High definition map metadata for autonomous vehicles

Abstract

This document discloses a technique for generating and providing autonomous vehicles with an indication of the level of confidence in the accuracy or quality of map data, wherein the indication is determined based on observation data received from other vehicles.

Description

Technical Field

[0001] This invention relates to methods, systems, computer programs, etc., related to autonomous driving systems in autonomous vehicles. Specifically, this invention relates to high-definition maps used in autonomous driving systems in autonomous vehicles. Background Technology

[0002] Autonomous vehicles (sometimes called automated vehicles) typically include an automated driving system (ADS) that allows the vehicle to drive fully or partially autonomously. ADS relies on two key sets of input data to maintain a model of the vehicle's environment: sensor-derived observations (SDO) and high-definition (HD) maps.

[0003] SDO (Situational Dot) is the observation of the vehicle's current environment derived from its sensors. Vehicle sensors can include both position sensors (such as GPS) and environmental sensors (such as cameras, RADAR, LIDAR). These vehicle sensors are typically intelligent and equipped with embedded sensing capabilities for detecting and classifying geospatial objects, such as traffic signs. Vehicle sensors observe both stationary and moving objects.

[0004] HD maps are highly detailed 3D maps with high precision, suitable for use by Adaptive Driving Systems (ADS) to provide vehicles with sufficiently accurate information about the road environment, enabling effective and safe driving. HD maps effectively expand a vehicle's field of vision, resulting in smoother, safer, and more efficient driving scenarios. As part of ADS, HD maps can be used for a wide range of advanced driving applications. HD maps require a highly accurate representation of the road system and its infrastructure, such as lane models, including the geometry of lane markings, lane centerlines, and road boundaries. Therefore, HD maps suitable for autonomous driving offer significantly higher precision compared to maps used in in-vehicle satellite navigation or smartphone map applications.

[0005] HD maps can be viewed as a geospatial model of the road system relevant to driving automation, containing abstractions of stationary objects and their relationships. Stationary objects can be called real-world features, while their representation in an HD map can be called map features. Map features are distinguished by three geometric categories: point features (e.g., traffic signs), line features (e.g., road boundaries), and area features (e.g., road surface areas). Map features may have associated attributes, such as speed limits associated with roads or lanes, or sign types associated with traffic signs. Compared to SDOs (Spatial Domains), HD maps only include features representing stationary objects, and observations of map features in HD maps are historical (i.e., made in the past).

[0006] HD maps can be subdivided into blocks and layers. For example, a map block describes a rectangular map area containing map data associated with a region of the map. A map layer contains a subset of available map data. For example, an HD map may include an HD road layer, a speed limit layer, and a road inspection layer. The HD road layer includes map data associated with arcs (representing intersection areas and lane groups) and nodes (connecting arcs). The map data in the speed limit layer describes speed limits. The road inspection layer includes map data representing driving automation restrictions. HD maps may contain additional layers. In summary, HD map data is structured as layers of blocks.

[0007] As mentioned above, the ADS (Adaptive Data System) for autonomous vehicles uses SDO (Surface Dot) and data from HD (High Definition) maps to model the vehicle's current environment. Therefore, the ADS needs to determine the extent to which it can rely on map features to accurately represent corresponding stationary objects. This drives the need for map quality metadata, which enables in-vehicle logic to quantify the quality of the representation of stationary objects residing in the vehicle's environment model.

[0008] The quality of HD maps is specified using the quality indicators (i.e., completeness, logical consistency, location accuracy, thematic accuracy, and temporal accuracy) defined in ISO 19157:13. HD map quality depends on the time, quality, and quantity of the source data, as well as the quality of the map-making process applied. Currently, most source data used to create HD maps originates from high-quality survey vehicles. However, it is economically impractical to frequently survey roads using survey vehicles to capture changes. Reality is constantly changing for various reasons, and not all roads represented in an HD map were surveyed on the same day; therefore, it is practically impossible to provide an HD map that accurately reflects current reality for all its features. As discussed in WO2017021473, WO2017021474, WO2017021475, and WO2017021778, vehicle sensor data from conventional passenger vehicles can also be used as source data for creating HD maps.

[0009] As discussed above, autonomous vehicles require highly reliable HD maps for safe operation. Therefore, HD map updates should enable automated vehicles to quickly understand relevant reality changes. However, the time from reality change to delivering the associated HD map update to the vehicle is considerable. It takes time before the vehicle can investigate the location of the change and provide high-quality environmental sensor data, or before a conventional passenger vehicle can provide sufficient medium-quality environmental sensor data to derive observations.

[0010] Typically, Content Delivery Networks (CDNs) use known content distribution technologies and communication network infrastructure to distribute HD maps to HD map clients. CDN content distribution models employ content caching storage facilities to ensure that content is readily available to HD map clients requesting specific map tiles while driving. This CDN approach reduces communication overhead and content distribution latency. It also means that relatively stable content can achieve high cache hit rates, thereby improving CDN efficiency.

[0011] This application seeks to improve current methods and systems related to HD maps used by ADS in autonomous vehicles. Specifically, this application seeks to provide methods and systems to better handle changes (or lack thereof) in real-world features and associated metadata. Summary of the Invention

[0012] According to a first aspect of the invention, a computer-implemented method at a server system is provided, the server system storing HD map data representing a road system having a plurality of objects, the HD map data including a plurality of map features representing the plurality of objects of the road system, the server system further storing HD map metadata, the metadata including confidence levels of the HD map data for the plurality of map features, the HD map data and the metadata being provided for use by an autonomous driving system in an autonomous vehicle, the method comprising: receiving observation data of the road system, the observation data including one or more observations of the road system; identifying one or more objects among the plurality of objects associated with the observation data; identifying one or more map features of the HD map data corresponding to the one or more objects of the road system; generating updated metadata of the identified one or more map features based on the observation data to reflect the updated confidence level of the identified one or more map features compared to a corresponding confidence level of the identified one or more map features in the HD map metadata; and providing the updated metadata for use by the autonomous driving system, wherein the updated metadata is provided to the autonomous driving system independently of the provision of the HD map data.

[0013] In some embodiments of the first aspect, for each of the identified one or more map features, if the observation data is consistent with the map feature, then generating updated metadata includes one or more of the following: increasing or maintaining the confidence level of the identified one or more map features; updating the confirmation date field in the metadata of the map feature to the date of the observation data; and updating the confirmation confidence field in the metadata of the map feature based on the confidence level associated with the observation data.

[0014] In some embodiments of the first aspect, for each of the identified one or more map features, if the observed data is inconsistent with the map feature, but the inconsistency is insufficient to meet the map change requirement for updating the HD map data, then generating updated metadata includes: reducing the confidence level of the map feature.

[0015] In some embodiments of the first aspect, for each of the identified one or more map features, if the observation data is inconsistent with the map feature, and the inconsistency is sufficient to satisfy the map change requirement for updating the HD map data, then the method further includes: using the observation data to determine changes in the object corresponding to the map feature; based on the determined changes, generating map change features describing the changes in the map feature to reflect the determined changes in the corresponding object; combining the map change features with other map change features of the identified one or more features to form map change data; and providing the map change data for use by the autonomous driving system, wherein the map change data is provided to the autonomous driving system independently of the provision of the HD map data. The map change data may be provided to the autonomous driving system along with the updated metadata.

[0016] According to a second aspect of the present invention, a server system is provided, the server system storing HD map data representing a road system having multiple objects, the HD map data including multiple map features representing the multiple objects of the road system, the server system further storing HD map metadata, the metadata including confidence levels of the HD map data for the multiple map features, the HD map data and the metadata being provided for use by an autonomous driving system in an autonomous vehicle, the server system including one or more processors arranged to: receive observation data of the road system, the observation data including one or more observations of the road system; identify one or more objects among the multiple objects associated with the observation data; identify one or more map features of the HD map data corresponding to the one or more objects of the road system; based on the observation data, generate updated metadata of the identified one or more map features to reflect the updated confidence level of the identified one or more map features compared to the corresponding confidence levels of the identified one or more map features in the HD map metadata; and provide the updated metadata for use by the autonomous driving system, wherein the updated metadata is provided to the autonomous driving system independently of the provision of the HD map data.

[0017] In some embodiments of the second aspect, the one or more processors may be arranged such that, for each of the identified one or more map features, if the observation data matches the map feature, then generating updated metadata includes one or more of the following: increasing or maintaining the confidence level of the identified one or more map features; updating the confirmation date field in the metadata of the map feature to the date of the observation data; and updating the confirmation confidence field of the metadata of the map feature based on the confidence level associated with the observation data.

[0018] In some embodiments of the second aspect, the one or more processors may be arranged such that, for each of the identified one or more map features, if the observed data is inconsistent with the map feature, but the inconsistency is insufficient to meet the map change requirement of updating the HD map data, then generating updated metadata includes: reducing the confidence level of the map feature.

[0019] In some embodiments of the second aspect, the one or more processors may be arranged such that, for each of the identified one or more map features, if the observation data is inconsistent with the map feature, and the inconsistency is sufficient to satisfy a map change requirement for updating the HD map data, then the one or more processors: use the observation data to determine a change in the object corresponding to the map feature; based on the determined change, generate a map change feature describing the change in the map feature to reflect the determined change in the corresponding object; combine the map change feature with other map change features of the identified one or more features to form map change data; and provide the map change data for use by the autonomous driving system, wherein the map change data is provided to the autonomous driving system independently of the provision of the HD map data. The map change data may be provided to the autonomous driving system along with the updated metadata.

