Parking lot map generation method and device, electronic equipment, storage medium and vehicle

Abstract

The invention relates to a parking lot map generation method and device, electronic equipment, a storage medium and a vehicle. The method comprises the following steps: registering a local parking lot map and a published parking lot map based on a semantic grid; under the condition that registration is completed, whether a road network and interest points in a local parking lot map change or not is judged on the basis of the published parking lot map; and if the change is generated, acquiring a changed road network and interest points in the local parking lot map, and carrying out differential updating on the published parking lot map based on the changed road network and interest points. According to the invention, the changed road network and the position information of the interest point in the current local parking lot map are updated to the published parking lot map, and the updated parking lot map can meet the navigation and positioning requirements in the parking lot scene; and meanwhile, the hardware configuration cost and the software operation cost required for generating the updated parking lot map are also reduced, and the problem that the map production cost is relatively high is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and particularly to a method, device, electronic device, storage medium and vehicle for generating a parking lot map. Background Art

[0002] With the trend of automotive intelligence, in-vehicle digital maps are gradually developing towards networking, intelligence and multi-functionality. Among them, due to the uniqueness of its production method, relevant laws and regulations and uses, the parking lot map has gradually become a specialized in-vehicle digital map in terms of production and use methods.

[0003] Existing methods for generating parking lot maps generally establish a matching relationship of trajectory shapes and an association of semantic data identifiers by extracting the movement trajectories and semantic data identifiers of local parking lot maps, and generate a vector semantic map and a topological map based on the matching relationship of trajectory shapes and the association of semantic data identifiers, and combine the topological map and the vector semantic map to form a global map of the parking lot.

[0004] However, the existing methods for generating parking lot maps rely too much on the movement trajectories of vehicles, which leads to higher requirements for sensors on the vehicles. Therefore, there are problems of higher map production costs and lower applicability of the methods. Summary of the Invention

[0005] To overcome the problems in the related art, the present invention provides a method, device, electronic device, storage medium and vehicle for generating a parking lot map.

[0006] According to the first aspect of the embodiments of the present invention, a method for generating a parking lot map is provided, which is applied to an autonomous driving domain controller. The method includes:

[0007] Registering a local parking lot map and a published parking lot map based on a semantic grid;

[0008] When the registration is completed, determining whether the road network and points of interest in the local parking lot map have changed based on the published parking lot map;

[0009] If a change occurs, obtaining the road network and points of interest that have changed in the local parking lot map, and performing differential update on the published parking lot map based on the changed road network and points of interest.

[0010] Optionally, before the step of registering the local parking lot map and the published parking lot map based on the semantic grid, the method includes:

[0011] Obtaining a local parking lot map through the vehicle terminal, and obtaining a published parking lot map through a cloud server.

[0012] Optionally, before the step of obtaining the local parking lot map through the vehicle terminal, the method includes:

[0013] When the target condition is met, start the parking lot crowdsourced map production program;

[0014] When the parking lot crowdsourced map production program is successfully started, obtain the parking lot semantic data;

[0015] Generate a local parking lot map based on the parking lot semantic data, and store the local parking lot map locally in the vehicle terminal.

[0016] Optionally, the target condition is that the current vehicle is located at the parking lot entrance; or,

[0017] The current vehicle is in a parked state.

[0018] Optionally, the obtaining of the parking lot semantic data includes:

[0019] Obtain parking lot image data through a vision sensor;

[0020] Perform semantic segmentation on the parking lot image data to generate parking lot semantic data.

[0021] Optionally, the generating of the local parking lot map based on the parking lot semantic data includes:

[0022] Standardize the parking lot semantic data to generate semantic grids, and process the parking lot semantic data through a vectorization algorithm to generate vectorized data, where the vectorized data includes road networks and points of interest;

[0023] Generate a local parking lot map according to the semantic grids and the vectorized data.

