阅读说明：本技术 地图信息检测处理方法、装置、设备及系统 (Map information detection processing method, device, equipment and system ) 是由 樊帅 冯洁 包俊强 李新 于 2021-07-15 设计创作，主要内容包括：本申请涉及一种地图信息检测处理方法、装置、设备及系统。该方法包括：获取地图数据和获取通过车辆的传感器检测得到的感知数据；将所述地图数据与所述感知数据进行比较,得到差异数据；将所述差异数据上传到云端服务器,以使所述云端服务器根据所述差异数据对所述地图数据进行标记,得到标记数据,根据所述标记数据确定对应的行驶策略。本申请提供的方案,能快速检测出地图数据与当前感知数据的差异,从而使得可以及时根据检测结果进行相应处理,提高行驶安全性。(The application relates to a map information detection processing method, device, equipment and system. The method comprises the following steps: acquiring map data and sensing data obtained by detecting a sensor of a vehicle; comparing the map data with the perception data to obtain difference data; and uploading the difference data to a cloud server so that the cloud server marks the map data according to the difference data to obtain marked data, and determining a corresponding driving strategy according to the marked data. The scheme provided by the application can quickly detect the difference between the map data and the current sensing data, so that corresponding processing can be performed in time according to the detection result, and the driving safety is improved.)

1. A map information detection processing method is characterized by comprising the following steps:

acquiring map data and sensing data obtained by detecting a sensor of a vehicle;

comparing the map data with the perception data to obtain difference data;

and uploading the difference data to a cloud server so that the cloud server marks the map data according to the difference data to obtain marked data, and determining a corresponding driving strategy according to the marked data.

2. The method of claim 1, wherein comparing the map data to the perception data to obtain difference data comprises:

comparing the map data with the perception data, and obtaining difference data of lane lines in the map data and the perception data when the vehicle is in a high-speed road driving scene, wherein the difference data comprises information of starting points and end points of the lane lines with differences; or the like, or, alternatively,

and comparing the map data with the perception data, and obtaining difference data of map elements in the map data and the perception data when the vehicle is in an urban road driving scene, wherein the difference data comprises ID information of the map elements with differences.

3. The method of claim 1 or 2, wherein after comparing the map data with the perception data to obtain difference data, further comprising:

and setting a display layer on the map data, and displaying difference data or reminding information of the perception data and the map data on the display layer.

4. The method of claim 1 or 2, wherein after comparing the map data with the perception data to obtain difference data, further comprising:

and controlling the vehicle to run according to the running strategies corresponding to the different levels according to the different levels corresponding to the difference data.

5. A map information detection processing method is characterized by comprising the following steps:

receiving difference data which is uploaded by a vehicle and obtained by comparing map data with perception data, wherein the perception data is detected by a sensor of the vehicle;

marking the map data according to the difference data to obtain marked data;

determining a corresponding driving strategy according to the marking data;

and issuing the marking data and the driving strategy to each vehicle with the established communication connection.

6. The method of claim 5, wherein said determining a corresponding driving strategy from said tag data comprises:

and determining corresponding different driving strategies according to different levels of the mark data identification.

7. The method of claim 6, wherein determining corresponding different driving strategies based on different levels identified by the marking data comprises:

determining the corresponding driving strategy as degradation passing according to the first level identified by the mark data; or the like, or, alternatively,

determining the corresponding driving strategy as a deceleration pass according to the second level identified by the marking data; or the like, or, alternatively,

and determining the corresponding driving strategy as sending out a prompt according to the third level of the mark data identifier.

8. The method according to any one of claims 5 to 7, wherein said tagging the map data according to the difference data, resulting in tagged data, comprises:

and after the difference data are checked, marking the map data to obtain marked data.

9. A map information detection processing apparatus, comprising:

the acquisition module is used for acquiring map data and sensing data obtained by detecting a sensor of a vehicle;

the comparison module is used for comparing the map data acquired by the acquisition module with the perception data to obtain difference data;

and the processing module is used for uploading the difference data obtained by the comparison module to a cloud server so that the cloud server marks the map data according to the difference data to obtain marked data, and determining a corresponding driving strategy according to the marked data.

10. An automobile characterized by comprising the map information detection processing apparatus according to claim 9.

11. A cloud server, comprising:

the receiving module is used for receiving difference data which are obtained by comparing map data with perception data and uploaded by a vehicle, wherein the perception data are obtained by detecting a sensor of the vehicle;

the marking module is used for marking the map data according to the difference data received by the receiving module to obtain marked data;

the strategy module is used for determining a corresponding driving strategy according to the marking data obtained by the marking module;

and the sending module is used for sending the marking data obtained by the marking module and the driving strategy determined by the strategy module to the vehicle with the established communication connection.

12. A map information detection processing system characterized by:

the system comprises a vehicle and a cloud server; wherein the content of the first and second substances,

the vehicle is used for acquiring map data and perception data detected by a sensor of the vehicle, comparing the map data with the perception data to obtain difference data, and uploading the difference data to a cloud server;

and the cloud server is used for marking the map data according to the difference data to obtain marked data, determining a corresponding driving strategy according to the marked data, and issuing the marked data and the driving strategy to the vehicle with the established communication connection.

13. A computer-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform the method of any one of claims 1-8.

Technical Field

The present application relates to the field of automatic driving technologies, and in particular, to a method, an apparatus, a device, and a system for detecting and processing map information.

