positioning information of the vehicle and the second positioning information stored before the vehicle was powered off last time;

Determine a target positioning method from different positioning methods according to a magnitude relationship between a deviation value between the first positioning information and the second positioning information and a preset deviation threshold;

According to the target positioning method, the target positioning information of the vehicle is determined.

Optionally, the step of determining a target positioning mode from different positioning modes according to a size relationship between a deviation value between the first positioning information and the second positioning information and a preset deviation threshold value includes:

When the deviation value is less than the deviation threshold, the target positioning mode is determined to be a first positioning mode, where the first positioning mode is a mode of determining the first positioning information as the target positioning information.

When the deviation value is greater than the deviation threshold, the target positioning method is determined to be a second positioning method, where the second positioning method is a method of determining the target positioning information based on an environmental image around the vehicle and the first positioning information.

Optionally, the step of determining the target positioning information of the vehicle according to the target positioning method includes:

When it is determined that the target positioning mode is the second positioning mode, acquiring the environment image;

According to the environment image, obtaining the number information of the parking space where the vehicle is located;

The target positioning information is obtained according to the numbering information and the first positioning information.

Optionally, the step of obtaining the target positioning information according to the numbering information and the first positioning information includes:

Obtaining real-time point cloud information of the vehicle according to the first positioning information;

Determine the parking space cloud information of the parking space where the vehicle is located according to the number information;

The ICP algorithm is used to align the real-time point cloud information and the parking spot point cloud information to obtain the target positioning information.

Optionally, the step of registering the real-time point cloud information and the parking spot point cloud information using an ICP algorithm to obtain the target positioning information includes:

Initializing the value of the feature matrix of the real-time point cloud information according to the parking spot cloud information;

Acquire a target point that satisfies a distance condition with respect to the real-time point cloud information from the parking spot cloud information;

According to the distance error between the target point and the point corresponding to the target point in the real-time point cloud information, the value of the feature matrix is iteratively calculated using the least square method to obtain a target feature matrix;

The target positioning information is obtained according to the target feature matrix.

Optionally, the step of obtaining the target positioning information according to the target feature matrix includes:

The target feature matrix is solved by using the SVD method to obtain a target rotation matrix;

The target positioning information is obtained according to the target rotation matrix.

Optionally, after the step of determining the target positioning information of the vehicle according to the target positioning mode, the method further includes:

According to the target positioning information, updating the actual position of the vehicle in the map;

The vehicle's driving path is obtained based on the actual position and the target position input by the user.

In order to achieve the above object, the present disclosure also provides a vehicle positioning device, the device comprising:

An acquisition module, used for acquiring the first positioning information of the vehicle and the second positioning information stored before the vehicle was powered off last time after the vehicle was powered on;

A first determination module, configured to determine a target positioning mode from different positioning modes according to a magnitude relationship between a deviation value between the first positioning information and the second positioning information and a preset deviation threshold;

The second determination module is used to determine the target positioning information of the vehicle according to the target positioning method.

In order to achieve the above object, the present disclosure further provides a vehicle, the vehicle comprising:

A processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor is used to execute the machine executable instructions to implement the above-mentioned vehicle positioning method.

The embodiment of the present disclosure determines a target positioning method based on a relationship between a deviation value between first positioning information obtained after the vehicle is powered on and second positioning information stored before the vehicle was last powered off and a preset deviation threshold, and determines the target positioning information based on the target positioning method. Compared with the method in the prior art that directly uses the positioning information stored before the vehicle is powered off as the initial position of the vehicle, the present disclosure uses the deviation value between the first positioning information obtained after the vehicle is powered on and the second positioning information stored before the vehicle is powered off as the basis for selecting the target positioning method, and selects different positioning methods when the vehicle positioning deviation size is different. In this way, the positioning method determined after comparing the difference size between the positioning information of the vehicle after power-on and before power-off can effectively solve the problem of large positioning deviation after moving the vehicle when the automatic parking system of the vehicle is not started, and improves the positioning accuracy of the vehicle in occluded scenarios.

