High-precision map dynamic update method and system for unmanned vehicles

Abstract

The present invention discloses a method and system for dynamically updating high-precision maps of unmanned vehicles, and relates to the field of map update technology. The method comprises: analyzing the map update timing of the current travel route according to the current planned route of the target vehicle in combination with the current travel speed; setting collaborative connection conditions; connecting collaborative update vehicles, performing spatial position alignment and temporal arrangement according to the collaborative leading time zone of the collaborative update vehicles, and configuring collaborative weights of the collaborative update vehicles; based on the collaborative weights, performing feature aggregation on the dynamic map acquired by the collaborative update vehicles according to the spatial position alignment and temporal arrangement relationship, obtaining map update data, and using the map update data to dynamically update the map. This solves the technical problems of poor real-time performance and inaccurate data in the prior art of high-precision map updates for unmanned vehicles, and achieves the technical effect of improving the accuracy and real-time performance of map updates, and enhancing the driving safety and reliability of unmanned vehicles.

Description

Technical Field

[0001] The present invention relates to the field of map updating technology, and in particular to a method and system for dynamically updating high-precision maps of unmanned vehicles. Background Art

[0002] With the rapid development of autonomous driving technology, high-precision maps have become a critical foundation for autonomous vehicles to achieve core functions such as autonomous navigation, path planning, and obstacle avoidance. High-precision maps not only provide detailed road geometry information, such as lane markings, traffic signs, and intersection layouts, but also contain rich semantic information, such as road type, speed limit, and traffic signal status, providing accurate environmental perception and decision-making support for autonomous vehicles. However, the real-world road environment is dynamic, including road construction, traffic sign changes, and temporary closures. If these changes are not reflected in high-precision maps in a timely manner, they will pose a threat to the driving safety and reliability of autonomous vehicles. Therefore, how to dynamically update high-precision maps and ensure the real-time and accuracy of map information has become a critical issue that needs to be addressed in the field of autonomous driving technology. Summary of the Invention

[0003] This application provides a method and system for dynamically updating high-precision maps for unmanned vehicles, which solves the technical problems of poor real-time performance and inaccurate data in the prior art of updating high-precision maps for unmanned vehicles.

[0004] In view of the above problems, this application provides a method and system for dynamically updating high-precision maps of unmanned vehicles.

[0005] A first aspect of the present application provides a method for dynamically updating a high-precision map of an unmanned vehicle, the method comprising:

[0006] According to the current planned route of the target vehicle and the current driving speed, the map update timing of the current driving route is analyzed, and the map update timing is the map update time window of each section on the planned route; according to the current planned route and its map update timing, collaborative connection conditions are set, and the collaborative connection conditions include collaborative vehicle lines and collaborative leading time zones, and the collaborative leading time zones are used to characterize the leading driving space-time areas of collaborative vehicles; based on the collaborative connection conditions, collaborative update vehicles are connected, spatial position alignment and time sequence arrangement are performed according to the collaborative leading time zones of the collaborative update vehicles, and collaborative weights of the collaborative update vehicles are configured, and the collaborative weights correspond to the offset differences of the spatial position alignment and time sequence arrangement; according to the collaborative weights, the acquired dynamic maps of the collaborative update vehicles are feature aggregated according to the spatial position alignment and time sequence arrangement relationships to obtain map update data, and the map update data is used to dynamically update the map.

[0007] A second aspect of the present application provides a high-precision map dynamic update system for unmanned vehicles, the system comprising:

[0008] Analysis module: Analyzes the map update timing of the current driving route based on the current planned route of the target vehicle in combination with the current driving speed. The map update timing is the map update time window of each road section on the planned route; Condition setting module: Sets collaborative connection conditions based on the current planned route and its map update timing. The collaborative connection conditions include collaborative vehicle lines and collaborative leading time zones. The collaborative leading time zones are used to characterize the leading driving space-time areas of collaborative vehicles; Configuration module: Connects collaborative update vehicles based on the collaborative connection conditions, performs spatial position alignment and time sequence arrangement according to the collaborative leading time zones of the collaborative update vehicles, and configures the collaborative weights of the collaborative update vehicles. The collaborative weights correspond to the offset differences of the spatial position alignment and time sequence arrangement; Map update module: Based on the collaborative weights, performs feature aggregation on the dynamic map acquired by the collaborative update vehicles according to the spatial position alignment and time sequence arrangement relationship to obtain map update data, and uses the map update data to dynamically update the map.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, based on the target vehicle's current planned route and current driving speed, the map update sequence of the current route is analyzed. The map update sequence is the map update time window for each road segment on the planned route. Next, based on the current planned route and its map update sequence, collaborative connection conditions are set. These conditions include the collaborative vehicle route and the collaborative lead time zone, which characterizes the preceding spatiotemporal region of the collaborative vehicle's travel. Then, based on the collaborative connection conditions, the collaborative updating vehicles are connected. Spatial alignment and temporal arrangement are performed according to their collaborative lead time zones, and collaborative weights are assigned for the collaborative updating vehicles. The collaborative weights correspond to the offset difference between the spatial alignment and temporal arrangement. Finally, based on the collaborative weights, feature aggregation is performed on the acquired dynamic map of the collaborative updating vehicles according to the spatial alignment and temporal arrangement relationship to obtain map update data, which is then used for dynamic map updates. This method solves the technical problems of poor real-time performance and inaccurate data in existing technologies for high-precision map updates for unmanned vehicles, achieving the technical effect of improving map update accuracy and real-time performance, and enhancing the driving safety and reliability of unmanned vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic diagram of a flow chart of a method for dynamically updating a high-precision map for an unmanned vehicle provided in an embodiment of the present application;