Background

At present, with the continuous development of automobile intellectualization, the automatic driving technology is gradually widely applied. In the related art, the related vehicle may provide an NGP (Navigation Guided Pilot) function to a user. By utilizing the NGP function, automatic navigation auxiliary driving from a starting point to a terminal point can be realized on a navigation route set by a user, the driving fatigue of the user is reduced, and the user can enjoy easier and more convenient travel life.

The automatic navigation driving assistance function is generally used in cooperation with map data such as high-precision map data, and can be understood as a high-order driving assistance function realized on the basis of a high-precision map. In the related art, the generation process of map data includes key processes such as collection, production, quality inspection, compilation, image examination, release and the like, and the cycle of completing the process takes about one year. However, in the time period from the collection to the distribution of the map data, the actual road may change due to road repair or the like, which may cause inconsistency between the map data and the actual road data when the user uses the automatic navigation assistance driving function, thereby possibly causing a dangerous situation.

Disclosure of Invention

In order to solve or partially solve the problems in the related art, the application provides a map information detection processing method, device, equipment and system, which can quickly detect the difference between map data and current sensing data, so that corresponding processing can be performed in time according to the detection result, and the driving safety is improved.

A first aspect of the present application provides a map information detection processing method, including:

acquiring map data and sensing data obtained by detecting a sensor of a vehicle;

comparing the map data with the perception data to obtain difference data;

and uploading the difference data to a cloud server so that the cloud server marks the map data according to the difference data to obtain marked data, and determining a corresponding driving strategy according to the marked data.

In one embodiment, the comparing the map data with the perception data to obtain difference data includes:

comparing the map data with the perception data, and obtaining difference data of lane lines in the map data and the perception data when the vehicle is in a high-speed road driving scene, wherein the difference data comprises information of starting points and end points of the lane lines with differences; or the like, or, alternatively,

and comparing the map data with the perception data, and obtaining difference data of map elements in the map data and the perception data when the vehicle is in an urban road driving scene, wherein the difference data comprises ID information of the map elements with differences.

In one embodiment, the sensor comprises at least one of: camera, ultrasonic sensor, radar.

In one embodiment, when the sensor is a camera, the acquiring sensing data detected by a sensor of a vehicle includes:

and acquiring an image shot by a camera of the vehicle, and taking image data identified from the image as perception data.

In one embodiment, after the comparing the map data with the perception data to obtain difference data, the method further includes:

and setting a display layer on the map data, and displaying difference data or reminding information of the perception data and the map data on the display layer.

In one embodiment, after the comparing the map data with the perception data to obtain difference data, the method further includes:

and controlling the vehicle to run according to the running strategies corresponding to the different levels according to the different levels corresponding to the difference data.

A second aspect of the present application provides a map information detection processing method, including:

receiving difference data which is uploaded by a vehicle and obtained by comparing map data with perception data, wherein the perception data is detected by a sensor of the vehicle;

marking the map data according to the difference data to obtain marked data;

determining a corresponding driving strategy according to the marking data;

and issuing the marking data and the driving strategy to each vehicle with the established communication connection.

In one embodiment, the determining a corresponding driving strategy according to the marking data includes:

and determining corresponding different driving strategies according to different levels of the mark data identification.

In one embodiment, the determining different corresponding driving strategies according to different levels identified by the marking data includes:

determining the corresponding driving strategy as degradation passing according to the first level identified by the mark data; or the like, or, alternatively,

determining the corresponding driving strategy as a deceleration pass according to the second level identified by the marking data; or the like, or, alternatively,

and determining the corresponding driving strategy as sending out a prompt according to the third level of the mark data identifier.

In one embodiment, the tagging the map data according to the difference data to obtain tagged data includes:

and after the difference data are checked, marking the map data to obtain marked data.

A third aspect of the present application provides a map information detection processing apparatus including:

the acquisition module is used for acquiring map data and sensing data obtained by detecting a sensor of a vehicle;

the comparison module is used for comparing the map data acquired by the acquisition module with the perception data to obtain difference data;

and the processing module is used for uploading the difference data obtained by the comparison module to a cloud server so that the cloud server marks the map data according to the difference data to obtain marked data, and determining a corresponding driving strategy according to the marked data.

The fourth aspect of the present application provides an automobile, including the above map information detection processing apparatus.

The fifth aspect of the present application provides a cloud server, including:

the receiving module is used for receiving difference data which are obtained by comparing map data with perception data and uploaded by a vehicle, wherein the perception data are obtained by detecting a sensor of the vehicle;

the marking module is used for marking the map data according to the difference data received by the receiving module to obtain marked data;

the strategy module is used for determining a corresponding driving strategy according to the marking data obtained by the marking module;

and the sending module is used for sending the marking data obtained by the marking module and the driving strategy determined by the strategy module to the vehicle with the established communication connection.

The sixth aspect of the application provides a map information detection processing system, which comprises a vehicle and a cloud server; wherein the content of the first and second substances,

the vehicle is used for acquiring map data and perception data detected by a sensor of the vehicle, comparing the map data with the perception data to obtain difference data, and uploading the difference data to a cloud server;

and the cloud server is used for marking the map data according to the difference data to obtain marked data, determining a corresponding driving strategy according to the marked data, and issuing the marked data and the driving strategy to the vehicle with the established communication connection.

A seventh aspect of the present application provides a computer-readable storage medium having stored thereon executable code, which, when executed by a processor of an electronic device, causes the processor to perform the above-mentioned method.

