Map data updating method and device, equipment, storage medium and program product

Abstract

The present disclosure provides a map data updating method and device, equipment, storage medium and program product, relates to the technical field of map, and especially relates to the technical field of high-precision map. The specific implementation scheme is: acquiring survey line data, wherein the survey line data comprises road data of an updated road; assuming that the updated road is connected to an existing road in map data according to the road data, to obtain an assumed connection relationship between the updated road and the existing road; verifying the assumed connection relationship in a multi-modal manner to obtain an assumed connection verification result; and adding the updated road to the map data based on the assumed connection verification result. The present disclosure can improve the accuracy of map data updating.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of map, in particular to the technical field of high-definition map, and specifically to a map data updating method, device, equipment, storage medium and program product. BACKGROUND

[0002] It is often necessary to update roads in map data. Currently, the main way to update roads in map data is for workers to obtain updated road data using a collection vehicle, and then to connect the updated road to an existing road in the map data according to experience, thereby completing map data updating. SUMMARY

[0003] The present disclosure provides a map data updating method, device, equipment, storage medium and program product.

[0004] According to an aspect of the present disclosure, a map data updating method is provided, comprising:

[0005] obtaining survey line data, the survey line data comprising road data of an updated road;

[0006] connecting the updated road to an existing road in map data according to the road data, to obtain a hypothetical connection relationship between the updated road and the existing road;

[0007] verifying the hypothetical connection relationship in a multi-modal manner, to obtain a hypothetical connection verification result;

[0008] adding the updated road to the map data based on the hypothetical connection verification result.

[0009] According to another aspect of the present disclosure, a map data updating device is provided, comprising:

[0010] a obtaining module configured to obtain survey line data, the survey line data comprising road data of an updated road;

[0011] a connecting module configured to connect the updated road to an existing road in map data according to the road data, to obtain a hypothetical connection relationship between the updated road and the existing road;

[0012] a verifying module configured to verify the hypothetical connection relationship in a multi-modal manner, to obtain a hypothetical connection verification result;

[0013] an updating module configured to add the updated road to the map data based on the hypothetical connection verification result.

[0014] According to another aspect of the present disclosure, an electronic device is provided, comprising:

[0015] at least one processor; and

[0016] a memory in communication connection with the at least one processor; wherein

[0017] The memory has stored instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the map data updating method provided by the present disclosure.

[0018] According to another aspect of the present disclosure, a non-transitory computer readable storage medium having stored computer instructions is provided, wherein the computer instructions are used to enable the computer to perform the map data updating method provided by the present disclosure.

[0019] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the map data updating method provided by the present disclosure.

[0020] In the present disclosure, since the assumed connection of the updated road and the existing road is verified in a multi-modal manner, and the updated road is added to the map data based on the assumed connection verification result, the accuracy of the map data updating can be improved.

[0021] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0022] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0023] Figure 1 is a flowchart of a map data updating method provided by the present disclosure;

[0024] Figure 2 is a schematic diagram of an assumed connection provided by the present disclosure;

[0025] Figure 3 is a schematic diagram of vehicle trajectory verification provided by the present disclosure;

[0026] Figure 4 is a schematic diagram of another vehicle trajectory verification provided by the present disclosure;

[0027] Figure 5 is a schematic diagram of another vehicle trajectory verification provided by the present disclosure;

[0028] Figure 6 is a schematic diagram of image data verification provided by the present disclosure;

[0029] Figure 7is a schematic diagram of a passable path provided by the present disclosure;

[0030] Figures 8a to 8c is a structural diagram of a map data updating device provided by the present disclosure;

[0031] Figure 9 is a block diagram of an electronic device for implementing the video generation method of the embodiments of the present disclosure. DETAILED DESCRIPTION

[0032] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, and should be considered as merely exemplary. Thus, those skilled in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, for the sake of brevity and clarity, descriptions of well-known functions and constructions are omitted from the following description.

