Road change information processing method, system and device and medium

Abstract

The embodiment of the invention provides a road change information processing method, system and device and a medium. The method comprises the steps that multiple pieces of target road change information are acquired; clustering the multiple pieces of target road change information based on at least one of the change space, the change time and the change type of the multiple pieces of target road change information to obtain at least one piece of comprehensive change information; for each piece of comprehensive change information, affected surface information of the comprehensive change information is generated, and the affected surface information comprises a change area of the comprehensive change information and the change degree of the change area.

Description

Technical Field

[0001] The present specification relates to the field of mobile control, and in particular to a road change information processing method and system. Background Art

[0002] For mobile control of the terminal, for example, when a vehicle is performing intelligent driving, it usually needs to rely on high-precision maps for auxiliary perception, planning, and decision-making. When the real world changes, such as changes in road structure and ground markings, the real world does not match the static high-precision map, which hinders the intelligent driving function. At this time, the problem of change can be solved by updating the high-precision map. During the period from the change to the completion of the map update, when the intelligent driving vehicle passes through the changed area, it still uses the original map for mobile control, resulting in its inability to pass through the changed area normally.

[0003] Therefore, it is hoped to provide a road change information processing method, system, device and medium, which can process the road change information of the changed area during the time period between the change and the update of the high-precision map, so as to ensure that the intelligent driving vehicle can pass through the changed area smoothly. Summary of the invention

[0004] One of the embodiments of the present specification provides a method for processing road change information, which includes: obtaining multiple target road change information; clustering the multiple target road change information based on at least one of the change space, change time and change type of the multiple target road change information to obtain at least one comprehensive change information; for each of the comprehensive change information, generating affected surface information of the comprehensive change information, wherein the affected surface information includes the change area of ​​the comprehensive change information and the degree of change of the change area.

[0005] One of the embodiments of the present specification provides a road change information processing system, which includes: an acquisition module, used to acquire multiple target road change information in a target area; a comprehensive change module, used to cluster the multiple target road change information based on at least one of the change space, change time and change type of the multiple target road change information to obtain at least one comprehensive change information; a generation module, used to generate affected surface information of the comprehensive change information for each of the comprehensive change information, wherein the affected surface information includes the change area of ​​the comprehensive change information and the change degree of the change area.

[0006] One of the embodiments of the present specification provides a road change information processing device, including a processor, wherein the processor is used to execute the road change information processing method as described in the above embodiment.

[0007] One of the embodiments of this specification provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the road change information processing method described in the above embodiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 is a schematic diagram of an application scenario of a road change information processing system according to some embodiments of this specification;

[0010] Figure 2 is an exemplary module diagram of a road change information processing system according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart of a method for processing road change information according to some embodiments of this specification;

[0012] Figure 4 is an exemplary flow chart of obtaining at least one comprehensive change information according to some embodiments of this specification;

[0013] Figure 5 is an exemplary flow chart for determining target road change information according to some embodiments of this specification;

[0014] Fig. 6A is a schematic diagram of a frame of original road data according to some embodiments of this specification;

[0015] Figure 6B is a schematic diagram of another frame of original road data according to some embodiments of this specification;

[0016] Figure 6C is a schematic diagram of another frame of original road data according to some embodiments of this specification;

[0017] Fig.6D is a schematic diagram of another frame of original road data according to some embodiments of this specification;

[0018] Figure 7 This is an exemplary flowchart of determining the target road change information of the target area according to some embodiments of this specification. DETAILED DESCRIPTION

[0019] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0020] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0021] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0022] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0023] Figure 1 It is a schematic diagram of an application scenario of a road change information processing system according to some embodiments of this specification.

[0024] The systems and methods in this specification can be applied to scenarios of terminal mobile control, such as autonomous driving scenarios (e.g., pure unmanned driving without a driver); for example, scenarios such as assisted driving in vehicles. The assisted driving module in the vehicle can autonomously control the vehicle's driving, and can also output driving prompts to the driver. Movable terminals can be applied to land, sea, aerospace, etc., or any combination thereof. Movable terminals may include taxis, private cars, ride-sharing, shared vehicles, buses, trains, motor vehicles, high-speed railways, subways, ships, airplanes, spacecraft, hot air balloons, bicycles, tricycles, motorcycles, robots, etc., or any combination thereof. In some embodiments, the road change information processing system can implement the methods and / or processes disclosed in this specification to process road change information during the time period between the change and the update of the high-precision map, thereby ensuring the mobile control of the terminal, for example, performing operations such as perception, positioning, prediction, decision-making and planning related to the movement of the terminal.

[0025] like Figure 1 As shown, the application scenario 100 of the road change information processing system may include target road change information 110 , a network 120 , a server 130 , and a terminal 140 .

[0026] The target road change information 110 is the relevant information of the road change. Figure 1 As shown, the target road change information 110 may be information about changes in lane markings. The road change information may also be information about changes in other road contents. For example, the target road change information 110 may also include, but is not limited to, relevant information about changes in lane lines, stop lines, road boundaries, etc. The target road change information 110 may be generated by a variety of methods. In some embodiments, such as Figure 1 As shown, the target road change information 110 may be generated by a reference vehicle 111. For more information about the reference vehicle 111 and the generation of the target road change information 110 by the reference vehicle 111, see Figure 3 , Figure 4 The target road change information 110 can also be generated by other methods. For more information about generating the target road change information 110 by other methods, please refer to Figure 4 and its related description.

