WO2021115395A1

WO2021115395A1 - Map-based fault diagnosis

Info

Publication number: WO2021115395A1
Application number: PCT/CN2020/135398
Authority: WO
Inventors: 廖方波
Original assignee: 北京三快在线科技有限公司
Priority date: 2019-12-13
Filing date: 2020-12-10
Publication date: 2021-06-17
Also published as: CN111160420B; CN111160420A

Abstract

A map-based fault diagnosis method and apparatus, an electronic device, and a storage medium. The method comprises: receiving map use information reported by each autonomous driving device (S110); generating the state information of each region in a map according to the map use information (S120); determining a hotspot region in the map according to the state information of each region (S130); and determining a fault object according to the state information of the hotspot region (S140).

Description

Map-based fault diagnosis

Technical field

This application relates to the field of automatic driving, and specifically to map-based fault diagnosis methods, devices, electronic equipment, and storage media.

Background technique

Autonomous driving can be applied to areas such as logistics, food delivery, and so on. Maps are an important part of autonomous driving. The autonomous driving equipment matches the map with various measurement data collected by itself to determine its own location.

Summary of the invention

According to one aspect of this application, a map-based fault diagnosis method is provided, including: receiving map usage information reported by each automatic driving device; generating state information of each area in the map according to the map usage information; The state information of the area determines a hot spot area in the map; and the fault object is determined according to the state information of the hot spot area.

Optionally, the map usage information includes a map matching degree score and pose information of the autonomous driving device, and generating state information of each area in the map according to the map usage information includes: using Information, according to the pose information of the automatic driving device that reports the piece of map usage information, determine the area that matches the piece of map usage information, and obtain the correspondence between the piece of map usage information and the matched area; For each of the regions, the average value of the map matching scores corresponding to the region is calculated according to the corresponding relationship, and the average value is used as the state score of the region.

Optionally, determining the hotspot area in the map according to the status information of each of the areas includes: selecting several areas as the hotspot area according to the status score from low to high; and/or The area where the state score is lower than the preset value is regarded as the hot spot area.

Optionally, the map usage information further includes the identification of the automatic driving device, and determining the fault object according to the status information of the hotspot area includes: for each of the hotspot areas, according to the identification of the automatic driving device, based on the identification of the hotspot area The map matching degree score in the map usage information is calculated, and the state score of each of the autonomous driving devices related to the hot spot area is calculated; if the state score of the target automatic driving device is not consistent with the state scores of other automatic driving devices If it is not, the target autopilot device is regarded as the fault target.

Optionally, the map usage information further includes time information, and determining the fault object according to the status information of the hotspot area further includes: for each hotspot area, if the status score of each of the automatic driving devices related to the hotspot area is scored If there is consistency, the map matching degree scores corresponding to the hot spot area are sorted in chronological order to obtain a map matching degree score curve; if the map matching degree score curve meets the fault characteristics, the hot spot area is regarded as a fault object.

Optionally, the area is a map grid obtained by rasterizing a map, and the method further includes: providing a visualization interface based on the map grid, and displaying the information of each map grid in the visualization interface. status information.

Optionally, the method according to any one of the above, wherein the method further includes: generating a confidence map corresponding to the map according to the status information of each of the regions; and sending the confidence map to the automatic driving Device, so that when the automatic driving device uses the map, it adjusts the use weight of the map according to the confidence map.

According to another aspect of the present application, there is provided a map-based fault diagnosis device, including: a receiving unit for receiving map usage information reported by each automatic driving device; a diagnosis unit for generating a map based on the map usage information The status information of each area in each of the areas; determine the hot spot area in the map according to the status information of each area; determine the fault object according to the status information of the hot spot area.

Optionally, the map usage information includes a map matching degree score and pose information of the automatic driving device, and the diagnosis unit is used for each piece of the map usage information, according to the report of the piece of map usage information. The pose information of the automatic driving device determines the area that matches the piece of map usage information, and obtains the correspondence between the piece of map usage information and the matched area; for each of the areas, according to the correspondence Count the average value of the map matching scores corresponding to the area, and use the average value as the state score of the area.

Optionally, the diagnosis unit is configured to select several areas as the hot spot area according to the state score from low to high; and/or use the area with the state score lower than a preset value as the Hot spot area.