Other features and advantages of the present disclosure will be described in detail in the following detailed description.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

Fig. 1 is a flow chart showing a vehicle positioning method according to an exemplary embodiment.

Fig. 2 is a block diagram of a vehicle positioning device according to an exemplary embodiment.

Fig. 3 is a schematic diagram of a functional block diagram of a vehicle according to an exemplary embodiment.

Fig. 4 is a block diagram showing a device for a vehicle positioning method according to an exemplary embodiment.

Detailed ways

Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

Among related technologies, the main function of SLAM is to enable robots to complete localization, mapping, and navigation in unknown environments. SLAM technology is widely used in robots, drones, unmanned driving, AR, VR and other fields. Sensors can be used to achieve autonomous positioning, mapping, and path planning of machines. Vehicle sensors can include lidar, millimeter-wave radar, ultrasonic radar, and visual sensors.

When the vehicle is powered on and started, it is generally positioned based on integrated navigation. Integrated navigation refers to a navigation system that integrates various navigation devices and is controlled by a monitor and a computer. Most integrated navigation systems are based on inertial navigation systems. The main reason is that inertial navigation can provide more navigation parameters and full attitude information parameters. However, when the vehicle is parked in a covered parking lot, the combined navigation has poor satellite search performance and cannot provide accurate positioning of the vehicle when the signal is blocked. When the laser SLAM technology is used to locate the environment in which the vehicle is located, the poor robustness of the SLAM algorithm leads to a large deviation in vehicle positioning.

In addition, after the vehicle is parked in a parking space and the power is turned off, the driver may complete the parking space change without the parking system being started normally. The vehicle position recorded by the automatic parking system when parking before power is turned off is inconsistent with the actual position of the started vehicle, resulting in a large deviation in vehicle positioning.

Based on the above problems, an embodiment of the present disclosure provides a concept for solving the above problems. Based on the deviation value between the first positioning information obtained after power-on and the second positioning information stored before the vehicle was last powered off, as well as a preset deviation threshold, a target positioning method is determined from different positioning methods, thereby obtaining target positioning information.

The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

Please refer to FIG. 1 , which is a flow chart of a vehicle positioning method according to an exemplary embodiment. As shown in FIG. 1 , the vehicle positioning method includes:

S101. After a vehicle is powered on, first positioning information of the vehicle and second positioning information stored before the vehicle was powered off last time are obtained.

In the specific implementation process, the first positioning information is obtained by repositioning the vehicle after power-on, and the second positioning information is stored before the vehicle is powered off after the last trip. Both the first positioning information and the second positioning information are positioned according to the sensors on the vehicle, and the map constructed by SLAM is displayed on the vehicle's head-mounted entertainment control system (HUT). Among them, the vehicle's sensors may include inertial measurement units (IMU), laser radars, millimeter-wave radars, ultrasonic radars, and cameras.

When parking the vehicle, the driver turns on the vehicle's automatic parking system. After the vehicle completes parking, the automatic parking system will record the vehicle's second positioning information before power is turned off and store it in the vehicle controller to determine the vehicle's actual positioning position after the vehicle is powered on.

S102: Determine a target positioning method from different positioning methods according to a deviation value between the first positioning information and the second positioning information and a size relationship between a preset deviation threshold.

In the specific implementation process, the deviation value is obtained based on the first positioning information and the second positioning information, and the preset deviation threshold can be determined according to the size of the vehicle itself and the error of the sensor. In general, the larger the size of the vehicle itself and the larger the sensor error, the larger the deviation value, and vice versa. The existing positioning method, for example, directly determines the initial position of this trip based on the positioning information after the vehicle is re-positioned by the sensor and combined navigation after this power-on. In this case, the positioning information of the vehicle before power-off may not be stored before the vehicle is powered off. That is, the existing positioning method generally determines the initial position of the vehicle for this trip based on the stored positioning information before the last power-off, or determines the initial position of the vehicle for this trip based on the positioning information re-acquired after the vehicle is powered on.