[0024] According to a second aspect of an embodiment of the present invention, there is provided a parking lot map generation device, the device includes:

[0025] A data registration module for registering the local parking lot map and the published parking lot map based on semantic grids;

[0026] A data judgment module for, when the registration is completed, judging whether the road networks and points of interest in the local parking lot map have changed based on the published parking lot map;

[0027] A differential update module for, if a change occurs, obtaining the road networks and points of interest that have changed in the local parking lot map, and performing differential update on the published parking lot map based on the changed road networks and points of interest.

[0028] Optionally, the device further includes:

[0029] A parking lot map acquisition module, configured to acquire a local parking lot map through the vehicle side and acquire a published parking lot map through a cloud server.

[0030] Optionally, the device further includes:

[0031] A crowdsourced parking lot map production program startup module, configured to start a crowdsourced parking lot map production program when target conditions are met;

[0032] A parking lot semantic data acquisition module, configured to acquire parking lot semantic data when the crowdsourced parking lot map production program is started successfully;

[0033] A local parking lot map generation module, configured to generate a local parking lot map based on the parking lot semantic data and store the local parking lot map locally in the vehicle side.

[0034] Optionally, the target condition is that the current vehicle is located at the entrance of the parking lot; or,

[0035] The current vehicle is in a parking state.

[0036] Optionally, the parking lot semantic data acquisition module includes:

[0037] A parking lot image data acquisition sub-module, configured to acquire parking lot image data through a vision sensor;

[0038] A semantic segmentation sub-module, configured to perform semantic segmentation on the parking lot image data to generate parking lot semantic data.

[0039] Optionally, the local parking lot map generation module includes:

[0040] A data standardization and vectorization sub-module, configured to standardize the parking lot semantic data to generate semantic grids and process the parking lot semantic data through a vectorization algorithm to generate vectorized data, where the vectorized data includes road networks and points of interest;

[0041] A local parking lot map generation sub-module, configured to generate a local parking lot map according to the semantic grids and the vectorized data.

[0042] According to a third aspect of an embodiment of the present invention, an electronic device is provided, including:

[0043] A processor;

[0044] A memory for storing executable instructions of the processor;

[0045] Wherein, the processor is configured to execute the instructions to implement the parking lot map generation method as described in the first aspect.

[0046] According to a fourth aspect of the embodiments of the present invention, there is provided a computer storage medium, and when the instructions in the storage medium are executed by a processor of a mobile terminal, the mobile terminal can execute the parking lot map generation method as described in the first aspect of the present invention.

[0047] According to a fifth aspect of the embodiments of the present invention, there is provided a vehicle, including the parking lot map generation device as described in the second aspect of the present invention.

[0048] According to a sixth aspect of the embodiments of the present invention, there is provided a computer program product, and when the computer program product runs on a terminal device, the terminal device executes the parking lot map generation method as described in any one of the above first aspects.

[0049] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0050] In the present invention, by registering the local parking lot map and the published parking lot map based on a semantic grid, and when the registration is completed, it is determined whether the road network and points of interest in the local parking lot map have changed based on the published parking lot map. If a change occurs, the road network and points of interest that have changed in the local parking lot map are obtained, and the published parking lot map is differentially updated based on the changed road network and points of interest. The acquisition of the local parking lot map does not impose any restrictions on the sensors on the vehicle. The sensors carried by the vehicle itself, or additionally installed sensors, or low-cost sensors, etc. can all be used for map acquisition. Therefore, in this application, the position information of the road network and points of interest that have changed in the current local parking lot map is updated to the published parking lot map. The updated parking lot map can not only meet the navigation and positioning requirements in the parking lot scenario, but also reduce the hardware configuration cost and software operation cost required to generate the updated parking lot map, thereby improving the applicability of the parking lot map generation method. In this application, by differentially updating the position information of the road network and points of interest that have changed in the current local parking lot map to the published parking lot map, the time and data volume required for update and upgrade are greatly reduced, the efficiency of update and upgrade is improved, and thus the production efficiency of the parking lot map is improved.