The technical scheme provided by the application can comprise the following beneficial effects:

according to the scheme provided by the application, after sensing data are obtained through detection of a sensor of a vehicle, the map data are compared with the sensing data to obtain difference data; and then uploading the difference data to a cloud server, wherein the cloud server can mark the map data according to the difference data to obtain mark data, and a corresponding driving strategy is determined according to the mark data. Through the processing, even though the road data of the map data may change due to reasons such as road repair and the like, the difference between the map data and the current sensing data can be quickly detected, the error of the map data can be found in time, corresponding processing is carried out according to the detection result, the error of the map data can be marked, and a corresponding driving strategy can be formulated for a vehicle user to refer to, so that the driving safety is improved.

Furthermore, the scheme provided by the application can determine corresponding different driving strategies according to different levels of the marking data identification, for example, the different levels respectively correspond to driving strategies such as degradation passing, deceleration passing, reminding sending and the like, and different strategies are set for different degrees of difference results, so that the coping measures are more reasonable, and the user experience is better.

Furthermore, the scheme provided by the application can be used for checking the difference data and then marking the map data to obtain marked data, so that the marking is more accurate.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The foregoing and other objects, features and advantages of the application will be apparent from the following more particular descriptions of exemplary embodiments of the application, as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the application.

Fig. 1 is a schematic flowchart illustrating a map information detection processing method according to an embodiment of the present application;

fig. 2 is a schematic flowchart of a map information detection processing method according to another embodiment of the present application;

fig. 3 is a flowchart illustrating a map information detection processing method according to another embodiment of the present application;

fig. 4 is a flowchart illustrating a map information detection processing method according to another embodiment of the present application;

fig. 5 is a flowchart illustrating a map information detection processing method according to another embodiment of the present application;

fig. 6 is a schematic structural diagram of a map information detection processing apparatus according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of a map information detection processing apparatus according to another embodiment of the present application;

fig. 8 is a schematic structural diagram of a cloud server according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a cloud server according to another embodiment of the present application;

fig. 10 is a schematic structural diagram of a map information detection processing system according to an embodiment of the present application.

Detailed Description

Preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While the preferred 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.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It should be understood that although the terms "first," "second," "third," etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.

In the related art, in a time period from the collection to the release of map data, an actual road may change due to reasons such as road repair, and the like, so that the driving safety of a user is affected. In view of the above problems, embodiments of the present application provide a map information detection processing method, which can quickly detect a difference between map data and current sensing data, so that corresponding processing can be performed in time according to a detection result, and driving safety is improved.

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

Fig. 1 is a flowchart illustrating a map information detection processing method according to an embodiment of the present application. The embodiment of FIG. 1 is illustrated as applied to a vehicle end.

Referring to fig. 1, the method includes:

step S101, map data and perception data detected by a sensor of the vehicle are acquired.

The sensor comprises at least one of: camera, ultrasonic sensor, radar. When the sensor is a camera, acquiring sensing data detected by a sensor of the vehicle may include: an image captured by a camera of a vehicle is acquired, and image data recognized from the image is taken as perception data. Wherein the map data may be high-precision map data.

And S102, comparing the map data with the perception data to obtain difference data.

The step can be comparing the map data with the perception data, and when the vehicle is in a high-speed road driving scene, obtaining the difference data of the lane lines in the map data and the perception data, wherein the difference data comprises the information of the starting point and the end point of the lane line with difference; or comparing the map data with the perception data, and obtaining difference data of map elements in the map data and the perception data when the vehicle is in an urban road driving scene, wherein the difference data comprises ID information of the map elements with differences.

And step S103, uploading the difference data to a cloud server so that the cloud server marks the map data according to the difference data to obtain marked data, and determining a corresponding driving strategy according to the marked data.

In the step, the difference data are uploaded to a cloud server, so that the cloud server marks the map data according to the difference data to obtain marked data, and a corresponding driving strategy is determined according to the marked data. The cloud server can determine corresponding different driving strategies according to different levels of the marking data identification, for example, driving strategies such as degradation passing, deceleration passing and reminding are respectively corresponding to different levels. The cloud server can issue the mark data of the map data and the corresponding driving strategies to all vehicles establishing communication connection, and after the vehicles download the contents, if the vehicles drive to the starting point of the mark in the map data, the vehicles can execute the contents in advance according to the driving strategies corresponding to the mark, so that the driving safety is improved.

It should be noted that the marking data sent by the cloud server may include start point and end point information of lane lines with differences, or ID information of map elements with differences; additionally, a level of the degree of difference may also be included.

According to the scheme provided by the embodiment of the application, after the sensing data is obtained through the detection of the sensor of the vehicle, the map data is compared with the sensing data to obtain the difference data; and then uploading the difference data to a cloud server, wherein the cloud server can mark the map data according to the difference data to obtain mark data, and a corresponding driving strategy is determined according to the mark data. Through the processing, even though the road data of the map data may change due to reasons such as road repair and the like, the difference between the map data and the current sensing data can be quickly detected, the error of the map data can be found in time, corresponding processing is carried out according to the detection result, the error of the map data can be marked, and a corresponding driving strategy can be formulated for a vehicle user to refer to, so that the driving safety is improved.

Fig. 2 is a flowchart illustrating a map information detection processing method according to another embodiment of the present application. FIG. 2 depicts aspects of embodiments of the present application in greater detail with respect to FIG. 1.