[0033] Please refer to Figure 1 , Figure 1 is a flowchart of a map data updating method provided by the present disclosure, as shown in Figure 1 , comprising the following steps:

[0034] Step S101, acquiring survey line data, the survey line data comprising road data of an updated road.

[0035] The survey line data can be data collected by a vehicle or data collected by a satellite positioning system.

[0036] The survey line data can comprise road data of one or more updated roads, and the road data can represent information such as the position, size, shape, etc. of the updated data.

[0037] In the present disclosure, the map data can be high-definition map data.

[0038] Step S102, assuming that the updated road is connected to an existing road in the map data according to the road data, to obtain an assumed connection relationship between the updated road and the existing road.

[0039] The existing road is one or more roads in the map data that match the position of the updated road, or one or more roads that are logically connected to the updated road.

[0040] The above-mentioned connecting the updated road to the existing road in the map data can be establishing the assumed connection relationship between the updated road and the existing road in the map data, and specifically can be establishing all the assumed connection relationships between the updated road and the existing road in the map data, such as full connection according to the geometry of the updated road. For example, for the updated road at an existing intersection, the updated road is directly connected to all the logical passing points of the intersection, and for the updated road at a non-intersection position, the existing road can be disconnected first and then full connection is performed.

[0041] In step S103, the assumed connection relationship is verified by a multi-modal manner to obtain an assumed connection verification result.

[0042] The above-mentioned verifying the assumed connection relationship by a multi-modal manner can be verifying the assumed connection relationship by multiple manners, for example, verifying the assumed connection relationship by vehicle trajectory data and image road.

[0043] The assumed connection verification result can represent the passable path and the impassable path included in the assumed connection relationship.

[0044] In step S104, the updated road is added to the map data based on the assumed connection verification result.

[0045] The above-mentioned adding the updated road to the map data based on the assumed connection verification result can be deleting the impassable path, retaining the other passable paths, and updating to the map data in the case that the assumed connection verification result represents that there is an impassable path, or directly updating the updated road to the map data based on the assumed connection relationship in the case that the assumed connection verification result represents that all are passable paths.

[0046] In the present disclosure, the assumed connection relationship between the updated road and the existing road can be verified by a multi-modal manner through the above-mentioned steps, and the updated road is added to the map data based on the assumed connection verification result, which can improve the accuracy of the map data updating.

[0047] It should be noted that the map data updating method provided by the present disclosure can be executed by an electronic device, such as a server, a computer, a mobile phone, and the like.

[0048] As an optional implementation manner, the assumed connection relationship includes at least one logically connected path.

[0049] The assumed connection relationship is verified by a multi-modal manner to obtain an assumed connection verification result, and the assumed connection verification result includes:

[0050] The logical communication paths are verified by the multi-modal manner respectively to obtain a hypothesis connection verification result, wherein the hypothesis connection verification result is used to indicate at least one of the following:

[0051] The passable path and the impassable path.

[0052] The logical communication path can be a path that logically exists in a communication relationship, for example, as shown in Figure 2 Figure 2 The thick black line represents an updated road, the dashed line represents a logical communication relationship, and the black solid line represents an existing road in the road network. For example, for the updated road of intersection 1, the hypothesis connection relationship can include the logical communication path shown by the three dashed lines as shown in Figure 2 For the updated road of intersection 2, the hypothesis connection relationship can include the logical communication path of the updated road and the opposite road of the intersection, and the logical communication path of the updated road and the self-side road of the intersection as shown in Figure 2 For the updated road of intersection 3, the hypothesis connection relationship can include the logical communication path of the updated road and the opposite road of the intersection, and the logical communication path of the updated road and the self-side road of the intersection as shown in Figure 3

[0053] It should be noted that Figure 2 is only an example, and the present disclosure can be assumed to meet various needs according to actual conditions when setting the hypothesis connection. In addition, different hypothesis connection methods can be used for different types of roads when assuming the connection, for example, in the case of including separated roads and non-separated roads in the existing roads, the breaking rules for the separated roads and the non-separated roads are different when assuming the connection, for example, the separated roads need to consider whether to break the separation line to assume the connection, and the non-separated roads do not need to be considered.

