CN115077538A

CN115077538A - Vehicle positioning method and device

Info

Publication number: CN115077538A
Application number: CN202210706651.7A
Authority: CN
Inventors: 李春辉
Original assignee: Hozon New Energy Automobile Co Ltd
Current assignee: Hozon New Energy Automobile Co Ltd
Priority date: 2022-06-21
Filing date: 2022-06-21
Publication date: 2022-09-20

Abstract

The application discloses a vehicle positioning method and device, and relates to the technical field of navigation positioning. The method of the present application comprises: acquiring running data of the vehicle in running, wherein the running data is used for representing the position of the vehicle in running and relevant parameters of the environment; matching the operation data with a preset map based on a preset first algorithm to obtain an initial matching result, wherein the initial matching result is used for representing a target area of the vehicle in the preset map; extracting key data from the initial matching result, wherein the key data are indicative targets or target parameters in the target area; matching the operation data with the key data based on a preset second algorithm to obtain an accurate matching result, wherein the accurate matching result is used for representing the target position of the vehicle in the target area; and performing iterative computation on the accurate matching result in a preset error model to obtain a positioning result, wherein the positioning result is used for representing the position of the vehicle in a preset map.

Description

Vehicle positioning method and device

Technical Field

The present application relates to the field of navigation and positioning technologies, and in particular, to a vehicle positioning method and apparatus.

Background

In the current map use and vehicle navigation processes, a vehicle needs to be positioned, and the positioning is generally performed based on a GPS positioning technology in combination with an electronic map. The GPS Positioning technology is called Global Positioning System (GPS for short), and is a high-precision radio navigation Positioning System based on artificial earth satellites.

Generally, in a conventional vehicle positioning process, a current longitude and a current latitude of a vehicle are acquired based on a GPS positioning technology, and then are searched with an electronic map, so that a position of the vehicle is determined in the electronic map, and a positioning function is realized. However, in practical applications, since the positioning process needs GPS technology, that is, the vehicle position is located by longitude and latitude information, which is suitable for positioning objects with large sizes such as airplanes and ships, or under a scene with a single surrounding environment, for vehicles, especially for the requirement of accuracy reaching the centimeter level, the current positioning result can only determine the approximate area of the vehicle, resulting in low accuracy of vehicle positioning.

Disclosure of Invention

The embodiment of the application provides a vehicle positioning method and device, and mainly aims to solve the problem that the accuracy of vehicle positioning is low in the current vehicle positioning process.

In order to solve the above technical problem, an embodiment of the present application provides the following technical solutions:

in a first aspect, the present application provides a vehicle localization method, the method comprising:

acquiring running data of a vehicle in running, wherein the running data is used for representing the position of the vehicle in running and relevant parameters of the environment;

matching the operation data with a preset map based on a preset first algorithm to obtain an initial matching result, wherein the initial matching result is used for representing a target area of the vehicle in the preset map;

extracting key data from the initial matching result, wherein the key data are indicative targets or target parameters in the target area;

matching the operating data with the key data based on a preset second algorithm to obtain an accurate matching result, wherein the accurate matching result is used for representing the target position of the vehicle in the target area;

and performing iterative computation on the accurate matching result in a preset error model to obtain a positioning result, wherein the positioning result is used for representing the position of the vehicle in the preset map.

Optionally, the acquiring the operating data of the vehicle during operation includes:

acquiring a position parameter of the vehicle during operation based on a first preset sensing system, wherein the position parameter is used for representing the actual geographic position of the vehicle;

and acquiring an environmental parameter of the vehicle during running based on a second preset sensing system, wherein the environmental parameter is used for representing the environment around the vehicle during running.

Optionally, the preset first algorithm includes a hidden markov algorithm;

the matching of the operation data and a preset map based on a preset first algorithm to obtain an initial matching result comprises the following steps:

and matching the position parameters with the preset map based on the hidden Markov algorithm to obtain the initial matching result, wherein the position parameters comprise satellite positioning parameters and/or inertial positioning parameters.

Optionally, the preset second algorithm includes a graph optimization algorithm;

matching the operating data with the key data based on a preset second algorithm to obtain an accurate matching result, wherein the method comprises the following steps:

and matching the environmental parameters with the key data based on the graph optimization algorithm to obtain the accurate matching result, wherein the environmental parameters comprise point cloud environmental parameters and/or image environmental parameters.

