Data uploading method and system and storage medium

Abstract

The invention relates to a data uploading method and system and a storage medium. The method applied to a vehicle end comprises the steps that a driving environment map generated by the vehicle end at a target driving track point and a high-precision lane-level map corresponding to the driving environment map are acquired; when it is determined that there is a difference between the driving environment map and the high-precision lane-level map, sending an uploading request carrying a target driving track point to a cloud; and under the condition that an uploading permission response sent by the cloud for the uploading request is received, sending the driving environment map to the cloud, so that the cloud updates the high-precision lane-level map based on the driving environment map. According to the invention, under the condition that there is a difference between the traveling vehicle environment map and the high-precision lane-level map, the uploading request is sent to the cloud, and the traveling vehicle environment map is uploaded only under the condition that the uploading permission response sent by the cloud is received, so that repeated data uploading can be effectively avoided, the data volume of data uploading is controlled, and the user experience is improved. And the data uploading efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and particularly relates to a data uploading method, system and storage medium. Background Art

[0002] On the vehicle side of mass-produced autonomous driving vehicles, a variety of sensors such as lidar, millimeter-wave radar, and cameras are installed. The main vehicle manufacturers and map manufacturers can rely on multi-source sensors to collect relevant information about the real world and the vehicle, and upload it to the cloud for the production and update of high-precision map data. However, for roads where the map has been built and has not changed for a long time, if the data of thousands of vehicles are uploaded every day, it will cause a large amount of upload traffic consumption and waste of cloud processing resources. Summary of the Invention

[0003] One of the purposes of the present invention is to provide a data uploading method applied to the vehicle side to solve the problems of large data upload volume and low upload efficiency caused by a large number of vehicle sides uploading data in the prior art; the second purpose is to provide a data uploading method applied to the cloud to solve the problem of waste of cloud processing resources.

[0004] In order to achieve the above purposes, the technical solutions adopted by the present invention are as follows:

[0005] A data uploading method, applied to the vehicle side, the method includes:

[0006] Obtain the driving environment map generated by the vehicle side at the target driving trajectory point, and the high-precision lane-level map corresponding to the driving environment map; in the case of determining that there is a difference between the driving environment map and the high-precision lane-level map, send an upload request carrying the target driving trajectory point to the cloud for the cloud to find the corresponding historical trajectory data in the preset trajectory library based on the target driving trajectory point, and in the case where the historical trajectory data meets the preset upload condition, send an allow-upload response to the vehicle side; the preset upload condition includes: in the historical trajectory data, there is a time difference from the upload request that is not less than a preset time threshold, and the number of trajectory data corresponding to the target driving trajectory point is not greater than a preset number; in the case of receiving the allow-upload response sent by the cloud for the upload request, send the driving environment map to the cloud for the cloud to update the high-precision lane-level map based on the driving environment map.

[0007] According to the above technical means, in the case of a difference between the driving environment map and the high-precision lane-level map, an upload request will be sent to the cloud, and the driving environment map will only be uploaded in the case of receiving the allow-upload response sent by the cloud, which can effectively control the data volume of data upload and improve the efficiency of data upload.

[0008] Further, in the case of receiving a rejection upload response sent by the cloud for the upload request, delete the driving environment map.

[0009] According to the above technical means, if the cloud sends a rejection upload response for the upload request, it indicates that the cloud already stores the driving environment map at the target driving trajectory. At this time, there is no need to upload the driving environment map to the cloud, so it is deleted locally to release the local cache.

[0010] Further, the obtaining of the driving environment map generated by the vehicle terminal at the target driving trajectory point includes: real-time collecting lane scene data of the vehicle terminal at the target driving trajectory point; the lane scene data includes at least one or more of the following map elements: lane lines, road boundaries, signs, traffic lights, zebra crossings, stop lines, and ground arrows; generating the driving environment map based on the lane scene data.

[0011] According to the above technical means, real-time collecting the lane scene data of the vehicle terminal at the target driving trajectory point, and then generating the driving environment map at the target driving trajectory point based on the lane scene data, ensures the real-time nature of the driving environment map.

[0012] Further, before sending an upload request for the driving environment map to the cloud in the case of determining that there is a difference between the driving environment map and the high-precision lane-level map, the method further includes: comparing the existence differences between the map elements in the driving environment map and the high-precision lane-level map to obtain an existence difference result, and determining that there is a difference between the driving environment map and the high-precision lane-level map in the case where the existence difference result indicates an existence difference; in the case where the existence difference result indicates no existence difference, comparing the attribute differences between the map elements in the driving environment map and the high-precision lane-level map to obtain an attribute difference result, and determining that there is a difference between the driving environment map and the high-precision lane-level map in the case where the attribute difference result indicates an attribute difference.

[0013] According to the above technical means, by comparing the existence differences between each map element in the driving environment map and the high-precision lane-level map, it can be clarified whether the driving environment map has changed compared to the high-precision lane-level map. If there is a change, it is determined that there is a difference between the driving environment map and the high-precision lane-level map, and then an upload request is sent to the cloud. If there is no change, there is no need to upload, so the data upload volume can be reduced.

[0014] Further, comparing the existence differences between the map elements in the driving environment map and the high-precision lane-level map to obtain an existence difference result includes: for each first map element included in the driving environment map, if there is a corresponding first matching map element in the high-precision lane-level map, it is determined that the existence difference result is no existence difference; if there is any first map element that has no corresponding first matching map element in the high-precision lane-level map, it is determined that the existence difference result is there is an existence difference; and / or, for each second map element included in the high-precision lane-level map, if there is a corresponding second matching map element in the driving environment map, it is determined that the existence difference result is no existence difference; if there is any second map element that has no corresponding second matching map element in the driving environment map, it is determined that the existence difference result is there is an existence difference.