Step S201, map data and perception data detected by a camera of the vehicle are acquired.

This step may acquire an image taken by a camera of the vehicle, and take image data recognized from the image as perception data. The camera may be a monocular camera or a binocular camera, for example. The map data may be high-precision map data.

Step S202, comparing the map data with the perception data to obtain difference data.

The step can be comparing the map data with the perception data, and when the vehicle is in a high-speed road driving scene, obtaining the difference data of the lane lines in the map data and the perception data, wherein the difference data comprises the information of the starting point and the end point of the lane line with difference; or comparing the map data with the perception data, and obtaining difference data of map elements in the map data and the perception data when the vehicle is in an urban road driving scene, wherein the difference data comprises ID information of the map elements with differences. Map elements in urban roads, such as lane lines, traffic lights, zebra crossings, intersections, roadside buildings, etc., are generally identified in a map by ID information.

Step S203, uploading the difference data to a cloud server, so that the cloud server marks the map data according to the difference data to obtain marked data, and determining a corresponding driving strategy according to the marked data.

The cloud server can determine corresponding different driving strategies according to different levels of the marking data identification, for example, driving strategies such as degradation passing, deceleration passing and reminding are respectively corresponding to different levels. The cloud server can issue the marking data of the map data and the corresponding driving strategies to all vehicles with the communication connection established for execution of all vehicles.

And step S204, setting a display layer on the map data, and displaying the difference data of the perception data and the map data or displaying the reminding information on the display layer.

In step S203, the embodiment uploads the difference data to the cloud server, which is mainly used for the cloud server to perform the marking process. However, the vehicle itself may also perform some processing accordingly, for example, after comparing the difference data, a display layer is set on the map data, and the vehicle user is reminded by displaying the difference data between the perception data and the map data or displaying a reminding message on the display layer.

It should be noted that step S204 may not be required in this embodiment.

And S205, controlling the vehicle to run according to the running strategies corresponding to different levels according to different levels corresponding to the difference data.

Although the embodiment may upload the difference data to the cloud server in step S203, so that the cloud server performs the marking processing and makes the corresponding driving policy, the processing performed by the cloud server is mainly performed by each subsequent vehicle according to the marking data and the driving policy of the cloud server, and the current vehicle may not be able to obtain the processing result of the cloud server in time during the driving process. For example, different levels of difference data and corresponding driving strategies may be seen in table 1 below.

TABLE 1

For example, in the perception data identified according to the image shot by the camera, it is detected that the lane line in front is 4 lane lines, but the mark in the map data is 3 lane lines, which indicates that the lane line in the map data is obviously wrong, the level of the difference degree is serious, and the determined driving strategy for the situation can be degraded to pass so as to ensure the driving safety; if the sensing data detects that the solid lines among the lane lines in front cannot change lanes, but the dotted lines among the lane lines marked in the map data can change lanes, the lane lines in the map data are wrong but not obvious, the level of the difference degree is general, and the determined driving strategy can be decelerated to ensure the driving safety; if the sensing data detects that the front lane lines are completely connected, but a small part of the lane lines marked in the map data is missing, the lane lines in the map data are not smooth, the level of the difference degree is slight, and the determined driving strategy for the situation can be to give out a prompt to remind a driver.

The degradation may be degradation of the auxiliary driving function, for example, degradation from an NGP (Navigation Guided Pilot) function to an LCC (Lane Centering Control) function.

According to different levels corresponding to the difference degree of the difference data, the current vehicle executes the driving strategies according to different corresponding settings, for example, the operations of degradation passing, deceleration passing, reminding sending and the like are respectively executed, and when the map data of the front road is detected to be consistent with the sensing data, the normal driving is recovered, for example, the automatic navigation auxiliary driving function is recovered, so that the driving safety can be improved.

It can be seen from the embodiment that, according to the scheme provided by the embodiment of the application, the detected difference data can be uploaded to the cloud server, so that the cloud server marks the map data according to the difference data to obtain marked data, and the corresponding driving strategy is determined according to the marked data; and the current vehicle can be controlled to run according to the running strategies corresponding to different levels according to different levels corresponding to the difference data, so that the running safety is improved.

Fig. 3 is a flowchart illustrating a map information detection processing method according to another embodiment of the present application. The embodiment of fig. 3 is illustrated as being applied to a cloud server.

Referring to fig. 3, the method includes:

step S301, receiving difference data obtained by comparing map data with perception data uploaded by a vehicle, wherein the perception data is detected by a sensor of the vehicle.

After the vehicle acquires map data and perception data obtained through detection of a sensor of the vehicle, comparing the map data with the perception data to obtain difference data; and then uploading the difference data to a cloud server, so that the cloud server can upload the difference data to the vehicle. Wherein the map data may be high-precision map data.

Step S302, marking the map data according to the difference data to obtain marked data.

And the cloud server marks the map data according to the difference data to obtain marked data. For example, for the difference data, a lane line has obvious errors, and the difference data is marked as serious degree of difference; marking the difference data as the lane line error is not obvious and the difference degree is general; for the difference data, which is a small portion of the lane line missing, the lane line is not smooth and the mark is a slight difference.

Step S303, determining a corresponding driving strategy according to the marking data.