[0013] Figure 2 Schematic diagram of the structure of a high-precision map dynamic update system for unmanned vehicles provided in an embodiment of the present application.

[0014] Description of reference numerals: analysis module 11 , condition setting module 12 , configuration module 13 , map updating module 14 . DETAILED DESCRIPTION

[0015] This application solves the technical problems of poor real-time performance and inaccurate data in the prior art of high-precision map updates for unmanned vehicles by providing a method and system for dynamic updating of high-precision maps for unmanned vehicles.

[0016] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0017] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0018] Example 1, as Figure 1 As shown, the present application provides a method for dynamically updating a high-precision map of an unmanned vehicle, wherein the method includes:

[0019] According to the current planned route of the target vehicle and the current driving speed, the map update sequence of the current driving route is analyzed. The map update sequence is the map update time window of each road section on the planned route.

[0020] The target vehicle's currently planned route refers to the road or path the vehicle plans to travel during the current trip. The current driving speed refers to the vehicle's current motion state, which affects the vehicle's driving time and the frequency of map data updates. The faster the speed, the shorter the time it takes for the vehicle to pass through each road section, and the time window for map updates may also need to be adjusted accordingly.

[0021] Based on the target vehicle's currently planned route and current driving speed, the system analyzes the map update timing for each section of the route. The map update timing refers to the map update time window for each section, which determines when the map data for that section needs to be updated. These time windows can be dynamically calculated and adjusted based on factors such as the vehicle's driving speed, current route planning, and road conditions. For example, if the target vehicle is traveling faster, the frequency of map updates may increase to ensure that the map data can promptly reflect changes in road conditions.

[0022] Furthermore, analyzing the map update sequence of the current driving route based on the current planned route of the target vehicle in combination with the current driving speed includes:

[0023] Extract the road segment nodes of the currently planned route and identify the length of each road segment; calculate the estimated travel time of each road segment node based on the current driving speed and the length of each road segment; and arrange the road segment nodes in a time sequence and a time interval based on the estimated travel time of each road segment node to obtain a map update sequence for the current driving route.

[0024] Specifically, multiple road section nodes are extracted from the target vehicle's currently planned route. Each road section node represents an important geographical location during the target vehicle's travel, such as an intersection or crossroads. For each road section node, the length of the road section (i.e., the distance between two adjacent nodes) is identified and recorded. Based on the target vehicle's current driving speed, the estimated travel time for each road section is calculated (estimated travel time = road section length / current driving speed). According to the estimated travel time of each road section, the road sections are arranged in chronological order. Based on the time sequence of the road section nodes, the map update sequence of the current driving route is obtained.

[0025] Furthermore, obtaining the map update timing of the current driving route includes:

[0026] An adjustment time threshold for each road section node is calculated based on the length of the road section and the current driving speed; a window tolerance duration is set based on a change penalty coefficient for each road section node in the currently planned route, where the change penalty coefficient is determined based on the road section length and the difficulty of route adjustment; the adjustment time threshold is constrained and adjusted based on the window tolerance duration, a map update time window for each road section node is determined, and a map update timing sequence for the current driving route is obtained.

[0027] Specifically, the adjustment time threshold for each road segment is calculated based on the target vehicle's current speed and the length of each road segment. The adjustment time threshold refers to the time interval allowed for map updates within a certain spatiotemporal range. The adjustment time threshold is equal to the road segment length divided by the current speed. A window tolerance period is set based on the change penalty coefficient for each road segment. The change penalty coefficient is calculated based on the road segment length and the difficulty of route adjustment. For example, longer roads and complex traffic conditions will result in larger change penalties. Therefore, the window tolerance period is appropriately extended to ensure sufficient flexibility in the update process. Wherein, window tolerance period = change penalty coefficient × adjustment time threshold. After the window tolerance period is determined, the adjustment time threshold for each road segment is constrained and adjusted based on this tolerance period. Based on the set window tolerance period, the original adjustment time threshold is appropriately extended or shortened to ensure that the map update can be carried out within the optimal time and avoid the occurrence of time windows that are too small or too large. Based on the adjusted time threshold and window tolerance period, the map update time window for each road segment node is determined, thus obtaining the map update sequence for the current route.