[0051] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present invention, and are used together with the specification to explain the principles of the present invention.

[0053] Figure 1One of the step flowcharts of a parking lot map generation method shown according to an exemplary embodiment;

[0054] Figure 2 One of the step flowcharts of a parking lot map generation method shown according to an exemplary embodiment;

[0055] Figure 3 One of the step flowcharts of a parking lot map generation method shown according to an exemplary embodiment;

[0056] Figure 4 One of the step flowcharts of a parking lot map generation method shown according to an exemplary embodiment;

[0057] Figure 5 The device block diagram of a parking lot map generation device shown according to an exemplary embodiment;

[0058] Figure 6 The block diagram of an electronic device shown according to an exemplary embodiment. Detailed implementation mode

[0059] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present invention. On the contrary, they are only examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0060] It should be noted that in the embodiments of the present invention, the technical solution of the present invention is applied to the autonomous driving domain controller on the vehicle, which integrates the three parts of automatic perception, decision-making, and control of autonomous driving into one control unit, and belongs to a vehicle-grade heterogeneous multi-core controller, which can meet all the functional requirements of perception, decision-making, and control.

[0061] The first embodiment of the present invention relates to a parking lot map generation method, Figure 1 It is a step flowchart of a parking lot map generation method shown according to an exemplary embodiment, as Figure 1 shown, and includes the following steps:

[0062] Step 101, registering the local parking lot map and the published parking lot map based on the semantic grid.

[0063] It should be noted that in the embodiments of the present invention, registration refers to the matching of the geographical coordinates of different image graphics obtained by different imaging means in the same area, including three aspects of processing: geometric correction, projection transformation, and unified scale.

[0064] The semantic grid is a series of regular square or rectangular grids, and each grid is called a pixel or a grid cell. The present invention uses each pixel or grid cell in the semantic grid as the basis for registration, and matches and calibrates, that is, registers, the local parking lot map obtained from the vehicle end locally and the published parking lot map obtained from the cloud server, so that the local parking lot map and the published parking lot map can correspond and be associated with each other.

[0065] Further, in the embodiment of the present invention, before step 101, the following steps may further be included: obtaining a local parking lot map through the vehicle end, and obtaining a published parking lot map through the cloud server.

[0066] It should be noted that, in the embodiment of the present invention, since the local parking lot map generated by the current vehicle is stored locally in the vehicle end in step 203, the autonomous driving domain controller needs to obtain the local parking lot map from the local of the vehicle end in advance; at the same time, the autonomous driving domain controller sends a request to the cloud server to obtain the published parking lot map, where the published parking lot map is a highly accurate parking lot map generated by the cloud server based on the parking lot maps collected by multiple vehicles and the parking lot maps already stored in the cloud server.

[0067] Further, as Figure 2 shown, in the embodiment of the present invention, before the step of obtaining the local parking lot map through the vehicle end, the following steps may further be included:

[0068] Step 201, when the target condition is met, start the parking lot crowdsourced map production program.

[0069] Step 202, when the parking lot crowdsourced map production program is successfully started, obtain parking lot semantic data.

[0070] Step 203, generate a local parking lot map based on the parking lot semantic data, and store the local parking lot map in the local of the vehicle end.

[0071] It should be noted that, in the embodiment of the present invention, when the current vehicle meets the target condition, the autonomous driving domain controller will start the parking lot crowdsourced map production program to generate a parking lot crowdsourced map, where the current vehicle can be any passenger vehicle that is itself equipped with a vision sensor, or any passenger vehicle that is additionally installed with a dedicated vision sensor.

[0072] After starting the parking lot crowdsourced map production program, the autonomous driving domain controller will obtain parking lot semantic data through the vision sensor on the vehicle, generate a local parking lot map based on the currently obtained parking lot semantic data, and store the generated local parking lot map in the local of the vehicle end.