This step may determine different corresponding driving strategies according to different levels identified by the marking data. For example, a corresponding travel policy may be determined to be degraded pass based on the first level identified by the marking data; or, according to the second level identified by the marking data, determining that the corresponding driving strategy is deceleration passing; or determining the corresponding driving strategy as sending out a prompt according to the third level identified by the marking data. Wherein the first level may be the severity of the difference; the second level may be a general degree of difference; the third level may be slightly different.

And step S304, transmitting the marking data and the driving strategy to each vehicle with the established communication connection.

In this step, the cloud server may issue the tag data and the driving policy to each vehicle that has established the communication connection, for reference by each vehicle. Each vehicle establishing communication connection with the cloud server can download the marking data and the driving strategy from the cloud server. The marking data sent by the cloud server can comprise the starting point and the end point information of the lane lines with differences or the ID information of the map elements with differences; additionally, a level of the degree of difference may also be included.

According to the embodiment, the scheme provided by the embodiment of the application can upload the detected difference data to the cloud server, the cloud server can mark the map data according to the difference data to obtain marked data, and the corresponding driving strategy is determined according to the marked data; and issuing the marking data and the driving strategy to each vehicle with the established communication connection. Thus, after the vehicles download the contents, if the vehicles run to the starting point marked in the map data, the operations such as degradation passing, deceleration passing, reminding and the like can be executed in advance according to the running strategies corresponding to the marks, and after the ending point marked in the map data is passed, the normal running is recovered, such as the automatic navigation driving assistance function is recovered, so that the running safety is improved.

Fig. 4 is a flowchart illustrating a map information detection processing method according to another embodiment of the present application. FIG. 4 depicts aspects of embodiments of the present application in greater detail with respect to FIG. 3.

Referring to fig. 4, the method includes:

step S401, receiving difference data obtained by comparing map data with perception data uploaded by a vehicle, wherein the perception data is detected by a camera of the vehicle.

After the vehicle acquires map data and perception data obtained through detection of a camera of the vehicle, comparing the map data with the perception data to obtain difference data; and then uploading the difference data to a cloud server, so that the cloud server can upload the difference data to the vehicle. Wherein the map data may be high-precision map data.

And step S402, after the difference data are checked, marking the map data to obtain marked data.

After the cloud server receives the relevant data such as the difference data, the difference data can be rechecked, for example, machine rechecking or manual rechecking is carried out, and then the map data is marked to obtain marked data. For example, for the difference data, a lane line has obvious errors, and the difference data is marked as serious degree of difference; marking the difference data as the lane line error is not obvious and the difference degree is general; for the difference data, which is a small portion of the lane line missing, the lane line is not smooth and the mark is a slight difference.

And step S403, determining a corresponding driving strategy according to the marking data.

This step may determine different corresponding driving strategies according to different levels identified by the marking data. For example, a corresponding travel policy may be determined to be degraded pass based on the first level identified by the marking data; or, according to the second level identified by the marking data, determining that the corresponding driving strategy is deceleration passing; or determining the corresponding driving strategy as sending out a prompt according to the third level identified by the marking data. Wherein the first level may be the severity of the difference; the second level may be a general degree of difference; the third level may be slightly different.

And step S404, transmitting the marking data and the driving strategy to each vehicle with the established communication connection.

In this step, the cloud server may issue the tag data and the driving policy to each vehicle that has established the communication connection, for reference by each vehicle. Each vehicle establishing communication connection with the cloud server can download the marking data and the driving strategy from the cloud server. Generally speaking, after each vehicle is powered on, the vehicle can be connected with a cloud server, whether data updating exists or not is automatically inquired from the cloud server, and if the updating of the marking data and the like is found, the marking data and the corresponding driving strategy are automatically downloaded to the vehicle.

In step S405, the tag data is transmitted to the map manufacturer.

The cloud server can also send the marked data to a map manufacturer for the map manufacturer to update the map data.

It can be seen from this embodiment that, in the solution provided in this embodiment of the application, the cloud server may issue the mark data and the driving policy to each vehicle that has established the communication connection, so that after the vehicles download the contents, if the vehicles drive to the start point of the mark in the map data, the vehicles can execute the mark data in advance according to the driving policy corresponding to the mark, thereby improving the driving security. In addition, the cloud server can also send the marked data to a map manufacturer for the map manufacturer to update the map data, so that the map data can be more accurate when being issued.

Fig. 5 is a flowchart illustrating a map information detection processing method according to another embodiment of the present application. The embodiment is described in terms of an interaction process between a vehicle and a cloud server.

According to the scheme, the difference part between the map data and the actual sensing data is obtained and serves as difference data by mainly utilizing the matching of the sensing data and the map data, the difference data comprises starting point and end point information of a lane line with difference and the like, and the difference data is uploaded to a cloud server; the cloud server determines the actual difference degree of the map data and the perception data by using the matching result, marks the map data of the corresponding position into serious, general, slight and other classifications according to the difference degree, and defines different processing measures, such as different driving strategies, for the difference classifications of different degrees. And then, the mark data of the map data and the corresponding driving strategies are issued to all vehicles establishing communication connection, after the vehicles download the contents, if the vehicles drive to the starting point of the mark in the map data, the vehicles can execute the operations in advance according to the driving strategies corresponding to the mark, such as respectively executing degradation passing, deceleration passing, reminding and the like, and after the end point of the mark in the map data is passed, the normal driving is recovered, such as recovering the automatic navigation driving assistance function, so that the driving safety is improved.