[0054] The hypothesis connection verification result is used to indicate whether each logical communication path is a passable path or an impassable path.

[0055] In this embodiment, it can be realized that whether each logical communication path is a passable path or an impassable path is verified by the multi-modal manner, so as to improve the accuracy of verification, and further improve the accuracy of map data updating.

[0056] It should be noted that the present disclosure does not limit the verification of each logical communication path by the multi-modal manner, for example, in some scenarios or embodiments, the multi-modal verification can also be performed for part of the logical communication paths, and the non-modal verification, i.e., single-mode verification, is performed for another part of the logical communication paths.

[0057] ​​Optionally, the verification of each logical communication path by the multi-modal manner respectively obtains a hypothesis connection verification result, including:

[0058] The vehicle trajectory verification of each logical communication path by the acquired vehicle trajectory data obtains a first verification result, the first verification result is used to indicate at least one of the candidate passable path and the impassable path, the vehicle trajectory data has the trajectory data matched with the candidate passable path, and the vehicle trajectory data does not have the trajectory data matched with the impassable path.

[0059] The road image verification of the candidate passable path by the acquired road image data corresponding to the candidate passable path obtains a second verification result, the second verification result is used to indicate that the candidate passable path is a passable path or an impassable path.

[0060] The vehicle trajectory data can be the trajectory data of the vehicle driving on the updated road pre-acquired.

[0061] The candidate passable path can be understood as that the vehicle trajectory data has the trajectory data matched with the candidate passable path. The impassable path can be understood as that the vehicle trajectory data does not have the trajectory data matched with the impassable path. For example, as shown in Figure 3 there is the trajectory data of turning right and left from the updated road into the intersection, the logical communication path between the updated road and the straight road of the intersection is the candidate passable path, but there is no trajectory data of straight driving from the updated road into the intersection, so the logical communication path between the updated road and the opposite road of the intersection is the impassable path; for example, as shown in Figure 4 there is the trajectory data of turning right and left from the updated road into the intersection, the logical communication path between the updated road and the straight road of the intersection is the candidate passable path, but there is no trajectory data of straight driving from the updated road into the intersection, so the logical communication path between the updated road and the opposite road of the intersection is the impassable path; for example, as shown in Figure 5 there is the trajectory data of turning right and left from the updated road into the intersection, the logical communication path between the updated road and the straight road of the intersection is the candidate passable path, but there is no trajectory data of straight driving from the updated road into the intersection, so the logical communication path between the updated road and the opposite road of the intersection is the impassable path.

[0062] The road image data corresponding to the candidate passable path can be the image data collected at the position corresponding to the candidate passable path.

[0063] The road image verification of the candidate passable path by the acquired road image data corresponding to the candidate passable path can be that whether the candidate passable path is passable is judged according to the road image data, for example, when the road image data indicates that the candidate passable path has no construction, no obstacle or the pavement laying state meets the conventional road requirements, it is determined as the passable path, and vice versa.

[0064] In this embodiment, the road image verification is performed on the candidate passable path, so that the accuracy of the map data updating is further improved.

[0065] Optionally, the road image verification on the candidate passable path is performed by using the acquired road image data corresponding to the candidate passable path, and a second verification result is obtained.

[0066] The acquired road image data corresponding to the candidate passable path is subjected to semantic segmentation, and a semantic segmentation result is obtained.

[0067] It is determined, based on the semantic segmentation result, whether the road image data includes an obstacle.

[0068] In a case where the road image data includes the obstacle, the obstacle is classified, and the second verification result is obtained based on the classification.

[0069] In a case where the road image data does not include the obstacle, a second verification result is obtained, and the second verification result indicates that the candidate passable path is a passable path.

[0070] The semantic segmentation on the acquired road image data corresponding to the candidate passable path can be performed by using a pre-acquired image semantic segmentation model, such as a Residual Network (ResNet) segmentation network model, a Pyramid Scene Parsing Network (PSPNet), or a ResNet50+PSP segmentation network model.