The target positioning method is a positioning method determined from different positioning methods. Generally, the positioning methods may include multiple methods. For example, when the vehicle sensor includes a laser radar or a camera, the target positioning information may be obtained based on a SLAM algorithm. When the vehicle sensor includes an integrated navigation, the target positioning information may be obtained based on a track recursion method.

In one embodiment, vehicle positioning can also be achieved based on data collected by multiple vehicle sensors, thereby avoiding the situation where the vehicle cannot perform self-positioning due to failure of a single sensor, thereby improving the robustness of the positioning result.

In the embodiment of the present disclosure, the positioning method can specifically determine the initial position of the vehicle based on the first positioning information determined after the vehicle is powered on, or it can determine the initial position of the vehicle based on the environmental image of the current surroundings of the vehicle and the positioning information stored before power-off.

S103: Determine the target positioning information of the vehicle according to the target positioning method.

In the specific implementation process, the target positioning information is used to determine the initial position of the vehicle after power-on. After the target positioning method is determined, the target positioning information of the vehicle can be obtained according to the target positioning method. Wherein, when the deviation value between the first positioning information and the second positioning information is less than the preset deviation threshold, the first positioning information is directly determined as the target positioning information; or, when the deviation value between the first positioning information and the second positioning information is greater than the preset deviation threshold, the number information of the parking space where the vehicle is currently located is identified according to the vehicle environment image, and a matching operation is performed according to the number information and the first positioning information to obtain the updated target positioning information.

In some embodiments, the step of determining the target positioning mode from different positioning modes according to the deviation value between the first positioning information and the second positioning information and the size relationship between the preset deviation threshold value includes:

When the deviation value is less than the deviation threshold, the target positioning mode is determined to be the first positioning mode, where the first positioning mode is a mode of determining the first positioning information as the target positioning information.

During the specific implementation process, when the deviation value is less than the deviation threshold, the deviation value is within the positioning deviation range, and it is determined that the vehicle has not moved after the automatic parking system is turned off or the position has not moved too far. The first positioning information obtained by the vehicle after this power-on can be used as the target positioning information of the current vehicle.

When the deviation value is greater than the deviation threshold, the target positioning method is determined to be the second positioning method, which is a method of determining the target positioning information based on the environmental image around the vehicle and the first positioning information.

In the specific implementation process, when the deviation value is greater than the deviation threshold, it is determined that the vehicle has undergone a large displacement or a large deviation in the positioning system after the parking system is turned off. Due to the poor robustness of the laser SLAM algorithm and the influence of the parking lot occlusion scene, the positioning performance is poor. Directly using the first positioning information as the target positioning information will cause a large deviation in the vehicle positioning and require repositioning. At this time, the vehicle's visual sensor can be used to obtain the environmental image around the vehicle. Generally, the visual sensor is a camera device that comes with the vehicle. According to the environmental image and the first positioning information obtained by repositioning the vehicle after power-on, the target positioning information of the vehicle is matched.

In some embodiments, the step of determining the target positioning information of the vehicle according to the target positioning method includes:

When it is determined that the target positioning mode is the second positioning mode, acquiring an environment image;

According to the environment image, the number information of the parking space where the vehicle is located is obtained;

In the specific implementation process, after acquiring the environmental image, the parking space number information in the environmental image can be identified according to the image recognition algorithm. Since a map of the parking lot has been constructed according to SLAM before the vehicle was last powered off, when the camera device recognizes the number information of the parking space where the vehicle is currently located, the number information can be matched and located in the constructed map to obtain the target positioning information.

It should be noted that the image recognition algorithm is not specifically limited here. For example, it can be an image recognition algorithm based on a deep neural network, an image recognition algorithm based on a classifier, and an image recognition algorithm based on a support vector machine (SVM).