[0028] According to the current planned route and its map update sequence, collaborative connection conditions are set. The collaborative connection conditions include collaborative vehicle routes and collaborative leading time zones. The collaborative leading time zones are used to characterize the leading travel time and space areas of the collaborative vehicles.

[0029] Based on the target vehicle's currently planned route, identify collaborative vehicle routes that are adjacent to or intersecting with the target vehicle's route. Collaborative vehicle routes refer to routes of other vehicles that are connected to or closely related to the target vehicle's route. Vehicles on these routes may travel within the same time and space range and may affect the target vehicle's map update.

[0030] The collaborative lead time zone is used to characterize the leading time and space area of ​​the collaborative vehicle. Specifically, the collaborative lead time zone refers to the area within a certain time or space range ahead during the driving process of the collaborative vehicle; the collaborative lead time zone includes the road sections or areas that the collaborative vehicle is about to pass through, and the map data of these areas needs to be connected with the map update sequence of the target vehicle. The setting of the collaborative lead time zone depends on multiple factors, including the driving speed, route and driving sequence of the collaborative vehicle. For example, a faster-moving collaborative vehicle may have a shorter lead time zone, while a slower-moving vehicle may have a longer lead time zone. Through a comprehensive analysis of these factors, the system can reasonably predict the scope of influence of the collaborative vehicle on the map update of the target vehicle.

[0031] Collaborative connection conditions are set by combining the collaborative vehicle routes and collaborative lead time zones, ensuring that map update data between the target vehicle and the collaborative vehicle is synchronized within the appropriate time and space range. By analyzing the driving sequence, location, and lead time zone of the target and collaborative vehicles, the collaborative connection conditions can be flexibly adjusted to ensure that the collaborative vehicles can provide necessary map data support in a timely manner, improving the accuracy and real-time performance of map updates.

[0032] The collaborative update vehicles are connected based on the collaborative connection conditions, spatial position alignment and time sequence arrangement are performed according to the collaborative leading time zone of the collaborative update vehicles, and the collaborative weight of the collaborative update vehicles is configured, and the collaborative weight corresponds to the offset difference of the spatial position alignment and time sequence arrangement.

[0033] Based on the collaborative connection conditions, the system connects the collaborative update vehicle with the target vehicle and performs spatial alignment and time sequence arrangement according to the collaborative lead time zone of the collaborative update vehicle. The collaborative update vehicles related to the target vehicle are determined based on the collaborative connection conditions, and it is ensured that the data of these collaborative vehicles can effectively coordinate with the map update requirements of the target vehicle. In terms of spatial alignment, the system will align the driving trajectory of the collaborative vehicle with the map update area of ​​the target vehicle based on the current position of the collaborative vehicle and the map update requirements of the target vehicle. This includes calculating the relative spatial position between the collaborative vehicle and the target vehicle, and making appropriate adjustments to ensure that the collaborative vehicle can provide map update data at the correct location. In terms of time sequence arrangement, the system reasonably arranges the driving sequence of the collaborative vehicles to ensure that the map update timing of different collaborative vehicles can accurately match the map update timing of the target vehicle. Through this time sequence arrangement, the system can ensure that the map data of different collaborative vehicles are integrated in the appropriate time sequence to improve the real-time and accuracy of map updates.

[0034] The system assigns a cooperation weight to each cooperative update vehicle. This weight represents the importance of the cooperative vehicle in the map update process and is associated with the offset difference between the vehicle's spatial alignment and temporal arrangement. Specifically, the weight depends on the accuracy of the spatial alignment and the degree of temporal matching between the cooperative vehicle and the target vehicle. The smaller the offset difference in spatial alignment and temporal arrangement, the greater the cooperation weight, while the smaller the offset difference in spatial alignment and temporal arrangement, the smaller the weight.