[0015] According to the above technical means, for each first map element included in the driving environment map, it can be checked whether there is a corresponding first matching map element in the high-precision lane-level map, and / or, for each second map element included in the high-precision lane-level map, it can be checked whether there is a corresponding second matching map element in the driving environment map, so as to determine whether there is an existence difference between the map elements in the driving environment map and the high-precision lane-level map.

[0016] Further, comparing the attribute differences between the map elements in the driving environment map and the high-precision lane-level map to obtain an attribute difference result includes: for each of the first map elements, if there are first matching map elements with consistent attributes in the high-precision lane-level map, it is determined that the attribute difference result is no attribute difference; if there is any first map element that has a first matching map element with inconsistent attributes in the high-precision lane-level map, it is determined that the attribute difference result is there is an attribute difference.

[0017] According to the above technical means, in the case of no existence difference, further judge the attribute differences between the map elements in the driving environment map and the high-precision lane-level map. If there are attribute differences, it means that there are also differences between the driving environment map and the high-precision lane-level map. In this way, it can avoid the occurrence of attribute differences when there is no existence difference in the map elements, and can improve the accuracy of determining whether there are differences between the driving environment map and the high-precision lane-level map.

[0018] A data upload method is applied to the cloud. The method includes: when receiving an upload request carrying a target driving trajectory point sent by the vehicle terminal, searching for corresponding historical trajectory data in a preset trajectory library; when the historical trajectory data meets the preset upload conditions, sending an upload permission response to the vehicle terminal for the upload request; the preset upload conditions include: in the historical trajectory data, there is a time difference from the upload request greater than a preset time threshold, and the number of trajectory data corresponding to the target driving trajectory point is less than a preset number; receiving the driving environment map of the target driving trajectory point uploaded by the vehicle terminal in response to the upload permission response, and updating the high-precision lane-level map at the target driving trajectory point based on the driving environment map.

[0019] According to the above technical means, after the cloud receives the target driving trajectory point, it will search for the corresponding historical trajectory data in the preset trajectory library, and only when the historical trajectory data meets the preset upload conditions, will it allow the vehicle terminal to upload the driving environment map. In this way, the uploaded data can be effectively controlled.

[0020] Further, the method further includes: when the historical trajectory data does not meet the preset upload conditions, sending a rejection upload response to the vehicle terminal for the upload request.

[0021] According to the above technical means, if the historical trajectory data does not meet the preset upload conditions, a rejection upload response is sent to the vehicle terminal. In this way, the amount of data uploaded by the vehicle terminal can be effectively reduced.

[0022] A vehicle terminal includes:

[0023] An acquisition module, configured to acquire the driving environment map generated by the vehicle terminal at the target driving trajectory point, and the high-precision lane-level map corresponding to the driving environment map;

[0024] A first sending module, configured to send an upload request carrying the target driving trajectory point to the cloud when it is determined that there is a difference between the driving environment map and the high-precision lane-level map, so that the cloud can search for corresponding historical trajectory data in the preset trajectory library based on the target driving trajectory point, and when the historical trajectory data meets the preset upload conditions, send an upload permission response to the vehicle terminal; the preset upload conditions include: in the historical trajectory data, there is a time difference from the upload request not less than a preset time threshold, and the number of trajectory data corresponding to the target driving trajectory point is not greater than a preset number;

[0025] A first receiving module, configured to, when receiving an upload permission response sent by the cloud for the upload request, send the driving environment map to the cloud for the cloud to update the high-precision lane-level map based on the driving environment map.

[0026] A vehicle terminal includes: a first processor, a first memory, and a first communication bus; the first communication bus is used to implement a communication connection between the first processor and the first memory; the first processor is configured to execute a computer program stored in the first memory to implement the above data upload method.

[0027] A cloud includes:

[0028] A search module, configured to, when receiving an upload request carrying a target driving trajectory point sent by a vehicle terminal, search for historical trajectory data corresponding to the target driving trajectory point in a preset trajectory library;

[0029] A second sending module, configured to, when the historical trajectory data meets a preset upload condition, send an upload permission response to the vehicle terminal for the upload request; the preset upload condition includes: in the historical trajectory data, there is a time difference from the upload request greater than a preset time threshold, and the number of trajectory data corresponding to the target driving trajectory point is less than a preset number;

[0030] A second receiving module, configured to receive the driving environment map of the target driving trajectory point uploaded by the vehicle terminal in response to the upload permission response, and update the high-precision lane-level map at the target driving trajectory point based on the driving environment map.

[0031] A cloud includes: a second processor, a second memory, and a second communication bus; the second communication bus is used to implement a communication connection between the second processor and the second memory; the second processor is configured to execute a computer program stored in the second memory to implement the above data upload method.

[0032] A data upload system includes: a vehicle terminal and a cloud;

[0033] The vehicle terminal is configured to obtain the driving environment map generated by the vehicle terminal at a target driving trajectory point, and the high-precision lane-level map corresponding to the driving environment map, and send an upload request carrying the target driving trajectory point to the cloud when it is determined that there is a difference between the driving environment map and the high-precision lane-level map;

[0034] The cloud is configured to, when receiving an upload request carrying a target driving trajectory point sent by the vehicle terminal, search for historical trajectory data corresponding to the target driving trajectory point in a preset trajectory library, and when the historical trajectory data meets a preset upload condition, send an upload permission response to the vehicle terminal for the upload request.