[0071] The semantic segmentation result can indicate semantic information of road states such as a roadblock, a fence, and a road surface state.

[0072] In this embodiment, the semantic segmentation result can be used to more accurately verify whether the logically connected path is passable.

[0073] Optionally, in a case where the obstacle includes a preset target classification obstacle, the candidate passable path is an impassable path; in a case where the obstacle does not include the preset target classification obstacle, the candidate passable path is a passable path; or

[0074] In a case where the obstacle includes a preset target classification obstacle and the obstacle hinders the passing, the candidate passable path is an impassable path; in a case where the obstacle includes a preset target classification obstacle and the obstacle does not hinder the passing, the candidate passable path is a passable path; in a case where the obstacle does not include the preset target classification obstacle, the candidate passable path is a passable path.

[0075] The preset target classification obstacle can include a baffle, a fence, a barrier, a water-filled barrier, a sand-filled barrier, a conical ice cream cone, and the like.

[0076] When the obstacle is the preset target classification obstacle, it indicates that the vehicle trajectory data corresponding to the candidate passable path can be a special vehicle trajectory, for example, a construction vehicle performing construction on a construction site, and the logical connected path is actually impassable. When the obstacle is not the preset target classification obstacle, it indicates that the candidate passable path is passable, or in a case where the road image data does not include an obstacle, it indicates that the candidate passable path is passable.

[0077] The hindering passing can be that the obstacle representing the preset target classification obstacle hinders the passing of the vehicle in the candidate passable path.

[0078] In this embodiment, when the obstacle includes the preset target classification obstacle, the passable or impassable can be directly determined, which can save computing overhead, and further determine the passable or impassable according to whether the preset target classification obstacle hinders the passing, so as to improve the accuracy. For example, as shown in Figure 6 The method includes the following steps:

[0079] Obtaining road image data of a candidate passable path;

[0080] Performing semantic segmentation on the road image data by using a semantic segmentation model;

[0081] Classifying the obstacle based on the semantic segmentation result;

[0082] When the obstacle is not the preset target classification obstacle, it is verified that the logical connected path passes, that is, it is passable;

[0083] When the obstacle is the preset target classification obstacle, it is further analyzed whether the passing is hindered;

[0084] If the passing is not hindered, it is verified that the logical connected path passes, that is, it is passable;

[0085] If the passing is hindered, the logical connected path is deleted, that is, it is impassable.

[0086] Optionally, the vehicle trajectory verification is performed on each logical connected path based on the obtained vehicle trajectory data, and a first verification result is obtained, including:

[0087] The vehicle trajectory verification is performed on each logical connected path based on the obtained vehicle trajectory data and vehicle trajectory attribute information, and a first verification result is obtained, wherein the first verification result is used to indicate at least one of a candidate passable path and an impassable path, and is also used to indicate a confidence of each candidate passable path, and the confidence is determined based on the vehicle trajectory attribute information;

[0088] The road image verification is performed on the candidate passable path based on obtained road image data corresponding to the candidate passable path, and a second verification result is obtained, including:

[0089] In a case where the confidence is lower than a preset threshold, the road image verification is performed on the first candidate passable path based on obtained road image data corresponding to the first candidate passable path, and a second verification result is obtained, wherein the second verification result is used to indicate that the first candidate passable path is a passable path or an impassable path.

[0090] In a case where the confidence is higher than or equal to the preset threshold, the second candidate passable path is a passable path.

[0091] The vehicle trajectory attribute information can be attribute information of a vehicle, for example, a category and a model of the vehicle.

[0092] The confidence determined based on the vehicle trajectory attribute information can be that different weights are configured for different vehicle trajectory attribute information in advance, for example, a weight of a car is greater than that of a large special vehicle, so that when a proportion of the car passing through the logical connected path is higher, the confidence of the candidate passable path is higher, and vice versa.

[0093] In this embodiment, the road image verification can be performed again on the candidate passable path with low confidence, and the candidate passable path with high confidence can be directly determined as a passable path, so as to save the calculation cost.