[0027] The network 120 can connect the components of the application scenario 100 of the road change information processing system and / or connect the application scenario 100 of the road change information processing system with external resources. The application scenario 100 of the road change information processing system enables communication between the components and other components outside the application scenario 100 of the road change information processing system to promote the exchange of data and / or information. For example, the reference vehicle 111 can transmit the target road change information 110 to the server 130 through the network 120. For another example, the reference vehicle 111 can also obtain the relevant instructions issued by the server 130 through the network 120. For another example, the terminal 140 can obtain the affected surface information issued by the server 130 through the network 120. For more information about the above examples, please refer to the following of this specification. The network 120 can be any one or more of a wired network or a wireless network. For example, the network 120 can include but is not limited to a cable network, an optical fiber network, a telecommunications network, the Internet, a Bluetooth network, a near field communication, a bus within a device, a line within a device, a cable connection, etc. or any combination thereof. The network connection between the various parts can be in one of the above methods or in multiple methods. The network can be of various topologies such as point-to-point, shared, centralized, or a combination of multiple topologies.

[0028] The server 130 is a system with computing capabilities. The server 130 can process data and / or information obtained from various components of the application scenario 100 of the road change information processing system or other devices, and execute program instructions based on these data, information and / or processing results to perform one or more functions described in this specification. For example, the server 130 can obtain multiple target road change information; cluster the multiple target road change information based on at least one of the change space, change time and change type of the multiple target road change information to obtain at least one comprehensive change information; for each of the comprehensive change information, generate affected surface information of the comprehensive change information, wherein the affected surface information includes the change area of ​​the comprehensive change information and the degree of change of the change area. For more information about the above embodiments, please refer to Figure 3 and its related description. The server 130 may include one or more processing devices (e.g., a single-core processing device or a multi-core multi-core processing device). As an example only, the server 130 may include a central processing unit, an application-specific integrated circuit, a dedicated instruction processor, a graphics processor, a physical processor, a microprocessor, etc., or any combination thereof.

[0029] The terminal 140 may refer to a terminal device used by a user affected by the target road change information 110. The aforementioned user may refer to a person who may pass through the change area corresponding to the target road change information 110. Figure 1As shown, the aforementioned terminal device may include but is not limited to a mobile phone, a tablet, a computer or a vehicle. The aforementioned vehicle may be the reference vehicle 111, or may be another intelligent driving vehicle. The aforementioned intelligent driving vehicle may include but is not limited to autonomous driving assistance vehicles, networked driving assistance vehicles, human-machine co-driving vehicles and autonomous driving vehicles. The aforementioned terminal device may also include other devices, for example, a vehicle computer on a vehicle.

[0030] As shown in some embodiments of this specification, in the application scenario 100 of the road change information processing system, the target road change information 110 is transmitted to the server 130 via the network 120, and the target road change information 110 is processed by the server 130 to determine the corresponding affected surface information. The server 130 can transmit the aforementioned affected surface information to the terminal 140 via the network 120, so that the terminal 140 can perform a mobile control operation based on the high-precision map and the affected surface information, thereby ensuring that the intelligent driving vehicle can smoothly pass through the changed area during the time period between the change and the update of the high-precision map. For more information about the above embodiments, please refer to Figure 3 and its related description.

[0031] It should be noted that the application scenario 100 of the road change information processing system is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various modifications or variations can be made based on the description of this specification. For example, the application scenario 100 of the road change information processing system may also include a storage device, a database, an information source, etc. For another example, the application scenario 100 of the road change information processing system may be implemented on other devices to achieve similar or different functions. However, the changes and modifications will not deviate from the scope of this specification.

[0032] Figure 2 1 is an exemplary module diagram of a road change information processing system according to some embodiments of the present specification. The road change information processing system 200 may be implemented by the server 130 .

[0033] like Figure 2 As shown, the road change information processing system 200 may include an acquisition module 210 , a comprehensive change module 220 and a generation module 230 .

[0034] The acquisition module 210 may be used to acquire a plurality of target road change information in a target area.

[0035] The comprehensive change module 220 can be used to cluster the multiple target road change information based on at least one of the change space, change time and change type of the multiple target road change information to obtain at least one comprehensive change information. In some embodiments, the comprehensive change module 220 can be further used to cluster the multiple target road change information based on the change space and the change time to obtain at least one change combination; cluster the target road change information of the same type in the at least one change combination based on the change type to obtain the at least one comprehensive change information of the target area.

[0036] The generating module 230 may be configured to generate, for each piece of the comprehensive change information, affected surface information of the comprehensive change information, wherein the affected surface information includes a changed region of the comprehensive change information and a change degree of the changed region.

[0037] In some embodiments, the road change information processing system 200 may further include a collection module 240 .

[0038] The acquisition module 240 can be used to obtain an original road data set of a target area; detect the original road data set to obtain a road semantic element set of the target area, the road semantic element set including multiple road semantic elements; obtain a high-precision road element set of the target area, the high-precision road element set including multiple high-precision road elements; determine the target road change information of the target area according to the high-precision road element set and the road semantic element set. In some embodiments, the original road data set includes multiple frames of original road data, wherein each frame of original road data corresponds to a sub-area in the target area, and the acquisition module 240 can be further used to detect the original road data for each frame of original road data to obtain the road semantic elements of the sub-area; obtain the high-precision road elements of the sub-area; determine the initial road change information of the sub-area according to the high-precision road elements and the road semantic elements of the sub-area; track the initial road change information corresponding to the multiple frames of original road data to determine the target road change information of the target area.

[0039] It should be understood that Figure 2 The road change information processing system 200 and its modules shown can be implemented in various ways. It should be noted that the above description of the road change information processing system 200 and its modules is only for the convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. For example, Figure 2 The acquisition module 210, the comprehensive change module 220, the generation module 230 and the acquisition module 240 disclosed in the system can be different modules in a system, or a module can realize the functions of two or more modules mentioned above. For another example, the acquisition module 240 can be deployed in the server 130 or in the reference vehicle 111.