[0035] Furthermore, the collaborative updating vehicles are connected based on the collaborative connection conditions, spatial position alignment and time sequence arrangement are performed according to the collaborative leading time zones of the collaborative updating vehicles, and the collaborative weights of the collaborative updating vehicles are configured, including:

[0036] Obtain the leading spatial position and leading time relationship between the collaborative update vehicle and the target vehicle; align the coordinates of the target vehicle and the collaborative update vehicle according to the leading spatial position, and determine the position alignment amount; calculate the time deviation between the collaborative update vehicle and the target vehicle according to the leading time relationship; calculate the spatial alignment weight and the time alignment weight based on the position alignment amount and the time deviation amount, and perform weight fusion according to the preset fusion coefficient to obtain the collaborative weight of the collaborative update vehicle.

[0037] Specifically, the leading spatial position and leading time relationship between the collaborative update vehicle and the target vehicle are obtained. The leading spatial position refers to the geographical location of the collaborative vehicle in front, and the leading time relationship refers to the difference in driving sequence between the collaborative vehicle and the target vehicle. Based on the obtained leading spatial position relationship, the system will coordinately align the target vehicle and the collaborative update vehicle, that is, by calculating the spatial offset between the two, the spatial position of the collaborative vehicle is adjusted to align it with the target vehicle in space. The aligned position alignment reflects the degree of spatial alignment between the two. The smaller the position alignment, the more accurate the position alignment of the two. On the basis of spatial position alignment, the time deviation is calculated according to the leading time relationship. The time deviation refers to the difference between the time node of the cooperative vehicle and the time node of the target vehicle. By calculating this difference, the system can judge the degree of time synchronization between the cooperative vehicle and the target vehicle. The smaller the time deviation, the more accurate the timing docking between the cooperative vehicle and the target vehicle; according to the calculated position alignment and time deviation, the spatial alignment weight and time alignment weight are calculated respectively. The spatial alignment weight is determined by the spatial alignment of the two. The smaller the spatial alignment, the greater the weight; similarly, the time alignment weight is calculated based on the time deviation. The smaller the time deviation, the greater the weight; the spatial alignment weight and the time alignment weight are fused according to the preset fusion coefficient to obtain the cooperative weight of each cooperative update vehicle.

[0038] Furthermore, the cooperative weight of the cooperatively updated vehicle is obtained, and its calculation expression is:

[0039] ,in, To collaboratively update the cooperative weight of vehicle i, is the fusion coefficient of the spatial alignment weight, is the fusion coefficient of the time alignment weight, is the position alignment deviation, is the time deviation, is the spatial alignment attenuation factor, is the time alignment attenuation factor.

[0040] is the fusion coefficient of the spatial alignment weight, which indicates the contribution of spatial alignment to the collaborative weight; is the fusion coefficient of the time alignment weight, which indicates the contribution of time alignment to the collaborative weight; is the position alignment deviation, which indicates the deviation in spatial position between the collaboratively updated vehicle and the target vehicle; is the time deviation, which indicates the time deviation between the collaborative update vehicle and the target vehicle; The spatial alignment attenuation factor measures the attenuation effect of the spatial position difference between vehicles on the data contribution in the collaborative update task. The spatial alignment attenuation factor is used to adjust the influence of the position alignment deviation and determines the decay rate of the position deviation on the collaborative weight. The larger the attenuation factor, the more sensitive the influence of the position alignment deviation on the weight. The larger the position deviation, the faster the weight decreases. The time alignment attenuation factor measures how the time synchronization between vehicles (i.e., differences in data collection times) affects their contributions. The time alignment attenuation factor adjusts the impact of time deviation and determines how quickly the time deviation decays the collaborative weight. A larger attenuation factor indicates a more sensitive impact of time deviation on the weight, while a larger time deviation results in a faster weight decrease. This calculation formula allows the system to adjust the collaborative weights of collaboratively updated vehicles based on the spatial alignment deviation and time deviation, using the fusion coefficient and attenuation factor, thereby achieving a reasonable assessment of the contributions of different collaborative vehicles.

[0041] Furthermore, obtaining the cooperative weight of the cooperatively updated vehicle further includes:

[0042] Obtain a record update database of the collaborative update vehicle, wherein the record update database is the historical collection data of the collaborative update vehicle, including different collection device labels; perform data credibility evaluation based on the record update database to obtain a data evaluation coefficient of each collection device; configure the collaborative weight of the collection data source of the collaborative update vehicle based on the data evaluation coefficient of each collection device, and add the collaborative weight of the collection data source to the collaborative weight of the collaborative update vehicle.