Referring to fig. 5, the method includes:

in step S501, the vehicle acquires map data.

This step of acquiring map data may be acquiring high-precision map data. The high-precision map data can be decimetre high-precision map data and the like.

In step S502, the vehicle acquires an image captured by a camera of the vehicle, and uses image data recognized from the image as perception data.

In this step, an image may be captured by an on-vehicle camera of the vehicle, and image data recognized from the captured image may be used as perception data. The camera may be a monocular camera or a binocular camera, for example.

In this step, a sensor of the vehicle is taken as a camera for example, but the method is not limited to this, and data detected by other sensors of the vehicle, such as an ultrasonic sensor and a radar, may be used as the sensing data. The radar may be, for example, an ultrasonic radar, a millimeter wave radar, a laser radar, or the like. In some vehicles, multiple sensors may be installed, such as 14 cameras, 12 ultrasonic radars, 5 millimeter wave radars, and so forth.

In step S503, the vehicle compares the map data with the perception data to obtain difference data.

In the step, the map data and the perception data are compared, and the part with difference between the map data and the perception data can be determined to obtain difference data. When the vehicle is in different driving scenes, the obtained difference data can be different. For example, when the method is applied to a highway driving scene, the main comparison is the lane lines, and when the method is applied to an urban road driving scene, the main comparison is the lane lines, traffic lights, zebra crossings, road junctions, roadside buildings and the like.

The step compares the map data with the perception data, and when the vehicle is in a high-speed road driving scene, obtains the difference data of the lane lines in the map data and the perception data, wherein the difference data can comprise the information of the starting point and the end point of the lane lines with differences. The perception data recognized from the captured image includes data related to the lane line, and may include, for example, position information of the lane line, the road ahead including several lane lines, and the like. And comparing the relevant data of the lane line in the perception data with the data of the lane line in the acquired map data to obtain the difference result of the lane line and obtain the information of the starting point and the end point of the lane line with the difference. For example, in the perception data recognized from the image captured by the camera, it is detected that the lane line in front is 4 lane lines, but if the map data is marked with 3 lane lines, there is a difference, and after the distance is traveled, the information of the start point and the end point of the lane line with the difference can be obtained.

The step compares the map data with the perception data, and when the vehicle is in an urban road driving scene, difference data of map elements in the map data and the perception data is obtained, wherein the difference data can comprise ID information of the map elements with differences. Map elements in urban roads, such as lane lines, traffic lights, zebra crossings, intersections, roadside buildings and the like, are generally identified in a map by ID information, such as lane line IDs, traffic light IDs, zebra crossings IDs, intersection IDs, roadside building IDs and the like, respectively. For example, in the perception data recognized from the image captured by the camera, if 2 lane lines are detected in front, but 3 lane lines are marked in the map data, a difference exists, and the lane line ID having the difference is recorded.

In step S504, the vehicle uploads the difference data to the cloud server.

And after the vehicle obtains the difference data, the compared difference result related data, namely the difference data, is sent to the cloud server.

Step S505, the cloud server marks the map data according to the difference data to obtain marked data; and determining a corresponding driving strategy according to the marking data.

The cloud server can check the difference data and then mark the map data to obtain marked data. After the cloud server receives the relevant data such as the difference data, the difference data can be rechecked, for example, machine rechecking or manual rechecking is performed, so that whether the comparison between the map data and the perception data performed by the vehicle is matched incorrectly or not is recognized, and therefore position refinement or correction can be performed, and the marked position or the marked result is more accurate. And after rechecking, marking the map data to obtain marked data.

The cloud server can be respectively marked as different levels according to different difference degrees of the difference data, and different corresponding processing measures, such as different driving strategies, are set. Wherein the first level may be the severity of the difference; the second level may be a general degree of difference; the third level may be slightly different. The tag data of the cloud server and the corresponding driving strategy can be seen from table 2 below.

TABLE 2

For example, in the perception data identified according to the image shot by the camera, it is detected that the lane line in front is 4 lane lines, but the mark in the map data is 3 lane lines, which indicates that the lane line of the map data is obviously wrong, and the difference degree is serious, and the determined driving strategy for the situation can be degraded to ensure the driving safety; if the sensing data detects that the solid lines among the lane lines in front cannot change lanes, but the dotted lines among the lane lines marked in the map data can change lanes, the lane lines in the map data are wrong but not obvious, the difference degree is general, and the determined driving strategy can be deceleration to ensure driving safety; if the sensing data detects that the front lane lines are completely connected, but a small part of the lane lines marked in the map data is missing, the lane lines in the map data are not smooth, the difference degree is slight, and the determined driving strategy for the situation can be to give out a prompt to remind a driver.

The degradation may be degradation of the auxiliary driving function, for example, degradation from an NGP (Navigation Guided Pilot) function to an LCC (Lane Centering Control) function. The lane centering auxiliary function is a comfortable auxiliary driving function and can assist a driver to control a steering wheel and continuously center a vehicle in a current lane.

It should be noted that the above classification is only an example, and more classes and driving strategies may be divided according to needs.

The cloud server marks marking data, which may also be referred to as error layer data. The cloud server may issue the tagged data to each vehicle for reference.

In step S506, the cloud server issues the tag data and the driving policy to each vehicle that has established the communication connection.