[0040] The following description of the method for generating affected surface information takes intelligent driving as an example, but it can be understood that the method for generating affected surface information can also be applied to other mobile control scenarios, such as robots.

[0041] Figure 3 is an exemplary flow chart of a road change information processing method according to some embodiments of this specification. In some embodiments, process 300 may be executed by server 130. For example, process 300 may be executed by road change information processing system 200 implemented by server 130. Figure 3 As shown, process 300 includes the following steps:

[0042] Step 310 , obtaining a plurality of target road change information. In some embodiments, step 310 is performed by the obtaining module 210 .

[0043] In some embodiments, the target road change information may include the change space, change time, change type, high-precision road elements before the change, and road semantic elements after the change where the road-related content changes.

[0044] The change space may refer to the location where the road-related content in the target road change information has changed. The change space may be the location information corresponding to the target road change information. The change space may be the specific location where the change has occurred (for example, the lane marking at a specific longitude and latitude has changed) or the location range where the change has occurred (for example, a traffic road construction fence is set within a certain longitude and latitude range).

[0045] The change time may refer to the time when the road-related content in the target road change information is changed.

[0046] The change type may refer to the specific type of change in the road-related content in the target road change information. The change type may include, but is not limited to, road structure change (e.g., setting up a traffic road construction fence), road sign change, road element change (e.g., adding a traffic light), etc.

[0047] The aforementioned high-precision road element before the change may refer to the road element before the change event occurs in the change area. The aforementioned road semantic element after the change may refer to the road semantic element after the change event occurs in the change area. For more information about high-precision road elements and road semantic elements, please refer to Figure 5 and its related description.

[0048] In some embodiments, the target road change information may further include other content. For example, the target road change information may further include the degree of change. The aforementioned degree of change may be used to characterize the degree of change before and after the change event occurs. The degree of change may be represented in a variety of ways. For example, the degree of change may be represented by a grade or a score. The higher the grade or the larger the score, the more drastic the change. For another example, the target road change information may further include a change identifier. The aforementioned change identifier may refer to an identification identifier of the corresponding change type, and the aforementioned change identifier may be a number. The change identifier corresponds one-to-one to the change type.

[0049] The target road change information can be obtained in a variety of ways. For example, the target road change information can be uploaded and obtained by the staff who implements the change to the road (such as the organization responsible for making the change to the road). For another example, the target road change information can also be obtained through the reference vehicle 111. The reference vehicle 111 can perform a change detection operation during driving to determine the target road change information. Specifically, the reference vehicle 111 can obtain the original road data set of the target area; detect the original road data set to obtain a road semantic element set of the target area, the road semantic element set includes multiple road semantic elements; obtain a high-precision road element set of the target area, the high-precision road element set includes multiple high-precision road elements; determine the target road change information based on the high-precision road element set and the road semantic element set. For more information about the aforementioned examples, see Figure 5 and its related description.

[0050] The acquisition module 210 can acquire multiple target road change information, which can be related to one change area or multiple change areas. The multiple target road change information can be acquired through one or more information sources (for example, the same reference vehicle 111 or multiple different reference vehicles 111).

[0051] For example, the acquisition module 210 acquires three target road change information uploaded by a reference vehicle 111 , and the three target road change information may be information related to changes in lane markings of road A, road B, and road C, respectively.

[0052] For another example, the acquisition module 210 acquires three target road change information uploaded by three reference vehicles 111 respectively. The three target road change information may also be information related to changes in lane markings of road A.

[0053] In some embodiments, when the reference vehicle 111 detects the target road change information, the reference vehicle 111 can determine the passage plan through the change space based on the change degree of the target road change information. The reference vehicle 111 can determine whether the aforementioned change degree is greater than a preset change threshold. When the change degree is less than or equal to the preset change threshold, the reference vehicle 111 can be controlled in combination with the road semantic elements detected in real time and the high-precision map to pass through the change space; when the aforementioned change degree is greater than the preset change threshold, the reference vehicle 111 can send a manual control request to the server to pass through the change space through manual takeover. The reference vehicle 111 can upload the driving data of passing through the change space together with the target road change information to the server 130. The aforementioned driving data may include but is not limited to the passage plan, whether it passes smoothly, whether there is an abnormality and specific abnormal problems, and may also include vehicle data, passing time, weather conditions (for example, visibility at the time), road condition information (for example, the degree of road congestion at the time), etc.

[0054] Step 320 , clustering the multiple target road change information based on at least one of the change space, change time and change type of the multiple target road change information to obtain at least one comprehensive change information. In some embodiments, step 320 is performed by the comprehensive change module 220 .

[0055] Comprehensive change information may refer to change information related to the same change event after being merged. A change event may refer to an event in which road-related content changes. It is understandable that, for a change event in a certain area, the server 130 may obtain multiple target road change information of the change event (for example, multiple different reference vehicles 111 have detected the change event during driving and uploaded the target road change information corresponding to the change event), and the server 130 may merge the aforementioned multiple target road change information to determine the comprehensive change information corresponding to the change event.

[0056] Similar to the target road change information, the comprehensive change information may include but is not limited to the change area, change time, change type, high-precision road elements before the change, road semantic elements after the change, degree of change and change identification of the corresponding change event. The aforementioned change area may refer to the area where the change event occurs.