Optionally, the map usage information further includes an automatic driving device identification, and the diagnosis unit is configured to, for each of the hotspot areas, according to the automatic driving device identification, based on the map usage information corresponding to the hotspot area Calculate the state score of each of the autonomous driving devices related to the hot spot area; if the state score of the target autonomous driving device is not consistent with the state scores of other autonomous driving devices, then the The target autopilot equipment is the target of the failure.

Optionally, the map usage information further includes time information, and the diagnosis unit is configured to, for each hotspot area, if the state scores of the autonomous driving devices related to the hotspot area are consistent, then The map matching degree scores corresponding to the hot spot areas are sorted in chronological order to obtain a map matching degree score curve; if the map matching degree score curve meets the fault characteristics, the hot spot area is taken as the fault object.

Optionally, the area is a map grid obtained by rasterizing a map, and the diagnosis unit is further configured to provide a visualization interface based on the map grid, and display each of the map grids in the visualization interface. The status information of the grid.

Optionally, the device further includes: a confidence unit, configured to generate a confidence map corresponding to the map according to the state information of each of the regions; and send the confidence map to an automatic driving device to enable the automatic driving When the driving device uses the map, it adjusts the usage weight of the map according to the confidence map.

According to another aspect of the present application, there is provided an electronic device, including: a processor; and a memory storing computer-executable instructions, which when executed, cause the processor to execute any of the foregoing Methods.

According to another aspect of the present application, there is provided a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, the Any of the methods described above.

It can be seen from the above that the embodiment of the present application receives map usage information reported by each automatic driving device; generates status information of each area in the map according to the map usage information; determines the hotspot area in the map according to the status information; The status information of the hot spot area determines the fault object. The beneficial effect is that it can quickly diagnose the possible defects of the map based on the information of the map, determine the faulty object, improve the efficiency of the fault diagnosis, and provide a reliable guarantee for the normal operation of the map-based autonomous driving, thereby providing logistics and food delivery. Provide technical support in other business areas.

The above description is only an overview of the embodiments of the application. In order to understand the technical means of the application more clearly, it can be implemented in accordance with the content of the specification, and to make the above and other purposes, features and advantages of the application more obvious and understandable. , The specific implementations of this application are cited below.

Description of the drawings

By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only used for the purpose of illustrating the preferred embodiments, and are not considered as a limitation to the application. Also, throughout the drawings, the same reference symbols are used to denote the same components. In the attached picture:

Fig. 1 shows a schematic flowchart of a map-based fault diagnosis method according to an embodiment of the present application;

Figure 2 shows a schematic structural diagram of a map-based fault diagnosis device according to an embodiment of the present application;

Fig. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the present application;

Fig. 4 shows a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present application.

Detailed ways

Hereinafter, exemplary embodiments of the present application will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the application and to fully convey the scope of the application to those skilled in the art.

The automatic driving equipment uses the laser point cloud collected by the laser radar to match the laser map. At this time, the laser map can also be called a laser location map. In order to ensure the safety of autonomous driving, higher requirements are imposed on the accuracy and real-time accuracy of the map. However, in actual applications, the matching degree may be low, which may be caused by reasons such as untimely map update or failure of automatic driving equipment. However, at present, only the map update is often concerned, and there is no diagnosis plan for the cause of the failure.

Fig. 1 shows a schematic flowchart of a map-based fault diagnosis method according to an embodiment of the present application. As shown in Fig. 1, the method includes step S110 to step S140.

Step S110: Receive map usage information reported by each automatic driving device.

The map can be established in the following ways: firstly, data collection is performed. The map collection vehicle records sensor measurement data while driving on the road in the target area, such as laser data measured by lidar sensors, GNSS (Global Navigation Satellite System, Global Navigation Satellite System) Location data measured by the sensor. Secondly, build a map based on the collected data, align the measurement data collected by the sensor with time stamps, and then project the laser data measured by the lidar sensor onto the map based on the measurement attitude of the GNSS sensor and the internal sensor calibration of the map collection vehicle . In this way, the map contains the location information corresponding to the laser data, and the map can also be called a location map. The above scenario takes the use of lidar to collect data as an example. In practical applications, it can also be extended to the scene of using a camera to collect data. For example, when building a map, the feature points are extracted from the image collected by the camera, and then projected onto the map.