In this step, the cloud server may issue the tag data and the driving policy to each vehicle that has established the communication connection, for reference by each vehicle. Each vehicle establishing communication connection with the cloud server can download the marking data and the driving strategy from the cloud server. Generally speaking, after each vehicle is powered on, the vehicle can be connected with a cloud server, whether data updating exists or not is automatically inquired from the cloud server, and if the updating of the marking data and the like is found, the marking data and the corresponding driving strategy are automatically downloaded to the vehicle. It should be noted that the marking data sent by the cloud server may include start point and end point information of lane lines with differences, or ID information of map elements with differences; additionally, a level of the degree of difference may also be included.

It should be further noted that the cloud server may also send the tag data to a map manufacturer for the map manufacturer to update the map data, so that the map data can be more accurate when being issued.

And step S507, each vehicle drives according to the driving strategy when driving to the position corresponding to the marking data according to the marking data and the driving strategy acquired from the cloud server.

After the vehicle downloads the mark data and the corresponding driving strategy, if the vehicle runs to the starting point marked in the map data, the vehicle can execute the operations in advance according to the driving strategy corresponding to the mark, such as respectively executing degradation passing, deceleration passing, reminding and the like, and after the end point marked in the map data, the vehicle can resume normal driving, such as resuming the automatic navigation driving assistance function, thereby realizing the improvement of the driving safety.

It should be noted that, in each vehicle, a reminder may also be sent to the vehicle user in a voice manner, and the content of the reminder may be the content of the tag data and/or the content of the driving policy.

In addition, a display layer can be arranged on the map data, and the display layer can display the difference data of the perception data and the map data, or display the content of the marking data, or display the content of the driving strategy, or display the content of the correct lane line and the like for the reference of the vehicle user.

In summary, according to the scheme provided by the embodiment of the application, the difference between the map data and the perception data, that is, the actual environment data, can be obtained according to the comparison between the perception data and the map data, the map data at the corresponding position is marked after rechecking is performed on the cloud server to obtain the marked data, the corresponding driving strategy is determined according to the marked data, and then the marked data and the driving strategy are issued to each vehicle. Subsequently, after each vehicle downloads the marking data and the driving strategy, when the vehicle passes through the corresponding road section in the map, the vehicle can drive according to the corresponding driving strategy, for example, the vehicle respectively performs degradation passing, deceleration passing, reminding sending and other operations, so that the driving safety is improved. In addition, the cloud server can also send the marked data to a map manufacturer for the map manufacturer to update the map data, so that the map data can be more accurate when being issued.

The map information detection processing method disclosed by the embodiment of the application is introduced in detail, and correspondingly, the embodiment of the application further provides a corresponding map information detection processing device, an automobile, a cloud server and a related system.

Fig. 6 is a schematic structural diagram of a map information detection processing apparatus according to an embodiment of the present application.

Referring to fig. 6, a map information detection processing apparatus 60 includes: an acquisition module 61, a comparison module 62 and a processing module 63.

The acquisition module 61 is used for acquiring map data and acquiring perception data detected by a sensor of a vehicle. The sensor may comprise at least one of: camera, ultrasonic sensor, radar. When the sensor is a camera, the acquisition module 61 acquires an image captured by the camera of the vehicle, and uses image data recognized from the image as perception data. Wherein the map data may be high-precision map data.

And the comparison module 62 is configured to compare the map data acquired by the acquisition module 61 with the perception data to obtain difference data. The comparing module 62 may compare the map data with the perception data, and when the vehicle is in an expressway driving scene, obtain difference data of lane lines in the map data and the perception data, where the difference data includes information of starting points and ending points of the lane lines with differences; or comparing the map data with the perception data, and obtaining difference data of map elements in the map data and the perception data when the vehicle is in an urban road driving scene, wherein the difference data comprises ID information of the map elements with differences.

And the processing module 63 is configured to upload the difference data obtained by the comparing module 62 to a cloud server, so that the cloud server marks the map data according to the difference data to obtain marked data, and determines a corresponding driving strategy according to the marked data.

As can be seen from this embodiment, the map information detection processing apparatus provided in the embodiment of the present application compares map data with perception data to obtain difference data after obtaining the perception data through the detection of the sensor of the vehicle; and then uploading the difference data to a cloud server, wherein the cloud server can mark the map data according to the difference data to obtain mark data, and a corresponding driving strategy is determined according to the mark data. Through the processing, even though the road data of the map data may change due to reasons such as road repair and the like, the difference between the map data and the current sensing data can be quickly detected, the error of the map data can be found in time, corresponding processing is carried out according to the detection result, the error of the map data can be marked, and a corresponding driving strategy can be formulated for a vehicle user to refer to, so that the driving safety is improved.

Fig. 7 is a schematic structural diagram of a map information detection processing apparatus according to another embodiment of the present application.

Referring to fig. 7, a map information detection processing apparatus 60 includes: an acquisition module 61, a comparison module 62, a processing module 63 and an execution module 64. The comparison module 62 may include a first comparison sub-module 621 and a second comparison sub-module 622.

The functions of the acquisition module 61, the comparison module 62 and the processing module 63 can be referred to the description in fig. 6.

The first comparing sub-module 621 is configured to compare the map data with the sensing data, and obtain difference data of lane lines in the map data and the sensing data when the vehicle is in an expressway driving scene, where the difference data includes information of a start point and an end point of the lane line having a difference.

And the second comparing submodule 622 is configured to compare the map data with the perception data, and when the vehicle is in an urban road driving scene, obtain difference data of map elements in the map data and the perception data, where the difference data includes ID information of the map elements with differences.