[0057] Each of the at least one comprehensive change information may be related to at least one target road change information. At least one of the change space, change time, and change type corresponding to the target road change information related to the comprehensive change information is the same or similar. For example, a comprehensive change information is the change information after merging three target road change information, and the aforementioned three target road change information are all related to the lane marking changes of road A within the same time range.

[0058] In some embodiments, the comprehensive change module 220 may cluster the multiple target road change information based on at least one of the change space, change time, and change type of the multiple target road change information, so as to determine whether the multiple target road change information are related to the same change event. The clustering method of the aforementioned clustering may include but is not limited to Euclidean clustering, K-means clustering, agglomerative hierarchical clustering, etc.

[0059] Exemplarily, the comprehensive change module 220 can vectorize the change space and change type of multiple target road change information, and perform Euclidean clustering based on the change space and change type, and determine whether the multiple target road change information belong to the same change event through the vector distance corresponding to the multiple target road change information.

[0060] In some embodiments, after clustering, the multiple target road change information can be divided into at least one combination, and each combination corresponds to a change event. The comprehensive change module 220 can determine the comprehensive change information corresponding to the change event based on the target road change information of each combination. Among them, the change area in the comprehensive change information can be determined based on the change space of the target road change information in the corresponding combination. For example, the change area in the aforementioned comprehensive change information can be determined based on the intersection or union of the change space of the target road change information in the corresponding combination. The high-precision road element before the change can be determined by obtaining the high-precision map corresponding to the change area and based on the aforementioned high-precision map. The road semantic element after the change can be determined based on the change type of the target road change information. The degree of change of the change event can be determined based on the degree of change of the target road change information in the combination. For example, the comprehensive change module 220 can determine the maximum value, minimum value, or mean value of the degree of change of the target road change information in the combination as the degree of change of the corresponding change event.

[0061] In some embodiments, when a change event is only related to one target road change information, the comprehensive change module 220 can determine the comprehensive change information corresponding to the change event based on the target road change information. For example, the comprehensive change module 220 can directly determine the target road change information corresponding to the change event as the comprehensive change information corresponding to the change event.

[0062] In some embodiments, when a change event is related to multiple target road change information, the comprehensive change module 220 can fuse the multiple target road change information to determine the comprehensive change information corresponding to the change event. The above fusion method can be probability fusion, model fusion, etc. or other feasible methods.

[0063] In some embodiments, the comprehensive change module 220 can also cluster multiple target road change information based on the change space and change time to obtain at least one change combination; cluster the same type of target road change information in at least one change combination based on the change type to obtain at least one comprehensive change information of the target area. For more information about the above embodiments, please refer to Figure 4 and its related description.

[0064] In some embodiments, the comprehensive change module 220 may perform step 320 at a fixed frequency. For example, the comprehensive change module 220 may perform step 320 once every 2 hours. In some embodiments, when the target road change information meets a preset condition, the comprehensive change module 220 may perform step 320. For example, the preset condition may be that the number of target road change information meets a preset threshold (e.g., 5).

[0065] Step 330 : for each piece of comprehensive change information, generate the affected surface information of the comprehensive change information. In some embodiments, step 330 is performed by the generation module 230 .

[0066] The affected surface information may refer to the relevant information of the affected surface corresponding to the comprehensive change information. In some embodiments, the affected surface information includes the changed area of ​​the comprehensive change information and the degree of change of the changed area. Similar to the comprehensive change information, the affected surface information may also include the change type, the high-precision road elements before the change, the road semantic elements after the change, and the change mark.

[0067] In some embodiments, the affected surface information may include an affected range. The affected range may refer to a range that may be affected by the change event. The generation module 230 may determine the affected range based on the change area of ​​the aforementioned comprehensive change information. The generation module 230 may directly determine the change area of ​​the comprehensive change information as the affected range. The generation module 230 may also expand the change area by a preset range to determine the affected range. For example, with the change area as the center and 20M as the radius, a circular range is extended outward, and the aforementioned circular range is determined as the affected range. The generation module 230 may also expand based on the change area and its adjacent road elements to determine the affected range. For example, a section of road between two intersections, this section of road is fenced from the middle, causing half of the section of road to change from three lanes to two lanes. Correspondingly, the changed area is a section of the road that changes from three lanes to two lanes. However, due to the large traffic volume on this section of the road, the reduction of lanes will cause congestion on the entire road, and the entire road may be affected. Therefore, the generation module 230 can expand the changed area to the other half of the road section adjacent to it that has not changed, and expand the affected range to the entire road.

[0068] In some embodiments, the affected surface information may also include affected terminals. The affected terminals may refer to smart driving vehicles that may be affected by the change event. The generation module 230 may obtain the driving data of each smart driving vehicle after receiving permission from the smart driving vehicle, and determine the vehicles whose driving routes in the aforementioned driving data involve the affected range as affected terminals.

[0069] In some embodiments, the affected surface information may also include potential movement control solutions for the aforementioned changed area. The aforementioned potential movement control solution may refer to a solution for controlling the intelligent driving vehicle to pass through the changed area. The affected surface information may include one or more potential movement control solutions for the changed area.

[0070] In some embodiments, the potential mobile control scheme may include whether it is necessary to bypass the change area and / or pass through the change area (e.g., manual takeover, virtual pass area, etc.). The generation module 230 can integrate the driving data corresponding to the change area in the comprehensive change information to determine whether it is necessary to bypass the change area. For example, the generation module 230 can determine that 90% of the reference vehicles 111 cannot pass through the change area smoothly based on the driving data corresponding to the change area, then the potential mobile control scheme is to bypass the change area, or manually take over to pass through the change area. For another example, the generation module 230 can determine that 90% of the reference vehicles 111 can pass through the change area smoothly based on the driving data corresponding to the change area, or that there are problems when passing through the change area, but they can still pass, or the problems are not serious, then the potential mobile control scheme may be that there is no need to bypass the change area, and further, the generation module 230 can also fit a pass area based on the implementation trajectory of these reference vehicles 111 through the change area, and determine the specific potential mobile control scheme based on the aforementioned pass area.