That is to say, the map (location map) contains scene contour features (such as lidar measurement points, feature points extracted by camera photography) and corresponding location information. During the driving process, the automatic driving equipment obtains map usage information by matching the real-time measurement data of the sensor with the corresponding data contained in the map.

In step S120, the status information of each area in the map is generated according to the map usage information.

The map can be divided into different areas, and the status information of each area in the map can be generated according to the map usage information. In this application, multiple automatic driving devices can be used to comprehensively obtain the reported usage information to generate status information of each area, so as to avoid diagnosis errors caused by a single automatic driving device false alarm. In this way, the status information of each area in the map can be obtained, thereby providing technical support for business areas such as logistics and food delivery.

Step S130: Determine a hotspot area in the map according to the status information of each area.

In the absence of faults, the status information of each area is almost the same. Therefore, by searching for areas that are inconsistent with the status information of other areas, areas with obvious abnormal features can be determined as hot spots. In this way, hotspot areas in the map can be determined based on the status information, which is convenient for quickly determining areas that may have defects.

Step S140: Determine the fault object according to the status information of the hotspot area.

The status information of the hotspot area can be analyzed to obtain whether the analyzed hotspot area has a fault. In this way, the fault object is determined based on the status information of the hot spot area.

It can be seen that the method shown in Figure 1 can quickly diagnose possible defects in the map based on the information of the map, and determine the faulty object. Improve the efficiency of fault diagnosis, and provide reliable guarantee for the normal operation of map-based automatic driving.

In an embodiment of the present application, in the above method, the map usage information may include the map matching degree score and the pose information of the automatic driving device. According to the map usage information, generating the state information of each area in the map includes: Map usage information, according to the posture information of the automatic driving device that reported the map usage information, determine the area matching the map usage information, and obtain the correspondence between the map usage information and the matched area; for each For the region, the average value of the map matching score corresponding to the region is calculated according to the corresponding relationship, and the average value is used as the state score of the region.

For example, in the course of driving, the automatic driving equipment uses lidar sensors and GNSS sensors to measure data respectively. Find the corresponding laser data in the positioning map according to the current GNSS sensor measurement data, and then calculate the matching degree between the current laser radar sensor measurement data and the found laser data to obtain a map matching score.

Therefore, the map usage information may include the map matching degree score and the pose information of the automatic driving device, where the map matching degree score is the score of the positioning result. The scoring basis may include the matching degree between the laser radar measurement result of the autopilot device and the corresponding laser data in the map. The better the match between the two, the higher the map matching score score. The pose information of the autopilot device is the position information of the autopilot device in space and the posture information of the autopilot device, which can be represented by coordinates (x, y, theta). Where x represents the abscissa value of the space, y represents the ordinate value of the space, and theta represents the angle value between the posture of the autonomous driving device in the space and the coordinate system. The status information of each area in the map can be generated according to the content characteristics of the map usage information. For example, based on each piece of map usage information, such as the location information of the autonomous driving device that reports the piece of map usage information in space and the posture information of the autonomous driving device, an area that matches the piece of map usage information can be determined, and Confirm the correspondence between the piece of map usage information and the matched area. In this way, you can get the area that matches the usage information of each map. For each region, the average value of the map matching degree score corresponding to the region can also be calculated according to the corresponding relationship, and the statistically obtained average value is used as the state score of the region, which reflects the state matching degree of the region.

In an embodiment of the present application, in the above method, determining the hotspot area in the map according to the state information of each area includes: selecting several areas as hotspot areas according to the state score from low to high; and/or The area where the status score is lower than the preset value is regarded as a hot spot area.

A hot spot area is an area where there may be anomalies or map defects. In order to determine the hot spot area more accurately and efficiently, the state scores of each area can be calculated separately, and then the state scores are performed in descending order Sort. In this way, several state scores can be selected according to the state scores from low to high, and the area corresponding to the selected state score can be used as a hot spot area. It is also possible to preset a certain threshold, and then compare the state score with the preset value. If the state score is lower than the preset value, the area corresponding to the state score is regarded as a hot spot area. In this way, hot spots can be determined automatically and quickly.