Optionally, the initial matching result includes first map data; the first map data is environment data corresponding to the target area in the preset map;

the extracting key data from the initial matching result comprises:

extracting a target object and a corresponding target object parameter from the first map data, and determining the target object and the corresponding target object parameter as the key data; the target object comprises at least one of a road boundary, a lane line, a sign board and key frame information, wherein the key frame information is a frame of which the content change degree with a previous frame exceeds a preset threshold value in the frame-by-frame dynamic display process of the preset map.

Optionally, the performing iterative computation on the accurate matching result in a preset error model to obtain a positioning result includes:

and executing iterative computation operation on the input value of the accurate matching result in the preset error matching model, and determining an iterative computation result as the positioning result, wherein the preset error matching model is a pre-trained computation model for performing convergence fitting on the error of the matching result.

Optionally, after performing iterative computation on the accurate matching result in a preset error model to obtain a positioning result, the method further includes:

and judging the positioning result through a preset positioning judgment model to obtain a judgment result, wherein the judgment result is used for representing the accuracy based on the positioning result, and the accuracy is determined based on the size of the difference between the positioning error of the positioning result and the average positioning error.

In a second aspect, the present application further provides a vehicle positioning device comprising:

the system comprises an acquisition unit, a processing unit and a control unit, wherein the acquisition unit is used for acquiring operation data when a vehicle runs, and the operation data is used for representing the position of the vehicle and relevant parameters of the environment when the vehicle runs;

the first matching unit is used for matching the running data with a preset map based on a preset first algorithm to obtain an initial matching result, and the initial matching result is used for representing a target area of the vehicle in the preset map;

an extracting unit, configured to extract key data from the initial matching result, where the key data is a target object or a target parameter having an indication in the target region;

the second matching unit is used for matching the operating data with the key data based on a preset second algorithm to obtain an accurate matching result, and the accurate matching result is used for representing the target position of the vehicle in the target area;

and the calculating unit is used for performing iterative calculation on the accurate matching result in a preset error model to obtain a positioning result, and the positioning result is used for representing the position of the vehicle in the preset map.

Optionally, the obtaining unit includes:

the system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring a position parameter of the vehicle during operation based on a first preset sensing system, and the position parameter is used for representing the actual geographic position of the vehicle;

the second acquisition module is used for acquiring the environment parameters of the vehicle during running based on a second preset sensing system, and the environment parameters are used for representing the environment around the vehicle during running.

Optionally, the preset first algorithm includes a hidden markov algorithm;

the first matching unit is specifically configured to match the position parameter with the preset map based on the hidden markov algorithm to obtain the initial matching result, where the position parameter includes a satellite positioning parameter and/or an inertial positioning parameter.

the second matching unit is specifically configured to match the environmental parameters with the key data based on the graph optimization algorithm to obtain the accurate matching result, where the environmental parameters include point cloud environmental parameters and/or image environmental parameters.

the extraction unit is specifically configured to extract a target object and a corresponding target object parameter from the first map data, and determine the target object and the corresponding target object parameter as the key data; the target object comprises at least one of a road boundary, a lane line, a sign board and key frame information, wherein the key frame information is a frame of which the content change degree with a previous frame exceeds a preset threshold value in the frame-by-frame dynamic display process of the preset map.

Optionally, the pair calculation unit is specifically configured to execute iterative calculation operation on the accurate matching result input value in the preset error matching model, and determine an iterative calculation result as the positioning result, where the preset error matching model is a pre-trained calculation model for performing convergence fitting on an error of a matching result.

Optionally, the apparatus further comprises:

and the judging unit is used for judging the positioning result through a preset positioning judging model to obtain a judging result, wherein the judging result is used for representing the accuracy based on the positioning result, and the accuracy is determined based on the size of the difference between the positioning error of the positioning result and the average positioning error.

In a third aspect, an embodiment of the present application provides a storage medium including a stored program, wherein when the program runs, a device on which the storage medium is located is controlled to execute the vehicle positioning method according to any one of the first aspect.

In a fourth aspect, embodiments of the present application provide a vehicle localization apparatus, the apparatus comprising a storage medium; and one or more processors, the storage medium coupled with the processors, the processors configured to execute program instructions stored in the storage medium; the program instructions when executed perform the vehicle localization method of any one of the first aspects.