[0073] Further, in the embodiments of the present invention, the target condition is that the current vehicle is located at the entrance of the parking lot; or, the current vehicle is in a parking state.

[0074] It should be noted that, in the embodiments of the present invention, the target condition satisfied by the current vehicle in step 201 is that the current vehicle is located at the entrance of the parking lot, or the current vehicle is in a parking state.

[0075] Among them, the specific implementation process of detecting whether the current vehicle is located at the entrance of the parking lot is as follows: obtain a reference map, which can be a map of the parking lot obtained by other vehicles except the current vehicle, or a map of the parking lot obtained by the current vehicle last time, or a map of the parking lot obtained through other channels; after the current vehicle obtains the reference map, the position information of the current vehicle can be obtained through the GPS on the vehicle, and the angle of the vehicle can also be measured through an inertial sensor. This angle refers to the attitude of the vehicle body, such as whether the top of the vehicle head is upward or downward. The image data around the current vehicle can also be obtained through a vision sensor; since the information of the parking lot entrance is displayed on the reference map, combined with the obtained position information of the current vehicle, the attitude of the current vehicle body, and the image data around the current vehicle, it can be determined whether the current vehicle is located at the entrance of the parking lot.

[0076] Among them, detecting whether the current vehicle is in a parking state can be detecting whether the current vehicle is in the dynamic process of parking into a parking space, or detecting whether the current vehicle is in the dynamic process of parking out of a parking space; if it is detected that the current vehicle is in the dynamic process of parking into a parking space, or the current vehicle is in the dynamic process of parking out of a parking space, it can be determined that the current vehicle is in a parking state.

[0077] Further, as Figure 3 shown, in the embodiments of the present invention, step 202 may further include the following steps:

[0078] Step 301, obtain parking lot image data through a vision sensor.

[0079] Step 302, perform semantic segmentation on the parking lot image data to generate parking lot semantic data.

[0080] It should be noted that, in the embodiments of the present invention, the specific implementation process of obtaining parking lot semantic data in step 202 includes: obtaining parking lot image data through a vision sensor. Specifically, the autonomous driving domain controller collects parking lot image data through the vision sensor mounted on the current vehicle; after obtaining the parking lot image data, perform semantic segmentation processing on the obtained parking lot image data, that is, assign each pixel in each obtained parking lot image data to one of the predefined semantic categories.

[0081] Further, as Figure 4 shown, in the embodiment of the present invention, step 203 may further include the following steps:

[0082] Step 401: Standardize the parking lot semantic data to generate a semantic grid, and process the parking lot semantic data through a vectorization algorithm to generate vectorized data, where the vectorized data includes a road network and points of interest.

[0083] Step 402: Generate a local parking lot map based on the semantic grid and the vectorized data.

[0084] It should be noted that in the embodiment of the present invention, the specific implementation process of generating a local parking lot map based on the parking lot semantic data in step 203 includes: simultaneously standardizing the parking lot semantic data to generate a semantic grid, and processing the parking lot semantic data through a vectorization algorithm to generate vectorized data.

[0085] Among them, to standardize the parking lot semantic data to generate a semantic grid, specifically, the parking lot semantic data is scaled to a specified range, usually between 0 and 1, through a linear transformation. The specific formula is (x - minimum value) / (maximum value - minimum value). By standardizing the parking lot semantic data, it helps to eliminate the deviation in the parking lot semantic data, making it easier to compare and analyze different variables.

[0086] After completing the standardization of the parking lot semantic data, the parking lot semantic data is stored in a raster form, that is, the parking lot semantic data is organized and stored in the form of a grid, and finally a semantic grid is generated; it should be noted that the semantic grid is a series of regular square or rectangular grids, each grid is called a pixel or grid cell, each pixel or grid cell represents a specific data point or area, and each pixel or grid cell stores the corresponding attribute value or feature information.

