Methods, apparatus, and electronic equipment for updating high-precision map data based on positioning results

Abstract

This disclosure provides a map data updating method, apparatus, electronic device, storage medium, and program product, relating to the field of autonomous driving technology, and particularly to the field of high-precision map technology. The specific implementation scheme is as follows: based on the positioning results of multiple test points on a predetermined road segment, a target road segment is determined from the predetermined road segment; the positioning results of the multiple test points are obtained by matching the current point cloud data of the multiple test points with multiple historical point cloud data in the map; and based on the geographical location information of the target road segment, the area of ​​the map to be updated is determined.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and more particularly to the field of high-precision map technology, and more particularly to map data updating methods, devices, electronic devices, storage media and program products. Background Technology

[0002] Autonomous vehicles are vehicles that can perceive their surroundings and make driving decisions and controls based on their perceptions without human intervention. During the operation of autonomous vehicles, maps play a crucial role in enabling them to make driving decisions and controls based on their perceptions. High-precision maps, also known as high-resolution maps, are used by autonomous vehicles. High-precision maps possess accurate vehicle location information and rich road element data, helping vehicles anticipate complex road conditions such as slope, curvature, and heading, thus better avoiding potential risks. Summary of the Invention

[0003] This disclosure provides a map data updating method, apparatus, electronic device, storage medium, and program product.

[0004] According to one aspect of this disclosure, a map data update method is provided, comprising: determining a target road segment from the predetermined road segment based on the positioning results of each of the plurality of test points in the predetermined road segment, wherein the positioning results of each of the plurality of test points are obtained by matching the current point cloud data of each of the plurality of test points with the historical point cloud data in the map; and determining the area of ​​the map to be updated based on the geographical location information of the target road segment.

[0005] According to another aspect of this disclosure, a map data updating apparatus is provided, comprising: a first determining module, configured to determine a target road segment from the predetermined road segment based on the positioning results of each of the plurality of test points, wherein the positioning results of each of the plurality of test points are obtained by matching the current point cloud data of each of the plurality of test points with the historical point cloud data in the map; and a second determining module, configured to determine the area of ​​the map to be updated based on the geographical location information of the target road segment.

[0006] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method as described above.

[0007] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method described above.

[0008] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method described above.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0011] Figure 1 This illustration schematically shows an exemplary system architecture for applying map data update methods and apparatus according to embodiments of the present disclosure;

[0012] Figure 2 A flowchart illustrating a map data update method according to an embodiment of the present disclosure is shown schematically.

[0013] Figure 3 A flowchart illustrating the determination of a target road segment according to another embodiment of the present disclosure is shown schematically;

[0014] Figure 4 A flowchart illustrating a map data update method according to another embodiment of the present disclosure is shown schematically;

[0015] Figure 5 A block diagram of a map data updating apparatus according to an embodiment of the present disclosure is schematically shown; and

[0016] Figure 6 A block diagram of an electronic device suitable for implementing a map data update method according to an embodiment of the present disclosure is shown schematically. Detailed Implementation

[0017] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0018] This disclosure provides a map data updating method, apparatus, electronic device, storage medium, and program product.

[0019] According to embodiments of this disclosure, a map data update method is provided, comprising: determining a target road segment from the predetermined road segment based on the positioning results of multiple test points on the predetermined road segment, wherein the positioning results of the multiple test points are obtained by matching the current point cloud data of the multiple test points with multiple historical point cloud data in the map; and determining the area of ​​the map to be updated based on the geographical location information of the target road segment.

[0020] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0021] Figure 1 The illustration schematically shows an exemplary system architecture for applying map data update methods and apparatus according to embodiments of the present disclosure.

[0022] It is important to note that Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.

[0023] like Figure 1 As shown, the system architecture 100 according to this embodiment may include an autonomous vehicle 101, a network 102, and a server 103. The network 102 serves as a medium for providing a communication link between the autonomous vehicle 101 and the server 103. The network 102 may include various connection types, such as wireless communication links.

[0024] The autonomous vehicle 101 may be equipped with camera acquisition devices, such as those used to collect image data of the road. The autonomous vehicle 101 may also be equipped with laser sensors, such as those used to collect point cloud data of the road. The autonomous vehicle 101 may also be equipped with a positioning system, such as those used to determine the real-time geographical location of the autonomous vehicle 101.

