High-precision Map Diagnosis and Update Method Based on Multi-source Fusion Positioning

Abstract

The present invention relates to a high-precision map diagnosis and update method based on multi-source fusion positioning. The diagnosis method includes: obtaining various types of map feature data of the entity environment in the to-be-measured space-time area based on multiple sensing devices, and statistically obtaining the sensing results of any map feature data; classifying the sensing results to obtain the statistical numbers of various types of sensing results, where the statistical number is the number of sensing devices that sense the sensing results of this type; making a consistency judgment between the type of the sensing result when the statistical number is the largest and the type of the map feature in the current high-precision map. When they are inconsistent, the diagnosis result of the to-be-measured space-time area is that the current high-precision map needs to be updated; through automated data analysis and matching of the program, it is known whether there is locally incorrect map information based on statistics, realizing an effective diagnosis of map problems and reducing the time, manpower, and material costs of manual problem troubleshooting.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a high-precision map diagnosis and update method based on multi-source fusion positioning. Background Art

[0002] An autonomous vehicle, also known as a driverless car, is a type of intelligent vehicle and is also called a wheeled mobile robot. It mainly relies on an in-vehicle intelligent driver mainly composed of a computer system to achieve the goal of driverless driving.

[0003] Multi-source information fusion, also known as multi-source fusion, is a method for processing multi-source information. Due to its advantages such as high accuracy, good fault tolerance, low information acquisition cost, and information complementarity, this method has been widely used in modern military, industrial, transportation, and financial fields, playing a promoting role in the development of scientific and technological modernization.

[0004] In an outdoor open scene, GNSS can provide real-time, reliable, and stable navigation and positioning services. However, in an urban environment, due to the complex scene, problems such as few visible satellites in urban canyons, multipath effects, and signal loss in tunnels and other scenes lead to poor positioning accuracy and low reliability, making it difficult to meet the positioning requirements for full-scene, real-time, high-precision, and high-reliability. Therefore, the multi-source fusion positioning technology is proposed, which uses the method of information fusion to process satellite navigation and positioning, wireless sensor positioning, and other auxiliary positioning technologies, and finally obtains a reliable, accurate, and stable positioning service.

[0005] A high-precision map (HD Map or HAD Map) is a type of electronic map with both absolute and relative accuracies in the centimeter level, featuring high precision, high freshness, and high richness. The high-precision map provides an environmental model for an autonomous driving vehicle, including the most basic static high-precision map and other dynamic information. High-precision maps have been regarded as "important infrastructure" in the era of autonomous driving and will surely play an important role as the "data base" in fields such as intelligent transportation and smart cities. Problems often occur in the produced high-precision maps, such as incorrect map data. Due to the large amount of map data, manually checking the problems of high-precision maps requires a large amount of human, material, and time costs, and will also affect the map update production efficiency.

[0006] The generated vehicle-end data cannot upload data containing absolute position information to the cloud. In order to ensure normal map generation on the premise that the vehicle-end data upload does not contain absolute position information, a vehicle-end perception data upload method needs to be designed for map update. Summary of the Invention

[0007] In view of the technical problems existing in the prior art, the present invention provides a high-precision map diagnosis and update method based on multi-source fusion positioning. Under the data conditions provided by numerous autonomous vehicles with environmental perception and positioning capabilities, through automated data analysis and matching procedures, map information with local errors is obtained based on statistical mathematics. Then, the absolute position in the perception information is converted into relative position information relative to a pre-selected reference point and quickly uploaded to the cloud through a network, and the map is updated through a series of professional processing methods to meet the requirements of problem diagnosis and update of high-precision maps.

[0008] According to a first aspect of the present invention, there is provided a high-precision map diagnosis method based on multi-source fusion positioning, comprising:

[0009] Step 1, obtaining various types of map feature data of the physical environment of the to-be-measured spatio-temporal region based on multiple perception devices, and statistically obtaining the perception results of any map feature data;

[0010] Step 2, classifying the perception results to obtain the statistical number of each type of perception result, where the statistical number is the number of perception devices that perceive the perception result of this type;

[0011] Step 3, making a consistency judgment between the type of the perception result when the statistical number is the largest and the type of this map feature in the current high-precision map. When they are inconsistent, the diagnosis result of the to-be-measured spatio-temporal region is that the current high-precision map needs to be updated.

[0012] Based on the above technical solutions, the present invention can also be improved as follows.