[0020] In some embodiments of the first and second aspects, the HD map data and the HD map metadata may be based at least on sensor data from the HD map-drawing vehicle, wherein the observation data may be based on a data source other than the HD map-drawing vehicle.

[0021] In some embodiments of the first and second aspects, the observation data may include one or more of the following: data from a passenger vehicle equipped with sensors; observation reports provided by a person, such as a vehicle user; and data from an earthquake information service provider.

[0022] In some embodiments of the first and second aspects, the updated confidence level may be associated with the data source of the observed data.

[0023] In some embodiments of the first and second aspects, the updated metadata may further reflect the rate of change over time of the updated confidence level to be applied to the identified one or more map features.

[0024] In some embodiments of the first and second aspects, the observation data may include multiple observations related to a particular object, and the updated confidence level of the particular object may be based on statistical confidence levels associated with the multiple observations.

[0025] According to a third aspect of the invention, a computer-implemented method is provided at a client computer system in an autonomous vehicle, the client computer system including an autonomous driving system, the client computer system being arranged to receive and store HD map data representing a road system having a plurality of objects, the HD map data including a plurality of map features representing the plurality of objects of the road system, the client computer system being further arranged to receive and store HD map metadata, the metadata including confidence levels of the HD map data for the plurality of map features, the HD map data and the metadata being used by the autonomous driving system, the method comprising: receiving updated metadata of one or more map features of the plurality of map features of the HD map data, wherein the updated metadata is received independently of receiving the HD map data; processing the updated metadata to identify an updated map feature, the updated map feature being a map feature among one or more map features associated with a designated portion of the road system; and generating updated HD map data for the designated portion of the road system based on the updated metadata associated with the updated map feature, such that the autonomous driving system can use the updated HD map data.

[0026] In some embodiments of the third aspect, the method may further include distributing at least a portion of the updated HD map data to at least one electronic control unit in the vehicle.

[0027] In some embodiments of the third aspect, the method may further include sending a request for updated metadata to a server, wherein the updated metadata is received from the server in response to the request. The request may be a request for updated metadata covering the same geographic area as the HD map data stored in the client computer system. Alternatively, the request may be a request for updated metadata covering a sub-region of the geographic area covered by the HD map data stored in the client computer system. The request may indicate the sub-region by: explicitly indicating the sub-region; indicating the vicinity of the vehicle; and indicating the current location of the vehicle and the vehicle's driving history, enabling the server to determine an appropriate sub-region. Alternatively, in some embodiments, the request may be a request for updated metadata associated with a specified map feature among the plurality of map features.

[0028] In some embodiments of the third aspect, the method may further include: receiving map change data describing changes in one or more map features among the plurality of map features of the HD map data, wherein the map change data is received independently of receiving the HD map data; wherein the updated map features are further identified by processing the map change data to identify map features among one or more map features associated with the designated portion of the road system; and wherein the updated HD map data is generated further based on the map change data associated with the updated map features.

[0029] According to a fourth aspect of the present invention, a client computer system for an autonomous vehicle is provided, the client computer system including an autonomous driving system, the client computer system being arranged to receive and store HD map data representing a road system having a plurality of objects, the HD map data including a plurality of map features representing the plurality of objects of the road system, the client computer system being further arranged to receive and store HD map metadata, the metadata including confidence levels of the HD map data for the plurality of map features, the HD map data and the metadata being used by the autonomous driving system, the client computer system including one or more processors arranged to: receive updated metadata of one or more map features of the plurality of map features of the HD map data, wherein the updated metadata is received independently of the reception of the HD map data; process the updated metadata to identify updated map features, the updated map features being map features among one or more map features associated with a designated portion of the road system; and generate updated HD map data for the designated portion of the road system based on the updated metadata associated with the updated map features, such that the autonomous driving system can use the updated HD map data.

[0030] In some embodiments of the fourth aspect, the one or more processors may be further arranged to distribute at least a portion of the updated HD map data to at least one electronic control unit in the vehicle.

[0031] In some embodiments of the fourth aspect, the one or more processors may be further arranged to send a request for updated metadata to a server, wherein the updated metadata is received from the server in response to the request. The request may be a request for updated metadata covering the same geographic area as the HD map data stored in the client computer system. Alternatively, the request may be a request for updated metadata covering a sub-region of the geographic area covered by the HD map data stored in the client computer system. The request may indicate the sub-region by: explicitly indicating the sub-region; indicating the vicinity of the vehicle; and indicating the current location of the vehicle and the vehicle's driving history, enabling the server to determine an appropriate sub-region. Alternatively, in some embodiments, the request may be a request for updated metadata associated with a specific map feature among the plurality of map features.

[0032] In some embodiments of the fourth aspect, the one or more processors may be further arranged to: receive map change data describing changes in one or more map features of the plurality of map features of the HD map data, wherein the map change data is received independently of the reception of the HD map data; wherein the updated map feature is further identified by processing the map change data to identify one of the one or more map features associated with the designated portion of the road system; and wherein the updated HD map data is generated further based on the map change data associated with the updated map feature.

[0033] In some embodiments of the third and fourth aspects, the designated portion of the road system may be a part of the road system near the vehicle, wherein the proximity of the vehicle is determined based on the vehicle's current location. The proximity of the vehicle may be further determined based on the vehicle's predicted direction of travel or area.

[0034] In some embodiments of the first to fourth aspects, the HD map data may cover a specified geographic area and include multiple layers, each layer including different types of map data for the specified geographic area, wherein the HD map metadata and the updated metadata cover the same specified geographic area, such that they can be processed as layers of the HD map data.

[0035] In some embodiments of the first to fourth aspects, the size of the updated metadata may be one or more orders of magnitude smaller than the size of the HD map data.

[0036] According to a fifth aspect of the invention, a computer program is provided that, when executed by one or more processors, causes the one or more processors to perform the method according to the first aspect (or embodiments thereof) mentioned above or the third aspect (or embodiments thereof) mentioned above. The computer program may be stored on a computer-readable medium. Attached Figure Description

[0037] Embodiments of the invention will now be described by way of example with reference to the accompanying drawings, in which:

[0038] Figure 1 This illustration schematically depicts a client-server system architecture according to one embodiment.

[0039] Figure 2 This illustration depicts a server-side system used to generate map change data.

[0040] Figure 3 This illustration depicts a server-side system used to generate updated metadata.

[0041] Figure 4a and 4b Two examples of client-side systems are illustrated.

[0042] Figure 5 This illustrates the use of an online API server.

[0043] Figure 6 This illustration illustrates the methods implemented by the server used to generate map change data.

[0044] Figure 7 This illustrates the method implemented by the server for generating updated metadata.

[0045] Figure 8 This illustration depicts a client-side method for generating updated HD map data based on map change data for a specified portion of a road system.

[0046] Figure 9 This illustration schematically describes a client-side implementation for generating updated HD map data based on updated metadata of a specified portion of a road system. Detailed Implementation

[0047] Reality changes

[0048] The geospatial reality associated with road systems is constantly changing. This change in reality has several causes, such as:

[0049] • Changes in traffic regulations: For example, in March 2020, the speed limit on Dutch highways was changed from 120 / 130 km / h to 100 km / h during certain times of the day. Related practical changes included adding, removing, or altering traffic signs, as well as repainting markings on road surfaces.

[0050] • Wear and tear on road markings and pavement: This depends on the durability of asphalt and road paint, weather conditions, and intensity of use. Related real-world changes include road construction and / or repainting of road surfaces.

[0051] • Changes in traffic intensity: Such changes may necessitate the expansion or alteration of the road network. Therefore, the associated real-world changes include road construction.

[0052] • Precipitation: For example, rain and snow can cause traffic signs to become dirty or potholes to become stagnant. Related real-world changes include traffic sign maintenance activities (such as cleaning), which may involve minor, unintended directional changes to signs, and roadworks to repair potholes.

[0053] • Intentional vandalism: For example, graffiti, stickers, and / or shooting may damage traffic signs. Related real-world changes include the replacement of traffic signs.

[0054] • Earthquake: Earthquakes may cause displacement and / or damage to roads, traffic signs, traffic lights, etc. Related changes in reality include changes in the location of existing features and / or repair work on damaged roads.

[0055] Many real-world changes are spatially and temporally related, such as repainting road markings and traffic signs due to changes in speed limits. Real-world changes can also be periodic, such as repainting road markings as part of regular road maintenance. On highways, regular maintenance typically occurs every 4 to 8 years. This means that 12.5 to 25% of the road network is repainted annually. Some real-world changes are more frequent than others; for example, traffic sign changes due to speed limit changes are more frequent than traffic sign replacements due to vandalism.

[0056] Reality features change at a rate of approximately 5 to 20% per year. This means that 5 to 20% of map features need to be updated within a year. These changes are often unevenly distributed; for example, during major road works, substantial changes in reality features may occur in small areas within a relatively short period. After such road works are carried out, the rate of change over the same period can decrease significantly.

[0057] Observations on Real-world Changes

[0058] Observations of real-world changes can be derived from a range of sources, such as:

[0059] • High-quality survey vehicles.

[0060] • A large number of conventional passenger cars equipped with both position sensors and environmental sensors (especially cameras, RADAR and / or LIDAR).

[0061] • Active Community Input (ACI), which includes real-world observation reports provided by people (especially vehicle users).

[0062] • Geophysical information sources, such as in https: / / earthquake.usgs.gov / fdsnws / event / 1 / Available USGS (United States Geological Survey) earthquake hazard plans.

[0063] Real-world change observations derived from survey vehicles automatically acquire a quality index associated with them. This reduces the quality index associated with other data sources (e.g., the number of independent observations dependent on a specific real-world change, the accuracy / precision of the observations, the type of observation, etc.).