[0025] Users can use autonomous vehicle 101 to interact with server 103 via network 102 to receive or send operational data, such as point cloud data, image data, and geographic location information.

[0026] Server 103 may be a server that provides various services, such as a back-end management server that supports the navigation application used by the user in the autonomous vehicle 101 (for example only).

[0027] Server 103 can also be a cloud server, also known as a cloud computing server or cloud host. It is a host product in the cloud computing service system, which solves the shortcomings of traditional physical hosts and VPS services ("Virtual Private Server", or simply "VPS"), such as high management difficulty and weak business scalability. The server can also be a server for a distributed system or a server combined with blockchain.

[0028] It should be noted that the map data update method provided in this embodiment can generally be executed by the server 103. Accordingly, the map data update device provided in this embodiment can also be located in the server 103.

[0029] For example, the autonomous vehicle 101 can collect current point cloud data for multiple test points on a predetermined road segment, and match the current point cloud data of each test point with multiple historical point cloud data in the map loaded on the autonomous vehicle 101 to obtain multiple positioning results corresponding one-to-one with the multiple test points. These multiple positioning results are then transmitted to the server 103. Based on the positioning results of the multiple test points on the predetermined road segment, the server determines the target road segment from the predetermined road segment, and based on the geographical location information of the target road segment, determines the area of ​​the map to be updated.

[0030] It should be understood that Figure 1 The number of autonomous vehicles, networks, and servers shown is merely illustrative. Depending on implementation needs, there can be any number of terminal devices, networks, and servers.

[0031] Figure 2 A flowchart illustrating a map data update method according to an embodiment of the present disclosure is shown schematically.

[0032] like Figure 2 As shown, the method includes operations S210~S220.

[0033] In operation S210, based on the positioning results of multiple test points on a predetermined road segment, the target road segment is determined from the predetermined road segment. The positioning results of the multiple test points are obtained by matching the current point cloud data of the multiple test points with multiple historical point cloud data in the map.

[0034] When operating S220, the area of ​​the map to be updated is determined based on the geographical location information of the target road segment.

[0035] According to embodiments of this disclosure, the predetermined road segment can be a continuous road segment or a non-continuous road segment; the predetermined road segment can be a highway segment, an expressway segment, an urban road segment, or a road segment within a community, etc.

[0036] According to embodiments of this disclosure, when an autonomous vehicle travels on a predetermined road segment, the segment can be divided into equal intervals according to the distance traveled, with each interval serving as a test point. However, this is not a limitation; the test point can also be determined based on the acquisition frequency of the LiDAR sensor. For example, the acquisition frequency could be 10 frames of point cloud data per second. The location point corresponding to a frame of point cloud data acquired every 10 seconds could be used as a test point, or the location point corresponding to a frame of point cloud data acquired every 1 second could be used as a test point. Any set of test points that can achieve full coverage detection of the predetermined road segment is acceptable.

[0037] According to embodiments of this disclosure, the current point cloud data can be point cloud data of the surrounding environment of the test point collected by a LiDAR sensor mounted on an autonomous vehicle. For example, a non-contact laser beam emitted by a LiDAR sensor is used to detect a target object, and the beam incident on the target object and reflected back is collected to form point cloud data. The current point cloud data can be a collection of massive sampling point data on the surface of the target object in the environment surrounding the test point, and each sampling point data contains three-dimensional spatial coordinate information. The target objects involved in the current point cloud data can be static target objects, including, for example, lane lines, road signs, or buildings, where dynamic target objects such as vehicles and pedestrians are excluded.

[0038] According to embodiments of this disclosure, the multiple historical point cloud data in the map can be raw point cloud data collected using LiDAR sensors mounted on autonomous vehicles. The collection methods and types of each of the multiple historical point cloud data in the map are the same as those of the current point cloud data, so that the positioning results can be obtained quickly and accurately during point cloud localization. Unlike the current point cloud data, the multiple historical point cloud data are denser, with overlapping data between each adjacent pair, allowing for stitching to form full coverage of the point cloud data for a predetermined road segment. This ensures that for each test point involved in the current point cloud data collected for the predetermined road segment, corresponding historical point cloud data can be found in the multiple historical point cloud data of the map.