[0013] Optionally, the perception devices are vehicles with environmental perception and positioning capabilities, and multiple vehicles drive in the to-be-measured spatio-temporal region to obtain the map feature data; the types of the map feature data include: lane lines and POIs.

[0014] Optionally, the classification result of classifying the perception results in Step 2 is:

[0015] {(obj0,N0)…(obj i ,N i )…(obj m ,N m )};

[0016] Wherein, obj i is the i-th type of perception result of this map feature, and (obj i ,N i ) indicates that the statistical number of the i-th type of perception result obj i of this map feature is N i, where m is the total number of types of perception results;

[0017] The types of the perception results include: type, relative position information, track angle, and time.

[0018] Optionally, before performing the consistency judgment in step 3, it includes:

[0019] Match and locate the corresponding map feature element in the current high-precision map according to the position information, and obtain the type of the map feature element in the current high-precision map.

[0020] According to the second aspect of the present invention, a high-precision map update method based on multi-source fusion positioning is provided. The update method is based on the high-precision map diagnosis method described in the embodiments of the present invention. When the result of the consistency judgment in step 3 is inconsistent, the method for updating the current high-precision map includes:

[0021] Step 4, at the perception device end, convert the absolute position information of the map feature element into relative position information relative to a preset reference point;

[0022] Step 5, upload the information of the feature element whose position has been converted to relative position and the reference point index information to the cloud;

[0023] Step 6, regularly pull the latest data from the cloud, obtain the reference point data from the vehicle end according to the index information, generate a local vector map, and update the local information of the high-precision map.

[0024] On the basis of the above technical solutions, the present invention can also be improved as follows.

[0025] Optionally, the position information in step 4 includes longitude lon, latitude lat, and elevation high;

[0026] In step 4, the absolute position information of the map feature element is (lon i , lat i , high i ), and the absolute position information of the reference point is longitude, latitude, and elevation (lon b , lat b , high b ). The converted relative position information is (lon i - lon b , lat i - lat b , high i - high b ).

[0027] Optionally, the reference point index information is time information.

[0028] A high-precision map diagnosis and update method based on multi-source fusion positioning provided by the present invention, under the data conditions provided by numerous unmanned vehicles with environmental perception and positioning capabilities, through automated data analysis and matching of programs, obtains map information with local errors based on statistical mathematics. Then, the absolute position in the perception information is converted into relative position information relative to a pre-selected reference point and quickly uploaded to the cloud through a network, and the map is updated through a series of professional processing methods to meet the requirements of problem diagnosis and update of high-precision maps. The effective diagnosis of map problems is realized. By uploading the key feature information after diagnosis, it helps to improve the data update and repair efficiency of local problem maps, and reduces the time, manpower, and material costs of manual problem troubleshooting. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a flowchart of a high-precision map diagnosis method based on multi-source fusion positioning provided by the present invention;

[0030] Figure 2 is a flowchart of a high-precision map diagnosis and update method based on multi-source fusion positioning provided by the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0031] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only used to explain the present invention and are not intended to limit the scope of the present invention.

[0032] Figure 1 is a flowchart of a high-precision map diagnosis method based on multi-source fusion positioning provided by the present invention, as Figure 1 shown, the diagnosis method includes:

[0033] Step 1, based on multiple sensing devices, obtain various types of map feature element data of the physical environment in the to-be-measured space-time region, and statistically obtain the sensing results of any map feature element data.

[0034] Step 2, classify the sensing results to obtain the statistical numbers of various types of sensing results. The statistical number is the number of sensing devices that sense the sensing results of this type.

[0035] Step 3, make a consistency judgment between the type of the sensing result when the statistical number is the largest and the type of this map feature element in the current high-precision map. If they are inconsistent, the diagnosis result of the to-be-measured space-time region is that the current high-precision map needs to be updated.

[0036] The present invention provides a high-precision map diagnosis method based on multi-source fusion positioning. Under the data conditions provided by a large number of unmanned vehicles with environmental perception and positioning capabilities, through program-automated data analysis and matching, it is determined whether there is any local erroneous map information on the basis of statistical mathematics, thereby achieving effective diagnosis of map problems and reducing the time, manpower and material costs of manual troubleshooting.