[0043] Preferably, a record update database is obtained for each collaborative update vehicle. The record update database contains historical data collected by the collaborative update vehicle through various collection devices over a period of time. These data include multiple different types of collection device tags (such as GPS sensors, lidars, cameras, etc.). Each device may collect different types of geographic location information, environmental data or road features. After obtaining the record update database, the data credibility of each collection device is evaluated based on the historical collection data, and the data evaluation coefficient of each collection device is calculated based on the historical performance of each device (such as data accuracy, stability, collection frequency, etc.). These coefficients reflect the reliability of the data provided by each device. degree, the larger the coefficient, the higher the credibility of the device data, and vice versa; based on the obtained data evaluation coefficient, the system configures a collaborative weight for the collection data source of each collaborative update vehicle. These collaborative weights are used to measure the weight that the collection data source should have in the entire map update process. Specifically, the collection data source with higher credibility will be assigned a higher collaborative weight, while the collection data source with lower credibility will be assigned a lower weight; the collaborative weight of each collection data source is fused with the original collaborative weight of the corresponding collaborative update vehicle. By fusing the collaborative weights of the collection data sources, the system can comprehensively consider factors such as spatial alignment, time alignment, and device credibility to obtain a final collaborative weight.

[0044] According to the cooperation weight, feature aggregation is performed on the dynamic map acquired by the cooperative updating vehicle in accordance with the spatial position alignment and time sequence arrangement relationship to obtain map update data, and the map is dynamically updated using the map update data.

[0045] Based on the collaborative weights, the system will perform feature aggregation on the dynamic maps acquired by collaborative update vehicles according to spatial position alignment and temporal arrangement relationships. Feature aggregation integrates the map information of each collaborative vehicle to create a more accurate and complete map update data; the map is dynamically updated based on the map update data to ensure that unmanned vehicles can obtain the latest and most accurate map data.

[0046] Furthermore, based on the cooperation weight, feature aggregation is performed on the dynamic map acquired by the cooperative updating vehicle according to the spatial position alignment and time sequence arrangement relationship to obtain map update data, including:

[0047] Acquire dynamic map feature data of the collaboratively updated vehicle, the dynamic map feature data having a data source identifier; spatially align and temporally arrange the dynamic map feature data, and perform feature screening on the dynamic map feature data using the collaborative weights obtained by spatial alignment and temporal alignment to obtain the spatiotemporal features of the map to be aggregated; calculate the feature data contribution value of each collaboratively updated vehicle through an attention mechanism based on the collaborative weights of the collected data sources and the collaborative weights of the collaboratively updated vehicles; perform feature aggregation on the spatiotemporal features of the map to be aggregated based on the feature data contribution value of each collaboratively updated vehicle to obtain the map update data.

[0048] Specifically, the system obtains dynamic map feature data from each collaborative updating vehicle. This data includes map feature information obtained from various acquisition devices (such as GPS, LiDAR, and cameras). Each data source's feature data is identified by a data source identifier to distinguish data from different sources. The system then spatially aligns and temporally arranges this dynamic map feature data. Spatial alignment ensures that data provided by different collaborative vehicles is aligned within a unified geographic coordinate system to avoid positional deviations. Temporal arrangement ensures that all data is arranged chronologically to maintain freshness and timeliness. After spatial and temporal alignment, the system performs feature filtering based on the collaborative weights. By setting these weights, the system selects data from highly weighted collaborative vehicles, which will be given greater weight in the aggregation process. Next, the system uses an attention mechanism to calculate the contribution of each collaborative updating vehicle's feature data based on its collaborative weight and the weight of each acquisition data source. Vehicle feature data refers to the relevant information provided by each collaborative updating vehicle during dynamic map updates. Through this mechanism, data from vehicles with higher weights will have a greater impact on the final map update results. Finally, the system performs a weighted aggregation of the map's spatiotemporal features based on the calculated contribution values ​​of the feature data. This process weights the data from different collaborative vehicles, ensuring that each vehicle's contribution receives an appropriate weight in the final map update. Ultimately, through these steps, the system obtains consolidated, more accurate, and comprehensive map update data, providing real-time, precise mapping support for autonomous vehicles.

[0049] The attention mechanism dynamically assigns weights to different components of data when processing data, thereby focusing on the most important information for the task. During the feature aggregation phase, the attention mechanism calculates the contribution of each collaboratively updating vehicle's feature data. Specifically, the attention mechanism automatically adjusts the influence of each vehicle's feature data based on the collaborative weights of the collaborative updating vehicles and the collaborative weights of the collected data sources.

[0050] By defining the scoring function , used to represent the correlation between each collaborative update vehicle and the data source, where is the scoring function, To collaboratively update the vehicle's collaborative weight, The weight of the data source.

[0051] The scoring function is used to calculate the score between each collaborative update vehicle and the data source, and then the attention weight of each data source to the collaborative vehicle is obtained through the normalization process. The calculation formula is: ,in, The attention weight of cooperative vehicle i to the collected data source j, m is the total number of data sources, It is the exponential result of the scoring function, which ensures that higher scores have a greater impact on the weight.