[0071] In some embodiments, when there is no need to bypass the changed area, the potential mobility control scheme may also include other contents. For example, the potential mobility control scheme may also include a specific traffic scheme (e.g., a virtual traffic zone) for passing through the changed area determined based on driving data, and may also include vehicle data (e.g., vehicle model, size, etc.), passing time, driving weather, driving road conditions, etc. applicable to each potential mobility control scheme for the same changed area.

[0072] In some embodiments, the affected surface information can be used to enable the terminal to perform mobile control operations based on the high-precision map and the affected surface information. For example, the affected surface represents that the road in a certain area is closed, and the terminal needs to drive around it. For another example, the affected surface represents that only a certain lane in a certain area is closed, and other lanes can be driven normally. The terminal can pass through the area and determine the corresponding mobile control plan to allow the terminal to drive in other lanes. For another example, the affected surface represents that the speed limit sign in a certain area has been changed, then the terminal can pass through the area and determine the corresponding mobile control plan to allow the terminal to pass through the area at an appropriate speed.

[0073] The server 130 can determine the affected terminal through the affected surface information. For each affected terminal, in some embodiments, the server 130 can determine the cost of the affected terminal passing through the changed area based on the affected surface information. The aforementioned cost value represents the degree of influence of the affected terminal passing through the changed area on the affected terminal. For example, the server 130 can determine the cost of the affected terminal passing through the changed area based on the affected surface information through a preset cost relationship table. For another example, the server 130 can also determine the cost of the affected terminal passing through the changed area through a machine learning model based on the affected surface information and the vehicle data, driving requirements (for example, the fastest passing time, the shortest detour, etc.) and driving information (for example, the weather and road congestion level of the affected terminal at present) of the affected terminal. The aforementioned machine learning model can be obtained through training, and the training samples include sample affected surface information and sample vehicle data, sample driving requirements and sample driving information of the sample affected terminal, and the training labels include the cost values ​​obtained by manually marking the sample affected terminal passing through the changed area.

[0074] When the contemporary value is greater than or equal to the preset cost value threshold, the server 130 can enable the affected terminal to bypass the change area in advance and re-plan the driving route for the affected terminal. When the contemporary value is less than the preset cost value threshold, the server 130 can further determine the mobile control scheme of the affected terminal. For example, the server 130 can vectorize the potential mobile control scheme, generate a reference feature vector and store it in the database. The server 130 can generate a retrieval feature vector based on the vehicle data, driving requirements and driving information of the affected terminal, and search in the database based on the retrieval feature vector to determine the reference feature vector with the smallest vector distance, and determine the potential mobile control scheme corresponding to the reference feature vector as the mobile control scheme of the affected terminal for the change area. The server 130 can send the aforementioned mobile control scheme to the affected terminal, so that the affected terminal can perform mobile control operations based on the high-precision map and the mobile control scheme, and pass through the change area smoothly.

[0075] It is understandable that the aforementioned determination of whether the affected terminal needs to bypass the changed area by calculating the cost value and the determination of the corresponding mobile control solution of the affected terminal can also be performed by the control component of the vehicle. For example, the server 130 sends the affected surface information to the vehicle, and the vehicle determines whether it needs to bypass the changed area and determines the corresponding mobile control solution by calculating the cost value.

[0076] In some embodiments, for each comprehensive change information, when the server 130 obtains the updated high-precision map of the change area corresponding to the comprehensive change information, the server 130 may stop sending the affected information to the affected terminal. The terminal that may pass through the aforementioned change area can perform intelligent driving based on the updated high-precision map. In addition, the server 130 can also send the updated high-precision map to the affected terminal, and after the affected terminal receives the updated high-precision map, it can automatically delete the previous affected surface information.

[0077] Some embodiments of the present specification process multiple target road change information to determine at least one change event and its corresponding comprehensive change information, and generate affected surface information corresponding to each change event, so that based on the affected surface information, it can be ensured that the affected terminal can smoothly pass through the change area during the time period between the change and the update of the high-precision map. In addition, some embodiments of the present specification can upload a large amount of target road change information through a large number of reference vehicles, and the server 130 can analyze and process the aforementioned large amount of target road change information, and generate affected surface information based on big data analysis, so that the result is more reliable and accurate.

[0078] Figure 4 FIG. 4 is an exemplary flow chart of obtaining at least one comprehensive change information according to some embodiments of the present specification. In some embodiments, process 400 may be executed by comprehensive change module 220. Figure 4 As shown, process 400 includes the following steps:

[0079] Step 410 : clustering a plurality of target road change information based on the change space and the change time to obtain at least one change combination.

[0080] The change combination may refer to a combination of target road change information with the same or similar change space and change time. Each change combination includes at least one target road change information.

[0081] The comprehensive change module 220 can cluster the multiple target road change information by change space and change time to obtain at least one change combination. The clustering method of the above clustering can include but is not limited to Euclidean clustering, K-means clustering, agglomerative hierarchical clustering, etc.

[0082] Step 420 : clustering target road change information of the same type in at least one change combination based on the change type to obtain at least one comprehensive change information.