[0037] Example 1

[0038] Embodiment 1 provided by the present invention is an embodiment of a high-precision map diagnosis method based on multi-source fusion positioning provided by the present invention, combined with Figure 2 It can be seen that embodiments of the diagnostic method include:

[0039] Step 1: Based on multiple sensing devices, various types of map feature element data of the physical environment of the time-space area to be measured are obtained, and the perception results of any map feature element data are statistically obtained.

[0040] In a possible implementation mode, the sensing device is an unmanned vehicle with environmental sensing and positioning capabilities, and multiple vehicles travel in the time and space area to be measured to obtain map feature data. The types of map feature data include: lane lines and POI (Point of Interest), etc.

[0041] Step 2: classify the perception results to obtain the statistical number of perception results of each category, where the statistical number is the number of perception devices that perceive the perception results of this category.

[0042] In a possible implementation manner, the classification result of classifying the perception result in step 2 is:

[0043] {(obj0,N0)…(obj i ,N i )…(obj m ,N m )}.

[0044] Among them, obj i is the perception result of the i-th type of the map feature, (obj i ,N i ) represents the perception result obj of the i-th type of the map feature i The statistical number is N i , m is the total number of types of perception results.

[0045] The types of perception results include key information such as type, relative position information, track angle and time.

[0046] In specific implementation, when the system is powered on, the classification number of the perception results of a certain map feature data in the same spatio-temporal region is counted {(obj0, N0)…(obj i , N i )…(obj m , N m )}. When the perception device is a vehicle, N is the number of vehicles that perceive the perception result of this type of the map feature.

[0047] Step 3: Perform a consistency judgment on the type of the perception result when the statistical number is the largest and the type of this map feature in the current high-precision map. When they are inconsistent, the diagnosis result of the to-be-tested spatio-temporal region is that the current high-precision map needs to be updated.

[0048] In a possible implementation manner, before step 3 performs the consistency judgment, it includes:

[0049] Match and locate the corresponding map feature in the current high-precision map according to the position information, and obtain the type of this map feature in the current high-precision map.

[0050] In specific implementation, in step 3, the perception result corresponding to the maximum statistical number is taken as the classification information of this map feature, that is, obj = argmax{(obj0, N0)…(obj i , N i )…(obj m , N m )}. Match and locate the corresponding map feature in the current high-precision map, and obtain the attribute information objMap of this feature. Check whether it is consistent with the perceived feature type. If it is consistent, there is no need to upload data and update the map, and the process ends; if it is inconsistent, the map needs to be updated.

[0051] Embodiment 2

[0052] Embodiment 2 provided by the present invention is an embodiment of a high-precision map update method based on multi-source fusion positioning provided by the present invention. Figure 2 It is a flowchart of a high-precision map update method based on multi-source fusion positioning provided by an embodiment of the present invention. As can be seen from Figure 2 , the embodiment of this update method includes:

[0053] Step 1: Based on multiple perception devices, obtain the map feature data of various types of the entity environment in the to-be-tested spatio-temporal region, and count the perception results of any map feature data.

[0054] Step 2: Classify the perception results to obtain the statistical number of the perception results of various types. The statistical number is the number of perception devices that perceive the perception result of this type.

[0055] Step 3: Determine the consistency between the type of the perception result when the statistical count is the largest and the type of the map feature element in the current high-precision map. When they are inconsistent, the diagnosis result of the to-be-tested spatio-temporal region is that the current high-precision map needs to be updated. When the result of the consistency judgment in Step 3 is inconsistent, execute Steps 4-6.

[0056] Step 4: At the perception device end, convert the absolute position information of the map feature element into relative position information relative to a preset reference point.

[0057] In specific implementation, when the perception device is a vehicle, the vehicle end needs to select a reference point in advance.

[0058] In a possible embodiment, the position information in Step 4 includes longitude lon, latitude lat, and elevation high.

[0059] In Step 4, the absolute position information of the map feature element is (lon i , lat i , high i ), the absolute position information of the reference point is longitude, latitude, and elevation (lon b , lat b , high b ), and the converted relative position information is (lon i - lon b , lat i - lat b , high i - high b )

[0060] Step 5: Upload the feature element information of the map that has been converted to relative position and the reference point index information to the cloud.

[0061] In a possible embodiment, the reference point index information is time information. In specific implementation, the encoding can be in the order of year, month, day, hour, minute, and second (abbreviated as YMDHMS).