In some embodiments, the step of obtaining target positioning information according to the numbering information and the first positioning information includes:

According to the number information, determine the parking spot cloud information of the parking space where the vehicle is located;

In the specific implementation process, the real-time point cloud information is the coordinates of the point set used to characterize the vehicle position obtained according to the first positioning information, and the parking point cloud information is the coordinates of the point set used to characterize the parking space position of the vehicle. The ICP algorithm is based on the data registration method and uses the nearest point search method to solve an algorithm based on free-form surfaces.

In some embodiments, the step of using the ICP algorithm to register the real-time point cloud information and the parking spot point cloud information to obtain the target positioning information includes:

Initialize the value of the feature matrix of the real-time point cloud information according to the parking point cloud information;

Obtain a target point that meets the distance condition with the real-time point cloud information from the parking spot cloud information;

According to the distance error between the target point and the point corresponding to the target point in the real-time point cloud information, the value of the feature matrix is iteratively calculated using the least square method to obtain the target feature matrix;

According to the target feature matrix, the target positioning information is obtained.

In the specific implementation process, the value of the feature matrix of the real-time point cloud is initialized based on the coordinate system where the parking point cloud information is located, and each coordinate point in the real-time point cloud information is assigned a value. The distance condition can be that the distance between the matching point obtained in the parking point cloud information and the real-time point cloud information is less than a preset distance threshold. In the case of initializing the value of the feature matrix of the real-time point cloud information, the points in the real-time point cloud information and the parking point cloud information are matched, and each point in the real-time point cloud information and the parking point cloud information is a vector. According to the distance between the matching points between the real-time point cloud information and the parking point cloud information, the value of the feature matrix is iteratively updated using the least squares method to minimize the error function, and finally the optimized target feature matrix is obtained.

Specifically, the ICP algorithm steps may be:

(1) Take a point set p _i ∈ P from the real-time point cloud information P;

(2) Find the corresponding point set q _i ∈ Q in the parking spot cloud information Q, so that ||q _i -p _i || = min;

(3) Calculate the characteristic matrix to minimize the error function. The characteristic matrix includes the rotation matrix R and the translation matrix t;

(4) Use the rotation matrix R and translation matrix t obtained in step (3) to rotate and translate _{p i} to obtain a new corresponding point set p _i ′＝{p _i ′＝Rp _i +t, p _i ∈PP;

(5) Based on

Calculate the average distance between p _i ' and the corresponding point set q _i ;

(6) If d is less than a given threshold or greater than the preset maximum number of iterations, the iterative calculation is stopped. Otherwise, return to step (2) until the convergence condition is met.

In some embodiments, the step of obtaining target positioning information according to the target feature matrix includes:

The SVD method is used to solve the target feature matrix and obtain the target rotation matrix;

According to the target rotation matrix, the target positioning information is obtained.

In the specific implementation process, the methods for solving the target feature matrix generally include the SVD method and the nonlinear optimization method. In the present disclosure, the SVD algorithm is used for solving, and the specific steps include:

① Calculate the centroid of the matching points in the real-time point cloud information and the parking spot cloud information to obtain the point set without the centroid;

② Calculate the 3x3 matrix H, H = XY ^T , where X and Y are the feature matrices of the real-time point cloud information without centroid and the parking spot cloud information respectively.

③ Perform SVD decomposition on H to obtain H = U∑V ^T and obtain the target rotation matrix R ^* = VU ^T .

In some embodiments, after the step of determining the target positioning information of the vehicle according to the target positioning method, the method further includes:

Update the actual position of the vehicle in the map based on the target positioning information;

In the specific implementation process, after obtaining the target positioning information, the actual position of the vehicle is updated in the vehicle's SLAM map, and the vehicle controller can calculate the vehicle's driving path based on the actual position and the target position input by the user.

Please refer to FIG. 2 , which is a block diagram of a vehicle positioning device according to an exemplary embodiment. As shown in FIG. 2 , the vehicle positioning device 500 includes:

The acquisition module 520 is used to acquire the first positioning information of the vehicle and the second positioning information stored before the vehicle was powered off last time after the vehicle is powered on;

A first determination module 530 is used to determine a target positioning mode from different positioning modes according to a deviation value between the first positioning information and the second positioning information and a size relationship between a preset deviation threshold;

The second determination module 540 is used to determine the target positioning information of the vehicle according to the target positioning method.