[0064] Overview

[0065] This application relates to a technique for providing map features for HD map clients, the map features providing an accurate and current representation of real-world features.

[0066] Currently, HD map compilers may use real-world observations from survey vehicles or passenger cars, for example, when generating new HD map data. This new HD map data is then distributed to HD map clients via a CDN. This means that even small changes in real-world features can lead to the compilation and distribution of large amounts of map data. This requires significant map compilation and distribution resources. The overhead can introduce latency in change aggregation when new map data is provided. Therefore, when an update is deemed necessary, new HD map data (i.e., HD map features) is intermittently distributed from the server side (where observation data is received) to the client side (i.e., the HD map client in the autonomous vehicle).

[0067] Additionally, including HD map quality metadata in HD map features increases the size of the HD map data (although this may be relatively small). If the HD map quality metadata is no longer considered accurate enough, new HD map data needs to be compiled. This means that inaccuracies in a small portion of map data can lead to the compilation and distribution of a larger amount of data. This increases map compilation and distribution resources. It also results in a relatively static representation of the HD map quality metadata, which may require some predetermined aging of the confidence indicators contained in the HD map quality metadata.

[0068] According to this application, map change data is generated on the server side and distributed to the HD map client independently of HD map features (i.e., independent of the HD map data itself). This significantly reduces the overhead associated with distributed updates. On the client side, map change data is received and processed to update relevant portions of the (older) HD map data stored in the vehicle. This may involve creating, updating, or removing HD map features and / or associated attributes. The updated map data is then used by the autonomous driving system.

[0069] Similarly, according to this application, updated metadata (which contains updated confidence levels for one or more map features) is generated on the server side and distributed to the HD map client independently of the HD map features (i.e., independent of the HD map data itself). This again significantly reduces the overhead associated with distributed updates. On the client side, the updated metadata is received and processed to update relevant portions of the (older) HD map data stored in the vehicle. The updated map data is then used by the autonomous driving system. Including the updated metadata as part of the updated map data means that the autonomous driving system can determine how best to weight the (older) HD map data and the (current) SDO data while driving.

[0070] Obviously, when any map feature change has an associated metadata update, these two aspects of this application (i.e., map change data and updated metadata) can be combined. However, it is also considered that map feature changes may occur without metadata updates, and metadata updates may occur without map feature changes.

[0071] System Architecture

[0072] Figure 1 A system architecture 100 according to one embodiment is illustrated schematically. The server side of architecture 100 includes an HD map server 110, and the client side includes a client computer system 150, which contains an HD map client 160 coupled to an electronic control unit (ECU) platform 170. The HD map client is further coupled to an HD map application 180 via a map feature adjustment module 190. The client side of architecture 100 can be considered as a client computer system (including one or more computers) in an autonomous vehicle. The autonomous vehicle has an Adaptive Digital Assistant (ADS).

[0073] HD map server 110 is a server system including one or more servers. HD map server 110 includes a first storage medium 120 (e.g., a database) storing map source data associated with multiple objects in a road system. The first storage medium is coupled to a map creation module 122, configured to generate map data based on the map source data. Map creation module 122 is coupled to a map compiler 124, configured to compile the map data into multiple map features representing multiple objects and associated quality indices. Map compiler 124 is coupled to both a map data service 126 and a map metadata service 128. Map data service 126 is configured to provide digital HD map data including multiple map features. As described above, the HD map data can be structured into layers of blocks. Map metadata service 128 is configured to provide map metadata including quality indices (or confidence levels) associated with the multiple map features of the HD map data. The HD map data and map metadata are suitable for use by an autonomous driving system in an autonomous vehicle.

[0074] HD map server 110 further includes a second storage medium 142 (e.g., a database) that stores observations of real-world changes associated with multiple objects in the road system. Real-world change observations are received from a coupled real-world change observation manager 140. The second storage medium 142 is also coupled to a real-world change detection module 144, configured to analyze the real-world change observations to detect real-world changes in one or more objects in the road system that meet the map-changing requirements for updating HD map data. The real-world change detection module 144 can generate a real-world change token representing the detected real-world change. The real-world change detection module 144 is coupled to a map change compiler 146, configured to compile the detected real-world change by determining the map features affected by the detected real-world change (i.e., map features associated with one or more changed objects). The map change compiler 146 generates map change data describing changes in relevant map features to reflect the detected real-world changes in one or more objects in the road system. The map change data consists of one or more map feature changes corresponding to the observed changes in one or more objects in the road system. Essentially, map change data can be viewed as capturing "what," "where," and "when" changes in reality. A map change compiler 146 is coupled to a map change service 148, which is configured to provide map change data.

[0075] The distribution mechanism for map change data (i.e., map change service 148) is separated from the distribution mechanism for HD map features (i.e., map data service 126). This allows map change data updates to occur at a much faster rate without simultaneously updating HD map features. Since map change data describes changes to HD map features, each map feature change describes the creation, alteration, or removal of an HD map feature.

[0076] exist Figure 1 In one embodiment, the HD map client 160 includes an HTTPS client 161, a client library 162, a map data validator 163, a persistent map data cache 164, a map interface adapter 165, and a controller 166. However, it will be understood that in alternative embodiments, the functionality of at least some of these modules is composable. The HTTPS client 161 is configured to receive HD map data (i.e., multiple map features) from a map data service 126. The HTTPS client 161 is further configured to receive map metadata from a map metadata service 128. The HTTPS client 161 is further configured to receive map change data from a map change service 148. Each of these sets of data can be received independently of the others, such that each set of data can be considered to have its own communication channel. The client library 162 is coupled to the HTTPS client 161, the map data validator 163, the persistent map data cache 164, and the map interface adapter 165. The map data validator 163 is configured to validate any received map data (e.g., HD map data, map change data, and / or map metadata). Once verified, any received map data is stored in the persistent map data cache 164.

[0077] The controller 166 of the HD map client 160 is coupled to the ECU platform 170. A map interface adapter 165 is coupled to the HD map application 180 via a map feature adjustment module 190. The map interface adapter 165 is configured to provide various data to the map feature adjustment module 190. For example, the map interface adapter 165 can provide HD map data (i.e., map feature data stored in a persistent map data cache 164) and real-time changes (i.e., map change data) to the map feature adjustment module 190. The map feature adjustment module 190 is configured to process the received data to identify map features in the map change data that are associated with a specified portion of the road system. The map feature adjustment module 190 then generates updated HD map data for the specified portion of the road system. The updated HD map data includes relevant portions of the HD map data updated according to the map change data. The map feature adjustment module 190 is then configured to provide the updated HD map data as a map client service to the HD map application 180. The updated HD map data is configured to be used by the ADS of an autonomous vehicle associated with the client side of architecture 100. Figure 1 ADS is not explicitly shown, but it is represented by modules such as controller 166, ECU platform 170 and HD map application 180.

[0078] Generation of initial HD map data and associated HD map metadata

[0079] Initial HD map data generation is performed at the HD map server 110 using map source data stored in the first storage medium 120. The initial HD map data is primarily generated based on data collected by HD map drawing vehicles equipped with high-quality location and vehicle environment sensors. Therefore, the collected data is stored in the first storage medium 120. (See above reference.) Figure 1As described, map creation module 122 and map compiler 124 generate HD map data, making it available via map data service 126. Similarly, map creation module 122 and map compiler 124 generate corresponding HD map metadata, making it available via map metadata service 128. The quality index associated with the data collected by the HD map-drawing vehicle is typically very high (typically 100%), and this will be reflected in the HD map metadata associated with the initial HD map data. Each map feature and attribute in the HD map data has an associated observation date, which is the data for the underlying data collected by the HD map-drawing vehicle. The observation date constitutes part of the HD map metadata. The HD map metadata also contains the confirmation date and confirmation confidence level for each map feature or attribute. The confirmation date is the date the observation is confirmed and is set to the same date as the observation date of the HD map-drawing vehicle data. The confirmation confidence level reflects the confidence level of the underlying data associated with the confirmation date. Therefore, the confirmation confidence level value is set to a value representing 100% confidence in the HD map-drawing vehicle data.

[0080] Generation of map change data

[0081] Figure 2 This describes a portion 200 of the HD map server 110 responsible for generating map change data, namely the reality change observation manager 140, the second storage medium 142, the reality change detection module 144, the map change compiler 146, and the map change service 126. Figure 2 Reality change sources 210 are also depicted. These are data sources from which observations of reality changes are received, but it will be understood that these data sources 210 do not actually constitute part of the reality change map server 200; rather, they provide input to the reality change map server 200. The data sources 210 used to generate map change data are typically secondary data sources (i.e., data sources other than vehicles used for HD map creation). Examples of secondary data sources are sensor-equipped passenger vehicles, observation reports provided by people (e.g., vehicle users), and earthquake information service providers. Other examples are satellite data sources, geophysical data sources, and road engineering information sources, etc. Therefore, as referenced above... Figure 1 As described, the Reality Change Observation Manager 140 organizes the data collected from all these secondary sources 210 and stores it all in the second storage medium 142 as a Reality Change Observation. Then, the Reality Change Detection Module 144 and the Map Change Compiler 146 generate map change data and make it available via the Map Change Service 126.

[0082] like Figure 6As shown, map change data can be generated according to method 600 implemented by a computer at a server system (e.g., HD map server 110). The server system stores HD map data representing road systems with multiple objects (e.g., see HD map data available via map data service 126). The HD map data includes multiple map features representing the multiple objects of the road system. The HD map data is suitable for use by an autonomous driving system in an autonomous vehicle.