[0052] After the attention weights are calculated, the feature data of the cooperative vehicles are weighted according to these weights to obtain the feature data contribution value of each cooperative update vehicle. The calculation formula for the feature data contribution value of each cooperative update vehicle is: ,in, To collaboratively update the feature data contribution value of vehicle i, is the attention weight of collaborative vehicle i to data source j, It represents the feature data obtained by vehicle i from data source j, and m represents the total number of data sources.

[0053] Using the attention mechanism, the feature data contribution value of each collaborative updating vehicle is calculated based on the collaborative weight of each collaborative updating vehicle and the weight of each collected data source. Specifically, the collaborative weight of each collaborative updating vehicle and the weight of each collected data source are obtained. The collaborative weight represents the contribution of the collaborative vehicle in the map update process, while the weight of the data source reflects the reliability of the data provided by the data source. Then, the weight calculation method in the attention mechanism is defined. The collaborative weight of the collaborative vehicle and the weight of the collected data source are used to calculate the attention weight of each data source. This weight is obtained by combining the weight of the collaborative vehicle with the weight of the data source and normalizing it to ensure that the contribution of each collaborative vehicle and data source in the map update is distributed proportionally. Subsequently, the feature data contribution value of each collaborative updating vehicle is calculated. This process multiplies the attention weight with the feature data value provided by the collaborative vehicle to obtain the contribution of each vehicle data to the final map update. Finally, the feature data contribution values ​​of all collaborative updating vehicles will be weighted and aggregated according to the weight to ensure that the vehicle data with higher weights has a greater impact on the map update process.

[0054] In summary, the embodiments of the present application have at least the following technical effects:

[0055] First, based on the target vehicle's current planned route and current driving speed, the map update sequence of the current route is analyzed. The map update sequence is the map update time window for each road segment on the planned route. Next, based on the current planned route and its map update sequence, collaborative connection conditions are set. These conditions include the collaborative vehicle route and the collaborative lead time zone, which characterizes the preceding spatiotemporal region of the collaborative vehicle's travel. Then, based on the collaborative connection conditions, the collaborative updating vehicles are connected. Spatial alignment and temporal arrangement are performed according to their collaborative lead time zones, and collaborative weights are assigned for the collaborative updating vehicles. The collaborative weights correspond to the offset difference between the spatial alignment and temporal arrangement. Finally, based on the collaborative weights, feature aggregation is performed on the acquired dynamic map of the collaborative updating vehicles according to the spatial alignment and temporal arrangement relationship to obtain map update data, which is then used for dynamic map updates. This method solves the technical problems of poor real-time performance and inaccurate data in existing technologies for high-precision map updates for unmanned vehicles, achieving the technical effect of improving map update accuracy and real-time performance, and enhancing the driving safety and reliability of unmanned vehicles.

[0056] Embodiment 2 is based on the same inventive concept as the method for dynamically updating a high-precision map of an unmanned vehicle in the aforementioned embodiment. Figure 2 As shown, the present application provides a high-precision map dynamic update system for unmanned vehicles, wherein the system includes:

[0057] Analysis module 11: Analyzes the map update timing of the current driving route based on the current planned route of the target vehicle in combination with the current driving speed. The map update timing is the map update time window of each road section on the planned route; Condition setting module 12: Sets collaborative connection conditions based on the current planned route and its map update timing. The collaborative connection conditions include collaborative vehicle lines and collaborative leading time zones. The collaborative leading time zones are used to characterize the leading driving space-time areas of collaborative vehicles; Configuration module 13: Connects collaborative update vehicles based on the collaborative connection conditions, performs spatial position alignment and time sequence arrangement according to the collaborative leading time zones of the collaborative update vehicles, and configures the collaborative weights of the collaborative update vehicles. The collaborative weights correspond to the offset differences of the spatial position alignment and time sequence arrangement; Map update module 14: Based on the collaborative weights, the acquired dynamic map of the collaborative update vehicle is feature aggregated according to the spatial position alignment and time sequence arrangement relationship to obtain map update data, and the map update data is used to dynamically update the map.

[0058] Furthermore, the analysis module 11 is used to perform the following method:

[0059] Extract the road segment nodes of the currently planned route and identify the length of each road segment; calculate the estimated travel time of each road segment node based on the current driving speed and the length of each road segment; and arrange the road segment nodes in a time sequence and a time interval based on the estimated travel time of each road segment node to obtain a map update sequence for the current driving route.

[0060] Furthermore, the analysis module 11 is used to perform the following method:

[0061] An adjustment time threshold for each road section node is calculated based on the length of the road section and the current driving speed; a window tolerance duration is set based on a change penalty coefficient for each road section node in the currently planned route, where the change penalty coefficient is determined based on the road section length and the difficulty of route adjustment; the adjustment time threshold is constrained and adjusted based on the window tolerance duration, a map update time window for each road section node is determined, and a map update timing sequence for the current driving route is obtained.