[0039] According to embodiments of this disclosure, the map includes not only historical point cloud data but also geographic coordinate information of location points, and the mapping relationship between historical point cloud data and geographic coordinate information of location points. Therefore, when historical point cloud data matching the current point cloud data is determined, the geographic coordinate information of the current point cloud data can be determined based on the mapping relationship between historical point cloud data and geographic coordinate information of location points, thus obtaining a positioning result with geographic coordinate information at, for example, centimeter error level. However, this is not limited to this. In embodiments of this disclosure, the current point cloud data can also be used to represent point cloud data of target objects in the current environment of the test point. Multiple historical point cloud data in the map can be used to represent point cloud data of target objects in the historical environments of multiple test points. Matching can be performed between the current point cloud data and multiple historical point cloud data. When a corresponding historical point cloud data is matched between the current point cloud data and multiple historical point cloud data, it is determined that the current environment represented by the current point cloud data is consistent with the historical environment represented by the historical point cloud data and has not changed, thus obtaining a positioning result representing successful positioning. If the current environment represented by the current point cloud data is inconsistent with the historical environment represented by the historical point cloud data, and it is determined that the current environment has changed, such as due to road alterations or construction, then the mapping relationship between the historical point cloud data and the geographic coordinates of the location points cannot be used to obtain the geographic coordinates of the current point cloud data. This results in a positioning result indicating a positioning failure.

[0040] According to embodiments of this disclosure, a target road segment can be determined by a road segment formed by multiple test points that represent positioning failures, such as multiple test points where the current environment represented by the current point cloud data is inconsistent with the historical environment represented by the historical point cloud data. The target road segment can indicate that the availability of point cloud data with relative positions on the map has decreased and needs to be updated.

[0041] According to embodiments of this disclosure, the geographic location information of the target road segment can refer to the geographic location information of the starting point and the ending point of the target road segment, but it is not limited to this. It can also refer to the geographic location information of the starting point and the ending point of the target road segment, as well as the geographic location information of multiple locations between the starting point and the ending point of the target road segment. As long as the geographic location information of the target road segment can determine the area of ​​the map to be updated, it is acceptable.

[0042] According to embodiments of this disclosure, geographic location information can be obtained through an onboard INS (Inertial Navigation System), but is not limited to this. It can also be calculated using GNSS (Global Navigation Satellite System) data, IMU (Inertial Measurement Unit) data, and laser point cloud data from the autonomous vehicle. Alternatively, other positioning systems can be used for positioning, such as GPS (Global Positioning System) or BDS (BeiDou Navigation Satellite System). Taking GNSS data and differential GPS data as an example, differential GPS data is acquired in real time through the onboard INS and IMU data is acquired in real time through the inertial measurement unit during the autonomous vehicle's operation. Subsequently, the differential GPS data and multiple current point cloud data can be offline registered using the ICP (Iterative Closest Points) algorithm to obtain the current geographic location information of the autonomous vehicle. Alternatively, the acquired differential GPS data, IMU data, and current point cloud data can be compared with a pre-determined map, such as a high-precision map, to obtain the current geographic location information of the autonomous vehicle. Since the positioning accuracy of differential GPS data can reach the centimeter level, the accuracy of the geographical location information determined by offline registration using the ICP algorithm by combining multiple current point cloud data can be better than the centimeter level.

[0043] Furthermore, taking the use of INS (Inertial Navigation System) for positioning of autonomous vehicles as an example, the positioning sensors can include gyroscopes and accelerometers, and the sensing positioning data can include acceleration data and angular velocity data. INS calculates the positioning coordinates of the next point of the autonomous vehicle from its starting position based on the continuously measured heading angle and velocity of the autonomous vehicle, thus continuously measuring the positioning coordinates of the autonomous vehicle at every moment, i.e., the geographical location information.

[0044] The map data update method provided in this disclosure makes full use of the current point cloud data collected by the lidar sensor. It can not only locate autonomous vehicles in real time, but also detect environmental changes in a predetermined road segment in a timely and effective manner based on the current point cloud data, so as to update the map in a timely manner. This reduces the map data update cycle, reduces the cost of map updates, and improves the usability of the map.