By means of the technical scheme, the technical scheme provided by the application at least has the following advantages:

the application provides a vehicle positioning method and device, the method comprises the steps of firstly obtaining running data when a vehicle runs, matching the running data with a preset map based on a preset first algorithm to obtain an initial matching result, then extracting key data from the initial matching result, matching the running data with the key data based on a preset second algorithm to obtain an accurate matching result, and finally performing iterative calculation on the accurate matching result in a preset error model to obtain a positioning result, so that the positioning function of the vehicle is realized. Compared with the prior art, the operation data are used for representing the position of the vehicle during operation and relevant parameters of the environment, the key data are indicative objects or parameters in the target area, and the initial matching result is used for representing the target area of the vehicle in the preset map; the exact match result is used to characterize a target position of the vehicle in the target area; the positioning result is used for representing the position of the vehicle in the preset map, namely, the vehicle is matched through the preset first algorithm and the preset second algorithm and is matched with the key data based on the second algorithm in the matching process, so that the vehicle can be matched with the object in the target area in the preset map, the target position of the corresponding vehicle is obtained, the situation that the positioning result is only an approximate area due to the fact that only GPS positioning is relied on is avoided, and the positioning accuracy is improved. Meanwhile, the accurate matching result and the preset error model are subjected to iterative calculation in the positioning process, so that the finally obtained positioning result is ensured to be obtained after the preset error analysis model is corrected, and the accuracy of the positioning result is further improved.

The above description is only an overview of the technical solutions of the present application, and the present application may be implemented in accordance with the content of the description so as to make the technical means of the present application more clearly understood, and the detailed description of the present application will be given below in order to make the above and other objects, features, and advantages of the present application more clearly understood.

Drawings

The above and other objects, features and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the present application are illustrated by way of example and not by way of limitation in the figures of the accompanying drawings and in which like reference numerals refer to similar or corresponding parts and in which:

FIG. 1 is a flow chart illustrating a method for locating a vehicle according to an embodiment of the present application;

FIG. 2 is a flow chart illustrating another vehicle locating method provided by the embodiments of the present application;

FIG. 3 is a block diagram illustrating components of a vehicle locating device provided by an embodiment of the present application;

fig. 4 shows a block diagram of another vehicle positioning device provided in the embodiment of the present application.

Detailed Description

Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which this application belongs.

An embodiment of the present application provides a vehicle positioning method, specifically as shown in fig. 1, the method includes:

101. and acquiring running data of the running vehicle.

Wherein the operation data is used for representing the position of the vehicle in operation and relevant parameters of the environment.

In this embodiment, the location-related parameter may be a parameter obtained by a certain sensor or a positioning system, where the location-related parameter may indicate a current geographic location of the vehicle, and the environment-related parameter may be some parameter of the surrounding environment where the vehicle is operating, such as information of objects such as trees, buildings, and signboards. Certainly, in the embodiment, the type, form and quantity of the relevant parameters of the location and the environment included in the operation data are not specifically limited, so as to ensure that the subsequent positioning requirement is selected by the user. For example, the operational data may include geolocation coordinates and surrounding feature identifier information.

It should be noted that, in this embodiment, the obtaining manner of the operation data obtained when the vehicle operates may include, but is not limited to, requesting the vehicle control system for the data through a network, and also may control a specific sensor to obtain the data based on a command form, and of course, the specific obtaining manner is not specifically limited herein, and a corresponding form may be selected based on a type of data content included in the specific operation data.

102. And matching the operation data with a preset map based on a preset first algorithm to obtain an initial matching result.

And the initial matching result is used for representing a target area of the vehicle in the preset map.

In this step, based on the foregoing steps, after the operation data is acquired, since the operation data includes the relevant parameters of the location and the environment, the corresponding location, that is, the initial matching result, may be matched in the preset map by using the preset first algorithm based on the parameters. Specifically, the preset first algorithm may be any algorithm capable of performing map data comparison, for example, a hidden markov algorithm. Of course, in a specific application, the preset first algorithm may be selected based on actual needs.

In this embodiment, the initial matching result may be understood as determining an approximate position of the vehicle in the preset map through the preset first algorithm, where the approximate position may be understood as a certain area in the map, and a size range of the target area corresponding to the initial matching result is actually related to the selected algorithm type and the data type included in the operation data, which is not limited herein.

103. And extracting key data from the initial matching result.

Wherein the critical data is a target object or a target parameter having an indicative property in the target region.