[0035] The vehicle terminal is further configured to, when receiving the upload permission response sent by the cloud for the upload request, send the driving environment map to the cloud for the cloud to update the high-precision lane-level map based on the driving environment map.

[0036] A computer-readable storage medium stores one or more computer programs, and the one or more computer programs can be executed by one or more processors to implement the above data upload method.

[0037] Advantages of the present invention:

[0038] (1) In the present invention, an upload request is sent to the cloud only when it is determined that there is a difference between the driving environment map and the high-precision lane-level map, rather than uploading all the generated driving environment maps to the cloud. Thus, the amount of data uploaded can be better controlled.

[0039] (2) In order to avoid multiple vehicles from repeatedly uploading the driving environment map at the same driving trajectory point, the cloud is set to reject uploads. Thus, the situation of repeated uploads can be further avoided, and while controlling the amount of data uploaded, the efficiency of data upload is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a flowchart of a data upload method provided by an embodiment of the present invention Figure 1 ;

[0041] Figure 2 is a flowchart showing an exemplary process of generating a driving environment map provided by an embodiment of the present invention;

[0042] Figure 3 is a flowchart showing an exemplary process of determining the existence of differences between maps provided by an embodiment of the present invention;

[0043] Figure 4 is a schematic diagram showing an exemplary attribute difference between map elements provided by an embodiment of the present invention;

[0044] Figure 5 is a flowchart showing an exemplary process of determining the result of the existence of differences provided by an embodiment of the present invention;

[0045] Figure 6 Schematic diagram of a data upload method provided by an embodiment of the present invention Figure 2 ;

[0046] Figure 7 Exemplary schematic diagram of communication between multiple vehicles and the cloud provided by an embodiment of the present invention;

[0047] Figure 8 Schematic flow diagram of an exemplary data upload method provided by an embodiment of the present invention;

[0048] Figure 9 Schematic diagram of the structure of a vehicle end provided by an embodiment of the present invention Figure 1 ;

[0049] Figure 10 Schematic diagram of the structure of a vehicle end provided by an embodiment of the present invention Figure 2 ;

[0050] Figure 11 Schematic diagram of the structure of a cloud end provided by an embodiment of the present invention Figure 1 ;

[0051] Figure 12 Schematic diagram of the structure of a cloud end provided by an embodiment of the present invention Figure 2 。 Detailed implementation manners

[0052] The following will describe the implementation manners of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for explaining the present invention and not for limiting the protection scope of the present invention.

[0053] The present invention provides a data upload method implemented by a vehicle end. As Figure 1 shown, it includes the following steps S101 to step S103:

[0054] Step S101, obtain the driving environment map generated by the vehicle end at the target driving trajectory point, and the high-precision lane-level map corresponding to the driving environment map.

[0055] In an embodiment of the present invention, the vehicle end can obtain a driving environment map generated at a target driving trajectory point and a high-precision lane-level map corresponding to the target driving trajectory point. Exemplarily, if the driving environment map is a map within a preset range at the target driving trajectory point, then the range of the high-precision lane-level map is the same as that of the driving environment map, and it is also a high-precision lane-level map within the preset range at the target driving trajectory point. Herein, the preset range can be 50m, 100m, or other values around. The specific preset range can be set according to the application scenario and actual requirements, and the present invention does not make a limitation in this regard.

[0056] In an embodiment of the invention, the target driving trajectory point can be a point on the driving trajectory during the vehicle's driving process. Exemplarily, the vehicle end can determine a target driving trajectory point every fixed time interval during driving, or it can also be a target driving trajectory point determined every fixed mileage. The driving trajectory of the vehicle end is composed of multiple target driving trajectory points.

[0057] Step S102: In the case where it is determined that there is a difference between the driving environment map and the high-precision lane-level map, send an upload request carrying the target driving trajectory point to the cloud.

[0058] In an embodiment of the present invention, if the vehicle end determines that there is a difference between the driving environment map and the high-precision lane-level map, it indicates that there is a change in the driving environment map generated in real time by the vehicle end compared to the high-precision lane-level map. At this time, an upload request carrying the target driving trajectory point can be sent to the cloud for the cloud to find corresponding historical trajectory data in the preset trajectory library based on the target driving trajectory point, and in the case where the historical trajectory data meets the preset upload conditions, send an allow-upload response to the vehicle end; the preset upload conditions include: in the historical trajectory data, there is a time difference from the upload request that is not less than a preset time threshold, and the number of trajectory data corresponding to the target driving trajectory point is not greater than a preset number. In this way, the cloud can determine whether to upload the driving environment map based on the target driving trajectory point. Whether the cloud needs to upload the driving environment map depends on whether the historical trajectory data corresponding to the target driving trajectory point in the preset trajectory library meets the preset upload conditions. If it meets, an allow-upload response is sent to the vehicle end; if it does not meet, a reject-upload response is sent.

[0059] Step S103: In the case of receiving an allow-upload response sent by the cloud for the upload request, send the driving environment map to the cloud for the cloud to update the high-precision lane-level map based on the driving environment map.

[0060] In an embodiment of the present invention, if an allow-upload response sent by the cloud for the upload request is received, the driving environment map is sent to the cloud. In this way, the cloud can update the high-precision lane-level map based on the driving environment map.

[0061] Compared with the problems of large data volume and low data upload efficiency caused by each vehicle uploading data to the cloud in the related art, the present invention compares whether there are differences between the driving environment map and the high-precision lane-level map, and only when there are differences, will it send an upload request to the cloud and upload after receiving the cloud's permission to upload response, avoiding the problem of large upload data volume caused by uploading all data, reducing the data upload volume, and thus improving the data upload efficiency.