In some embodiments, the first determination module 530 includes:

The first determination submodule is used to determine that the target positioning mode is a first positioning mode when the deviation value is less than the deviation threshold. The first positioning mode is a mode of determining the first positioning information as the target positioning information.

In some embodiments, the first determination module 530 includes:

The second determination submodule is used to determine that the target positioning method is a second positioning method when the deviation value is greater than the deviation threshold. The second positioning method is a method of determining the target positioning information based on the environmental image around the vehicle and the first positioning information.

In some embodiments, the second determination module 540 includes:

An acquisition submodule, used for acquiring an environment image when it is determined that the target positioning mode is the second positioning mode;

The first obtaining submodule is used to obtain the number information of the parking space where the vehicle is located according to the environment image;

The second obtaining submodule is used to obtain target positioning information according to the numbering information and the first positioning information.

In some embodiments, the second obtaining submodule is specifically used for:

In some embodiments, the vehicle positioning device 500 further includes:

An update module, used to update the actual position of the vehicle in the map according to the target positioning information;

The acquisition module is used to obtain the vehicle's driving path based on the actual position and the target position input by the user.

Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

In addition, to achieve the above-mentioned purpose, an embodiment of the present disclosure further provides a vehicle, the vehicle comprising:

Please refer to FIG3 , which is a functional block diagram of a vehicle 600 according to an exemplary embodiment. For example, the vehicle 600 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. The vehicle 600 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

3 , the vehicle 600 may include various subsystems, such as an infotainment system 610, a perception system 620, a decision control system 630, a drive system 640, and a computing platform 650. The vehicle 600 may also include more or fewer subsystems, and each subsystem may include multiple components. In addition, each subsystem and each component of the vehicle 600 may be interconnected by wire or wireless means.

In some embodiments, the infotainment system 610 may include a communication system, an entertainment system, and a navigation system, etc.

The perception system 620 may include several sensors for sensing information about the environment around the vehicle 600. For example, the perception system 620 may include a global positioning system (the global positioning system may be a GPS system, or a Beidou system or other positioning systems), an inertial measurement unit (IMU), a laser radar, a millimeter wave radar, an ultrasonic radar, and a camera device.

The decision control system 630 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

The drive system 640 may include components that provide power movement for the vehicle 600. In one embodiment, the drive system 640 may include an engine, a torque source, a transmission system, and wheels. The engine may be one or a combination of multiple of an internal combustion engine, an electric motor, and an air compression engine. The engine is capable of converting the torque provided by the torque source into mechanical torque.

Some or all functions of the vehicle 600 are controlled by a computing platform 650. The computing platform 650 may include at least one processor 651 and a first memory 652, and the processor 651 may execute instructions 653 stored in the first memory 652.

The processor 651 may be any conventional processor, such as a commercially available CPU. The processor may also include a graphics processor (Graphic Process Unit, GPU), a field programmable gate array (Field Programmable Gate Array, FPGA), a system on chip (System on Chip, SOC), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or a combination thereof.

The first memory 652 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

In addition to the instructions 653 , the first memory 652 may also store data, such as road maps, route information, and data such as the location, direction, and speed of the vehicle. The data stored in the first memory 652 may be used by the computing platform 650 .

In the embodiment of the present disclosure, the processor 651 may execute the instruction 653 to complete all or part of the steps of the above-mentioned vehicle positioning method.

Please refer to FIG. 4, which is a block diagram of a device 1900 for a vehicle positioning method according to an exemplary embodiment. For example, the device 1900 can be provided as a server. Referring to FIG. 4, the device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a second memory 1932 for storing instructions that can be executed by the processing component 1922, such as an application. The application stored in the second memory 1932 may include one or more modules, each of which corresponds to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above-mentioned vehicle positioning method.