[0062] Step 6: The map generation center regularly pulls the latest data from the cloud, obtains the reference point data from the vehicle end according to the index information, generates a local vector map, and then updates the local information of the high-precision map through a series of professional processing methods.

[0063] It can be understood that a high-precision map update method based on multi-source fusion positioning provided by the present invention corresponds to the high-precision map diagnosis method based on multi-source fusion positioning provided in the foregoing embodiments. The relevant technical features of the high-precision map update method based on multi-source fusion positioning can refer to the relevant technical features of the high-precision map diagnosis method based on multi-source fusion positioning, and will not be elaborated herein.

[0064] A high-precision map diagnosis and update method based on multi-source fusion positioning provided by an embodiment of the present invention, under the data conditions provided by numerous unmanned vehicles with environmental perception and positioning capabilities, through automated data analysis and matching of programs, obtains map information with local errors based on statistical mathematics. Then, the absolute position in the perception information is converted into relative position information relative to a pre-selected reference point and quickly uploaded to the cloud through a network, and the map is updated through a series of professional processing methods to meet the requirements of problem diagnosis and update of high-precision maps. The effective diagnosis of map problems is realized. By uploading the key feature information after diagnosis, it helps to improve the data update and repair efficiency of local problem maps, and reduces the time, manpower, and material costs of manual problem detection.

[0065] It should be noted that in the above embodiments, the descriptions of each embodiment have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0066] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0067] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0068] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device realizes the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0069] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable apparatus provide steps for realizing the functions specified in one process or a plurality of processes and / or boxes Figure 1 one process or a plurality of processes and / or boxes Figure 1 or steps for realizing the functions specified in a plurality of boxes.

[0070] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn the basic inventive concept. Therefore, the appended claims are intended to be construed to cover the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0071] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A high-precision map diagnosis method based on multi-source fusion positioning, characterized in that, The described diagnostic method includes: Step 1: Based on multiple perception devices, obtain various types of map feature data of the entity environment in the space-time region to be measured, and statistically obtain the perception results of any map feature data. Step 2: Classify the perception results to obtain the statistical number of perception results of various types, where the statistical number is the number of perception devices that perceive the perception results of this type. Step 3: Make a consistency judgment between the type of the perception result when the statistical number is the largest and the type of this map feature in the current high-precision map. If they are inconsistent, the diagnostic result of the space-time region to be measured is that the current high-precision map needs to be updated.

2. The method according to claim 1, characterized in that, The perception devices are vehicles with environmental perception and positioning capabilities, and multiple such vehicles drive in the space-time region to be measured to obtain the map feature data. The types of the map feature data include: lane lines and POIs.

3. The high-precision map diagnosis method according to claim 1, characterized in that, The classification results of classifying the perception results in Step 2 are: {(obj0,N0)…(obj i ,N i )…(obj m ,N m )}; Among them, obj i is the perception result of the i-th type of the map feature. (obj i , N i ) indicates that the statistical number of the perception result obj i of the i-th type of the map feature is N i , and m is the total number of types of perception results; The types of the perception results include: type, relative position information, track angle, and time.

4. The high-precision map diagnosis method according to claim 1, characterized in that, Before making the consistency judgment in Step 3, it includes: Match and locate the corresponding map feature in the current high-precision map according to the position information, and obtain the type of this map feature in the current high-precision map.

5. A high-precision map update method based on multi-source fusion positioning, the update method being based on the high-precision map diagnosis method according to any one of claims 1-4, characterized in that, When the result of the consistency judgment in Step 3 is inconsistent, the method for updating the current high-precision map includes: Step 4: At the perception device end, convert the absolute position information of this map feature into relative position information relative to a preset reference point. Step 5: Upload the ground feature information that has been converted into relative position and the reference point index information to the cloud. Step 6: Regularly pull the latest data from the cloud, obtain the reference point data from the vehicle end according to the index information, generate a local vector map, and update the local information of the high-precision map.

6. The high-precision map update method based on multi-source fusion positioning according to claim 5, characterized in that, The position information in Step 4 includes longitude lon, latitude lat, and elevation high. In step 4, the absolute position information of the map feature is (lon i , lat i , high i ), the absolute position information of the reference point is longitude, latitude, elevation (lon b , lat b , high b ), and the converted relative position information is (lon i - lon b , lat i - lat b , high i - high b ).

7. The high-precision map update method based on multi-source fusion positioning according to claim 5, characterized in that, The reference point index information is time information.

Images