[0062] In some embodiments, the vehicle terminal can also perform the following steps: when receiving a rejection upload response sent by the cloud for the upload request, delete the driving environment map.

[0063] In an embodiment of the present invention, if a rejection upload response sent by the cloud for the upload request is received, the obtained driving environment map will be deleted. In this way, a part of the cache space can be released.

[0064] In some embodiments, when the vehicle terminal executes "obtain the driving environment map generated by the vehicle terminal at the target driving trajectory point" in the above step S101, as Figure 2 shown, it may include the following steps S201 and S202:

[0065] Step S201: Real-time collect lane scene data of the vehicle terminal at the target driving trajectory point; the lane scene data includes at least one or more of the following map elements: lane lines, road boundaries, signs, traffic lights, zebra crossings, stop lines, and ground arrows.

[0066] In an embodiment of the present invention, the vehicle terminal is equipped with a variety of sensors such as lidar, millimeter-wave radar, cameras, Global Navigation Satellite System (GNSS), and Real-time kinematic (RTK). Therefore, here, the vehicle terminal can obtain the lane scene data at the target driving trajectory point based on the various sensors deployed by itself, and the lane scene data includes: lane lines, road boundaries, signs, traffic lights, zebra crossings, stop lines, and ground arrows.

[0067] Step S202: Generate a driving environment map based on the lane scene data.

[0068] In an embodiment of the present invention, the vehicle terminal generates a driving environment map based on the lane scene data. Exemplarily, a driving environment map is obtained by real-time collecting Simultaneous Localization and Mapping (SLAM).

[0069] In some embodiments, before the vehicle terminal executes the above step S102, asFigure 3 As shown, the following steps S301 and S302 can also be performed:

[0070] Step S301: Compare the existence differences between the map elements in the driving environment map and the high-precision lane-level map, obtain the existence difference result, and determine that there is a difference between the driving environment map and the high-precision lane-level map when the existence difference result indicates an existence difference.

[0071] In an embodiment of the present invention, the vehicle terminal will compare the existence differences between the map elements in the driving environment map and the high-precision lane-level map. Exemplarily, as Figure 4 shown, there is no ground arrow in the high-precision lane-level map 41, while there is a ground arrow in the driving environment map 42 (see 43 in Figure 4 ), which indicates that there is a difference between the driving environment map 42 (real-time perception) and the high-precision lane-level map 41.

[0072] Exemplarily, during the real-time driving process of the vehicle (vehicle terminal), real-time slam mapping (driving environment map) is performed, and the vehicle terminal differential recognition module is run in real time to read the existing lane-level map (high-precision lane-level map), and through high-precision positioning, obtain the real-time position of the vehicle in the existing lane-level map, and read the element data such as lane lines, road boundaries, signs, traffic lights, zebra crossings, stop lines, ground arrows, etc. in the existing lane-level map. At the same time, through real-time perception (driving environment map), identify the elements such as lane lines, road boundaries, signs, traffic lights, zebra crossings, stop lines, ground arrows, etc. seen in real time; compare the elements perceived in real time with the elements in the map one by one. If there is an existence difference in the map elements, it is determined that the existence difference result is an existence difference.

[0073] Step S302: When the existence difference result indicates no existence difference, compare the attribute differences between the map elements in the driving environment map and the high-precision lane-level map, obtain the attribute difference result, and determine that there is a difference between the driving environment map and the high-precision lane-level map when the attribute difference result indicates an attribute difference.

[0074] In an embodiment of the present invention, if there is no existence difference between the map elements in the driving environment map and the high-precision lane-level map, the vehicle terminal will further compare the attribute differences between the map elements in the driving environment map and the high-precision lane-level map. Exemplarily, as Figure 4 shown, in the high-precision lane-level map, the right lane line of the lane where the vehicle terminal (see 44 in Figure 4 ) is located is a solid line. However, in the driving environment map, the right lane line of the lane where the vehicle terminal is located is a dotted line. Therefore, the lane line attributes are inconsistent, and thus there is a difference between the driving environment map and the high-precision lane-level map.

[0075] In some embodiments, when the vehicle end performs "comparing the existence differences between the map elements in the driving environment map and the high-precision lane-level map to obtain the existence difference result" in the above step S301, as Figure 5 shown, it may include the following steps S501 and S502:

[0076] Step S501: For each first map element included in the driving environment map, if there is a corresponding first matching map element in the high-precision lane-level map, it is determined that the existence difference result is no existence difference; if there is any first map element that has no corresponding first matching map element in the high-precision lane-level map, it is determined that the existence difference result is there is an existence difference.

[0077] In the embodiments of the present invention, the vehicle end will compare each first map element included in the driving environment map with the map elements existing in the high-precision lane-level map one by one. If each first map element has a corresponding first matching map element in the high-precision lane-level map, it is determined that the existence difference result is no existence difference. If there is any first map element that has no corresponding first matching map element in the high-precision lane-level map, it is determined that the existence difference result is there is an existence difference.

[0078] Exemplarily, the vehicle end will determine whether the elements perceived in real time (the first map elements in the driving environment map) and the map (the high-precision lane-level map) have all been made (the corresponding first matching map elements). If they have all been made (there are corresponding first matching map elements for all), it is regarded as no change (no existence difference). If they have not been made (there is any first map element that has no corresponding first matching map element in the high-precision lane-level map), it is regarded as there is a change (there is an existence difference).