[0045] According to embodiments of this disclosure, regarding operation S220, when precise geographic location information cannot be obtained using point cloud positioning, the aforementioned INS (Inertial Navigation System) positioning method can be used to obtain geographic location information. Alternatively, the aforementioned GPS or BDS positioning method can also be used to obtain geographic location information. Simultaneously, the received positioning results from multiple test points of the autonomous vehicle can be timestamped for each positioning result to obtain a positioning timestamp. The received geographic location information from multiple location points of the autonomous vehicle can also be timestamped to obtain a geographic timestamp. The geographic location information of a location point can be determined based on the matching degree between the positioning timestamp and the geographic timestamp. Therefore, when positioning results cannot be obtained through point cloud positioning or when the positioning results indicate positioning failure, the geographic location information of the target road segment can be determined based on the positioning timestamp and the geographic timestamp.

[0046] According to embodiments of this disclosure, taking an autonomous vehicle as an example, points with the same geographic timestamp and location timestamp can be grouped together. These test points are then mapped to geographic location information to determine their geographic location. However, this is not a limitation. Points with a time interval between their geographic timestamp and location timestamp that is less than or equal to a preset time interval threshold can also be grouped together. This avoids discrepancies between the geographic timestamp and location timestamp caused by inconsistencies between the collection frequency of point cloud data from the LiDAR sensor on the autonomous vehicle and the collection frequency of the positioning system.

[0047] According to embodiments of this disclosure, a map containing multiple historical point cloud data can be stored on an autonomous vehicle. The current point cloud data of the test point collected by the autonomous vehicle is matched with the multiple historical point cloud data in the map to determine the positioning result. The positioning result is then transmitted to a server, which determines the target road segment from a predetermined road segment based on the positioning result. However, this is not limited to this. Alternatively, the map containing multiple historical point cloud data can be stored on a server, which receives the current point cloud data of the test point collected by the autonomous vehicle, and matches the current point cloud data of the test point with the multiple historical point cloud data in the map to determine the positioning result.

[0048] According to embodiments of this disclosure, in the case where multiple autonomous vehicles report data and multiple autonomous vehicles interact with the server to update map data, the autonomous vehicles can use the current point cloud data to match multiple historical point cloud data in the map to determine the positioning result, thereby reducing the amount of data transmission and improving the server's determination rate for the target road segment.

[0049] According to embodiments of this disclosure, point cloud positioning can be used to determine the positioning results of each test point. For example, based on matching the current point cloud data of the test point with multiple historical point cloud data in a map, the current point cloud feature vector of the current point cloud data and the historical point cloud feature vectors of each of the multiple historical point cloud data in the map can be extracted. A similarity matching method is then used to determine the similarity between the current point cloud feature vector and each of the multiple historical point cloud feature vectors, thereby determining the positioning result. However, this is not limited to this. Point cloud positioning can also involve converting the laser reflection intensity data in the current point cloud data into current laser point cloud projection data on the ground plane, and converting the laser reflection intensity data of each of the multiple historical point cloud data into historical laser point cloud projection data on the ground plane. A similarity matching method is then used to determine the similarity between the current laser point cloud projection data and each of the multiple historical laser point cloud projection data, thereby determining the positioning result. It can be understood that any point cloud positioning method that determines the positioning result based on the current point cloud data and multiple historical point cloud data is acceptable.

[0050] Figure 3 A flowchart illustrating the determination of a target road segment according to another embodiment of the present disclosure is shown schematically.

[0051] like Figure 3 As shown, the map data update method may include operations S310~S320, S331~S332, and S340.

[0052] In operation S310, for each of the multiple test points, the confidence level of the localization result of the test point is determined.

[0053] In operation S320, the confidence level is compared with the predetermined confidence level.

[0054] In operation S331, in response to a confidence level less than or equal to a predetermined confidence threshold, the test point is determined as the target point, resulting in multiple target points.

[0055] In operation S340, a target road segment is determined from the predetermined road segments based on multiple target points.

[0056] In operation S332, if the confidence level is greater than a predetermined confidence threshold, the operation is stopped.