[0087] The vectorization algorithm is an algorithm that converts a two-dimensional (or three-dimensional) graphic into a series of coordinate points or vector values. Among them, the vectorization algorithm is used to process the parking lot semantic data to generate vectorized data. Specifically, in the process of vectorizing the parking lot semantic data through the vectorization algorithm, the parking lot semantic data can be decomposed into multiple basic elements, such as lines, arcs, curves, etc., and a set of coordinate values can be assigned to each element. These coordinate values can be two-dimensional (x, y) or three-dimensional (x, y, z). After completing the vectorization of the parking lot semantic data, the coordinate values corresponding to the road network and the coordinate values corresponding to the points of interest in the parking lot semantic data are the vectorized data; among them, the road network refers to a road system composed of various roads that are interconnected and intertwined into a network distribution within a certain area, including but not limited to detailed information such as the shape, length, and intersection points of the roads; the point of interest is a record of a location on the map that a person considers useful or interesting, such as the location information of restaurants, supermarkets, scenic spots, etc.

[0088] The local parking lot map can be generated by using the semantic grid generated based on the parking lot semantic data and the vectorized data generated based on the parking lot semantic data.

[0089] Step 102, in the case of completing the registration, based on the published parking lot map, determine whether the road network and the points of interest in the local parking lot map have changed.

[0090] Step 103, if there is a change, obtain the road network and the points of interest that have changed in the local parking lot map, and perform differential update on the published parking lot map based on the changed road network and points of interest.

[0091] It should be noted that in the embodiment of the present invention, after the automatic driving domain controller completes the registration, taking the published parking lot map as a reference, determine whether the position information of the road network and the points of interest in the local parking lot map has changed.

[0092] If the position information of the road network and the points of interest has changed, then the position information of the changed road network and points of interest in the current local parking lot map is differentially updated to the published parking lot map. The updated published parking lot map is the parking lot crowd-sourced map, that is, the parking lot map. Among them, differential update only updates the changed part of the file or data, rather than the entire firmware or software. By using differential update, the time and data volume required for update and upgrade can be greatly reduced, and the efficiency of update and upgrade can be improved.

[0093] Specifically, the specific implementation process of differentially updating the location information of the road network and points of interest that have changed in the current local parking lot map to the published parking lot map can be that the vehicle-mounted autonomous driving domain controller directly differentially updates the location information of the road network and points of interest that have changed in the current local parking lot map to the published parking lot map. It can also be that the autonomous driving domain controller sends a differential update request to the cloud server. After receiving the differential update request, the cloud server obtains the location information of the road network and points of interest that have changed in the current local parking lot map from the vehicle side, and differentially updates the location information of the road network and points of interest that have changed in the current local parking lot map to the published parking lot map in the cloud server, realizing the synchronous production of the parking lot crowdsourced map by the vehicle side and the cloud server.

[0094] In the present invention, by registering the local parking lot map and the published parking lot map based on a semantic grid, in the case of successful registration, it is determined whether the road network and points of interest in the local parking lot map have changed based on the published parking lot map. If a change occurs, the road network and points of interest that have changed in the local parking lot map are obtained, and the published parking lot map is differentially updated based on the road network and points of interest that have changed. The acquisition of the local parking lot map does not impose any restrictions on the sensors on the vehicle. Sensors mounted on the vehicle itself, or sensors installed additionally, or low-cost sensors, etc. can all be used for map acquisition. Therefore, in this application, the location information of the road network and points of interest that have changed in the current local parking lot map is updated to the published parking lot map. The updated parking lot map can not only meet the navigation and positioning requirements in the parking lot scenario, but also reduce the hardware configuration cost and software operation cost required to generate the updated parking lot map, thereby improving the applicability of the parking lot map generation method; in this application, by differentially updating the location information of the road network and points of interest that have changed in the current local parking lot map to the published parking lot map, the time and data volume required for update and upgrade are greatly reduced, the efficiency of update and upgrade is improved, and thus the production efficiency of the parking lot map is improved.