[0079] Step S502: For each second map element included in the high-precision lane-level map, if there is a corresponding second matching map element in the driving environment map, it is determined that the existence difference result is no existence difference; if there is any second map element that has no corresponding second matching map element in the driving environment map, it is determined that the existence difference result is there is an existence difference.

[0080] In the embodiments of the present invention, the vehicle end will, for each second map element included in the high-precision lane-level map, if there is a corresponding second map element in the driving environment map, it is determined that the existence difference result is no existence difference; if there is any second map element that has no corresponding second matching map element in the driving environment map, it is determined that the existence difference result is there is an existence difference.

[0081] Exemplarily, the vehicle end will determine the existing elements in the map (each second map element included in the high-precision lane-level map), and continuously sense whether there are still corresponding elements (whether there are corresponding second matching map elements in the driving environment map). If there are, it is considered that there is no change (no difference in existence). If it is continuously sensed that there are no corresponding elements (there is any second map element that has no corresponding second matching map element in the driving environment map), it is considered that there is a change (there is a difference in existence).

[0082] In an embodiment of the present invention, only one of step S501 and step S502 may be executed to compare the difference in existence between the map elements in the driving environment map and the high-precision lane-level map. Of course, step S501 and step S502 may also be executed. When the vehicle end executes step S501 and step S502, it can effectively avoid the situation where there are map elements on the high-precision lane-level map but not on the driving environment map when using step S501, and avoid the situation where there are map elements on the driving environment map but not on the high-precision lane-level map when using step S502, thereby improving the accuracy of the difference in existence between the map elements in the driving environment map and the high-precision lane-level map.

[0083] In some embodiments, when the vehicle end executes the step of "comparing the attribute differences between the map elements in the driving environment map and the high-precision lane-level map to obtain an attribute difference result" in step S302 above, the following steps may also be executed: for each first map element, if there are first matching map elements with consistent attributes in the high-precision lane-level map, it is determined that the attribute difference result is no attribute difference; if there is any first map element with inconsistent attributes in the high-precision lane-level map, it is determined that the attribute difference result is there is an attribute difference.

[0084] In an embodiment of the present invention, for the map (high-precision lane-level map) and the continuous perception (driving environment map) of the vehicle end, both have elements (map elements), and it is determined whether their attributes are consistent. If they are consistent, it is considered that there is no change (there is no difference between the driving environment map and the high-precision lane-level map); if the attributes are inconsistent, it is considered that there is a change (there is a difference between the driving environment map and the high-precision lane-level map).

[0085] Exemplarily, if it is found that there is a change (there is a difference between the driving environment map and the high-precision lane-level map), it is necessary to store its slam mapping data (driving environment map) into the data upload buffer module, and then upload it to the cloud for mapping and update the data. If there is no change, the slam mapping data is not stored, and there is no need to upload the data. In this way, the resource consumption of the vehicle end storage can be reduced, and the traffic required for uploading data with no changes in the actual road can also be reduced.

[0086] An embodiment of the present invention provides a data upload method, which is implemented by the cloud, asFigure 6 as shown, including the following steps S601 to S603:

[0087] Step S601: When receiving an upload request carrying a target driving trajectory point sent by the vehicle terminal, search for historical trajectory data corresponding to the target driving trajectory point in a preset trajectory library.

[0088] In an embodiment of the present invention, the cloud is an electronic device with a data upload function, which can be a tablet computer, a notebook computer, a handheld computer, a personal digital assistant (PDA), a desktop computer, etc. The specific cloud server is not limited here.

[0089] In an embodiment of the present invention, when the cloud receives an upload request carrying a target driving trajectory point sent by the vehicle terminal, it will search for data corresponding to the target driving trajectory point in the preset trajectory library and determine the found data as historical trajectory data.

[0090] Step S602: When the historical trajectory data meets the preset upload conditions, send an allow-upload response to the vehicle terminal for the upload request; the preset upload conditions include: in the historical trajectory data, there is a time difference from the upload request greater than a preset time threshold, and the number of trajectory data corresponding to the target driving trajectory point is less than a preset number.

[0091] In an embodiment of the present invention, if the historical trajectory data meets the preset upload conditions, an allow-upload response is sent to the vehicle terminal for the upload request. Among them, the preset upload conditions include: in the historical trajectory data, there is a time difference from the upload request greater than a preset time threshold, and the number of trajectory data corresponding to the target driving trajectory point is less than a preset number.

[0092] Exemplarily, when it is required that the vehicle terminal uploads a driving environment map, it means that there is already a trajectory of the same road in the historical trajectory library, and in the historical trajectory library, the number of trajectories with a time difference from the trajectory of the route to be uploaded of not less than N hours is not more than M pieces of historical trajectory data (the time difference from the upload request is not less than the preset time threshold (N hours), and the number of trajectory data corresponding to the target driving trajectory point is not more than the preset number (M pieces)), indicating that the road has not changed, and it is necessary to update the high-precision lane-level map based on the driving environment map, so it is necessary for the vehicle terminal to upload the driving environment map.

[0093] Step S603: Receive the driving environment map of the target driving trajectory point uploaded by the vehicle terminal in response to the allow-upload response, and update the high-precision lane-level map at the target driving trajectory point based on the driving environment map.

[0094] In an embodiment of the present invention, after the cloud receives the driving environment map of the target driving trajectory points allowed to be uploaded in response to the upload from the vehicle terminal, it can update the high-precision lane-level map at the target driving trajectory points based on the driving environment map.