In an embodiment of the present application, in the above method, the map usage information may also include the identification of the automatic driving device, and determining the fault object according to the status information of the hotspot area includes: for each hotspot area, according to the identification of the automatic driving device, based on the identification of the automatic driving device The map matching score in the map usage information corresponding to the hot spot area is calculated, and the state score of each automatic driving device related to the hot spot area is calculated; if the state score of the target automatic driving device is not the same as the state score of other automatic driving devices If there is consistency, the target autopilot device is regarded as the target of the failure.

The autonomous driving device is associated with a specific unique identifier. For example, the unique ID information of the autonomous driving device for each vehicle can be represented by vechile_id. The map usage information may also include the identification of the automatic driving device, and the fault object may be determined based on the unique identification and combined with the status information of the hotspot area. Specifically, the map matching score corresponding to each hot spot area can be calculated, and then the state score of each automatic driving device related to the hot spot area can be calculated according to the automatic driving device identification. The status score of the target autopilot device can be compared and analyzed with the status scores of other autopilot devices. If the status score of the target autopilot device is not consistent with the status scores of other autopilot devices, for example, the status of the target autopilot device If the score is significantly lower than the state scores of other autonomous driving devices, the target autonomous driving device will be regarded as the failure object. In this way, by means of multi-vehicle statistical analysis, combined with the identification of the automatic driving device, the target automatic driving device can be determined as the fault object, and the possible errors in the fault diagnosis can be reduced.

In an embodiment of the present application, in the above method, the map usage information may also include time information, and determining the fault object according to the status information of the hotspot area also includes: for each hotspot area, if the automatic driving related to the hotspot area If the status scores of the devices are consistent, the map matching scores corresponding to the hotspots are sorted in chronological order to obtain the map matching score curve; if the map matching scores curve meets the fault characteristics, the hotspot area is regarded as a fault Object.

Since different automatic driving devices have different vehicle speeds and time of occurrence, the analysis process of using hot spots as fault objects will be affected by vehicle speed and time. In order to determine the faulty object more accurately and quickly, the map usage information can also include time information, and the time information can be represented by a timestamp. Specifically, for each hotspot area, the state scores of each automatic driving device related to the hotspot area can be counted first. If the state scores of each automatic driving device have obvious similar characteristics, it can be considered as consistent. Then, the map matching degree scores corresponding to the hotspot area can be sorted in chronological order, so as to obtain the map matching degree score curve. The curve reflected by the fault object often has obvious characteristics, such as obvious violent fluctuations and sudden cliff-like changes in the curve. The curve characteristics of these fault objects can be summarized and stored in advance, and compared with the map matching degree scoring curve corresponding to the hot area. If the map matching degree scoring curve meets the fault characteristics, the hot area is regarded as the fault object. In this way, the faulty object can be determined automatically and quickly according to the map matching degree scoring curve.

In an embodiment of the present application, in the above method, the region is a map grid obtained by rasterizing the map, and the above method further includes: providing a visualization interface based on the map grid, and displaying the information of each map grid in the visualization interface status information.

The map raster is a raster dataset that is consistent with the map in terms of content, geometric accuracy, and color after geometric correction and color correction are performed on the map. The map grid can be obtained by rasterizing the map, that is, a rasterized map grid can be obtained. In order to facilitate management, maintenance and statistics, a visualization interface based on map grids can be provided. In this way, the user can view the status information of each map grid in the visualization interface of the map grid, for example, can view information such as the passage of automatic driving equipment in a unit time and the statistics of the number of faulty objects.

In an embodiment of the present application, in the method of any one of the above, the method further includes: generating a confidence map corresponding to the map according to the state information of each area; sending the confidence map to the automatic driving device to make When the autopilot device uses the map, it adjusts the weight of the map according to the confidence map.

When the map is not updated in time, in order to enable the automatic driving device to maintain normal driving, a confidence map corresponding to the map can be generated according to the status information of each area. The confidence map contains the weight ratio information used on the map. When the map is not updated in time, the confidence map can be sent to the automatic driving device, so that when the automatic driving device uses the map, the weight of the map is adjusted according to the confidence map. For example, when driving on the road corresponding to the unupdated data of the map, the weight of the positioning map can be reduced accordingly, and the automatic driving equipment's own sensing device and satellite navigation positioning data can continue to maintain normal driving. In this way, the normal operation of the automatic driving equipment is maintained without updating the map.