[0083] Method 600 includes a first step S602 of receiving observation data of a road system. The observation data (e.g., observations of real-world changes stored in a second storage medium 142) includes one or more observations of the road system. As described above, the observation data can be received via a real-world change observation manager 140.

[0084] Method 600 includes a second step S604 of determining changes in one or more of a plurality of objects using observation data. As described above, changes in one or more objects can be determined by the reality change detection module 144.

[0085] Determining changes in one or more objects using observational data is typically based on a small number of real-world change observations stored in the second storage medium 142. However, the changes can also be statistical in nature and based on a large number of historical real-world change observations.

[0086] Determining changes in one or more objects using observational data may involve determining the absolute and / or relative positions and / or geometry and / or type and / or changes in the presence of one or more objects.

[0087] Determining changes to one or more objects using observation data can include identifying changes within one or more objects that satisfy map-changing requirements for updating HD map data. For example, identified changes might involve changes in position and / or relative position and / or geometry above a threshold level (e.g., an object moving more than 10 cm). Alternatively, any change involving the removal of an object or the addition of a new object can be considered to satisfy map-changing requirements. Similarly, changes in object type are considered to satisfy map-changing requirements; an example could be a previously identified object that was considered a road sign, but observation data now indicates that it is something other than a road sign.

[0088] As described above, the reality change detection module 144 can generate a reality change token representing the detected reality change. The reality change token can be based on a small number of reality change observations, but can also describe reality changes derived from a large amount of (historical) reality change information.

[0089] Method 600 includes a third step S606 of identifying one or more map features in HD map data corresponding to one or more objects in a road system. As described above, one or more map features may be identified by map transformation compiler 146.

[0090] Changes in one or more objects may be correlated. For example, the change could indicate a 10cm shift in a large number of objects (roads, signs, etc.) within a given area due to an earthquake. As previously mentioned, there are three geometric categories of map features: point features (e.g., traffic signs), line features (e.g., road boundaries), and area features (e.g., road surface areas). Therefore, area map features can be used to effectively represent changes affecting all objects in a given area. This means that the number of objects that have changed (i.e., the number of one or more objects) may be greater than the number of identified one or more features. Obviously, this is more efficient in terms of the amount of data required to represent changes.

[0091] Method 600 includes a fourth step S608 of generating map change data describing changes in one or more map features to reflect determined changes in one or more objects, based on determined changes and identified map features. As described above, the map change data may be generated by map change compiler 146.

[0092] As described above, map change data consists of one or more map change features (corresponding to each of one or more identified map features). Each map change feature describes the creation, change, or removal of HD map features or several HD map features (e.g., HD map features in an area).

[0093] As discussed above, changes in regional map features can concisely represent real-world changes associated with a region. Therefore, such changes can be distributed to HD map clients at a relatively low cellular network cost. Once received by the HD client, the regional map feature changes can still be processed to correlate the changes with relevant parts of the road system, allowing this information to be transmitted over vehicular networks using horizontal protocols such as ADASIS V2 / V3.

[0094] Map change data may include one or more replacement map features (e.g., X') to directly replace one or more map features (e.g., X) in HD map data, thereby describing changes to one or more map features. In this example, the map change data effectively provides more recent versions of one or more map features. Alternatively, map change data may include changes to one or more map features relative to HD map data stored in a server system, thereby describing changes to one or more map features. In other words, for map feature X in HD map data, map change data may indicate a change ΔX, which can be applied to the original map feature X to provide an updated map feature X', where X' = X + ΔX.

[0095] Map change data may include new or updated attributes of one or more map features. New or updated attributes may include one or more of the following: new or updated absolute and / or relative position and / or geometry and / or category and / or cryptographic hash of the map feature. For example, consider a map feature identified as a road sign in HD map data, but the original HD map-drawing vehicle data cannot determine the category of the road sign (e.g., because it was partially obscured during map drawing). In this case, new attributes defining the category of the road sign can be provided as part of the map change data. In the case of new or updated cryptographic hashes, this can be an encrypted hash of the map change data for a specific change feature, which can be used in fault-tolerant map implementations.

[0096] HD map data covers a specified geographic area. As previously described, HD map data can include multiple layers, each containing different types of map data for a specified geographic area. In this scenario, map change data can be generated to cover the same specified geographic area, allowing it to be processed as layers of HD map data. Map change data is an application-related model of geospatial reality changes and contains abstractions of these reality changes. The reality changes represented in the map change data are directly or indirectly related to the geospatial object representations in the HD map data. Therefore, implementing map change data as layers of HD map data that can be created, updated, and delivered independently is technically practical. For example, this layer implementation simplifies client-side data processing.

[0097] Method 600 includes a fifth step S610 of providing map change data for use by an autonomous driving system, wherein the map change data is provided to the autonomous driving system independently of the provision of HD map data. As described above, the map change data may be provided by map change service 148, which is independent of the provision of HD map data by map data service 126 and independent of the provision of HD map metadata by map metadata service 128.

[0098] Method 600 may further include the step of distributing map change data to one or more client computers. The map change data may be distributed by map change service 148, which is independent of the distribution of HD map data by map data service 126 and independent of the distribution of HD map metadata by map metadata service 128.

[0099] In one instance, prior to distribution, the map change data may be processed by a server system such that it contains only map change data associated with a specified portion of the road system. In other words, only a subset of the map change data (i.e., the portion associated with the specified portion of the road system) is sent to a specific client computer. This sending may occur in response to a request from a specific client computer. This is a “pull” data distribution method for map change data, as opposed to a “push” data distribution method, which sends data to all client computers as soon as it becomes available (e.g., according to TomTom’s AutoStream map delivery system). The request may be a request for map change data for a sub-region covering a geographic area covered by the map change data. The request may indicate the sub-region by explicitly specifying it. Alternatively, the request may indicate the sub-region by indicating the vicinity of a vehicle associated with the request. In a further alternative, the request may indicate the sub-region by indicating the vehicle’s current location and driving history, enabling the server system to determine the appropriate sub-region. In this case, method 600 further includes determining the sub-region based on the current location and driving history in response to receiving the request. In another instance, a request could be for map change data related to a specified map feature among multiple map features.

[0100] Regarding the "pull" distribution of map change data described above Figure 5 This diagram illustrates a suitable system architecture, comprising a map server 110, a map client 160, and an API server 500 (e.g., TomTom MC API). The map server 110 and API server 500 can be considered as parts of the same server system. Although the map server 110 and API server 500 are... Figure 5 While described as different servers, it will be understood that they can actually be represented within a single server. In a "push" distribution system, map server 110 can distribute map change data 510 to one or more map clients 160 when map change data becomes available. In a "pull" distribution system, map server 100 can instead send map change data 512 to an API server when map change data becomes available, and then each map client 160 can request map change data 514 from the API server when needed. In response to such requests, the relevant map change data can be sent back 514 to the requesting map client 160.

[0101] As discussed above, HD map-making vehicles can only observe a given road system object intermittently. Despite the increased frequency of HD map updates, a considerable time can still pass between a change in reality and the release of new HD map data. Meanwhile, many sensor-equipped passenger vehicles are capable of observing the same object. Therefore, it will be understood that a change in reality observed for a given object stored in the second storage medium 142 is typically more up-to-date (i.e., more current) than the HD map-making vehicle data stored in the first storage medium 120 for the same object. Furthermore, the size of map change data is typically several orders of magnitude smaller than the size of HD map data. Therefore, map change data can be generated and made available relatively frequently compared to HD map data and its associated HD map metadata. Thus, method 600 is able to make map change data readily available before a sufficiently high-quality HD map update can be delivered. In other words, according to method 600, the time between a change in reality and the delivery of relevant reality change information to the vehicle is typically short. Therefore, autonomous vehicles can become aware of a change in reality shortly after it is detected and take appropriate action, for example, by disabling automated functionality or adopting conservative driving behavior strategies.

[0102] As discussed above, map change data can be viewed as including one or more map feature changes. In other words, map change data consists of a set of map feature changes, each of the identified one or more map features. Below are some examples of map feature changes, including associated map attribute changes.

[0103] In the first example, the impact of a specific earthquake is considered. The area around the earthquake's epicenter is divided into several sub-regions, each with associated map attribute changes and confidence levels. Sub-regions are regional features within the map change data. A first map attribute change in one sub-region might indicate 'roads within the region may be damaged' and / or 'roads within the region may have shifted by more than 10 cm'. A second map attribute change in the sub-region might indicate a confidence level of 70%. A third map attribute change in the sub-region might indicate a change occurring between January 12, 2020, and January 15, 2020.

[0104] In the second example, we consider a change in the speed limit for a specific road segment. The map attribute change is associated with existing features of the HD map (i.e., typically part of a lane group, such as a lane within a lane group). The map attribute change can indicate a reduction in the speed limit, with an associated confidence level of 70%.

[0105] In the third example, traffic sign replacement is considered. Based on extensive historical observations, it is known that traffic sign replacement results in changes in the location and direction of 1% of the replaced traffic signs along roads of a specific road category in the Netherlands. This information can be captured as changes in regional map features within map change data. Since the age of the HD map data is known (e.g., based on the observation date given in the HD map metadata), the confidence level associated (downward) with the relevant traffic sign map features can be adjusted to more closely reflect current reality. This is closely related to the generation of updated metadata described in the next section.