[0095] Compared with the prior art, the cloud can further control the amount of data uploaded, which is mainly applied to roads collected by a large number of vehicles, to avoid the situation where too many vehicles upload data for the same change point. For example, Figure 7 as shown, vehicles 71 to 7N all upload data to the cloud 70. At this time, it is easy to cause the situation of duplicate upload of data for the same change point. Therefore, the cloud determines whether to upload data based on the target driving trajectory points carried in the upload request, which can further reduce the amount of data uploaded.

[0096] Of course, the function of the cloud to control data upload can be selected to be turned on or off according to actual production requirements. If it is turned off, all the differences between the driving environment map determined by the vehicle terminal and the high-precision lane-level map will be uploaded.

[0097] In some embodiments, the cloud can also perform the following steps: when the historical trajectory data does not meet the preset upload conditions, send a rejection upload response to the vehicle terminal for the upload request.

[0098] In an embodiment of the present invention, if the historical data does not meet the preset upload conditions, the cloud sends a rejection upload response to the vehicle terminal for the upload request. Exemplarily, if there is already a trajectory of the same road in the historical trajectory library, and the number of trajectories with a time difference less than N hours from the trajectory of the route to be uploaded in the historical trajectory library is greater than M, it is considered that the road has changed and the high-precision lane-level map has been updated. At this time, there is no need for the vehicle terminal to upload the driving environment map. It is necessary to send a signal of "existing data, no need to upload" (rejection upload response) to the vehicle terminal, and the vehicle terminal deletes the data in the buffer.

[0099] The present invention provides a data upload system, which is characterized by including: a vehicle terminal and a cloud;

[0100] The vehicle terminal is used to obtain the driving environment map generated at the target driving trajectory point of the vehicle terminal, as well as the high-precision lane-level map corresponding to the driving environment map, and send an upload request carrying the target driving trajectory point to the cloud when it is determined that there is a difference between the driving environment map and the high-precision lane-level map; the cloud is used to, when receiving the upload request carrying the target driving trajectory point sent by the vehicle terminal, find the historical trajectory data corresponding to the target driving trajectory point in the preset trajectory library, and send an allow-upload response to the vehicle terminal for the upload request when the historical trajectory data meets the preset upload conditions; the vehicle terminal is further used to, when receiving the allow-upload response sent by the cloud for the upload request, send the driving environment map to the cloud for the cloud to update the high-precision lane-level map based on the driving environment map.

[0101] Figure 8 This is the overall architecture diagram of an exemplary data upload system provided by an embodiment of the present invention. As Figure 8 shown, the data upload system includes a vehicle terminal 81 and a cloud 82. The vehicle terminal 81 includes a differential judgment module 810 and a vehicle terminal data buffer 811. The vehicle terminal data buffer 811 stores the trajectory data 812 of the vehicle and the semantic data 813 of the driving environment map. The cloud 82 includes cloud lane-level map data 820, a data upload judgment module 821, a historical trajectory library 822, and a vehicle terminal database 823; the vehicle terminal 81 and the cloud 82 communicate through a vehicle-cloud protocol 83.

[0102] Step S801, collect data in real time.

[0103] Here, the vehicle terminal 81 can collect data (driving environment map) in real time through a variety of sensors and transmit the data collected in real time to the differential judgment module 810;

[0104] Step S802, obtain lane-level map data.

[0105] Here, the vehicle terminal 81 can obtain the lane-level map data (high-precision lane-level map) corresponding to the data collected in real time from the lane-level map data 820 of the cloud 82 through a map software development kit (SDK) 84 and transmit the obtained lane-level map data 82 to the differential judgment module 810.

[0106] Step S803, determine whether there is a change.

[0107] Here, the differential judgment module 810 is used to determine whether there is a change between the data collected in real time and the lane-level map data obtained from the cloud 82. If there is no change, step S804 is executed. If there is changed content, step S805 is executed.

[0108] Step S804: Collect data without disk storage.

[0109] Here, if the differential judgment module 810 determines that there is no change in the real-time collected data and the lane-level map data obtained from the cloud 82, there is no need to store it.

[0110] Step S805: Store it in the vehicle-end data buffer.

[0111] Here, if the differential judgment module 810 determines that there are changed contents in the real-time collected data and the lane-level map data obtained from the cloud 82, the real-time collected data will be stored in the vehicle-end data buffer 811.

[0112] Step S806: Upload request.

[0113] Here, the vehicle-end 81 will carry the vehicle-end trajectory data 812 (target driving trajectory points) in the upload request and upload it to the data upload judgment module 821 of the cloud 82 via the vehicle-cloud protocol 83.

[0114] Step S807: Allow upload.

[0115] Here, the cloud 82 will use the data upload judgment module 821 to obtain the trajectory data corresponding to the target driving trajectory points from the historical trajectory library 822. If there is already a trajectory of the same road in the historical trajectory library, and in the historical trajectory library, there are M trajectories whose time difference from the trajectory of the route to be uploaded is less than N hours, it is considered that for the change of this road, other vehicles have already uploaded data, and the data of this vehicle can no longer be uploaded. Otherwise, the data of this vehicle needs to be uploaded, and a "upload" signal (allow upload response) needs to be sent to the vehicle-end.

[0116] Step S808: Upload semantic data.

[0117] Here, when the vehicle-end 81 receives the semantic data 813 sent by the cloud 82, it will upload the semantic data to the cloud 82 for the cloud 82 to update the lane-level map data based on the uploaded semantic data.