In an embodiment of the present application, determining the faulty object can be achieved through statistical analysis of multiple positioning points. When each autopilot device is running, it can get the following data structure: (x, y, theta, score, vechile_id, timestamp). Among them, x represents the value of the abscissa in the coordinate system, y represents the value of the ordinate in the coordinate system, theta represents the angle between the posture of the autonomous driving device in the space and the coordinate system, score represents the map matching score, and vechile_id represents autonomous driving The ID information of the device, timestamp represents the time information represented by the timestamp. Since each positioning point is not completely coincident, visual statistics can be performed by establishing a coordinate system in space and normalizing x and y to the nearest 0.5 meter precision integral point. For example, rasterize the map to obtain the map grid, and use the grid in the map as a unit to analyze to determine the hotspot area. Specifically, taking a certain grid a in the map as an example, when multiple autopilot devices pass through grid a, the following data set can be obtained: (x, y, score1, vechile_id1, timestamp_1); (x, y, score2, vechile_id1 ,timestamp_3); (x,y,score3,vechile_id2,timestamp_7); (x,y,score4,vechile_id3,timestamp_4); (x,y,score5,vechile_id1,timestamp_2). In a rasterized map grid, assuming that for a certain grid, the number of map matching scores in the data set obtained is sum_count=n, then the average score of the map matching score of the grid average_score= (score1+score2+…+score n)/sum_count. Therefore, average_score of grid a=(score1+score2+score3+score4+score5)/5, and then perform the same calculation on other grids in the map to get the average of the map matching score of each grid in the map Score, and finally determine the grid with a lower average score as a hotspot grid, that is, a hotspot area. Then, analyze the hot spots. Specifically, different automatic driving devices can be scored separately to eliminate problems in the vehicle itself. For example, average_score_id1=(score1+score2+score5)/3; average_score_id2=(score3)/1; average_score_id2=(score4)/1. If the above scores are consistent, the influence and interference caused by the failure of the specific automatic driving equipment itself can be excluded; otherwise, the inspection and diagnosis of the specific automatic driving equipment needs to be carried out. The analysis can be performed by sorting the map matching scores in chronological order, drawing a time-map matching score curve, and analyzing the curve law shown by the time-map matching score curve, so as to determine the faulty object. Specifically, by drawing a curve with timestamp as the horizontal axis and score as the vertical axis, the corresponding curve characteristics can be obtained. Among them, the horizontal axis of the curve is [timestamp_1,timestamp_2,timestamp_3,timestamp_4,timestamp_5], and the vertical axis of the curve is [score1,score5,score2,score4,score5]. Assuming that in the time after a certain point in time, the matching score of the hotspot area starts to deteriorate, it means that the environment corresponding to the hotspot area has changed greatly. In this way, the fault object can be determined through the analysis of the hot spot area.

Fig. 2 shows a schematic structural diagram of a map-based fault diagnosis device according to an embodiment of the present application. As shown in FIG. 2, the map-based fault diagnosis device 200 includes:

The receiving unit 210 is configured to receive map usage information reported by each automatic driving device.

The embodiments of this application are mainly implemented based on maps, so map usage information of unmanned equipment is needed. Specifically, the map usage information may include map matching scores, pose information of the automatic driving device, and the like. In this way, it is possible to comprehensively analyze the cause of the failure by analyzing the map usage information reported by the automatic driving device, so as to determine the target of the failure.

The map can be divided into different areas, and the status information of each area in the map can be generated according to the map usage information. In this application, multiple automatic driving devices can be used to comprehensively obtain the reported usage information to generate status information of each area, so as to avoid diagnosis errors caused by a single automatic driving device false alarm. In this way, the status information of each area in the map can be obtained.

The diagnosis unit 220 is configured to generate status information of each area in the map according to the map usage information; determine a hot spot area in the map according to the status information of each area; determine a fault object according to the status information of the hot spot area.

It can be seen that the device shown in FIG. 2 can quickly diagnose possible defects in the map based on the information of the map, and determine the faulty object. Improve the efficiency of fault diagnosis, provide reliable guarantee for the normal operation of map-based autonomous driving, and provide technical support for logistics, food delivery and other business areas.