[0106] The server system may further store HD map metadata, wherein the metadata includes confidence levels of HD map data for multiple map features. Map change data may also have varying degrees of specificity and may typically have associated confidence levels. As discussed in the overview section, the generation of map change data may be accompanied by the generation of updated metadata. In this case, method 600 further includes: (a) generating updated metadata for one or more identified map features based on observation data to reflect the updated confidence levels of one or more identified map features in the map change data compared to the corresponding confidence levels of the identified map features in the HD map metadata; and (b) providing the updated metadata for use by an autonomous driving system, wherein the updated metadata is provided to the autonomous driving system independently of the provision of the HD map data.

[0107] Map change data and updated metadata can be generated and provided concatenated (i.e., effectively simultaneously) with respect to the same observation data. Method 600 may then further include the step of distributing the map change data and updated metadata to one or more client computer systems. The distribution of the map change data and updated metadata can occur simultaneously. Simultaneous distribution may involve simultaneous distribution via different communication channels or simultaneous distribution via the same communication channel.

[0108] Observational data can include multiple observations associated with a specific object. In this case, the updated confidence level of a specific object can be based on the statistical confidence levels associated with multiple observations. This means that vehicles can apply statistical reality change information to continuously adjust the confidence level of map data related to the current reality.

[0109] The generation of updated metadata is discussed in more detail in the section titled "Generation of Updated Metadata".

[0110] In addition to the above references Figure 6 In addition to the method 600 described, this application also considers server systems configured to implement this method (e.g., see [link to application]). Figure 1 and 2Also considered are the corresponding computer programs and the computer-readable media storing said computer programs.

[0111] Generation of updated metadata

[0112] In addition to generating map change data, the HD map server 110 can also be used to generate updated metadata. Although the frequency of HD map data updates is increasing, the time between updates can still be considerable. Therefore, the HD map data and HD map metadata used by autonomous vehicles may be quite outdated. This application proposes using newer observation data to provide updated metadata related to the existing HD map data used by the vehicle. This allows the vehicle to determine the quality of the HD map data when relating it to the current reality, rather than when relating it to historical reality.

[0113] The table below provides exemplary metadata fields that can be updated in accordance with this application. These fields are exemplary and are not intended to be limiting in any way.

[0114]

[0115]

[0116]

[0117] The quality indices in the table above are simple integers, thus allowing for a concise representation of map quality metadata and enabling efficient use of cellular networks (for map updates).

[0118] Figure 3 This describes part 300 of the HD map server 110 responsible for generating updated metadata, namely the first storage medium 120 and the second storage medium 142. Figure 3 It also describes a third storage medium 310 for storing map quality associations, a map quality metadata compiler 312, and a map quality metadata service 314. Figure 3 These additional components also exist Figure 1 The HD map server contains images of the map, but for simplicity, they have been omitted from the map.

[0119] As previously described, a first storage medium 120 stores map source data associated with multiple objects in the road system, and a second storage medium 142 stores observations of real-world changes associated with the multiple objects in the road system. These observations may include observations indicating the presence of real-world changes and observations indicating the absence of real-world changes. A third storage medium 310 (e.g., a database) stores map quality associations that may indicate confidence levels associated with different data sources stored in the first and second storage media 120, 142. Map quality associations may also indicate the rate of change of the confidence levels to be applied over time for different data sources. The three storage media 120, 142, 310 are coupled to a map quality metadata compiler 312, which is configured to compile updated metadata for one or more map features to reflect the updated confidence levels of the same map features compared to the corresponding confidence levels of the one or more map features in the HD map metadata. The compilation takes into account various input data sources. The map quality metadata compiler 312 is coupled to a map quality metadata service 314, which is configured to provide updated metadata.

[0120] like Figure 7 As shown, updated metadata can be generated by a method 700 implemented by a computer at a server system (e.g., HD map server 110 or map quality metadata server 300). The server system stores HD map data representing a road system with multiple objects (e.g., see HD map data available via map data service 126). The HD map data includes multiple map features representing the multiple objects of the road system. The server system further stores HD map metadata (e.g., see HD map metadata available via map metadata service 128). The HD map metadata includes confidence levels of the HD map data for the multiple map features. The HD map data and metadata are suitable for use by an autonomous driving system in an autonomous vehicle.

[0121] At least one of the multiple map features may have one or more associated attributes, and the HD map metadata of at least one map feature may include the confidence level of one or more attributes.

[0122] Confidence levels can be correlated with the level of accuracy associated with the data. For example, vehicles depicted on HD maps will be observed at a high level of accuracy, so the confidence level of the associated map features is typically higher than that of map features derived from lower-accuracy data sources.

[0123] Method 700 includes a first step S702 of receiving observation data of a road system. The observation data includes one or more observations of the road system.

[0124] HD map data and HD map metadata may be based at least on sensor data from the HD map drawing vehicle (i.e., map source data in the first storage medium 120), and observation data may be based on data sources other than the HD map drawing vehicle (i.e., observations of real-world changes in the second storage medium 142).

[0125] The observation data (i.e., observations of real-time changes in the second storage medium 142) may include one or more of the following: data from a passenger vehicle equipped with sensors, observation reports provided by a person such as a vehicle user, and data from an earthquake information service provider.

[0126] Method 700 includes a second step S704 of identifying one or more objects from a plurality of objects associated with the observation data. The one or more objects may be identified by the map quality metadata compiler 312.

[0127] Method 700 includes a third step S706 of identifying one or more map features in HD map data corresponding to one or more objects in the road system. The one or more features may be identified by the map quality metadata compiler 312.

[0128] Method 700 includes a fourth step S708, which generates updated metadata for one or more identified map features based on observation data to reflect the updated confidence level of the identified map features compared to the corresponding confidence level of the identified map features in the HD map metadata. As described above, the updated metadata may be generated by map quality metadata compiler 312.

[0129] The updated confidence level can be correlated with the data source of the observed data. As described above, this can be achieved by referencing map quality correlations stored in the third storage medium 310.

[0130] Updated metadata can also reflect the rate of change over time of the updated confidence level to be applied to one or more identified map features. In other words, updated metadata indicates the potential change over time relative to the observation time of one or more identified map features.

[0131] Observational data may include multiple observations related to a particular object. In this case, the updated confidence level of a particular object may be based on the statistical confidence levels associated with multiple observations.

[0132] The generated updated metadata can be further based on the HD map metadata associated with the HD map data (i.e., the latest HD map data provided by map data service 126).

[0133] HD map data covers a specified geographic area. As previously described, HD map data can comprise multiple layers, each containing different types of map data for the specified geographic area. In this scenario, both HD map metadata and updated metadata cover the same specified geographic area, allowing them to be treated as layers of HD map data. HD map data is a geospatial reality model relevant to the application and contains abstractions of real-world objects. Updated metadata is directly or indirectly related to one or more features represented in the HD map data. Therefore, implementing updated metadata as a layer of HD map data that can be created, updated, and delivered independently is technically practical. For example, this layer implementation simplifies client-side data processing.

[0134] For each of the identified map features, if the observed data is consistent with the map feature, generating updated metadata may include one or more of the following: (a) increasing or maintaining the confidence level of the identified map feature, (b) updating the confirmation date field in the metadata of the map feature to the date of the observed data, and (c) updating the confirmation confidence field in the metadata of the map feature based on the confidence level associated with the observed data. This describes how to handle situations where reality has not changed. In this case, confirmation is generated that the map features still reflect reality. Periodically (the frequency depends on typical reality change behavior), confirmations of these feature associations and attribute associations are distributed via updated metadata, for example, the confirmation date and confirmation confidence may be updated. Autonomous vehicles may consider confirmation information when determining the quality of features and attributes. Where the observed data has sufficiently high quality, the confirmation confidence may be updated to 100%. In such cases, the observation date is also updated. The confirmation date indicates the latest date of the observed data, and its confirmed map features still correctly represent the associated objects of the road system. The confirmation confidence level indicates the level of confidence associated with the observed data, confirming that the map feature still correctly represents the associated objects in the road system. As mentioned in the previous table, there may be several different confirmation confidence levels associated with a given map feature or attribute. Furthermore, if no confirmatory observation data exists, the confirmation date and confirmation confidence level may be empty fields.

[0135] Alternatively, if the observed data is inconsistent with the map features, and the inconsistency is sufficient to satisfy the map change requirement for updating HD map data, then method 700 further includes: (a) using the observed data to determine changes in objects corresponding to the map features; (b) based on the determined changes, generating map change features describing the changes in the map features to reflect the determined changes in the corresponding objects; (c) combining the map change features with other map change features of one or more identified features to form map change data; and (d) providing the map change data for use by an autonomous driving system, wherein the map change data is provided to the autonomous driving system independently of the provision of HD map data. In other words, this involves a combination of updated metadata and change map data. This describes how to handle situations where reality has changed. Generally, change map data is only provided when the change is large enough (or sufficiently certain) to warrant a change. In this case, change information is generated and delivered using map change data, as described in previous sections. Autonomous vehicles cannot rely on features / attributes in HD map data for which it is sufficiently obvious that the associated reality has changed. At some point after the reality has changed, sufficient sensor-derived observations will be available to provide associated map change data (e.g., via map change service 148). This map change data may have a quality level associated with the crowdsourced observations and will therefore be associated with an appropriate quality index for the crowdsourced data. Later, after an HD map-drawing vehicle visits the changed location, a new version of the HD map data may be compiled based on data from the HD map-drawing vehicle (e.g., again via map compiler 124) and will therefore be associated with an appropriate quality index (e.g., 100%) for the HD map-drawing vehicle data. The map change data and updated metadata may be generated and provided in concatenation (i.e., effectively simultaneously) with respect to the same observation data. Subsequently, method 700 may further include the step of distributing the map change data and updated metadata to one or more client computer systems. The distribution of the map change data and updated metadata may occur simultaneously. Co-distribution may involve simultaneous distribution via different communication channels or simultaneous distribution via the same communication channel.