Since the surrounding environment changes during the operation of the vehicle, representative objects around the vehicle can be identified during the positioning of the vehicle. In this step, data related to vehicle positioning, that is, key data, may be extracted from the initial matching result, where the key data is an object or a parameter of the object with an indication in the initial matching result, that is, after a target area of the vehicle in a preset map is determined, an object or a parameter with a certain indication is extracted, the key data may be an object such as a specific road sign, a building, a hill, a tree, or the like, or a text sign in the map, and the specific type and form of the key data are not limited herein, and may be selected based on actual needs

104. And matching the operating data with the key data based on a preset second algorithm to obtain an accurate matching result.

Wherein the exact match result is used to characterize a target position of the vehicle in the target area.

After the extracted key data is obtained in the foregoing step 103, since the key data includes an indicative target object or a target parameter, in this step, the operation data may be matched with the key data based on a preset second algorithm, that is, based on the parameter of the vehicle during operation being matched with the indicative target object or target parameter, so that an effect of further determining which position of the vehicle in the target area is in the target area, that is, the target position is achieved, and thus an accurate matching result is obtained.

105. And performing iterative computation on the accurate matching result in a preset error model to obtain a positioning result.

And the positioning result is used for representing the position of the vehicle in the preset map.

Since the precise matching result is actually the result of matching between the running data and the key data based on the vehicle, there may be an error in the matching in practical application, in this embodiment, the precise matching result may be iteratively calculated based on a preset error model, and since the preset error model is a model capable of calculating and analyzing the error of the matching result, after performing multiple iterations, the result after error optimization may be determined, and the calculated result may be used as the positioning result after the actual vehicle is positioned.

The embodiment provides a vehicle positioning method, and the method comprises the steps of firstly obtaining running data when a vehicle runs, matching the running data with a preset map based on a preset first algorithm to obtain an initial matching result, then extracting key data from the initial matching result, then matching the running data with the key data based on a preset second algorithm to obtain an accurate matching result, and finally performing iterative computation on the accurate matching result in a preset error model to obtain a positioning result, so that the function of positioning the vehicle is realized. Compared with the prior art, the operation data are used for representing the position of the vehicle during operation and relevant parameters of the environment, the key data are indicative objects or parameters in the target area, and the initial matching result is used for representing the target area of the vehicle in the preset map; the exact match result is used to characterize a target position of the vehicle in the target area; the positioning result is used for representing the position of the vehicle in the preset map, namely, the vehicle is matched through the preset first algorithm and the preset second algorithm and is matched with the key data based on the second algorithm in the matching process, so that the vehicle can be matched with the object in the target area in the preset map, the target position of the corresponding vehicle is obtained, the situation that the positioning result is only an approximate area due to the fact that only GPS positioning is relied on is avoided, and the positioning accuracy is improved. Meanwhile, the accurate matching result and the preset error model are subjected to iterative calculation in the positioning process, so that the finally obtained positioning result is ensured to be obtained after the preset error analysis model is corrected, and the accuracy of the positioning result is further improved.

For the following description in more detail, an embodiment of the present application provides another access control method, specifically as shown in fig. 2, the method includes:

201. and acquiring running data of the running vehicle.

Since the operation data of the vehicle during operation can be divided into the parameters related to the position and the parameters related to the environment, the following two aspects can be specifically divided when the step is executed:

on the one hand, position parameters of the vehicle during operation are acquired based on a first preset sensing system, and the position parameters are used for representing the actual geographic position of the vehicle.

In the method of the present aspect, the position parameters may be determined based on the GNSS and the IMU inertial measurement unit,

the GNSS is called a Global Navigation Satellite System (GNSS), which is also called a Global Navigation Satellite System (GNSS), and is a space-based radio Navigation positioning System capable of providing all-weather three-dimensional coordinates, speed and time information to a user at any place on the earth surface or in a near-earth space. Which may include one or more satellite constellations and their required augmentation systems to support a particular job. An Inertial Measurement Unit (IMU) is a sensor mainly used to detect and measure acceleration and rotational motion. The principle is realized by adopting an inertia law, and the position of a measured object can be calculated by combining the characteristics of the inertia law and related parameters. Based on this, in this embodiment, the first preset sensing system may be a GNSS-based positioning sensing system and an IMU-based inertial sensing system, and the specific type and manner are not limited herein and may be determined based on the actual configuration condition of the vehicle.