[0094] As an optional embodiment, the adding of the updated road to the map data based on the assumed hitching verification result includes:

[0095] In a case where the assumed hitching verification result indicates that there is an impassable path, the impassable path in the assumed hitching relationship is deleted, and the updated road is added to the map data according to the deleted assumed hitching relationship.

[0096] For example, for the assumed hanging relationship as shown in Figure 2 The assumed hanging verification result is indicated as follows:

[0097] For the updated road of intersection 1, the logical connected path shown by the dashed line is an impassable path;

[0098] For the updated road of intersection 2, the logical connected path between the updated road shown by the dashed line and the opposite road of the intersection is an impassable path;

[0099] For the updated road of intersection 3, the logical connected path between the updated road shown by the dashed line and the opposite road of the intersection is an impassable path.

[0100] In this embodiment, the above logical connected path is deleted, and then the hanging relationship as shown in Figure 7 is obtained, which specifically includes the following passable paths:

[0101] For the updated road of intersection 1, the logical connected path shown by the dashed line is an impassable path;

[0102] For the updated road of intersection 2, the logical connected path between the updated road and the local road of the intersection;

[0103] For the updated road of intersection 3, the logical connected path between the updated road and the local road of the intersection.

[0104] In this embodiment, since the impassable path in the assumed hanging relationship is deleted, the updated road can be directly added to the map data according to the deleted assumed hanging relationship, so as to save the calculation overhead.

[0105] As an optional embodiment, the adding of the updated road to the map data based on the assumed hanging verification result comprises:

[0106] determining the connected relationship between the updated road and the existing road based on the assumed hanging verification result;

[0107] identifying a target road subnet to which the existing road belongs;

[0108] adding the connected relationship between the updated road and the existing road to the target road subnet to obtain an updated target road subnet;

[0109] compiling the updated target road subnet to obtain a new compilation result of the target road subnet;

[0110] replacing the original compilation result of the target road subnet in the map data with the new compilation result.

[0111] The determination of the connectivity relationship between the updated road and the existing road can be a connectivity relationship corresponding to a passable path remaining after a non-passable path in the assumed connection relationship is deleted.

[0112] The identification of the target road subnet to which the existing road belongs can be identification of a subnet including a road topology relationship of the existing road, and specifically can be calculation of the target road subnet to which the existing road belongs in units of roads.

[0113] In the present disclosure, the subnets in the map data are connected through logical attributes, that is, the subnet data is logically cut and can be extracted independently without geometric interference.

[0114] The compiling of the target road subnet after the update can be compiling of the target road subnet by a navigation end road data compiling module.

[0115] The replacement of the new compilation result for the original compilation result of the target road subnet in the map data can be replacement of all logical attribute connections of the new compilation result for the original compilation result of the map data.

[0116] In this embodiment, a subnet-based incremental compilation mode can be implemented, the efficiency of map data update is improved, and the compiled data can be directly published.

[0117] In the present disclosure, the assumed connection relationship between the updated road and the existing road is verified in a multi-modal manner, the updated road is added to the map data based on the assumed connection verification result, and thus the accuracy of map data update is improved.

[0118] In the technical solution of the present disclosure, the acquisition, storage, and application of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0119] Please refer to Figure 8a , Figure 8a A map data updating device provided by the present disclosure, as shown in Figure 8a The map data updating device 800 includes:

[0120] The acquisition module 801 is configured to acquire survey line data, the survey line data including road data of an updated road.

[0121] The connection module 802 is configured to assume connection of the updated road to an existing road in map data according to the road data, to obtain an assumed connection relationship between the updated road and the existing road.

[0122] The verification module 803 is configured to verify the assumed connection relationship in a multi-modal manner, to obtain an assumed connection verification result.

[0123] The updating module 804 is configured to add the updated road into the map data based on the assumed hitching verification result.

[0124] Optionally, the assumed hitching relationship includes at least one logical connected path.