In an embodiment of the present application, in the above-mentioned device, the map use information may include the map matching degree score and the pose information of the automatic driving device. The diagnosis unit 220 is used for each piece of map use information, according to the report. The pose information of the automatic driving device of the map usage information determines the area that matches the piece of map usage information, and obtains the correspondence between the piece of map usage information and the matched area; for each area, according to the correspondence, Count the average value of the map matching scores corresponding to the area, and use the average value as the state score of the area.

In an embodiment of the present application, in the above-mentioned device, the diagnosis unit 220 is configured to select a number of areas as hot spots according to the state score from low to high; and/or, the state score is lower than a preset value The area serves as a hot spot.

In an embodiment of the present application, in the above-mentioned device, the map usage information may also include the identification of the automatic driving equipment, and the diagnosis unit 220 is used for each hotspot area, according to the identification of the automatic driving equipment, based on all the corresponding hotspot areas. According to the map matching score in the map usage information, calculate the state score of each automatic driving device related to the hot area; if the state score of the target automatic driving device is not consistent with the state scores of other automatic driving devices, then Take the target autopilot device as the target of the failure.

In an embodiment of the present application, in the above-mentioned device, the map usage information may also include time information, and the diagnosis unit 220 is used for each hotspot area, if the state scores of each automatic driving device related to the hotspot area are consistent If the map matching degree score corresponding to the hot spot area is sorted in chronological order, the map matching degree score curve is obtained; if the map matching degree score curve meets the fault characteristics, the hot spot area is regarded as the fault object.

In an embodiment of the present application, in the above-mentioned device, the area is a map grid obtained by rasterizing the map, and the diagnosis unit 220 is also used to provide a visualization interface based on the map grid, in which each map grid is displayed. The status information of the grid.

In an embodiment of the present application, in any of the above-mentioned devices, the device further includes: a confidence unit, configured to generate a confidence map corresponding to the map according to the state information of each region; and send the confidence map to the automatic driving equipment , So that when the automatic driving device uses the map, the weight of the map is adjusted according to the confidence map.

It should be noted that the specific implementation manners of the foregoing device embodiments can be performed with reference to the specific implementation manners of the foregoing corresponding method embodiments, and details are not described herein again.

In summary, the embodiment of the present application receives map usage information reported by each automatic driving device; generates state information of each area in the map based on the map use information; determines the location based on the state information of each area. The hot spot area in the map; the fault object is determined according to the status information of the hot spot area. The beneficial effect is that, based on the information of the map, the possible defects of the map can be quickly diagnosed, and the faulty object can be determined. Improve the efficiency of fault diagnosis, provide reliable guarantee for the normal operation of map-based autonomous driving, and provide technical support for logistics, food delivery and other business areas.

It should be noted that the algorithms and displays provided here are not inherently related to any specific computer, virtual device or other equipment. Various general-purpose devices can also be used with the teaching based on this. From the above description, the structure required to construct this type of device is obvious. In addition, this application is not aimed at any specific programming language. It should be understood that various programming languages can be used to implement the content of the application described herein, and the above description of a specific language is for the purpose of disclosing the best embodiment of the application.

In the instructions provided here, a lot of specific details are explained. However, it can be understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures, and technologies are not shown in detail, so as not to obscure the understanding of this specification.

Similarly, it should be understood that, in order to simplify this application and help understand one or more of the various inventive aspects, in the above description of the exemplary embodiments of this application, the various features of this application are sometimes grouped together into a single embodiment, Figure, or its description. However, the disclosed method should not be interpreted as reflecting the intention that the claimed application requires more features than the features explicitly recorded in each claim. More precisely, as reflected in the following claims, the inventive aspect lies in less than all the features of a single embodiment disclosed previously. Therefore, the claims following the specific embodiment are thus explicitly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the application.

Those skilled in the art can understand that it is possible to adaptively change the modules in the device in the embodiment and set them in one or more devices different from the embodiment. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and/or processes or units are mutually exclusive, any combination can be used to compare all features disclosed in this specification (including the accompanying claims, abstract and drawings) and any method or methods disclosed in this manner or All the processes or units of the equipment are combined. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

In addition, those skilled in the art can understand that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments means that they are within the scope of the present application. Within and form different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination.