[0057] According to embodiments of this disclosure, point cloud localization can be used to match multiple historical point cloud data with the point cloud data of the test point, resulting in multiple matching degrees corresponding one-to-one with the multiple historical point cloud data. The multiple matching degrees are then sorted from highest to lowest to obtain a ranking result. Based on the ranking result, the matching degree ranked first is determined as the confidence level of the localization result of the test point.

[0058] According to embodiments of this disclosure, the confidence level can be compared with a predetermined confidence threshold, and the test points that are less than or equal to the predetermined confidence threshold can be determined as target points, that is, the test points that fail to locate can be determined as target points, and the target road segment can be determined from the predetermined road segment based on multiple target points.

[0059] According to other embodiments of this disclosure, the multiple test points can be determined according to the extension direction of a predetermined road segment. The number of target points is determined from the multiple test points to obtain the total number of target points. The total number of target points can be compared with a predetermined target point threshold. If the total number of target points is greater than or equal to the predetermined target point threshold, the road segment formed by the multiple target points is determined as the target road segment. If the total number of target points is less than the predetermined target point threshold, the target points can be ignored.

[0060] According to other embodiments of this disclosure, in response to a confidence level less than or equal to a predetermined confidence threshold, the test point can be determined as an initial target point. Image data matching the initial target point is determined. The target point is determined based on the image data. An image recognition model can be used to process the image data corresponding to the initial target point to determine whether the initial target point is a target point. The image recognition model can be a model for recognizing text in an image; the accuracy can be improved by using the text "road construction ahead" to further assist in determining whether the test point is a target point.

[0061] According to embodiments of this disclosure, it can be carried out as follows Figure 3 The operation shown determines the target road segment based on multiple target points when there are only the location results for each of the multiple test points, i.e., only one set of location results. It then determines the map update area based on the geographical location information of the target road segment. However, it is not limited to this. It also determines a target location result set based on multiple sets of location results, identifies the target road segment from this target location result set, and determines the map update area based on the geographical location information of the target road segment.

[0062] Figure 4 A flowchart illustrating a map data update method according to another embodiment of the present disclosure is shown schematically.

[0063] like Figure 4 As shown, the method may include operations S410~S440 and S451~S452.

[0064] During operation of S410, multiple sets of positioning results are received.

[0065] According to embodiments of this disclosure, N autonomous vehicles operate on a predetermined road segment within a predetermined time period, such as one day or one week. Point cloud data of static target objects such as lane lines, road signs, and buildings on the predetermined road segment can be collected using lidar sensors on the autonomous vehicles, resulting in N current point cloud data sets corresponding one-to-one with the N autonomous vehicles. Multiple historical point cloud data from a positioning map mounted on the autonomous vehicles are then used to match and obtain a set of positioning results for each autonomous vehicle, such as a first positioning result set, a second positioning result set, a third positioning result set, and so on, up to an Nth positioning result set. The server can receive the positioning result sets from each of the N autonomous vehicles, thus obtaining N positioning result sets.

[0066] In operation S420, clustering is performed on multiple sets of location results.

[0067] According to embodiments of this disclosure, N location result sets can be clustered. Location result sets containing target road segments are grouped together, and location result sets without target road segments are grouped together. For example, if the first, second, and third location result sets include target road segments, then the first, second, and third location result sets are respectively determined as target location result sets.

[0068] In operation S430, the number of target road segments in the target location result set is calculated. Using the geographic location information of the target road segments, and considering the same location, the number of target location result sets containing the same target road segments can be calculated as the number of target road segments.

[0069] In operation S440, the determined number of target road segments is compared with a predetermined number threshold.

[0070] In operation S451, if the quantity is greater than or equal to a predetermined quantity threshold, it is determined that the surrounding environment of the target road segment is likely to have changed. Based on this, the operation of determining the area to be updated on the map based on the geographical location information of the target road segment can be performed.

[0071] In operation S452, if it is determined that the number is less than the predetermined threshold, it is possible that the lidar sensor on the autonomous vehicle has malfunctioned rather than the surrounding environment of the target road segment has changed, and then subsequent operations can be stopped.