[0095] The second embodiment of the present invention relates to a parking lot map generation device. Figure 5 It is a device block diagram of a parking lot map generation device shown according to an exemplary embodiment, as Figure 5 shown. The device includes:

[0096] A data registration module 501, configured to register the local parking lot map and the published parking lot map based on a semantic grid;

[0097] A data judgment module 502, configured to determine whether the road network and points of interest in the local parking lot map have changed based on the published parking lot map in the case of successful registration;

[0098] The differential update module 503 is configured to, if a change occurs, obtain the road network and points of interest that have changed in the local parking lot map, and perform differential update on the published parking lot map based on the road network and points of interest that have changed.

[0099] Optionally, the device further includes:

[0100] The parking lot map acquisition module is configured to obtain the local parking lot map through the vehicle terminal and obtain the published parking lot map through the cloud server.

[0101] Optionally, the device further includes:

[0102] The parking lot crowdsourced map production program startup module is configured to start the parking lot crowdsourced map production program when the target condition is met;

[0103] The parking lot semantic data acquisition module is configured to obtain the parking lot semantic data when the parking lot crowdsourced map production program is successfully started;

[0104] The local parking lot map generation module is configured to generate the local parking lot map based on the parking lot semantic data and store the local parking lot map locally in the vehicle terminal.

[0105] Optionally, the target condition is that the current vehicle is located at the entrance of the parking lot; or,

[0106] the current vehicle is in a parking state.

[0107] Optionally, the parking lot semantic data acquisition module includes:

[0108] The parking lot image data acquisition sub-module is configured to obtain the parking lot image data through the vision sensor;

[0109] The semantic segmentation sub-module is configured to perform semantic segmentation on the parking lot image data to generate the parking lot semantic data.

[0110] Optionally, the local parking lot map generation module includes:

[0111] The data standardization and vectorization sub-module is configured to standardize the parking lot semantic data to generate semantic grids, and process the parking lot semantic data through a vectorization algorithm to generate vectorized data, where the vectorized data includes the road network and points of interest;

[0112] The local parking lot map generation sub-module is configured to generate the local parking lot map according to the semantic grids and the vectorized data.

[0113] The present invention registers a local parking lot map and a published parking lot map based on a semantic grid. When the registration is completed, it determines whether the road network and points of interest in the local parking lot map have changed based on the published parking lot map. If a change occurs, it obtains the road network and points of interest that have changed in the local parking lot map, and performs differential update on the published parking lot map based on the changed road network and points of interest. The collection of the local parking lot map does not impose any restrictions on the sensors on the vehicle. Sensors carried by the vehicle itself, or sensors installed additionally, or low-cost sensors, etc. can all be used for map collection. Therefore, this application updates the position information of the road network and points of interest that have changed in the current local parking lot map to the published parking lot map. The updated parking lot map can not only meet the navigation and positioning requirements in the parking lot scenario, but also reduce the hardware configuration cost and software operation cost required to generate the updated parking lot map, thereby improving the applicability of the parking lot map generation method. By differentially updating the position information of the road network and points of interest that have changed in the current local parking lot map to the published parking lot map, this application greatly reduces the time and data volume required for update and upgrade, improves the efficiency of update and upgrade, and thus improves the production efficiency of the parking lot map.

[0114] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment related to the method, and will not be elaborated here.

[0115] The third embodiment of the present invention provides a communication device, as Figure 6 shown, including a processor 601, a communication interface 602, a memory 603, and a communication bus 604. Among them, the processor 601, the communication interface 602, and the memory 603 complete communication with each other through the communication bus 604.

[0116] The memory 603 is used to store a computer program.

[0117] When the processor 601 executes the program stored in the memory 603, the following steps can be implemented:

[0118] Register the local parking lot map and the published parking lot map based on a semantic grid.

[0119] When the registration is completed, determine whether the road network and points of interest in the local parking lot map have changed based on the published parking lot map.