The processing module 63 may further set a display layer on the map data, and display difference data between the sensing data and the map data or display the reminding information on the display layer.

And the execution module 64 is used for controlling the vehicle to run according to the running strategies corresponding to different levels according to different levels corresponding to the difference data. Although the map information detection processing device 60 may upload the difference data to the cloud server, so that the cloud server performs the marking processing and makes the corresponding driving policy, the processing performed by the cloud server is mainly performed by each subsequent vehicle according to the marking data and the driving policy of the cloud server, and the current vehicle may not be able to obtain the processing result of the cloud server in time during the driving process.

The embodiment of the present application also provides an automobile including the map information detection processing device 60 shown in fig. 6 or fig. 7.

Fig. 8 is a schematic structural diagram of a cloud server according to an embodiment of the present application;

referring to fig. 8, a cloud server 80 includes: a receiving module 81, a marking module 82, a policy module 83, and a sending module 84.

And the receiving module 81 is configured to receive difference data obtained by comparing the map data with perception data uploaded by the vehicle, where the perception data is detected by a sensor of the vehicle. Wherein the map data may be high-precision map data, and the sensor may include at least one of: camera, ultrasonic sensor, radar.

And the marking module 82 is configured to mark the map data according to the difference data received by the receiving module 81 to obtain marked data. The marking module 82 marks the map data according to the difference data to obtain marked data. For example, for the difference data, a lane line has obvious errors, and the difference data is marked as serious degree of difference; marking the difference data as the lane line error is not obvious and the difference degree is general; for the difference data, which is a small portion of the lane line missing, the lane line is not smooth and the mark is a slight difference.

And the strategy module 83 is used for determining a corresponding driving strategy according to the marking data obtained by the marking module 82. The policy module 83 may determine different corresponding driving policies based on different levels identified by the marking data.

And the sending module 84 is configured to send the marking data obtained by the marking module 82 and the driving strategy determined by the strategy module 83 to the vehicle with the established communication connection. After the vehicles download the contents, if the vehicles drive to the starting point marked in the map data, the vehicles can execute the operations in advance according to the driving strategies corresponding to the marks, such as respectively executing degradation passing, deceleration passing, reminding and the like, and after the end point marked in the map data is passed, the vehicles can resume normal driving, such as resuming the automatic navigation driving assistance function, so as to improve the driving safety.

Fig. 9 is a schematic structural diagram of a cloud server according to another embodiment of the present application.

Referring to fig. 9, a cloud server 80 includes: a receiving module 81, a marking module 82, a policy module 83, a sending module 84, and a checking module 85.

The functions of the receiving module 81, the marking module 82, the policy module 83 and the sending module 84 can be referred to the description in fig. 8.

The policy module 83 may determine different driving policies according to different levels identified by the marking data. For example, based on the first level identified by the marking data, determining the corresponding driving policy as degraded pass; or, according to the second level identified by the marking data, determining that the corresponding driving strategy is deceleration passing; or determining the corresponding driving strategy as sending out a prompt according to the third level identified by the marking data. Wherein the first level may be the severity of the difference; the second level may be a general degree of difference; the third level may be slightly different.

And the checking module 85 is configured to check the difference data received by the receiving module 81. After the checking module 85 checks the difference data, the marking module 82 marks the map data to obtain marked data. After the receiving module 81 receives the relevant data, such as the difference data, the checking module 85 may perform a review on the difference data, such as a machine review or a manual review, to identify whether the comparison between the map data and the perception data performed by the vehicle is a wrong match or an inaccurate match, so that the position may be refined or corrected, etc., to make the position or the result of the mark more accurate. After the checking module 85 rechecks, the marking module 82 marks the map data to obtain marked data.

FIG. 10 is a schematic structural diagram of a map information detection processing system according to an embodiment of the present application

Referring to fig. 10, a map information detection processing system includes at least one vehicle 60 and a cloud server 80; wherein the content of the first and second substances,

one of the vehicles 60 is configured to acquire map data and perception data detected by a sensor of the vehicle, compare the map data with the perception data to obtain difference data, and upload the difference data to the cloud server 80;

and the cloud server 80 is configured to mark the map data according to the difference data to obtain mark data, determine a corresponding driving strategy according to the mark data, and issue the mark data and the driving strategy to each vehicle 60 with which the communication connection is established.

The functions and structures of the cloud server 80 can be described in fig. 8 and fig. 9, and are not described herein again.

The method can find that after the vehicle obtains sensing data through the detection of the sensor, the map data and the sensing data are compared to obtain difference data; and then uploading the difference data to a cloud server, wherein the cloud server can mark the map data according to the difference data to obtain mark data, determine a corresponding driving strategy according to the mark data, and issue the mark data and the driving strategy to each vehicle with established communication connection, so that after the vehicles download the contents, if the vehicles drive to the starting point marked in the map data, the vehicles can execute the contents in advance according to the driving strategy corresponding to the mark, and the driving safety is improved.

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the applications disclosed herein may be implemented as electronic hardware, computer software, or combinations of both.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Furthermore, the method according to the present application may also be implemented as a computer program or computer program product comprising computer program code instructions for performing some or all of the steps of the above-described method of the present application.

Alternatively, the present application may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) which, when executed by a processor of an electronic device (or electronic device, server, etc.), causes the processor to perform some or all of the various steps of the above-described methods in accordance with the present application.

Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.