[0072] The method for determining the area to be updated in the map provided in this embodiment can reduce the amount of computation by clustering and improve the authenticity and effectiveness of the determination of the area to be updated by counting the number of target road segments.

[0073] According to embodiments of this disclosure, when the determined quantity exceeds a predetermined threshold, other operational data of the autonomous vehicle (i.e., road segment association data), such as road segment image data, can be combined for auxiliary judgment. For example, the received road segment image data from the autonomous vehicle can be marked according to the road segment image timestamp. The road segment image data corresponding to any target point in the target road segment can be determined based on the road segment image timestamp and the geographic timestamp or the location timestamp. The image recognition model provided in the embodiments of this disclosure can be used to process the road segment image data to further assist in determining whether the target road segment is an area to be updated on the map. However, it is not limited to this. Road segment driving trajectory data can also be formed based on the geographical location information obtained by the autonomous vehicle. It can be determined whether the road segment driving trajectory data and the predetermined road segment are the same trajectory. For example, if there is construction at location A in the predetermined road segment, and detour is required. In this case, the road segment driving trajectory data and the predetermined road segment trajectory are different, which can further assist in determining whether the target road segment is an area to be updated on the map. It is also possible to determine whether the target road segment is an area to be updated on the map by combining the road segment image data and the road segment driving trajectory data of the autonomous vehicle.

[0074] According to embodiments of this disclosure, when an area of ​​the map to be updated is determined, an update operation on the map can be performed.

[0075] For example, in response to a determined target road segment, multiple target current point cloud data of multiple target points in the target road segment are obtained, wherein multiple target points correspond one-to-one with multiple target current point cloud data; and multiple historical point cloud data of the area to be updated in the map are updated using multiple target current point cloud data.

[0076] According to embodiments of this disclosure, the historical point cloud data to be updated can refer to the historical point cloud data corresponding to the target point. The geographic location information of the target point can be used to determine the point cloud data to be updated corresponding to the current point cloud data of the target, and the current point cloud data of the target can be used to update the historical point cloud data to be updated. The update method is not limited, as long as it can utilize the current point cloud data of the target to update the area to be updated in the map.

[0077] The data processing method provided in this disclosure uses the current point cloud data of the target area to be updated to update the area in the map, and uses the operational data collected in normal times for detection and updating, resulting in a short update cycle and low cost.

[0078] Figure 5 A block diagram of a map data updating apparatus according to an embodiment of the present disclosure is shown schematically.

[0079] like Figure 5As shown, the map data update device 500 may include a first determining module 510 and a second determining module 520.

[0080] The first determining module 510 is used to determine the target road segment from the predetermined road segment based on the positioning results of each of the multiple test points in the predetermined road segment. The positioning results of each of the multiple test points are obtained by matching the current point cloud data of each of the multiple test points with multiple historical point cloud data in the map.

[0081] The second determination module 520 is used to determine the area of ​​the map to be updated based on the geographical location information of the target road segment.

[0082] According to embodiments of this disclosure, the first determining module may include a first determining unit, a second determining unit, and a third determining unit.

[0083] The first determining unit is used to determine the confidence level of the localization result for each of the multiple test points.

[0084] The second determining unit is used to determine the test point as the target point in response to determining that the confidence level is less than or equal to a predetermined confidence level threshold, thereby obtaining multiple target points.

[0085] The third determining unit is used to determine the target road segment from the predetermined road segments based on multiple target points.

[0086] According to embodiments of this disclosure, the first determining unit may include a first determining subunit, a second determining subunit, and a third determining subunit.

[0087] The first determining subunit is used to determine the test point as the initial target point in response to a confidence level less than or equal to a predetermined confidence level threshold.

[0088] The second determining subunit is used to determine the image data that matches the initial target point.

[0089] The third determining subunit is used to determine the initial target point as the target point based on image data.

[0090] According to embodiments of this disclosure, the map data update device may further include a first acquisition module, a clustering module, and a calculation module.

[0091] The first acquisition module is used to acquire multiple sets of location results for a predetermined road segment within a predetermined time period. Each set of multiple location results includes the location results of multiple test points.

[0092] The clustering module is used to cluster multiple sets of location results based on the location results, so as to obtain a set of target location results containing the target road segment.