[0083] It is understandable that a certain change space may have multiple change events at the same change time. Therefore, for each change combination, the comprehensive change module 220 can cluster the target road change information of the same type in the change combination by the change type, and determine the target road change information of the change combination related to the same change event. The comprehensive change module 220 can also process the target road change information related to the same change event to determine the comprehensive change information corresponding to the change event. For more information about processing the target road change information related to the same change event to determine the comprehensive change information corresponding to the change event, please refer to Figure 3 and its related description.

[0084] Some embodiments of the present specification can reduce the amount of calculation for a single calculation by clustering multiple target road change information twice, quickly and accurately determine the target road change information related to the same change event, and thus determine the corresponding comprehensive change information.

[0085] Figure 5 is an exemplary flow chart of determining target road change information according to some embodiments of this specification. In some embodiments, process 500 may be executed by acquisition module 240. Figure 5 As shown, process 500 includes the following steps:

[0086] Step 510: Acquire the original road dataset of the target area.

[0087] The target area may refer to an area currently being detected by the reference vehicle 111. The reference vehicle 111 may refer to a vehicle that collects road-related data.

[0088] The original road data set may refer to a collection of original road data. The original road data set includes multiple frames of original road data, and the original road data may refer to data related to the roads in the target area. The original road data may include, but is not limited to, one or a combination of point cloud data (such as point cloud frames), image data (such as image frames), position, time, direction, speed, acceleration, etc. related to the roads in the target area. For example, the original road data set may include multiple frames of point cloud frames and image frames, and each frame of original road data may include a frame of point cloud frames and image frames. The laser point cloud in the reference vehicle 111 rotates a preset angle (for example, rotates 360°) to collect a frame of point cloud data; the camera in the reference vehicle 111 may rotate a preset angle (for example, rotates 360°) synchronously with the aforementioned laser radar to collect a frame of image data. Each frame of original road data may correspond to a sub-area in the target area. The sub-areas corresponding to multiple frames of original road data may constitute the target area. There may or may not be overlapping areas between the sub-areas. For example, the original road data set may include such as Figure 6A to Figure 6DAs shown are four image frames related to the target area, the four image frames are four sub-areas of the target area respectively, and there are overlapping areas between the sub-areas.

[0089] The reference vehicle 111 can continuously collect data on the target area based on a collection device disposed thereon, thereby obtaining an original road data set of the target area. The aforementioned collection device may include but is not limited to a laser radar, a camera, a video camera, a positioning component, a speed sensor, etc. The collection module 240 can obtain the original road data set collected by the reference vehicle 111.

[0090] Step 520: Detect the original road data set to obtain a road semantic element set in the target area.

[0091] The road semantic element set refers to a set of road semantic elements related to roads in the target area obtained based on the original road data set of the target area. Road semantic elements may refer to road elements related to roads and their attribute characteristics obtained based on the original road data set of the target area. The aforementioned road elements may include road surface elements related to the road surface and roadside elements related to the roadside. The aforementioned road surface elements include but are not limited to lane lines, stop lines, lane markings, road boundaries, sidewalks, etc., and the aforementioned roadside elements include but are not limited to traffic lights, street lights, signs, etc. The attribute characteristics of the aforementioned road elements may include but are not limited to one or more of location, category, shape, etc. For example, the road semantic elements may include the type and location of lane markings. The road semantic element set may include multiple road semantic elements related to roads in the target area.

[0092] In some embodiments, the acquisition module 240 may perform modeling or use various data analysis algorithms, such as regression analysis, discriminant analysis, etc., to detect the original road data set and obtain a road semantic element set in the target area.

[0093] In some embodiments, for each frame of original road data, the acquisition module 240 may detect the original road data to obtain the road semantic element of the sub-region. Figure 7 and its related description.

[0094] Step 530: Obtain a high-precision road element set in the target area.

[0095] A high-precision road element set refers to a set of high-precision road elements related to roads in a target area in a high-precision map. Similar to road semantic elements, high-precision road elements can refer to road elements and their attribute features related to roads in a target area in a high-precision map. A high-precision road element set can include multiple high-precision road elements related to roads in a target area.

[0096] The acquisition module 240 can obtain the location information of the target area based on the positioning device set on the reference vehicle 111, perform matching based on the aforementioned location information, obtain a high-precision map of the target area, and thus obtain a high-precision road element set of the target area from the high-precision map.

[0097] Step 540: Determine target road change information of the target area based on the high-precision road element set and the road semantic element set.

[0098] The acquisition module 240 can compare the high-precision road element set and the road semantic element set through various methods to determine the changed road semantic elements (ie, the changed road semantic elements).

[0099] For example, the acquisition module 240 can construct graph structure data based on the high-precision road element set, where the nodes are related to the high-precision road elements, and the edges are related to the positional connection relationship between each high-precision road element, and construct the graph structure data of the road semantic element set in a similar way. By comparing the two graph structure data, it is determined whether the target area has changed. When a change occurs, the nodes and / or edges that have changed in the graph structure data are further determined to determine the road semantic elements that have changed.

[0100] In some embodiments, the acquisition module 240 can determine the target road change information based on the changed road semantic elements. For example, the acquisition module 240 can determine the position of the changed road semantic elements, thereby determining the change space of the target road change information and the high-precision road elements before the position is changed. For another example, the acquisition module 240 can also determine the change type and degree of change based on the high-precision road elements before the change and the road semantic elements after the change. For example, the high-precision road elements before the change represent the road signs in the changed area as being able to go straight and turn right, while the road semantic elements after the change represent the road signs in the changed area as being only able to go straight. The acquisition module 240 can also determine the change type as a lane sign change. The acquisition module 240 can also determine the corresponding degree of change based on the change type through a preset change relationship table. For example, the preset change relationship table includes: reducing the degree of change corresponding to the drivable direction in the lane sign to level III.