The various component embodiments of the present application may be implemented by hardware, or by software modules running on one or more processors, or by a combination of them. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the map-based fault diagnosis apparatus according to the embodiments of the present application. This application can also be implemented as a device or device program (for example, a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for implementing the present application may be stored on a computer-readable medium, or may have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

For example, FIG. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device 300 includes a processor 310 and a memory 320 storing computer-executable instructions (computer-readable program codes). The memory 320 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM. The memory 320 has a storage space 330 for storing computer-readable program codes 331 for executing any method steps in the above-mentioned methods. For example, the storage space 330 for storing computer-readable program codes may include various computer-readable program codes 331 respectively used to implement various steps in the above method. The computer-readable program code 331 may be read from or written into one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards, or floppy disks. Such a computer program product is usually, for example, a computer-readable storage medium as described in FIG. 4. Fig. 4 shows a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present application. The computer-readable storage medium 400 stores the computer-readable program code 331 for executing the method steps according to the present application, which can be read by the processor 310 of the electronic device 300, when the computer-readable program code 331 is run by the electronic device 300 , Causing the electronic device 300 to execute each step in the method described above. Specifically, the computer readable program code 331 stored in the computer readable storage medium can execute the method shown in any of the above embodiments. The computer readable program code 331 may be compressed in an appropriate form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application can be realized by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims listing several devices, several of these devices may be embodied in the same hardware item. The use of the words first, second, and third, etc. do not indicate any order. These words can be interpreted as names.

Claims

A map-based fault diagnosis method, including:

Receive map usage information reported by each autopilot device;

Generating state information of each area in the map according to the map usage information;

Determining a hot spot area in the map according to the state information of each of the areas;

The fault object is determined according to the status information of the hot spot area.
The method of claim 1, wherein the map usage information includes a map matching degree score and pose information of the automatic driving device, and generating state information of each area in the map according to the map usage information includes:

For each piece of map usage information,

Determine an area matching the piece of map usage information according to the pose information of the autonomous driving device that reports the piece of map usage information,

Obtain the correspondence between the piece of map usage information and the matched area;

For each said area,

According to the corresponding relationship, the average value of the map matching score corresponding to the area is counted,

The average value is used as the state score of the area.
3. The method of claim 2, wherein determining the hot spot area in the map according to the state information of each of the areas comprises:

Select a number of areas as the hot spot area according to the state score from low to high; and/or,

The area where the state score is lower than the preset value is taken as the hot spot area.
The method according to claim 2, wherein the map usage information further includes an automatic driving device identification, and determining the fault object according to the status information of the hotspot area includes:

For each of the hot spots,

According to the automatic driving device identifier, calculate the state score of each automatic driving device related to the hot spot area based on the map matching score in the map usage information corresponding to the hot spot area;

If the state score of the target automatic driving device is not consistent with the state scores of other automatic driving devices, then the target automatic driving device is taken as the failure target.
The method of claim 4, wherein the map usage information further includes time information, and determining the fault object according to the status information of the hotspot area further includes:

For each hot spot,

If the state scores of the autonomous driving devices related to the hot spot area are consistent, then the map matching degree scores corresponding to the hot spot area are sorted in chronological order to obtain a map matching degree score curve;

If the map matching degree scoring curve conforms to the fault feature, then the hot spot area is taken as the fault object.
The method according to claim 1, wherein the area is a map grid obtained by rasterizing a map, and the method further comprises:

Provide a visual interface based on the map grid,

The state information of each of the map grids is displayed in the visualization interface.
The method according to any one of claims 1-6, wherein the method further comprises:

Generating a confidence map corresponding to the map according to the state information of each of the regions;

The confidence map is sent to an automatic driving device, so that when the automatic driving device uses the map, the use weight of the map is adjusted according to the confidence map.
A map-based fault diagnosis device includes:

The receiving unit is used to receive map usage information reported by each automatic driving device;

The diagnosis unit is configured to generate status information of each area in the map according to the map usage information; determine a hot spot area in the map according to the status information of each area; determine a fault object according to the status information of the hot spot area .
An electronic device including:

Processor; and

A memory storing computer-executable instructions, which when executed, cause the processor to perform the method according to any one of claims 1-7.
A computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and the one or more programs, when executed by a processor, realize the The method described.