[0136] In a further alternative, if the observed data is inconsistent with the map features, but the inconsistency is insufficient to meet the map change requirements for updating HD map data (i.e., no map change data is generated for the map features), then generating updated metadata may include lowering the confidence level of the map features. Therefore, if the change is not large enough (or uncertain enough) to guarantee a change, then no changed map data is generated, and the updated metadata can instead be used to lower the confidence level of the relevant map features.

[0137] Method 700 includes a fifth step S710 of providing updated metadata for use by an autonomous driving system, wherein the updated metadata is provided to the autonomous driving system independently of the provision of HD map data. As described above, the updated metadata may be provided by map quality metadata service 314.

[0138] As discussed above, HD map-drawing vehicles can only intermittently observe a given road system object. Meanwhile, many sensor-equipped passenger vehicles can observe the same object. These observations may indicate that the object is still well represented by the map features of the HD map data, or conversely, that the object is no longer well represented by the map features of the HD map data. Therefore, it will be understood that observations of real-world changes for a given object stored in the second storage medium 142 are generally more up-to-date (i.e., more current) than HD map-drawing vehicle data for the same object stored in the first storage medium 120. Furthermore, the size of the updated metadata is generally several orders of magnitude smaller than the size of the HD map data. Therefore, the updated metadata can be generated and available relatively frequently compared to the HD map data and its associated HD map metadata. Thus, method 700 is able to make the updated metadata readily available before sufficient quality HD map updates can be delivered. Therefore, shortly after relevant observations are made, the autonomous vehicle can be informed of the updated metadata (e.g., confirmation can be provided to the autonomous vehicle to avoid increasing uncertainty over time without new map updates) and appropriate actions can be taken, such as by disabling / enabling automation functionality or adopting more or less conservative driving behavior strategies.

[0139] Method 700 may further include the step of distributing the updated metadata to one or more client computers. The updated metadata may be distributed by map quality metadata service 314, which is independent of the distribution of HD map data by map data service 126 and independent of the distribution of HD map metadata by map metadata service 128.

[0140] In one instance, prior to distribution, the updated map metadata is processed by the server system, resulting in a map containing only the updated metadata associated with a specified portion of the road system. In other words, only a subset of the updated metadata (i.e., the portion associated with the specified portion of the road system) is sent to a specific client computer. This sending can occur in response to a request from a specific client computer. This is a "pull" data distribution method for map change data, as opposed to a "push" data distribution method, which sends data to all client computers as it becomes available (according to the TomTom Automated Streaming Map Delivery System). See also Figure 5The above description relates to implementations of "push" and "pull" distribution systems. A request may be a request for updated metadata for a sub-region covering a geographic area covered by updated metadata. The request may indicate the sub-region by explicitly specifying it. Alternatively, the request may indicate the sub-region by indicating the vicinity of a vehicle associated with the request. In a further alternative, the request may indicate the sub-region by indicating the vehicle's current location and driving history, enabling the server system to determine the appropriate sub-region. In this case, method 700 further includes determining the sub-region based on the current location and driving history in response to receiving the request. In another instance, the request may be a request for updated metadata associated with a specific map feature among multiple map features.

[0141] In addition to the above references Figure 7 In addition to the method 700 described, this application also considers server systems configured to implement this method (e.g., see [link to application]). Figure 1 and 3 Also considered are the corresponding computer programs and the computer-readable media storing said computer programs.

[0142] Client-side processing of map change data

[0143] Referenced Figure 1 The client computer system 150 describes the client side of the system to a certain extent. For example, the map interface adapter 165 can provide HD map data (i.e., map feature data stored in the persistent map data cache 164) and reality changes (i.e., map change data) to the map feature adjustment module 190. The map feature adjustment module 190 is configured to process the received data to identify map features in the map change data that are associated with a specified portion of the road system. The map feature adjustment module 190 then generates updated HD map data for the specified portion of the road system. The updated HD map data contains the relevant portion of the HD map data updated according to the map change data. The map feature adjustment module 190 is then configured to provide the updated HD map data as a map client service to the HD map application 180. The updated HD map data is configured to be used by the ADS of the autonomous vehicle associated with the client side of architecture 100. Figure 1 ADS is not explicitly shown, but it is embodied by modules such as controller 166, ECU platform 170, and HD map application 180. Reference will now be made to... Figure 4a and 4b Let's discuss further details.

[0144] Figure 4a An embodiment depicting multiple HD map applications 180 associated with the same map feature adjustment module 190 is described.

[0145] Figure 4b An alternative embodiment is depicted in which each ECU platform 170 within the autonomous vehicle has its own associated map feature adjustment module 190 and HD map application 180. For example, Figure 4b The diagram depicts a first ECU platform 170a with a first map feature adjustment module 190a and a first HD map application 180a, and a second ECU platform 170b with a second map feature adjustment module 190b and a second HD map application 180b. This arrangement can be advantageous when different ECU platforms 170 require access to different areas of map data (i.e., different portions of the road system are specified for the first and second ECUs 170a and 170b). For example, the first ECU might be associated with automatic parking, which requires access to a relatively localized area of ​​map data around the vehicle. Conversely, the second ECU might be associated with autonomous driving (lane control) on highways, which requires access to a larger area of ​​road ahead of the vehicle.

[0146] like Figure 8 As shown, updated HD map data can be generated according to method 800 implemented by a computer at a client computer system (e.g., client computer system 150). The client computer system includes an autonomous driving system. The client computer system is arranged to receive and store HD map data representing a road system having multiple objects (e.g., see HD map data available via map data service 126). The HD map data includes multiple map features representing the multiple objects of the road system. The HD map data is suitable for use by the autonomous driving system.

[0147] Method 800 includes a first step S802 of receiving (e.g., via HTTPS client 161) map change data describing changes in one or more map features among a plurality of map features of HD map data. The map change data is received independently of the reception of the HD map data.

[0148] Method 800 includes a second step S804 of processing (e.g., via map feature adjustment module 190) map change data to identify updated map features, which are map features among one or more map features associated with a specified portion of the road system.

[0149] It is worth noting that this processing step can occur to a considerable extent after map change data is received (e.g., in a "push" distribution model of map change data). Alternatively, if map change data is received in response to a request from a client computer system (i.e., in a "pull" distribution model), then the processing step is likely to occur directly after the requested map change data is received.

[0150] A designated portion of the road system may be part of the road system near the vehicle, where the vehicle's proximity is determined based on the vehicle's current location. The vehicle's proximity can be further determined based on the predicted direction or area of ​​the vehicle's travel. In other words, identifying portions of map change data associated with the vehicle's proximity allows for appropriate processing of the data before it is distributed to the ECUs using the map data via the vehicle network using a line-of-sight protocol (e.g., ADASIS V2, V3). Specifically, the map data needs to be associated with road segments so that it can be transmitted using a line-of-sight protocol. As previously described, map change data may be associated with point, line, and / or area map features. Therefore, it is necessary to identify which of these point, line, and / or area map features in the map change data are associated with a specific road segment (i.e., a designated portion of the road system). Roads within changes in map area features in the map change data inherit subsequent real-world change information associated with the road from these map area features. This processing occurs before in-vehicle distribution using the applied line-of-sight protocol. In other words, changes (e.g., map area features shifted in direction relative to satellite positioning due to earthquakes) are processed first (e.g., in map feature adjustment module 190). If a request for HD map features is received from the ECU, the map feature data (i.e., HD map data) (in the HD map client 160) is retrieved and passed along with map change data to the map feature adjustment module 190. The map feature adjustment module 190 uses the map change data of the seismic map area features to identify the changes that need to be made to the HD map data before the updated HD map data is sent to the ECU (see below).

[0151] It is worth noting that applying map change data to the stored HD map data while the HD map data is stored in the persistent map data cache 164 would disrupt the independence of the two data streams. Therefore, it is desirable to store the original (i.e., original / unprocessed) HD map data (and HD map metadata) in the persistent data cache 164. Alternatively (where the designated portion of the road system is the entire road system), the entire HD map data and the changed map data can be processed to obtain updated HD map data for the entire road system. This updated HD map data needs to be stored separately from the original HD map data from which the requested map features are derived. This variant is suboptimal because it doubles the required storage in the persistent map data cache 164, even when only a small number of changes are represented in the map change data. Therefore, it is preferable that the designated portion of the road system is a relatively small part of the entire road system (e.g., near the vehicle), and updated HD map data is generated as needed for various ECUs.

[0152] Method 800 includes a third step S806, which generates (e.g., via map feature adjustment module 190) updated HD map data for a specified portion of the road system based on map change data associated with updated map features, so that the autonomous driving system can use the updated HD map data.

[0153] Method 800 may further include distributing at least a portion of the updated HD map data to at least one electronic control unit in the vehicle.

[0154] Regarding the above relative to Figure 5 In the described API server 500 embodiment, method 800 may further include sending a request for map change data to a server (e.g., API server 500 of a server system), and receiving map change data from the server in response to the request. The request may be a request for map change data covering the same geographic area as HD map data stored in the client computer system. Alternatively, the request may be a request for map change data covering a sub-region of a geographic area covered by HD map data stored in the client computer system. The request may indicate the sub-region by: (a) explicitly indicating the sub-region, (b) indicating the vicinity of a vehicle, and (c) indicating the current location of the vehicle and the vehicle's travel history, enabling the server to determine the appropriate sub-region. In a further alternative, the request may be a request for map change data related to a specific map feature among a plurality of map features.