[0125] The verification module 803 is configured to verify each logical connected path in a multi-modal manner to obtain an assumed hitching verification result, where the assumed hitching verification result is used to indicate at least one of the following:

[0126] A passable path and an impassable path.

[0127] Optionally, as shown in Figure 8b The verification module 803 includes:

[0128] The first verification unit 8031 is configured to perform vehicle trajectory verification on each logical connected path by using the obtained vehicle trajectory data to obtain a first verification result, where the first verification result is used to indicate at least one of a candidate passable path and an impassable path, there is trajectory data matching the candidate passable path in the vehicle trajectory data, and there is no trajectory data matching the impassable path in the vehicle trajectory data.

[0129] The second verification unit 8032 is configured to perform road image verification on the candidate passable path by using the obtained road image data corresponding to the candidate passable path to obtain a second verification result, where the second verification result is used to indicate whether the candidate passable path is a passable path or an impassable path.

[0130] Optionally, the second verification unit 8032 is configured to:

[0131] perform semantic segmentation on the obtained road image data corresponding to the candidate passable path to obtain a semantic segmentation result;

[0132] determine whether the road image data includes an obstacle based on the semantic segmentation result;

[0133] in a case where the road image data includes an obstacle, classify the obstacle, and obtain the second verification result based on the classification;

[0134] in a case where the road image data does not include an obstacle, obtain the second verification result, where the second verification result indicates that the candidate passable path is a passable path.

[0135] Optionally, in a case where the obstacle includes a preset target classification obstacle, the candidate passable path is an impassable path; in a case where the obstacle does not include the preset target classification obstacle, the candidate passable path is a passable path; or

[0136] in a case where the obstacle includes a preset target classification obstacle and the obstacle hinders passing, the candidate passable path is an impassable path; in a case where the obstacle includes a preset target classification obstacle and the obstacle does not hinder passing, the candidate passable path is a passable path; in a case where the obstacle does not include the preset target classification obstacle, the candidate passable path is a passable path.

[0137] Optionally, the first verification unit 8031 is configured to perform vehicle trajectory verification on each logical connected path respectively by using the acquired vehicle trajectory data and vehicle trajectory attribute information, to obtain a first verification result, wherein the first verification result is used to indicate at least one of a candidate passable path and an impassable path, and is also used to indicate a confidence degree of each candidate passable path, and the confidence degree is determined based on the vehicle trajectory attribute information.

[0138] The second verification unit 8031 is configured to, in a case where there is a first candidate passable path with a confidence degree lower than a preset threshold, perform road image verification on the first candidate passable path by using road image data corresponding to the first candidate passable path, to obtain a second verification result, wherein the second verification result is used to indicate whether the first candidate passable path is a passable path or an impassable path.

[0139] In a case where there is a second candidate passable path with a confidence degree higher than or equal to the preset threshold, the second candidate passable path is a passable path.

[0140] Optionally, as shown in Figure 8c The updating module 804 includes:

[0141] The determination unit 8041 is configured to determine a connected relationship between the updated road and the existing road based on the assumption connection verification result.

[0142] The identification unit 8041 is configured to identify a target road subnetwork to which the existing road belongs.

[0143] The adding unit 8042 is configured to add the connected relationship between the updated road and the existing road in the target road subnetwork, to obtain an updated target road subnetwork.

[0144] The compiling unit 8043 is configured to compile the updated target road subnet to obtain a new compilation result of the target road subnet.

[0145] The updating unit 8044 is configured to replace the original compilation result of the target road subnet in the map data with the new compilation result.

[0146] According to embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0147] The electronic device comprises at least one processor and a memory connected with the at least one processor in communication, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the map data updating method provided by the present disclosure.

[0148] The readable storage medium stores computer instructions, wherein the computer instructions are used to enable the computer to perform the map data updating method provided by the present disclosure.

[0149] The computer program product comprises a computer program, and the computer program, when executed by a processor, implements the map data updating method provided by the present disclosure.