[0118] It can be understood that the vehicle-end will first compare the real-time collected data with the data obtained from the cloud, and only when there are changed contents in the comparison will it be stored in the vehicle-end data buffer and send an upload request to the cloud. In this way, it can reduce the utilization rate of the storage space of the data buffer and reduce the amount of data to be uploaded. In addition, the cloud will also re-judge whether data needs to be uploaded based on the vehicle-end's trajectory data, further reducing the amount of data to be uploaded and improving the efficiency of data upload.

[0119] An embodiment of the present invention provides a vehicle-end, as Figure 9 shown, including:

[0120] An acquisition module 901, configured to acquire a driving environment map generated by the vehicle end at a target driving trajectory point, and a high-precision lane-level map corresponding to the driving environment map;

[0121] A first sending module 902, configured to, when it is determined that there is a difference between the driving environment map and the high-precision lane-level map, send an upload request carrying the target driving trajectory point to the cloud, so that the cloud can find corresponding historical trajectory data in a preset trajectory library based on the target driving trajectory point, and send an allow-upload response to the vehicle end when the historical trajectory data meets a preset upload condition; the preset upload condition includes: in the historical trajectory data, there is a time difference from the upload request that is not less than a preset time threshold, and the number of trajectory data corresponding to the target driving trajectory point does not exceed a preset number;

[0122] A first receiving module 903, configured to, when receiving an allow-upload response sent by the cloud for the upload request, send the driving environment map to the cloud for the cloud to update the high-precision lane-level map based on the driving environment map.

[0123] In an embodiment of the present invention, the first receiving module 903 is further configured to delete the driving environment map when receiving a reject-upload response sent by the cloud for the upload request.

[0124] In an embodiment of the present invention, the acquisition module 901 is further configured to collect in real time lane scene data of the vehicle end at the target driving trajectory point; the lane scene data includes at least one or more of the following map elements: lane lines, road boundaries, signs, traffic lights, zebra crossings, stop lines, and ground arrows; and generate a driving environment map based on the lane scene data.

[0125] In an embodiment of the present invention, the first sending module 902 is further configured to compare the existence differences between the map elements in the driving environment map and the high-precision lane-level map to obtain an existence difference result, and determine that there is a difference between the driving environment map and the high-precision lane-level map when the existence difference result indicates an existence difference; when the existence difference result indicates no existence difference, compare the attribute differences between the map elements in the driving environment map and the high-precision lane-level map to obtain an attribute difference result, and determine that there is a difference between the driving environment map and the high-precision lane-level map when the attribute difference result indicates an attribute difference.

[0126] In an embodiment of the present invention, the first sending module 902 is further configured to, for each first map element included in the driving environment map, if there are corresponding first matching map elements in the high-precision lane-level map, determine that the existence difference result is no existence difference; if there is any first map element that has no corresponding first matching map element in the high-precision lane-level map, determine that the existence difference result is there is an existence difference; and / or, for each second map element included in the high-precision lane-level map, if there are corresponding second matching map elements in the driving environment map, determine that the existence difference result is no existence difference; if there is any second map element that has no corresponding second matching map element in the driving environment map, determine that the existence difference result is there is an existence difference.

[0127] In an embodiment of the present invention, the first sending module 902 is further configured to, for each first map element, if there are first matching map elements with consistent attributes in the high-precision lane-level map, determine that the attribute difference result is no attribute difference; if there is any first map element that has a first matching map element with inconsistent attributes in the high-precision lane-level map, determine that the attribute difference result is there is an attribute difference.

[0128] An embodiment of the present invention provides a vehicle terminal, as Figure 10 shown, the pick-up vehicle includes: a first processor 1001, a first memory 1002, and a first communication bus 1003;

[0129] The first communication bus 1003 is used to implement a communication connection between the first processor 1001 and the first memory 1002;

[0130] The first processor 1001 is configured to execute a computer program stored in the first memory 1002 to implement the above data uploading method.

[0131] An embodiment of the present invention provides a cloud, as Figure 11 shown, including:

[0132] A search module 1101, configured to, when receiving an upload request carrying a target driving trajectory point sent by the vehicle terminal, search for historical trajectory data corresponding to the target driving trajectory point in a preset trajectory library;

[0133] A second sending module 1102, configured to, when the historical trajectory data meets a preset upload condition, send an upload permission response to the vehicle terminal for the upload request; the preset upload condition includes: in the historical trajectory data, there is a time difference from the upload request greater than a preset time threshold, and the number of trajectory data corresponding to the target driving trajectory point is less than a preset number;

[0134] A second receiving module 1103, configured to receive a driving environment map of a target driving trajectory point uploaded by a vehicle end in response to an allowed upload, and update a high-precision lane-level map at the target driving trajectory point based on the driving environment map.

[0135] In an embodiment of the present invention, the second sending module 1102 is further configured to send a rejection upload response to the vehicle end for an upload request when the historical trajectory data does not meet a preset upload condition.

[0136] An embodiment of the present invention provides a cloud, as Figure 12 shown, including: a second processor 1201, a second memory 1202, and a second communication bus 1203;

[0137] The second communication bus 1203 is configured to implement a communication connection between the second processor 1201 and the second memory 1202;

[0138] The second processor 1202 is configured to execute a computer program stored in the second memory 1202 to implement the above data upload method.

[0139] An embodiment of the present invention provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores one or more computer programs, and the one or more computer programs can be executed by one or more processors to implement the above data upload method. The computer-readable storage medium can be a volatile memory, such as a random access memory (RAM); or a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); it can also be a respective device including one or any combination of the above memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, etc.

[0140] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a hardware embodiment, a 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 memories and optical memories, etc.) containing computer-usable program codes.