[0155] While map change data for a sub-region can be requested, this type of model cannot be applied to actual HD map data (containing map feature data) because map features may contain links to other map features within the HD map data. Therefore, it is necessary to have a dataset of the entire HD map data to ensure the existence of linked data. In contrast, map change data does not contain links between map feature changes, so only a portion of the map change data can be processed. This makes it feasible to implement an API model using map change data. Therefore, map change data for a specified map area can be retrieved, processed, and used for streaming editing of the original HD map data.

[0156] As previously mentioned, the map change data and updated metadata aspects of this application can be combined. In this regard, the client computer system can be further configured to receive and store HD map metadata. The metadata includes confidence levels of multiple map features in the HD map data. In this case, method 800 may further include receiving updated metadata of one or more map features from the multiple map features of the HD map data, wherein the updated metadata is received independently of the receipt of the HD map data. Updated map features are further identified by processing the updated metadata to identify map features among one or more map features associated with a specified portion of the road system. Updated HD map data is generated further based on the updated metadata associated with the updated map features.

[0157] Therefore, method 800 is able to make good use of map change data before receiving HD map updates. In other words, according to method 800, the time between a change in reality and the vehicle receiving relevant information about that change is typically short. Thus, autonomous vehicles can become aware of a change in reality shortly after it is detected and take appropriate action, such as disabling automated features or adopting conservative driving behavior strategies.

[0158] In addition to the above references Figure 8 In addition to the method 800 described, this application also considers client computer systems configured to implement this method (e.g., see [reference 800]). Figure 1 and 4a (To 4b). Also considered are the corresponding computer programs and the computer-readable media storing said computer programs.

[0159] Client processing of updated metadata

[0160] Referenced Figure 1The client computer system 150 describes the client side of the system to a certain extent. As mentioned, the map interface adapter 165 is configured to provide various data to the map feature adjustment module 190. Regarding the client processing of updated metadata, the map interface adapter 165 can provide HD map data (such as received from map data service 126 and stored in permanent map data cache 164), HD map metadata (such as received from map metadata service 128 and stored in permanent map data cache 164), updated metadata (such as received from map quality metadata service 314 and stored in permanent map data cache 164), and any associated reality changes (i.e., map change data such as received from map change service 148 and stored in permanent map data cache 164). The map feature adjustment module 190 is configured to process the received data to identify map features in the updated metadata associated with a specified portion of the road system. It can also identify corresponding map features in the map change data. The map feature adjustment module 190 then generates updated HD map data for the specified portion of the road system. The updated HD map data includes relevant portions of the HD map data updated based on updated metadata (and any related map change data). The map feature adjustment module 190 is then configured to provide the updated HD map data as a map client service to the HD map application 180. The updated HD map data is configured to be used by the ADS of the autonomous vehicle associated with the client side of architecture 100. The ADS is not in... Figure 1 It is explicitly shown, but is embodied by modules such as controller 166, ECU platform 170, and HD map application 180. Also, see previous chapters. Figure 4a and 4b The description.

[0161] like Figure 9 As shown, updated HD map data can be generated according to method 900 implemented by a computer at a client computer system (e.g., client computer system 150). The client computer system includes an autonomous driving system. The client computer system is configured to receive and store HD map data representing a road system with multiple objects (e.g., see HD map data available via map data service 126). The HD map data includes multiple map features representing the multiple objects of the road system. The client computer system is further configured to receive and store HD map metadata. The metadata includes confidence levels of the HD map data for the multiple map features. The HD map data and metadata are suitable for use by the autonomous driving system.

[0162] Method 900 includes a first step S902 of receiving (e.g., via HTTPS client 161) updated metadata of one or more map features from a plurality of map features of HD map data. The updated metadata is received independently of the receipt of the HD map data.

[0163] Method 900 includes a second step S904 of processing (e.g., via map feature adjustment module 190) updated metadata to identify updated map features, said updated map features being map features among one or more map features associated with a specified portion of the road system.

[0164] It is worth noting that this processing step can occur to a considerable extent after the updated metadata is received (e.g., in a "push" distribution model with updated metadata). Alternatively, if the updated metadata is received in response to a request from a client computer system (i.e., in a "pull" distribution model), then the processing step is likely to occur directly after the requested updated metadata is received.

[0165] A designated portion of the road system can be part of the road system near the vehicle, where the vehicle's proximity is determined based on the vehicle's current location. The vehicle's proximity can be further determined based on the predicted direction or area of ​​the vehicle's travel. In other words, identifying portions of updated metadata associated with the vehicle's proximity allows for appropriate processing of the data before it is distributed to the ECUs using the applied map data via the vehicle network using a line-of-sight protocol (e.g., ADASIS V2, V3). Specifically, the map data needs to be associated with road segments so that it can be transmitted using a line-of-sight protocol. As previously described, updated metadata may be associated with point, line, and / or area map features. Therefore, it is necessary to determine which of these point, line, and / or area map features in the updated metadata are associated with a specific road segment (i.e., a designated portion of the road system). Roads within map area features in the updated metadata inherit subsequently updated metadata associated with roads from these map area features. This processing is performed before in-vehicle distribution using the applied line-of-sight protocol.

[0166] It is worth noting that applying updated metadata to the stored HD map metadata while the HD map data is stored in the persistent map data cache 164 would disrupt the independence of the two data streams. Therefore, it is desirable to store the original (i.e., the original / unprocessed) HD map metadata in the persistent data cache 164. Alternatively (where the designated portion of the road system is the entire road system), the entire HD map metadata and the updated metadata can be processed to obtain updated HD map data for the entire road system. This updated HD map data needs to be stored separately from the original HD map data and HD map metadata. This variant is suboptimal because it doubles the amount of metadata required to be stored in the persistent map data cache 164, even when only minor changes are represented in the updated metadata. Therefore, it is preferable that the designated portion of the road system is a relatively small part of the entire road system (e.g., near the vehicle), and updated HD map data is generated as needed for various ECUs.

[0167] Method 900 includes a third step S906, which generates (e.g., via map feature adjustment module 190) updated HD map data for a specified portion of the road system based on updated metadata associated with the updated map features, so that the autonomous driving system can use the updated HD map data.

[0168] Method 900 may further include distributing at least a portion of the updated HD map data to at least one electronic control unit in the vehicle.

[0169] Therefore, the client computer system has a module (e.g., map feature adjustment module 190) that first processes HD map quality metadata (i.e. updated metadata) and then uses it to insert the updated quality attributes into the HD map features requested by the HD map application (180) in the vehicle.

[0170] Regarding the above relative to Figure 5The described API server 500 embodiment, method 900 may further include sending a request for updated metadata to a server (e.g., API server 500 of a server system), and receiving updated metadata from the server in response to the request. The request may be a request for updated metadata covering the same geographic area as HD map data stored in the client computer system. Alternatively, the request may be a request for updated metadata covering a sub-region of a geographic area covered by HD map data stored in the client computer system. The request may indicate the sub-region by: (a) explicitly indicating the sub-region, (b) indicating the vicinity of a vehicle, and (c) indicating the current location of the vehicle and the vehicle's travel history, enabling the server to determine the appropriate sub-region. In a further alternative, the request may be a request for updated metadata associated with a specific map feature among a plurality of map features.

[0171] While updated metadata for a sub-region can be requested, this model cannot be applied to actual HD map data (containing map feature data) because map features may contain links to other map features within the HD map data. Therefore, it is necessary to have a dataset of the entire HD map data to ensure the existence of linked data. In contrast, updated metadata does not contain links between metadata features, so only a portion of the updated metadata can be processed. This makes it feasible to implement an API model incorporating updated metadata. Therefore, updated metadata for a specified map region can be retrieved, processed, and used for streaming editing of the original HD map metadata.

[0172] As previously mentioned, the map change data and updated metadata aspects of this application can be combined. In this regard, method 900 may further include receiving map change data describing changes in one or more map features among a plurality of map features of HD map data, wherein the map change data is received independently of the reception of the HD map data. Updated map features are further identified by processing the map change data to identify map features among one or more map features associated with a specified portion of the road system. Updated HD map data is generated further based on the map change data associated with the updated map features.

[0173] As mentioned in the section on the generation of updated metadata, metadata may include observation date, confirmation date, and confirmation confidence fields. These fields allow the autonomous vehicle's ADS to apply change statistics to continuously correct for map quality indicators of the changing differences between the current time and the time of the HD map-based observation. This enables the ADS to use HD map data and metadata, which provides a more accurate representation of the current reality. Therefore, when combining SDO and map data, the ADS has updated metadata to weight the relative inputs from these two key data sources. The ADS uses the updated metadata to determine confidence indicators of the representation of stationary geospatial objects in the environmental model. Thus, the autonomous vehicle can be informed of the updated metadata shortly after relevant observations are made (e.g., confirmation can be provided to the autonomous vehicle to avoid increasing uncertainty over time without new map updates) and can take appropriate action, such as disabling / enabling automated functionality or adopting more or less conservative driving behavior strategies.

[0174] In addition to the above references Figure 9 In addition to the method 900 described, this application also considers client computer systems configured to implement this method (e.g., see [reference 1]). Figure 1 and 4a (To 4b). Also considered are the corresponding computer programs and the computer-readable media storing said computer programs.

[0175] Revise

[0176] It will be understood that the described method has been shown as individual steps performed in a specific order. However, those skilled in the art will understand that these steps can be combined or performed in different orders while still achieving the desired result.