[0150] Figure 9 A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0151] As shown in Figure 9 The device 900 includes a computing unit 901 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. Various programs and data required for the operation of the device 900 can also be stored in the RAM 903. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0152] A number of components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a magnetic disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices through computer networks, such as the Internet, and / or various telecommunication networks.

[0153] The computing unit 901 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 901 performs various methods and processes described above, such as the map data updating method. For example, in some embodiments, the map data updating method can be implemented as a computer software program, which is tangibly embodied in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded onto the RAM 903 and executed by the computing unit 901, one or more steps of the map data updating method described above can be performed. Alternatively, in other embodiments, the computing unit 901 can be configured to perform the map data updating method by any other appropriate means, such as by means of firmware.

[0154] Various implementations of the systems and techniques described above herein can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0155] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package, or entirely on a remote machine or server.

[0156] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0157] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0158] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0159] The computer system can include clients and servers. This relationship can be. The servers are typically remote from the clients with the interactions typically happening over a communication network. This relationship between a client and a server is created by executing computer programs on the respective computers with the client and server programs interacting across a network. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0160] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, without departing from the desired results of the technology disclosed in the present disclosure, and are not limited herein.

[0161] The specific embodiments described above are not intended to be limiting. One of skill in the art will understand that various modifications, combinations, sub-combinations, and alternatives can be made to the specific embodiments described above without departing from the spirit and principles of this disclosure. Any further modifications, changes, or improvements that come within the spirit and principles of the disclosure are intended to fall within the scope of the disclosure.

Claims

1. A map data updating method, comprising: obtaining survey line data, the survey line data comprising road data of an updated road; assuming the updated road to be connected to an existing road in map data according to the road data, to obtain an assumed connection relationship between the updated road and the existing road; verifying the assumed connection relationship in a multi-modal manner to obtain an assumed connection verification result; adding the updated road to the map data based on the assumed connection verification result; wherein the assumed connection relationship comprises at least one logically connected path; the verifying the assumed connection relationship in a multi-modal manner to obtain an assumed connection verification result comprises: performing vehicle trajectory verification on each logically connected path respectively using obtained vehicle trajectory data to obtain a first verification result, the first verification result being used to indicate at least one of a candidate passable path and an impassable path, there being trajectory data in the vehicle trajectory data that matches the candidate passable path, and there being no trajectory data in the vehicle trajectory data that matches the impassable path; performing semantic segmentation on obtained road image data corresponding to the candidate passable path to obtain a semantic segmentation result; determining whether the road image data comprises an obstacle based on the semantic segmentation result; in a case where the road image data comprises an obstacle, classifying the obstacle to obtain a second verification result based on the classification; in a case where the road image data does not comprise an obstacle, obtaining a second verification result, the second verification result indicating that the candidate passable path is a passable path in a case where the obstacle comprises a preset target classification obstacle and the obstacle does not impede passage.

2. The method of claim 1, wherein, in a case where the obstacle comprises a preset target classification obstacle, the candidate passable path is an impassable path; in a case where the obstacle does not comprise the preset target classification obstacle, the candidate passable path is a passable path; or in a case where the obstacle comprises a preset target classification obstacle and the obstacle impedes passage, the candidate passable path is an impassable path; in a case where the obstacle does not comprise the preset target classification obstacle, the candidate passable path is a passable path.

3. The method of claim 1, wherein, the performing vehicle trajectory verification on each logically connected path respectively using obtained vehicle trajectory data to obtain a first verification result comprises: performing vehicle trajectory verification on each logically connected path respectively using obtained vehicle trajectory data and vehicle trajectory attribute information to obtain a first verification result, wherein the first verification result is used to indicate at least one of a candidate passable path and an impassable path, and is also used to indicate a confidence of each candidate passable path, the confidence being determined based on the vehicle trajectory attribute information; the performing road image verification on the candidate passable path using obtained road image data corresponding to the candidate passable path to obtain a second verification result comprises: In a case where the confidence is lower than the preset threshold, a road image verification is performed on the first candidate passable path by using the acquired road image data corresponding to the first candidate passable path, to obtain a second verification result, which is used to indicate whether the first candidate passable path is a passable path or an impassable path. In a case where the confidence is higher than or equal to the preset threshold, the second candidate passable path is a passable path.