[0062] Furthermore, the configuration module 13 is used to execute the following method:

[0063] Obtain the leading spatial position and leading time relationship between the collaborative update vehicle and the target vehicle; align the coordinates of the target vehicle and the collaborative update vehicle according to the leading spatial position, and determine the position alignment amount; calculate the time deviation between the collaborative update vehicle and the target vehicle according to the leading time relationship; calculate the spatial alignment weight and the time alignment weight based on the position alignment amount and the time deviation amount, and perform weight fusion according to the preset fusion coefficient to obtain the collaborative weight of the collaborative update vehicle.

[0064] Furthermore, the configuration module 13 is used to execute the following method:

[0065] The cooperative weight of the cooperatively updated vehicle is obtained, and its calculation expression is: ,in, To collaboratively update the cooperative weight of vehicle i, is the fusion coefficient of the spatial alignment weight, is the fusion coefficient of the time alignment weight, is the position alignment deviation, is the time deviation, is the spatial alignment attenuation factor, is the time alignment attenuation factor.

[0066] Furthermore, the configuration module 13 is used to execute the following method:

[0067] Obtain a record update database of the collaborative update vehicle, wherein the record update database is the historical collection data of the collaborative update vehicle, including different collection device labels; perform data credibility evaluation based on the record update database to obtain a data evaluation coefficient of each collection device; configure the collaborative weight of the collection data source of the collaborative update vehicle based on the data evaluation coefficient of each collection device, and add the collaborative weight of the collection data source to the collaborative weight of the collaborative update vehicle.

[0068] Furthermore, the map updating module 14 is configured to execute the following method:

[0069] Acquire dynamic map feature data of the collaboratively updated vehicle, the dynamic map feature data having a data source identifier; spatially align and temporally arrange the dynamic map feature data, and perform feature screening on the dynamic map feature data using the collaborative weights obtained by spatial alignment and temporal alignment to obtain the spatiotemporal features of the map to be aggregated; calculate the feature data contribution value of each collaboratively updated vehicle through an attention mechanism based on the collaborative weights of the collected data sources and the collaborative weights of the collaboratively updated vehicles; perform feature aggregation on the spatiotemporal features of the map to be aggregated based on the feature data contribution value of each collaboratively updated vehicle to obtain the map update data.

[0070] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0072] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A method for dynamically updating a high-precision map of an unmanned vehicle, characterized in that: The method comprises: Analyze the map update sequence of the current route based on the target vehicle's current planned route and current driving speed. The map update sequence is the map update time window for each road section on the planned route. According to the current planned route and its map update sequence, setting collaborative connection conditions, the collaborative connection conditions including the collaborative vehicle route and the collaborative lead time zone, the collaborative lead time zone being used to characterize the leading travel time and space area of ​​the collaborative vehicle; Connecting the collaborative update vehicles based on the collaborative connection conditions, performing spatial position alignment and temporal arrangement according to the collaborative leading time zones of the collaborative update vehicles, and configuring collaborative weights of the collaborative update vehicles, wherein the collaborative weights correspond to offset differences in the spatial position alignment and temporal arrangement; performing feature aggregation on the acquired dynamic map of the collaborative updating vehicle according to the collaborative weight and the spatial position alignment and the temporal arrangement relationship to obtain map update data, and performing dynamic map update using the map update data; The collaborative updating vehicles are connected based on the collaborative connection conditions, spatial position alignment and time sequence arrangement are performed according to the collaborative leading time zones of the collaborative updating vehicles, and collaborative weights of the collaborative updating vehicles are configured, including: Obtain the leading spatial position and leading time relationship between the collaborative update vehicle and the target vehicle; Align the coordinates of the target vehicle and the collaborative update vehicle according to the preceding spatial position and determine the position alignment amount; Calculating a time deviation between the collaborative updating vehicle and the target vehicle according to the lead time relationship; The spatial alignment weight and the temporal alignment weight are calculated according to the position alignment amount and the time deviation amount, and the weight fusion is performed according to the preset fusion coefficient to obtain the collaborative weight of the collaboratively updated vehicle.

2. The method for dynamically updating a high-precision map of an unmanned vehicle according to claim 1, wherein: The process of analyzing the map update sequence of the current driving route based on the current planned route of the target vehicle in combination with the current driving speed includes: Extracting the segment nodes of the currently planned route and identifying the length of each segment; Calculate the estimated travel time for each road segment node based on the current driving speed and the length of each road segment; According to the estimated travel time of each road section node, the road section nodes are arranged in time sequence according to the time sequence and the time interval distance to obtain the map update time sequence of the current driving route.