The device 1900 may also include a power supply component 1926 configured to perform power management of the device 1900, a wired or wireless network interface 1950 configured to connect the device 1900 to a network, and an input/output interface 1958. The device 1900 may operate based on an operating system stored in the second memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.

The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, and the program instructions, when executed by a processor, implement the steps of the vehicle positioning method provided by the present disclosure.

In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device. The computer program has a code portion for executing the above-mentioned vehicle positioning method when executed by the programmable device.

Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be regarded as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

A vehicle positioning method, characterized in that the method comprises:

After the vehicle is powered on, obtaining the first positioning information of the vehicle and the second positioning information stored before the vehicle was powered off last time;

Determine a target positioning method from different positioning methods according to a magnitude relationship between a deviation value between the first positioning information and the second positioning information and a preset deviation threshold;

According to the target positioning method, the target positioning information of the vehicle is determined.
The method according to claim 1, characterized in that the step of determining the target positioning mode from different positioning modes according to the size relationship between the deviation value between the first positioning information and the second positioning information and a preset deviation threshold value comprises:

When the deviation value is less than the deviation threshold, the target positioning mode is determined to be a first positioning mode, where the first positioning mode is a mode of determining the first positioning information as the target positioning information.
The method according to claim 1, characterized in that the step of determining the target positioning mode from different positioning modes according to the size relationship between the deviation value between the first positioning information and the second positioning information and a preset deviation threshold value comprises:

When the deviation value is greater than the deviation threshold, the target positioning method is determined to be a second positioning method, where the second positioning method is a method of determining the target positioning information based on an environmental image around the vehicle and the first positioning information.
The method according to claim 3 is characterized in that the step of determining the target positioning information of the vehicle according to the target positioning method comprises:

When it is determined that the target positioning mode is the second positioning mode, acquiring the environment image;

According to the environment image, obtaining the number information of the parking space where the vehicle is located;

The target positioning information is obtained according to the numbering information and the first positioning information.
The method according to claim 4, characterized in that the step of obtaining the target positioning information according to the numbering information and the first positioning information comprises:

Obtaining real-time point cloud information of the vehicle according to the first positioning information;

Determine the parking spot cloud information of the parking space where the vehicle is located according to the number information;

The ICP algorithm is used to align the real-time point cloud information and the parking spot point cloud information to obtain the target positioning information.
The method according to claim 5 is characterized in that the step of using an ICP algorithm to register the real-time point cloud information and the parking spot point cloud information to obtain the target positioning information comprises:

Initializing the value of the feature matrix of the real-time point cloud information according to the parking spot cloud information;

Acquire a target point that satisfies a distance condition with respect to the real-time point cloud information from the parking spot cloud information;

According to the distance error between the target point and the point corresponding to the target point in the real-time point cloud information, the value of the feature matrix is iteratively calculated using the least square method to obtain a target feature matrix;

The target positioning information is obtained according to the target feature matrix.
The method according to claim 6, characterized in that the step of obtaining the target positioning information according to the target feature matrix comprises:

The target feature matrix is solved by using the SVD method to obtain a target rotation matrix;

The target positioning information is obtained according to the target rotation matrix.
The method according to claim 1, characterized in that after the step of determining the target positioning information of the vehicle according to the target positioning method, the method further comprises:

According to the target positioning information, updating the actual position of the vehicle in the map;

The vehicle's driving path is obtained according to the actual position and the target position input by the user.
A vehicle positioning device, characterized in that the device comprises:

An acquisition module, used to acquire the first positioning information of the vehicle and the second positioning information stored before the vehicle was powered off last time after the vehicle was powered on;

A first determination module, configured to determine a target positioning mode from different positioning modes according to a magnitude relationship between a deviation value between the first positioning information and the second positioning information and a preset deviation threshold;

The second determination module is used to determine the target positioning information of the vehicle according to the target positioning method.
A vehicle, characterized in that the vehicle comprises:

A processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor is used to execute the machine executable instructions to implement the vehicle positioning method according to any one of claims 1 to 8.