[0093] The calculation module is used to calculate the number of target road segments based on the target location result set, so that if the number of targets is greater than or equal to a predetermined threshold, the operation of determining the area to be updated on the map based on the geographical location information of the target road segments is performed.

[0094] According to embodiments of this disclosure, the second determining module may include a fourth determining unit and a fifth determining unit.

[0095] The fourth determining unit is used to determine the road segment association data that matches the target road segment, wherein the road segment association data includes at least one of the following: road segment image data and road segment driving trajectory data.

[0096] The fifth determining unit is used to determine the area of ​​the map to be updated based on the geographical location information of the target road segment and the road segment association data.

[0097] According to embodiments of this disclosure, the map data update device may further include a first receiving module and a second receiving module.

[0098] The first receiving module is used to receive the positioning results of multiple test points, wherein the positioning results include positioning timestamps.

[0099] The second receiving module is used to receive the geographic location information of multiple location points, wherein the geographic location information includes geographic timestamps.

[0100] According to embodiments of this disclosure, the geographic location information of the target road segment is determined based on the location timestamp and the geographic timestamp.

[0101] According to embodiments of this disclosure, the map data update device may further include a second acquisition module and an update module.

[0102] The second acquisition module is used to acquire multiple target current point cloud data of multiple target points in the target road segment in response to the determined target road segment, wherein the multiple target points correspond one-to-one with the multiple target point current point cloud data.

[0103] The update module is used to update multiple historical point cloud data of the area to be updated in the map by utilizing the current point cloud data of multiple targets.

[0104] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0105] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described above.

[0106] According to embodiments of the present disclosure, a non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions are used to cause a computer to perform the method described above.

[0107] According to an embodiment of this disclosure, a computer program product includes a computer program that, when executed by a processor, implements the method described above.

[0108] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0109] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded into random access memory (RAM) 603 from storage unit 608. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0110] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0111] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the map data update method. For example, in some embodiments, the map data update method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the map data update method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the map data update method by any other suitable means (e.g., by means of firmware).

[0112] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0114] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0115] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0116] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0117] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, distributed system servers, or servers incorporating blockchain technology.

[0118] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0119] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for updating map data, comprising: determining a target road segment from a predetermined road segment based on respective positioning results of a plurality of test points of the predetermined road segment, the positioning results being from an autonomous vehicle, the target road segment including a test point with a failed positioning; receiving respective geographic location information of a plurality of location points, the geographic location information of the location points being determined based on a navigation system configured on the autonomous vehicle, the geographic location information including a geographic timestamp; and determining an area to be updated of the map according to geographic location information of the target road segment, the geographic location information of the target road segment being determined based on a positioning timestamp of the positioning result of the test point with the failed positioning and the geographic timestamp of the geographic location information of the location points; wherein the positioning result of the test point is determined by: matching respective current point cloud data of the test point with a plurality of historical point cloud data of the map stored on the autonomous vehicle to determine a positioning result indicating whether positioning is successful. The determining a target road segment from a predetermined road segment based on respective positioning results of a plurality of test points of the predetermined road segment comprises: determining, for each test point of the plurality of test points, a confidence level of the positioning result of the test point; in response to determining that the confidence level is less than or equal to a predetermined confidence threshold, determining the test point as a target point to obtain a plurality of target points; and determining the target road segment from the predetermined road segment based on the plurality of target points. The determining the test point as the target point in response to the confidence level being less than or equal to the predetermined confidence threshold comprises: in response to the confidence level being less than or equal to the predetermined confidence threshold, determining the test point as an initial target point; determining image data matching the initial target point; and determining the initial target point as the target point based on the image data. 4.The method of any one of claims 1 to 3, further comprising: obtaining a plurality of positioning result sets of the predetermined road segment within a predetermined time period, wherein each positioning result set of the plurality of positioning result sets includes respective positioning results of the plurality of test points; clustering the plurality of positioning result sets based on the positioning results to obtain a target positioning result set containing the target road segment; and based on the target positioning result set, calculating a determination quantity of determining the target road segment, so that the operation of determining the area to be updated of the map according to the geographic location information of the target road segment is performed in a case where the determination quantity is greater than or equal to a predetermined quantity threshold. The determining the area to be updated of the map according to the geographic location information of the target road segment comprises: determining road segment associated data matching the target road segment, wherein the road segment associated data includes at least one of the following: road segment image data, road segment driving trajectory data; and determining the area to be updated of the map based on the geographic location information of the target road segment and the road segment associated data. 6.The method of any one of claims 1 to 3, further comprising: ​ 2. The method of claim 1, wherein, ​ ​ ​ ​ 3. The method of claim 2, wherein, ​ ​ ​ ​ ​ ​ ​ ​ 5. The method of any one of claims 1 to 3, wherein, ​ ​ ​ ​ In response to having determined the target road segment, a plurality of target current point cloud data of a plurality of target points in the target road segment is acquired, wherein the plurality of target points correspond one-to-one to the plurality of target current point cloud data; and The plurality of target current point cloud data is used to update a plurality of to-be-updated historical point cloud data of a to-be-updated area in the map.