3. The method for dynamically updating a high-precision map of an unmanned vehicle according to claim 2, wherein: Obtaining a map update sequence for the current driving route includes: Calculate the adjustment time threshold of each road node based on the length of the road section and the current driving speed; Setting a window tolerance time based on a penalty coefficient for each section node in the currently planned route, wherein the penalty coefficient for each section node is determined based on the section length and the difficulty of route adjustment; The adjustment time threshold is constrained and adjusted according to the window tolerance time, the map update time window of each road segment node is determined, and the map update timing of the current driving route is obtained.

4. The method for dynamically updating a high-precision map of an unmanned vehicle according to claim 1, wherein: The cooperative weight of the cooperatively updated vehicle is obtained, and its calculation expression is: ,in, To collaboratively update the cooperative weight of vehicle i, is the fusion coefficient of the spatial alignment weight, is the fusion coefficient of the time alignment weight, is the position alignment deviation, is the time deviation, is the spatial alignment attenuation factor, is the time alignment attenuation factor; Among them, the spatial alignment attenuation factor is used to adjust the influence of the position alignment deviation and determine the attenuation rate of the position deviation on the collaborative weight. The larger the attenuation factor, the more sensitive the influence of the position alignment deviation on the weight. The larger the position deviation, the faster the weight decreases. The time alignment attenuation factor is used to adjust the influence of the time deviation and determine the attenuation rate of the time deviation on the collaborative weight. The larger the attenuation factor, the more sensitive the influence of the time deviation on the weight. The larger the time deviation, the faster the weight decreases.

5. The method for dynamically updating a high-precision map of an unmanned vehicle according to claim 1, wherein: Obtaining the cooperative weight of the cooperatively updated vehicle further includes: Obtaining a record update database of the collaborative update vehicle, wherein the record update database is historically collected data of the collaborative update vehicle, including different collection device labels; Update the database based on the records to evaluate the data credibility and obtain the data evaluation coefficient of each acquisition device; According to the data evaluation coefficient of each acquisition device, the collaborative weight of the acquisition data source of the collaborative update vehicle is configured, and the collaborative weight of the acquisition data source is added to the collaborative weight of the collaborative update vehicle.

6. The method for dynamically updating a high-precision map of an unmanned vehicle according to claim 5, wherein: According to the cooperation weight, feature aggregation is performed on the dynamic map acquired by the cooperative updating vehicle according to the spatial position alignment and the time sequence arrangement relationship to obtain map update data, including: Acquiring dynamic map feature data of the collaboratively updated vehicle, the dynamic map feature data having a data source identifier; Performing spatial position alignment and temporal arrangement on the dynamic map feature data, and using the collaborative weights obtained from the spatial alignment and temporal alignment to perform feature screening on the dynamic map feature data to obtain the spatiotemporal features of the map to be aggregated; Based on the collaborative weight of the collected data source and the collaborative weight of the collaborative updating vehicle, the attention mechanism is used to calculate the contribution value of the feature data of each collaborative updating vehicle. The feature data of the vehicle refers to the relevant information provided by each collaborative updating vehicle when performing dynamic map updates. The attention mechanism automatically adjusts the influence of each vehicle's feature data based on the collaborative weight of each collaborative updating vehicle and the collaborative weight of the collected data source. The map update data is obtained by performing feature aggregation on the spatiotemporal features of the map to be aggregated according to the feature data contribution value of each collaborative updating vehicle.

7. A high-precision map dynamic update system for unmanned vehicles, characterized by: A method for dynamically updating a high-precision map of an unmanned vehicle according to any one of claims 1 to 6, the system comprising: Analysis module: Analyzes the map update sequence of the current route based on the target vehicle's current planned route and current driving speed. The map update sequence is the map update time window for each road section on the planned route. Condition setting module: setting cooperative connection conditions according to the current planned route and its map update sequence, wherein the cooperative connection conditions include the cooperative vehicle route and the cooperative leading time zone, wherein the cooperative leading time zone is used to represent the leading travel time and space area of ​​the cooperative vehicle; A configuration module connects the collaborative updating vehicles based on the collaborative connection conditions, performs spatial position alignment and temporal arrangement according to the collaborative leading time zones of the collaborative updating vehicles, and configures collaborative weights of the collaborative updating vehicles, wherein the collaborative weights correspond to offset differences in spatial position alignment and temporal arrangement; Map update module: Based on the collaborative weight, feature aggregation is performed on the dynamic map acquired by the collaborative update vehicle according to the spatial position alignment and time sequence arrangement relationship to obtain map update data, and the map is dynamically updated using the map update data.

Images