[0101] In some embodiments, for each frame of raw road data, the acquisition module 240 can also determine the initial road change information of the sub-region based on the high-precision road elements and road semantic elements of the sub-region; track the initial road change information corresponding to multiple frames of raw road data to determine the target road change information of the target area. For more information about the above embodiments, please refer to Figure 7 and its related description.

[0102] Some embodiments of the present specification can determine the target road change information of the target area through the original road data set of the aforementioned target area, and can detect the road in real time to avoid driving risks caused by road changes and ensure the normal progress of intelligent driving.

[0103] Figure 7 is an exemplary flow chart of determining the target road change information of the target area according to some embodiments of this specification. In some embodiments, process 700 may be executed by the acquisition module 240. Figure 7 As shown, process 700 includes the following steps:

[0104] For each frame of original road data, the acquisition module 240 may perform the following steps 710 to 730 to obtain initial road change information of the sub-area corresponding to the frame of original road data:

[0105] Step 710: Detect the original road data to obtain the road semantic elements of the sub-area.

[0106] The acquisition module 240 may perform modeling or use various data analysis algorithms, such as regression analysis, discriminant analysis, etc., to detect the original road data of the frame and obtain the road semantic elements of the sub-area.

[0107] In some embodiments, the acquisition module 240 can process the frame of raw road data based on the road semantic detection model to determine the road semantic elements of the corresponding sub-area. The acquisition module 240 can input a frame of raw road data (for example, an image frame and / or a point cloud frame) into the road semantic detection model, and the output of the road semantic detection model is the road semantic elements of the corresponding sub-area (i.e., road elements and the type, position, shape and other attribute characteristics of the aforementioned road elements). The aforementioned road semantic detection model can be a machine learning model. For example, a machine learning model built based on BEV fusion. Exemplarily, the acquisition module 240 can be such as Figure 6C The image frame shown is input into a road semantic detection model, and the output of the road semantic detection model may include lane lines and road signs for the sub-area.

[0108] The aforementioned road semantic detection model may be obtained through training, the training samples may include sample original road data, and the training labels may include sample road semantic elements corresponding to the aforementioned sample original road data obtained through manual annotation.

[0109] In some embodiments, the acquisition module 240 can also optimize the road semantic elements of the sub-region output by the road semantic detection model based on the vectorization post-processing algorithm to obtain the optimized road semantic elements of the sub-region. The vectorization post-processing algorithm can optimize the road semantic elements of the sub-region based on the characteristics of the preset road semantic elements and the constraint relationship between different road semantic elements. For example, when the road semantic elements include stop lines and lane lines, the acquisition module 240 can optimize the geometric positions of the stop lines and lane lines based on the preset constraint relationship between the stop lines and lane lines.

[0110] Step 720: Obtain high-precision road elements of the sub-area.

[0111] Step 730: Determine initial road change information of the sub-region based on the high-precision road elements and road semantic elements of the sub-region.

[0112] Initial road change information may refer to relevant information about road changes in a sub-region obtained based on the high-precision road elements and road semantic elements corresponding to the sub-region. Similar to the target road change information, the initial road change information may include but is not limited to the change space, change time, change type, high-precision road elements before the change, and road semantic elements after the change of the road-related content in the corresponding sub-region.

[0113] The acquisition module 240 can compare and analyze the high-precision road elements and road semantic elements of the sub-region to determine whether the road-related content in the sub-region has changed. For example, the acquisition module 240 can process the high-precision road elements and road semantic elements of the sub-region into graph structure data, and determine the initial road change information of the sub-region by comparing the two graph structure data. Regarding determining the initial road change information of the sub-region through the graph structure data, please refer to the previous text of this specification, whether the road-related content in the sub-region has changed through the graph structure data.

[0114] When the sub-region changes, the acquisition module 240 can determine the changed road semantic element (i.e., the changed road semantic element), thereby determining the initial road change information of the sub-region. For more information about determining the initial road change information of the sub-region through the changed road semantic element, please refer to the related description of determining the target road change information based on the changed road semantic element in the previous text of this specification.

[0115] In some embodiments, the acquisition module 240 may decompose the high-precision road elements corresponding to the sub-region into first geometric semantic units; and decompose the road semantic elements corresponding to the sub-region into second geometric semantic units.

[0116] The first geometric semantic unit may refer to data after simplifying the high-precision road elements based on preset simplification rules. The second geometric semantic unit may refer to data after simplifying the road semantic elements based on preset simplification rules. Among them, the simplification rules for simplifying the high-precision road elements and the road semantic elements may be the same. Taking the high-precision road elements as an example, the acquisition module 240 can model and express the high-precision road elements through the same preset simplification rules, and disassemble them into the most basic geometric semantic units (for example, simple point, line, and surface geometric semantic elements). For high-precision map elements, the acquisition module 240 can retain their element number mapping relationship.

[0117] In some embodiments, the acquisition module 240 may match the first geometric semantic unit with the second geometric semantic unit; and determine the initial road change information corresponding to the sub-region based on the matching result. The aforementioned matching result may refer to the judgment result of whether the first geometric semantic unit and the second geometric semantic unit match. The acquisition module 240 may establish two sets of spatial query trees based on the first geometric semantic unit and the second geometric semantic unit, and match them with each other. When the matching result responds to a mismatch, it is determined that the sub-region has changed, and the acquisition module 240 may further determine the initial road change information of the sub-region. For example, the first geometric semantic unit indicates that the sub-region includes lane line 1, and the second geometric semantic unit indicates that there is no lane line 1, then the acquisition module 240 may determine that the sub-region has changed and the corresponding initial road change information.