[0141] 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 combinations 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 processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one or more flows and / or blocks Figure 1 in one or more flows and / or blocks Figure 1 or in one or more blocks.

[0142] 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, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one or more flows and / or blocks Figure 1 in one or more flows and / or blocks Figure 1 or in one or more blocks.

[0143] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows and / or blocks Figure 1 in one or more flows and / or blocks Figure 1 or in one or more blocks.

[0144] As mentioned above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A data upload method, characterized in that, Applied to the vehicle end, the data upload method includes: Obtaining a driving environment map generated by the vehicle end at a target driving trajectory point, and a high-precision lane-level map corresponding to the driving environment map; When it is determined that there is a difference between the driving environment map and the high-precision lane-level map, sending an upload request carrying the target driving trajectory point to the cloud, so that the cloud can find corresponding historical trajectory data in a preset trajectory library based on the target driving trajectory point, and when the historical trajectory data meets the preset upload conditions, sending an allow-upload response to the vehicle end; the preset upload conditions include: in the historical trajectory data, there is a time difference from the upload request that is not less than a preset time threshold, and the number of trajectory data corresponding to the target driving trajectory point does not exceed a preset number; When receiving the allow-upload response sent by the cloud for the upload request, sending the driving environment map to the cloud, so that the cloud can update the high-precision lane-level map based on the driving environment map.

2. The data uploading method according to claim 1, wherein The method further includes: When receiving a reject-upload response sent by the cloud for the upload request, deleting the driving environment map.

3. The method according to claim 1, characterized in that The obtaining the driving environment map generated by the vehicle end at the target driving trajectory point includes: Real-time collecting lane scene data of the vehicle end at the target driving trajectory point; the lane scene data includes at least one or more of the following map elements: lane lines, road boundaries, signs, traffic lights, zebra crossings, stop lines, and ground arrows; Generating the driving environment map based on the lane scene data.

4. The data uploading method according to any one of claims 1 to 3, characterized in that, Before sending the upload request carrying the target driving trajectory point to the cloud when it is determined that there is a difference between the driving environment map and the high-precision lane-level map, the method further includes: Comparing the existence differences between the map elements in the driving environment map and the high-precision lane-level map to obtain an existence difference result, and when the existence difference result indicates an existence difference, determining that there is a difference between the driving environment map and the high-precision lane-level map; When the existence difference result indicates no existence difference, comparing the attribute differences between the map elements in the driving environment map and the high-precision lane-level map to obtain an attribute difference result, and when the attribute difference result indicates an attribute difference, determining that there is a difference between the driving environment map and the high-precision lane-level map.

5. The data uploading method according to claim 4, wherein The comparing the existence differences between the map elements in the driving environment map and the high-precision lane-level map to obtain an existence difference result includes: For each first map element included in the driving environment map, if there is a corresponding first matching map element in the high-precision lane-level map, determining that the existence difference result is no existence difference; if there is any first map element that has no corresponding first matching map element in the high-precision lane-level map, determining that the existence difference result is an existence difference; And / or, for each second map element included in the high-precision lane-level map, if there is a corresponding second matching map element in the driving environment map, it is determined that the existence difference result is no existence difference; if there is any second map element that has no corresponding second matching map element in the driving environment map, it is determined that the existence difference result is there is an existence difference.

6. The data uploading method according to claim 5, wherein Comparing the attribute differences between the map elements in the driving environment map and the high-precision lane-level map to obtain an attribute difference result, including: For each first map element, if there are first matching map elements with consistent attributes in the high-precision lane-level map, it is determined that the attribute difference result is no attribute difference; if there is any first map element that has a first matching map element with inconsistent attributes in the high-precision lane-level map, it is determined that the attribute difference result is there is an attribute difference.

7. A data uploading method, characterized in that, Applied to the cloud, the data upload method includes: When receiving an upload request carrying a target driving trajectory point sent by the vehicle terminal, searching for historical trajectory data corresponding to the target driving trajectory point in a preset trajectory library; When the historical trajectory data meets the preset upload conditions, sending an allow upload response to the vehicle terminal for the upload request; the preset upload conditions include: in the historical trajectory data, there is a time difference from the upload request that is not less than a preset time threshold, and the number of trajectory data corresponding to the target driving trajectory point is not greater than a preset number; Receiving the driving environment map of the target driving trajectory point uploaded by the vehicle terminal in response to the allow upload response, and updating the high-precision lane-level map at the target driving trajectory point based on the driving environment map.

8. The data uploading method according to claim 7, wherein The method further includes: When the historical trajectory data does not meet the preset upload conditions, sending a reject upload response to the vehicle terminal for the upload request.

9. A data upload system, characterized in that, Including: A vehicle terminal and a cloud; The vehicle terminal is used to obtain the driving environment map generated by the vehicle terminal at the target driving trajectory point and the corresponding high-precision lane-level map, and when it is determined that there is a difference between the driving environment map and the high-precision lane-level map, send an upload request carrying the target driving trajectory point to the cloud; The cloud is used to search for historical trajectory data corresponding to the target driving trajectory point in a preset trajectory library when receiving an upload request carrying the target driving trajectory point sent by the vehicle terminal, and when the historical trajectory data meets the preset upload conditions, send an allow upload response to the vehicle terminal for the upload request; The vehicle terminal is further used to send the driving environment map to the cloud when receiving the allow upload response sent by the cloud for the upload request, for the cloud to update the high-precision lane-level map based on the driving environment map.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more computer programs, and the one or more computer programs can be executed by one or more processors to implement the data uploading method according to any one of claims 1 to 8.

Images