4. The method of any one of claims 1 to 3, wherein, The adding of the updated road into the map data based on the assumed connection verification result comprises: determining a connection relationship between the updated road and the existing road based on the assumed connection verification result; identifying a target road subnet to which the existing road belongs; adding the connection relationship between the updated road and the existing road in the target road subnet to obtain an updated target road subnet; compiling the updated target road subnet to obtain a new compilation result of the target road subnet; and replacing an original compilation result of the target road subnet in the map data with the new compilation result.

5. A map data updating apparatus, comprising: an acquisition module configured to acquire survey line data, the survey line data comprising road data of an updated road; a connection module configured to assume that the updated road is connected to an existing road in map data according to the road data, to obtain an assumed connection relationship between the updated road and the existing road; a verification module configured to verify the assumed connection relationship in a multi-modal manner to obtain an assumed connection verification result; an updating module configured to add the updated road into the map data based on the assumed connection verification result; wherein the assumed connection relationship comprises at least one logical connection path. The verification module comprises: a first verification unit configured to perform vehicle trajectory verification on each logical connection path by using acquired vehicle trajectory data to obtain a first verification result, the first verification result being used to indicate at least one of a candidate passable path and an impassable path, there being trajectory data in the vehicle trajectory data that matches the candidate passable path, and there being no trajectory data in the vehicle trajectory data that matches the impassable path; a second verification unit configured to perform semantic segmentation on road image data corresponding to the candidate passable path to obtain a semantic segmentation result; determining whether the road image data comprises an obstacle based on the semantic segmentation result; in a case where the road image data comprises an obstacle, classifying the obstacle to obtain a second verification result based on the classification; in a case where the road image data does not comprise an obstacle, acquiring a second verification result, the second verification result indicating that the candidate passable path is a passable path in a case where the obstacle comprises a preset target classified obstacle and does not hinder passage.

6. The apparatus of claim 5, wherein, In a case where the obstacle includes a preset target classification obstacle, the candidate passable path is an impassable path; in a case where the obstacle does not include the preset target classification obstacle, the candidate passable path is a passable path. Or In a case where the obstacle includes a preset target classification obstacle and the obstacle hinders passing, the candidate passable path is an impassable path. In a case where the obstacle does not include the preset target classification obstacle, the candidate passable path is a passable path.

7. The apparatus of claim 5, wherein, The first verification unit is configured to perform vehicle trajectory verification on each logical connected path respectively by using the acquired vehicle trajectory data and vehicle trajectory attribute information, to obtain a first verification result, wherein the first verification result is used to indicate at least one of a candidate passable path and an impassable path, and is also used to indicate a confidence degree of each candidate passable path, and the confidence degree is determined based on the vehicle trajectory attribute information; The second verification unit is configured to, in a case where there is a first candidate passable path with a confidence degree lower than a preset threshold, perform road image verification on the first candidate passable path by using road image data corresponding to the first candidate passable path, to obtain a second verification result, wherein the second verification result is used to indicate whether the first candidate passable path is a passable path or an impassable path. In a case where there is a second candidate passable path with a confidence degree higher than or equal to the preset threshold, the second candidate passable path is a passable path.

8. The apparatus of any one of claims 5-7, wherein, The updating module comprises: A determination unit configured to determine a connected relationship between the updated road and the existing road based on the assumption of the hooking verification result; An identification unit configured to identify a target road subnetwork to which the existing road belongs; An adding unit configured to add the connected relationship between the updated road and the existing road in the target road subnetwork, to obtain an updated target road subnetwork; A compiling unit configured to compile the updated target road subnetwork, to obtain a new compilation result of the target road subnetwork; An updating unit configured to replace an original compilation result of the target road subnetwork in the map data with the new compilation result.

9. An electronic device comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

10. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-4.

11. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-4.

Images