[0120] If a change occurs, obtain the road network and points of interest that have changed in the local parking lot map, and perform differential update on the published parking lot map based on the changed road network and points of interest.

[0121] The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, only a thick line is used in the figure to represent it, but it does not mean that there is only one bus or one type of bus.

[0122] The communication interface is used for communication between the above terminal and other devices.

[0123] The memory may include a Random Access Memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0124] The above-mentioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0125] The fourth embodiment of the present invention provides a computer storage medium, in which instructions are stored. When it runs on a computer, it causes the computer to execute the parking lot map generation method described in any one of the above embodiments.

[0126] The fifth embodiment of the present invention provides a vehicle, including the parking lot map generation device described in the second embodiment of the present invention.

[0127] The sixth embodiment of the present invention provides a computer program product containing instructions. When it runs on a computer, it causes the computer to execute the parking lot map generation method described in any one of the above embodiments.

[0128] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or third database to another website, computer, server, or third database by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or third database that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

[0129] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise", or any other variation thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including an..." does not exclude the existence of additional identical elements in the process, method, article, or device that includes the element.

[0130] Each embodiment in this specification is described in a related manner. The same or similar parts between the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

[0131] The above are only the preferred embodiments of the present application and are not intended to limit the protection scope of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application are all included in the protection scope of the present application.

Claims

1. A method for generating a parking lot map, characterized in that, Applied to an autonomous driving domain controller, the method includes: Registering a local parking lot map and a published parking lot map based on a semantic grid; When the registration is completed, determining whether the road network and points of interest in the local parking lot map have changed based on the published parking lot map; If a change occurs, obtaining the road network and points of interest in the local parking lot map that have changed, and performing differential update on the published parking lot map based on the changed road network and points of interest.

2. The method for generating a parking lot map according to claim 1, wherein Before the step of registering the local parking lot map and the published parking lot map based on the semantic grid, the method includes: Obtaining the local parking lot map through the vehicle end, and obtaining the published parking lot map through the cloud server.

3. The method for generating a parking lot map according to claim 2, wherein Before the step of obtaining the local parking lot map through the vehicle end, the method includes: Starting a parking lot crowdsourced map production program when a target condition is met; When the parking lot crowdsourced map production program is started, obtaining parking lot semantic data; Generating a local parking lot map based on the parking lot semantic data, and storing the local parking lot map locally in the vehicle end.

4. The method for generating a parking lot map according to claim 3, wherein The target condition is that the current vehicle is located at the parking lot entrance; or, The current vehicle is in a parking state.

5. The method for generating a parking lot map according to claim 3, wherein The obtaining of the parking lot semantic data includes: Obtaining parking lot image data through a vision sensor; Performing semantic segmentation on the parking lot image data to generate parking lot semantic data.

6. The method for generating a parking lot map according to claim 3, wherein The generating of the local parking lot map based on the parking lot semantic data includes: Normalizing the parking lot semantic data to generate a semantic grid, and processing the parking lot semantic data through a vectorization algorithm to generate vectorized data, where the vectorized data includes a road network and points of interest; Generating a local parking lot map according to the semantic grid and the vectorized data.

7. A parking lot map generation device, characterized in that, The parking lot map generation device includes: A data registration module for registering a local parking lot map and a published parking lot map based on a semantic grid; A data judgment module for determining whether the road network and points of interest in the local parking lot map have changed based on the published parking lot map when the registration is completed; A differential update module for, if a change occurs, obtaining the road network and points of interest in the local parking lot map that have changed, and performing differential update on the published parking lot map based on the changed road network and points of interest.

8. An electronic device, characterized in that, Includes: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to execute the instructions to implement the parking lot map generation method according to any one of claims 1 to 6.

9. A computer storage medium, when the instructions in the storage medium are executed by a processor of a mobile terminal, enabling the mobile terminal to execute the parking lot map generation method according to any one of claims 1 to 6.

10. A vehicle, characterized in that, Includes the parking lot map generation device according to claim 7.

Images