[0177] It will be understood that embodiments of the present invention can be implemented using various different information processing systems. Specifically, although the accompanying drawings and discussion provide exemplary computing systems and methods, these are presented merely to provide useful reference in discussing various aspects of the invention. Embodiments of the invention can be implemented on any suitable data processing device, such as a personal computer, laptop computer, personal digital assistant, mobile phone, set-top box, television, server computer, etc. Of course, for the purposes of discussion, the description of the systems and methods has been simplified, and it is only one of many different types of systems and methods that can be used in embodiments of the invention. It will be understood that the boundaries between logic blocks are merely illustrative, and alternative embodiments may combine logic blocks or elements, or functional alternatives may be applied to various logic blocks or elements.

[0178] It will be understood that the functionality mentioned above can be implemented as one or more corresponding modules in hardware and / or software. For example, the functionality mentioned above can be implemented as one or more software components for execution by the system's processor. Alternatively, the functionality mentioned above can be implemented as hardware, such as on one or more field-programmable gate arrays (FPGAs) and / or one or more application-specific integrated circuits (ASICs) and / or one or more digital signal processors (DSPs) and / or one or more graphics processing units (GPUs) and / or other hardware arrangements. The method steps contained herein or implemented in the flowcharts described above can each be implemented by a corresponding module; multiple method steps contained herein or implemented in the flowcharts described above can be implemented together by a single module.

[0179] It will be understood that whenever embodiments of the present invention are implemented by a computer program, one or more storage media and / or one or more transmission media storing or carrying the computer program constitute aspects of the present invention. A computer program may have one or more program instructions or program code that, when executed by one or more processors (or one or more computers), implement embodiments of the present invention. As used herein, the term "program" may be a sequence of instructions designed to execute on a computer system and may include subroutines, functions, procedures, modules, object methods, object implementations, executable applications, applets, service programs, source code, object code, bytecode, shared libraries, dynamic link libraries, and / or other sequences of instructions designed to execute on a computer system. Storage media may be disks (e.g., hard disk drives or floppy disks), optical disks (e.g., CD-ROMs, DVD-ROMs, or Blu-ray discs) or memory (e.g., ROMs, RAMs, EEPROMs, EPROMs, flash memory, or portable / removable memory devices), etc. Transmission media may be communication signals, data broadcasts, communication links between two or more computers, etc.

[0180] Although preferred embodiments of the invention have been described, it should be understood that these are merely examples and various modifications are contemplated.

Claims

1. A computer-implemented method at a server system, the server system storing HD map data representing a road system having multiple objects, the HD map data including multiple map features representing the multiple objects of the road system, the server system further storing HD map metadata, the metadata including confidence levels of the HD map data for the multiple map features, the HD map data and the metadata being provided for use by an autonomous driving system in an autonomous vehicle, the method comprising: Receive observation data of the road system, the observation data including one or more observations of the road system; Identify one or more of the plurality of objects associated with the observed data; Identify one or more map features in the HD map data corresponding to one or more objects in the road system; Based on the observation data, updated metadata for one or more identified map features is generated to reflect the updated confidence level of the one or more identified map features compared to the corresponding confidence level of the identified map features in the HD map metadata, wherein the updated confidence level is associated with the confidence level of the data source, and the observation data is received from the data source. and The updated metadata is provided to the autonomous driving system for use, wherein the updated metadata is provided to the autonomous driving system independently of the provision of the HD map data, and independently of the update of the HD map metadata of the identified one or more map features using the updated metadata, and the provision of the updated HD map metadata.

2. The method of claim 1, wherein the HD map data and the HD map metadata are based at least on sensor data from the HD map drawing vehicle, and wherein the observation data is based on a data source other than the HD map drawing vehicle.

3. The method according to claim 1 or claim 2, wherein the observation data includes one or more of the following: Data from passenger vehicles equipped with sensors; Observation reports provided by people; and Data from earthquake information service providers.

4. The method of claim 1 or claim 2, wherein the updated metadata further reflects the rate of change over time of the updated confidence level to be applied to the identified one or more map features.

5. The method of claim 1 or claim 2, wherein the observation data comprises a plurality of observations related to a particular object, and wherein the updated confidence level of the particular object is based on a statistical confidence level associated with the plurality of observations.

6. The method according to claim 1 or claim 2, wherein the HD map data covers a specified geographic area and includes multiple layers, each layer including different types of map data of the specified geographic area, and wherein the HD map metadata and the updated metadata cover the same specified geographic area, such that they can be processed as layers of the HD map data.

7. The method of claim 1 or claim 2, wherein the size of the updated metadata is several orders of magnitude smaller than the size of the HD map data.

8. The method of claim 1 or claim 2, wherein for each of the identified map features, if the observation data matches the map feature, then generating updated metadata includes one or more of the following: Increase or maintain the confidence level of the identified one or more map features; Update the confirmation date field in the metadata of the map feature to the date of the observation data; and Based on the confidence level associated with the observed data, update the confirmation confidence field of the metadata of the map feature.

9. The method of claim 1 or claim 2, wherein for each of the identified one or more map features, if the observed data is inconsistent with the map feature, but the inconsistency is insufficient to meet the map change requirement for updating the HD map data, then generating updated metadata includes: Reduce the confidence level of the map features.

10. The method of claim 1 or claim 2, wherein for each of the identified one or more map features, if the observed data is inconsistent with the map feature, and the inconsistency is sufficient to satisfy the map change requirement for updating the HD map data, then the method further comprises: The observation data is used to determine the changes in the objects corresponding to the map features; Based on the determined changes, map change features are generated to describe the changes in the map features, so as to reflect the determined changes in the objects; The map change features are combined with other map change features of the identified one or more features to form map change data; and The map change data is provided to the autonomous driving system for use, wherein the map change data is provided to the autonomous driving system independently of the provision of the HD map data.

11. The method of claim 10, wherein the map change data is provided to the autonomous driving system along with the updated metadata.

12. The method according to claim 1 or claim 2, further comprising: The system receives a request for updated metadata from a client and sends the updated metadata to the client in response to the request, wherein the request is for updated metadata related to a specified map feature among the plurality of map features.

13. A server system configured to implement the method according to any one of claims 1 to 12.

14. A computer program product comprising a computer program that, when executed by one or more processors, causes the one or more processors to perform the method according to any one of claims 1 to 12.

15. A computer-readable medium storing a computer program that, when executed by one or more processors, causes the one or more processors to perform the method according to any one of claims 1 to 12.

16. A method implemented by a computer at a client computer system in a vehicle, the client computer system including an autonomous driving system, the client computer system being configured to receive and store HD map data representing a road system having multiple objects, the HD map data including multiple map features representing the multiple objects of the road system, the client computer system being further configured to receive and store HD map metadata from a server system, the metadata including confidence levels of the HD map data for the multiple map features, the HD map data and the metadata being used by the autonomous driving system, the method comprising: The system receives updated metadata of one or more map features from a plurality of map features in the HD map data to reflect the updated confidence level of the one or more map features, wherein the updated metadata is received independently of the receipt of the HD map data and independently of the server system updating the HD map metadata of the one or more map features using the updated metadata and receiving the updated HD map metadata, and wherein the updated confidence level is associated with the confidence level of the data source, the one or more map features being derived from the data source; The updated metadata is processed to identify updated map features, which are map features among one or more map features associated with a specified portion of the road system; and Based on the updated metadata associated with the updated map features, updated HD map data is generated for the designated portion of the road system so that the autonomous driving system can use the updated HD map data.

17. The method of claim 16, wherein the HD map data covers a specified geographic area and includes multiple layers, each layer including different types of map data of the specified geographic area, and wherein the HD map metadata and the updated metadata cover the same specified geographic area, such that they can be processed as layers of the HD map data.

18. The method of any one of claims 16 to 17, wherein the designated portion of the road system is a part of the road system near the vehicle, wherein the proximity of the vehicle is determined based on the current location of the vehicle.

19. The method of claim 18, wherein the vicinity of the vehicle is further determined based on the predicted driving direction or area of ​​the vehicle.

20. The method according to any one of claims 16 to 17, further comprising distributing at least a portion of the updated HD map data to at least one electronic control unit in the vehicle.

21. The method of any one of claims 16 to 17, further comprising sending a request for updated metadata to a server, wherein the updated metadata is received from the server in response to the request.

22. The method of claim 21, wherein the request is a request for updated metadata covering the same geographic area as the HD map data stored in the client computer system.

23. The method of claim 21, wherein the request is a request for updated metadata covering a subregion of a geographic area covered by the HD map data stored in the client computer system.

24. The method of claim 23, wherein the request indicates the sub-region by one of the following: Explicitly indicate the sub-region; Indicates the vicinity of the vehicle; and The server indicates the vehicle's current location and its driving history, enabling the server to determine the appropriate sub-region.

25. The method of claim 21, wherein the request is a request for updated metadata associated with a specified map feature among the plurality of map features.

26. The method according to any one of claims 16 to 17, further comprising: Receive map change data describing changes in one or more map features among the plurality of map features of the HD map data, wherein the map change data is received independently of the receipt of the HD map data. The updated map features are further identified by processing the map change data to identify map features among one or more map features associated with the designated portion of the road system; and The updated HD map data is generated based on map change data related to the updated map features.

27. A client computer system configured to implement the method according to any one of claims 16 to 26.

28. A computer program product comprising a computer program that, when executed by one or more processors, causes the one or more processors to perform the method according to any one of claims 16 to 26.

29. A computer-readable medium storing a computer program that, when executed by one or more processors, causes the one or more processors to perform the method according to any one of claims 16 to 26.

Images