[0118] It is understandable that because the online perception perspective technology of the reference vehicle 111 or other similar reasons may lead to incomplete observation, the acquisition module 240 can also filter out uninteresting results in the initial road change information based on constraints such as perspective occlusion relationships. For example, there is a lane line 2 in the sub-area, but because the lane line 2 is occluded when the road semantic detection model is generated, the corresponding change can be filtered in the corresponding initial road change information. The above method can be used to align high-precision road elements and road semantic elements for comparison, so that it can be quickly and conveniently determined whether the sub-area has changed, and the initial road change information when the change occurs can be further determined.

[0119] In some embodiments, the acquisition module 240 may process each raw road data to determine whether a change occurs in the corresponding sub-area. When a change occurs in the sub-area corresponding to a raw road data, the acquisition module 240 may perform the following steps 740 to track the subsequent raw road data to comprehensively evaluate the target road change information of the target area:

[0120] Step 740 , tracking the initial road change information corresponding to the multiple frames of original road data to determine the target road change information of the target area.

[0121] The acquisition module 240 can track the initial road change information corresponding to the multiple frames of original road data through a probability model or other similar feasible methods, and after accumulating the initial road change information corresponding to the multiple frames of original road data, determine the target road change information of the target area. Figure 6B to Figure 6D The initial road change information corresponding to the image frame shown is tracked and accumulated Figure 6B to Figure 6D After obtaining the initial road change information corresponding to the image frame shown, the target road change information of the target area can be determined.

[0122] Some embodiments of the present specification evaluate whether the sub-region corresponding to the original road data has changed frame by frame. The aforementioned frame-by-frame evaluation can reduce the amount of calculation at each calculation and quickly determine whether each sub-region has changed. If necessary, the original road data that has changed and the original road data thereafter can be tracked to determine the target road change information of the target area, thereby avoiding unnecessary waste of computing resources.

[0123] It is worth noting that the aforementioned processes 500 and 700 can be executed by the reference vehicle 111, and the reference vehicle 111 can also transmit relevant data (eg, original road data set) to the server 130 in real time, and the server 130 determines the target road change information.

[0124] The present specification also provides a road change information processing device, comprising a processor, wherein the processor is used to execute a road change information processing method as described in any one of the aforementioned embodiments of the present specification.

[0125] This specification also provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the road change information processing method as described in any of the aforementioned embodiments of this specification.

[0126] The solutions described in this specification and in the examples, if they involve the processing of personal information, will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0127] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0128] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0129] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0130] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0131] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0132] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0133] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for processing road change information, characterized in that: include: Obtain multiple target road change information; Clustering the plurality of target road change information based on at least one of a change space, a change time, and a change type of the plurality of target road change information to obtain at least one comprehensive change information; For each piece of comprehensive change information, the affected surface information of the comprehensive change information is generated, wherein the affected surface information includes a changed area of ​​the comprehensive change information and a change degree of the changed area.

2. The method according to claim 1, characterized in that At least one of the plurality of target road change information is generated based on the following operations: Obtain the original road dataset of the target area; Detecting the original road data set to obtain a road semantic element set of the target area, wherein the road semantic element set includes a plurality of road semantic elements; Acquire a high-precision road element set of the target area, wherein the high-precision road element set includes a plurality of high-precision road elements; According to the high-precision road element set and the road semantic element set, target road change information of the target area is determined.

3. The method according to claim 2, characterized in that The original road data set includes multiple frames of original road data, wherein each frame of original road data corresponds to a sub-area in the target area; At least one of the plurality of target road change information is generated based on the following operations: For each frame of raw road data, Detecting the original road data to obtain the road semantic elements of the sub-area; Acquire the high-precision road element of the sub-area; Determining initial road change information of the sub-area according to the high-precision road element and the road semantic element of the sub-area; The initial road change information corresponding to the multiple frames of original road data is tracked to determine the target road change information of the target area.

4. The method according to claim 3, characterized in that The determining, according to the high-precision road element and the road semantic element of the sub-area, the initial road change information of the sub-area comprises: Decomposing the high-precision road element corresponding to the sub-region into first geometric semantic units; Decomposing the road semantic element corresponding to the sub-region into second geometric semantic units; Matching the first geometric semantic unit and the second geometric semantic unit; The initial road change information corresponding to the sub-area is determined according to the matching result.

5. The method according to claim 1, characterized in that The clustering of the plurality of target road change information based on at least one of a change space, a change time, and a change type of the plurality of target road change information to obtain at least one comprehensive change information comprises: Clustering the plurality of target road change information based on the change space and the change time to obtain at least one change combination; The target road change information of the same type in the at least one change combination is clustered based on the change type to obtain the at least one comprehensive change information.

6. The method according to claim 1, characterized in that The affected surface information also includes potential movement control solutions for the changed area.

7. The method according to claim 1, characterized in that The affected surface information is used to enable the terminal to perform a mobile control operation based on the high-precision map and the affected surface information.

8. A road change information processing system, characterized in that: include: An acquisition module, used for acquiring multiple target road change information in a target area; a comprehensive change module, configured to cluster the plurality of target road change information based on at least one of a change space, a change time, and a change type of the plurality of target road change information to obtain at least one comprehensive change information; A generating module is used to generate, for each piece of the comprehensive change information, affected surface information of the comprehensive change information, wherein the affected surface information includes a changed area of ​​the comprehensive change information and a change degree of the changed area.

9. A road change information processing device, comprising a processor, characterized in that: The processor is used to execute the road change information processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the road change information processing method according to any one of claims 1 to 7.

Images