On the other hand, the environmental parameters of the vehicle during operation are obtained based on a second preset sensing system, and the environmental parameters are used for representing the environment around the vehicle during operation.

In this embodiment, the environmental parameter may be acquired by a vision system, or may be acquired by a laser radar system. Wherein, vision system can be for the camera that sets up in the vehicle, the in-process of obtaining the environmental parameter is in fact the process of constantly gathering the image through the camera in the vehicle, consequently, this environmental parameter can be the image, in addition, the lidar system can be the combination of one or more radars such as millimeter wave radar, lidar that set up in the vehicle, can carry out the collection of all ring border data through these radars in the application process, consequently, this environmental parameter also can be radar signal.

Based on this, in this embodiment, the second preset sensing system may be any system capable of collecting and recording the surrounding environment during the operation of the vehicle, such as a vision sensing system, a laser radar sensing system, and the like.

202. And matching the operation data with a preset map based on a preset first algorithm to obtain an initial matching result.

And the initial matching result is used for representing a target area of the vehicle in the preset map. The preset first algorithm includes a hidden markov algorithm. The Hidden Markov Model (HMM) is an algorithm for matching and recognizing two sets of data by using a Hidden Markov model.

Based on this, the step may be specifically performed as follows: and matching the position parameters with the preset map based on the hidden Markov algorithm to obtain the initial matching result, wherein the position parameters comprise satellite positioning parameters and/or inertial positioning parameters.

In the process of determining the initial matching result, the hidden markov model can match the two data, that is, after the position parameter of the current vehicle is input, the data corresponding to the position parameter, that is, the target region according to the embodiment, can be determined from the preset map based on the characteristics of the hidden markov model.

203. And extracting key data from the initial matching result.

Wherein the critical data is a target object or a target parameter having an indicative property in the target region. The initial matching result comprises first map data; the first map data is environment data corresponding to the target area in the preset map.

Specifically, the step may be executed as follows: extracting a target object and a corresponding target object parameter from the first map data, and determining the target object and the corresponding target object parameter as the key data.

The target object comprises at least one of a road boundary, a lane line, a sign board and key frame information, wherein the key frame information is a frame of which the content change degree with a previous frame exceeds a preset threshold value in the frame-by-frame dynamic display process of the preset map.

In this embodiment, the first map data may be understood as that after the foregoing steps preliminarily confirm which region of the preset map the vehicle is in, all map parameters in the region may include a plurality of different targets included in the target region and information of each target, since in practical applications, these targets are not all useful for vehicle positioning, such as weather information, information related to tree species, and the like. Therefore, in this embodiment, it is necessary to acquire information that can provide assistance for positioning the vehicle, that is, to extract the target object and the target object parameter from the first map data.

For the target objects, some objects capable of positioning the vehicle may be included, such as lane lines, road boundaries, signboards, and keyframes, and the first several objects may clearly position the vehicle in the road, which is not described herein. For the key frame, the matching process is actually a process of matching the current geographic position of the vehicle with the position in the preset map, and the preset map can be understood as a picture that can be displayed continuously frame by frame based on the vehicle position in the navigation process, so that some changes exist between frames in the display process, for example, when the vehicle runs to a certain intersection, a great difference is certainly existed between the image before the vehicle does not reach the intersection. For such a frame having a large difference between the previous frame and the next frame, the frame corresponding to the changed image may be determined as a key frame. The frame of image has a high probability of having environmental data capable of obviously distinguishing the previous vehicle running, so that the key frame can be extracted from the target area as key data for accurately determining the vehicle in the subsequent matching process.

204. And matching the operating data with the key data based on a preset second algorithm to obtain an accurate matching result.

Wherein the exact match result is used to characterize a target position of the vehicle in the target area. The preset second algorithm comprises a graph optimization algorithm.

The step may be specifically executed as follows: and matching the environmental parameters with the key data based on the graph optimization algorithm to obtain the accurate matching result. Wherein the environment parameter comprises a point cloud environment parameter and/or an image environment parameter.

Among them, the Graph Optimization algorithm, i.e., the G2O algorithm, (General Graph Optimization, collectively referred to as the G2O algorithm) is a process of using the least square method, regarding data as a Graph, and performing iterative computation by using input data in the form of a defined boundary, and is a common comparison algorithm. In the present embodiment, the environmental parameter in the operation data is compared with the key data based on a graph optimization algorithm, so as to determine the data corresponding to the environmental parameter, i.e. the exact matching result, wherein the implementation process can be understood as matching the target object parameter in the key data with the environmental parameter, so as to determine which object the current vehicle is in the vicinity of. Of course, in a specific application process, the using mode and the execution process of the graph optimization algorithm are the same as those of a conventional data matching process, and details are not described herein.