7. A map data updating apparatus, comprising: a first determining module configured to determine a target road segment from a predetermined road segment based on a positioning result of each of a plurality of to-be-tested points, the positioning result being from an autonomous vehicle, the target road segment including a to-be-tested point with a failed positioning; a second receiving module configured to receive geographic location information of each of a plurality of location points, the geographic location information of the location points being determined based on a navigation system configured on the autonomous vehicle, the geographic location information including a geographic time stamp; and a second determining module configured to determine a to-be-updated area of the map according to geographic location information of the target road segment, the geographic location information of the target road segment being determined based on a positioning time stamp of the positioning result of the to-be-tested point with the failed positioning and the geographic time stamp of the geographic location information of the location points; wherein the positioning result of the to-be-tested point is determined by: matching current point cloud data of the to-be-tested point with a plurality of historical point cloud data of the map stored on the autonomous vehicle respectively to determine a positioning result indicating whether positioning is successful.

8. The apparatus of claim 7, wherein, The first determining module comprises: a first determining unit configured to determine a confidence level of the positioning result of each of the to-be-tested points in the plurality of to-be-tested points; a second determining unit configured to determine the to-be-tested point as a target point in response to determining that the confidence level is less than or equal to a predetermined confidence level threshold, obtaining a plurality of target points; and a third determining unit configured to determine the target road segment from the predetermined road segment based on the plurality of target points.

9. The apparatus of claim 8, wherein, The first determining unit comprises: a first determining sub-unit configured to determine the to-be-tested point as an initial target point in response to the confidence level being less than or equal to the predetermined confidence level threshold; a second determining sub-unit configured to determine image data matching the initial target point; and a third determining sub-unit configured to determine the initial target point as the target point based on the image data.

10. The apparatus according to any one of claims 7 to 9, further comprising: a first acquiring module configured to acquire a plurality of positioning result sets of the predetermined road segment within a predetermined time period, wherein each of the plurality of positioning result sets includes a positioning result of each of the plurality of to-be-tested points; a clustering module configured to cluster the plurality of positioning result sets based on the positioning results to obtain a target positioning result set containing the target road segment; and a calculating module configured to calculate a determination quantity of determining the target road segment based on the target positioning result set, so as to perform the operation of determining the to-be-updated area of the map according to the geographic location information of the target road segment in a case where the determination quantity is greater than or equal to a predetermined quantity threshold.

11. The apparatus of any one of claims 7 to 9, wherein, The second determining module comprises: a fourth determining unit, configured to determine road section associated data matched with the target road section, wherein the road section associated data comprises at least one of the following: road section image data, road section driving track data; and a fifth determining unit, configured to determine the to-be-updated area of the map based on the geographic position information of the target road section and the road section associated data.

12. The apparatus according to any one of claims 7 to 9, further comprising: a second obtaining module, configured to, in response to having determined the target road section, obtain a plurality of target current point cloud data of a plurality of target points in the target road section, wherein the plurality of target points correspond to the plurality of target point current point cloud data one-to-one; and an updating module, configured to update a plurality of to-be-updated historical point cloud data of the to-be-updated area in the map by using the plurality of target current point cloud data.

13. An electronic device, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.

14. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1 to 6.

15. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1 to 6.

Images