205. And performing iterative computation on the accurate matching result in a preset error model to obtain a positioning result.

Specifically, the step may be executed as follows: and executing iterative computation operation on the input value of the accurate matching result in the preset error matching model, and determining an iterative computation result as the positioning result, wherein the preset error matching model is a pre-trained computation model for performing convergence fitting on the error of the matching result.

It should be noted that, before the present embodiment is applied, the preset error matching model described in the present embodiment may be trained in advance through a model training method, and the preset error matching model may be set based on a cost function, where the cost function is a function capable of fitting and normalizing a result, and is often used in a process of normalizing input data and converging the input data to an optimal solution. Therefore, in this embodiment, the preset error model may be trained in advance through a plurality of sample data, so as to obtain a model capable of further optimizing the accurate matching result. Based on this, after the accurate matching result is determined in the previous step, the accurate matching result input value can be optimized in the preset error model through continuous iterative calculation, so that the obtained result is the 'optimal solution' after convergence and fitting, and the 'optimal solution' can be determined as the actual more accurate positioning result of the vehicle.

206. And judging the positioning result through a preset positioning judgment model to obtain a judgment result.

Wherein the evaluation result is used for characterizing the accuracy based on the positioning result, and the accuracy is determined based on the size of the difference between the positioning error of the positioning result and the average positioning error.

The preset positioning evaluation model in this embodiment may be based on a Map-Matching Monitor, that is, a Map Matching model, and may be understood as a model in which the accuracy of the positioning result is scored and rated through the input of various parameters, and the specific evaluation manner is mainly determined based on the type of input data involved in the training of the model, for example, when the data of a wheel speed sensor and the data of a laser sensor are used in the training, in this step, in addition to the positioning result, the data of the wheel speed sensor and the data of the laser sensor of the current vehicle need to be acquired simultaneously during the evaluation, and of course, the type and the number of the data required in the specific evaluation process are not limited here, so that the data required in the training of the preset positioning evaluation model corresponds to each other.

In order to achieve the above object, according to another aspect of the present application, an embodiment of the present application further provides a storage medium, where the storage medium includes a stored program, and when the program runs, the apparatus on which the storage medium is located is controlled to execute the vehicle positioning method described above.

In order to achieve the above object, according to another aspect of the present application, embodiments of the present application further provide a vehicle positioning apparatus, which includes a storage medium; and one or more processors, the storage medium coupled with the processors, the processors configured to execute program instructions stored in the storage medium; the program instructions when executed perform the vehicle positioning method described above.

Further, as an implementation of the method shown in fig. 1 and fig. 2, another embodiment of the present application further provides a vehicle positioning apparatus. The embodiment of the vehicle positioning apparatus corresponds to the foregoing method embodiment, and for convenience of reading, details of the foregoing method embodiment are not repeated in the embodiment of the vehicle positioning apparatus, but it should be clear that the system in this embodiment can correspondingly implement all the contents of the foregoing method embodiment. As shown in fig. 3 in detail, the vehicle positioning apparatus includes:

the acquiring unit 31 may be configured to acquire operation data of a vehicle during operation, where the operation data may be used to characterize a location and an environment of the vehicle during operation;

a first matching unit 32, configured to match the operation data with a preset map based on a preset first algorithm, so as to obtain an initial matching result, where the initial matching result may be used to represent a target area of the vehicle in the preset map;

an extracting unit 33, configured to extract key data from the initial matching result, wherein the key data is an object or an object parameter indicative of the target area;

the second matching unit 34 may be configured to match the operating data with the key data based on a preset second algorithm to obtain an accurate matching result, where the accurate matching result may be used to represent a target position of the vehicle in the target area;

the calculating unit 35 may be configured to perform iterative calculation on the accurate matching result in a preset error model to obtain a positioning result, where the positioning result may be used to represent a position of the vehicle in the preset map.

Further, as shown in fig. 4, the acquiring unit 31 includes:

a first obtaining module 311, configured to obtain, based on a first preset sensing system, a position parameter of the vehicle during operation, where the position parameter may be used to represent an actual geographic position of the vehicle;

the second obtaining module 312 may be configured to obtain an environmental parameter of the vehicle during operation based on a second preset sensing system, where the environmental parameter may be used to characterize an environment around the vehicle during operation.

Further, as shown in fig. 4, the preset first algorithm includes a hidden markov algorithm;

the first matching unit 32 may be specifically configured to match the position parameter with the preset map based on the hidden markov algorithm to obtain the initial matching result, where the position parameter includes a satellite positioning parameter and/or an inertial positioning parameter.

Further, as shown in fig. 4, the preset second algorithm includes a graph optimization algorithm;

the second matching unit 34 may be specifically configured to match the environmental parameters with the key data based on the graph optimization algorithm to obtain the precise matching result, where the environmental parameters include point cloud environmental parameters and/or image environmental parameters.

Further, as shown in fig. 4, the initial matching result includes first map data; the first map data is environment data corresponding to the target area in the preset map;

the extracting unit 33 may be specifically configured to extract a target object and a corresponding target object parameter from the first map data, and determine the target object and the corresponding target object parameter as the key data; the target object comprises at least one of a road boundary, a lane line, a sign board and key frame information, wherein the key frame information is a frame of which the content change degree with the previous frame exceeds a preset threshold value in the process of dynamically displaying the preset map frame by frame.

Further, as shown in fig. 4, the pair calculating unit 35 may be specifically configured to perform an iterative calculation operation on the input value of the accurate matching result in the preset error matching model, and determine an iterative calculation result as the positioning result, where the preset error matching model is a pre-trained calculation model that may be used to perform convergence fitting on an error of the matching result.

Further, as shown in fig. 4, the apparatus further includes:

the evaluation unit 36 may be configured to evaluate the positioning result through a preset positioning evaluation model to obtain an evaluation result, where the evaluation result may be used to represent an accuracy based on the positioning result, and the accuracy is determined based on a size of a difference between a positioning error of the positioning result and an average positioning error.

The embodiment of the application provides a vehicle positioning method and device, the method comprises the steps of firstly, obtaining running data during vehicle running, matching the running data with a preset map based on a preset first algorithm to obtain an initial matching result, then extracting key data from the initial matching result, matching the running data with the key data based on a preset second algorithm to obtain an accurate matching result, and finally performing iterative calculation on the accurate matching result in a preset error model to obtain a positioning result, so that the positioning function of a vehicle is realized. Compared with the prior art, the operation data are used for representing the position of the vehicle during operation and relevant parameters of the environment, the key data are indicative objects or parameters in the target area, and the initial matching result is used for representing the target area of the vehicle in the preset map; the exact match result is used to characterize a target position of the vehicle in the target area; the positioning result is used for representing the position of the vehicle in the preset map, namely, the vehicle is matched through the preset first algorithm and the preset second algorithm and is matched with the key data based on the second algorithm in the matching process, so that the vehicle can be matched with the object in the target area in the preset map, the target position of the corresponding vehicle is obtained, the situation that the positioning result is only an approximate area due to the fact that only GPS positioning is relied on is avoided, and the positioning accuracy is improved. Meanwhile, the accurate matching result and the preset error model are subjected to iterative calculation in the positioning process, so that the finally obtained positioning result is ensured to be obtained after the preset error analysis model is corrected, and the accuracy of the positioning result is further improved.

The embodiment of the application provides a storage medium, which comprises a stored program, wherein when the program runs, the device where the storage medium is located is controlled to execute the vehicle positioning method.

The storage medium may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

The embodiment of the application also provides a vehicle positioning device, which comprises a storage medium; and one or more processors, the storage medium coupled with the processors, the processors configured to execute program instructions stored in the storage medium; the program instructions when executed perform the vehicle positioning method described above.

The embodiment of the application provides equipment, the equipment comprises a processor, a memory and a program which is stored on the memory and can run on the processor, and the following steps are realized when the processor executes the program: acquiring running data of a vehicle in running, wherein the running data is used for representing the position of the vehicle in running and relevant parameters of the environment; matching the operation data with a preset map based on a preset first algorithm to obtain an initial matching result, wherein the initial matching result is used for representing a target area of the vehicle in the preset map; extracting key data from the initial matching result, wherein the key data are indicative targets or target parameters in the target area; matching the operating data with the key data based on a preset second algorithm to obtain an accurate matching result, wherein the accurate matching result is used for representing the target position of the vehicle in the target area; and performing iterative computation on the accurate matching result in a preset error model to obtain a positioning result, wherein the positioning result is used for representing the position of the vehicle in the preset map.

Further, the acquiring the operation data when the vehicle operates includes:

and acquiring an environment parameter of the vehicle in operation based on a second preset sensing system, wherein the environment parameter is used for representing the environment around the vehicle in operation.

Further, the preset first algorithm comprises a hidden markov algorithm;

Further, the preset second algorithm comprises a graph optimization algorithm;

Further, the initial matching result includes first map data; the first map data is environment data corresponding to the target area in the preset map;

the extracting key data from the initial matching result comprises:

Further, the performing iterative computation on the accurate matching result in a preset error model to obtain a positioning result includes:

Further, after the performing iterative computation on the precise matching result in a preset error model to obtain a positioning result, the method further includes:

and judging the positioning result through a preset positioning judgment model to obtain a judgment result, wherein the judgment result is used for representing the accuracy based on the positioning result, and the accuracy is determined based on the difference between the positioning error of the positioning result and the average positioning error.

The present application further provides a computer program product adapted to perform program code for initializing the following method steps when executed on a data processing device: acquiring running data of a vehicle in running, wherein the running data is used for representing the position of the vehicle in running and relevant parameters of the environment; matching the operation data with a preset map based on a preset first algorithm to obtain an initial matching result, wherein the initial matching result is used for representing a target area of the vehicle in the preset map; extracting key data from the initial matching result, wherein the key data is an indicative target object or a target parameter in the target area; matching the operating data with the key data based on a preset second algorithm to obtain an accurate matching result, wherein the accurate matching result is used for representing the target position of the vehicle in the target area; and performing iterative computation on the accurate matching result in a preset error model to obtain a positioning result, wherein the positioning result is used for representing the position of the vehicle in the preset map.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art to which the present application pertains. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

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

matching the running data with a preset map based on a preset first algorithm to obtain an initial matching result, wherein the initial matching result is used for representing a target area of the vehicle in the preset map;

2. The method of claim 1, wherein the obtaining operational data while the vehicle is operating comprises:

3. The method of claim 2, wherein the predetermined first algorithm comprises a hidden markov algorithm;

4. The method of claim 2, wherein the predetermined second algorithm comprises a graph optimization algorithm;

5. The method of claim 1, wherein the initial matching result comprises first map data; the first map data is environment data corresponding to the target area in the preset map;

the extracting key data from the initial matching result comprises:

6. The method of claim 5, wherein the iteratively calculating the exact match result in a predetermined error model to obtain a positioning result comprises:

7. The method according to any one of claims 1-6, wherein after said iteratively calculating said exact match result in a predetermined error model to obtain a positioning result, said method further comprises:

8. A vehicle locating apparatus, characterized in that the apparatus comprises:

9. The apparatus of claim 8, wherein the obtaining unit comprises:

10. The apparatus of claim 9, wherein the predetermined first algorithm comprises a hidden markov algorithm;

11. The apparatus of claim 9, wherein the predetermined second algorithm comprises a graph optimization algorithm;

12. The apparatus of claim 8, wherein the initial matching result comprises first map data; the first map data is environment data corresponding to the target area in the preset map;

13. The apparatus of claim 12,

the pair calculation unit is specifically configured to execute iterative calculation operation on the accurate matching result input value in the preset error matching model, and determine an iterative calculation result as the positioning result, where the preset error matching model is a pre-trained calculation model used for performing convergence fitting on an error of a matching result.

14. The apparatus according to any one of claims 8-13, further comprising:

and the judging unit is used for judging the positioning result through a preset positioning judging model to obtain a judging result, wherein the judging result is used for representing the accuracy based on the positioning result, and the accuracy is determined based on the difference between the positioning error of the positioning result and the average positioning error.

15. A storage medium characterized in that the storage medium includes a stored program, wherein an apparatus in which the storage medium is located is controlled to execute the vehicle positioning method according to any one of claims 1 to 7 when the program is executed.

16. A vehicle locating apparatus, characterized in that the apparatus comprises a storage medium; and one or more processors, the storage medium coupled with the processors, the processors configured to execute program instructions stored in the storage medium; the program instructions when executed perform the vehicle localization method of any of claims 1-7.