A method and apparatus for determining a model region boundary

Abstract

The application discloses a method and device for determining a model area boundary. The application comprises: obtaining a scene simulation model; importing the scene simulation model into a scene simulation software, and configuring a simulation vehicle for the scene simulation model, wherein the simulation vehicle is configured with a virtual GPS positioning function and a camera model; controlling the simulation vehicle to drive around the scene simulation model for one round, and controlling the simulation vehicle to collect driving-around data corresponding to the one round during the driving around; and determining an area boundary of the scene simulation model and / or an area boundary of a ground map model according to the driving-around data. Through the application, the technical problem of inconsistency between a static scene model in a scene simulation software in a simulation platform and a map model area boundary in a GMS system is solved.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving, and more specifically, to a method and apparatus for determining the boundary of a model region. Background Technology

[0002] In related technologies, autonomous driving technology for mining trucks needs to undergo extensive testing before it can be truly commercialized and meet commercial requirements. Real-vehicle testing faces numerous challenges, such as the time cost of on-site testing, compliance issues, and safety in extreme scenarios and dangerous conditions. These problems pose significant difficulties for the research and testing of autonomous driving systems. Using on-site testing to optimize autonomous driving algorithms is too time-consuming and costly. According to research by the RAND Corporation, autonomous driving algorithms need at least 17.7 billion kilometers of driving data to reach the level of human drivers. If a fleet of 100 autonomous driving test vehicles were to conduct road tests 24 hours a day at an average speed of 25 miles per hour (40 kilometers per hour), it would take over 500 years to reach the target mileage, an amount that would be prohibitively expensive and time-consuming.

[0003] Currently, simulation testing based on virtual scenarios is an important approach to solving the problems of high cost, long cycle, and low coverage in autonomous driving testing. Simulation testing mainly achieves closed-loop simulation testing of autonomous driving algorithms such as perception, decision-making, planning, and control by constructing virtual scenarios. The simulation testing of autonomous vehicles first requires the construction of a vehicle operation scenario that is consistent with the real world.

[0004] Typically, unpaved roads in mining areas lack road boundaries, necessitating the manual delineation of boundaries between the operational and non-operational area scene models. Since the ground system's map creation and the scene simulation software's scene model creation are handled separately by different professionals using different tools and adhering to different standard formats, it is difficult to guarantee consistency in the boundaries and coordinate origins of both operational and non-operational area scene models.

[0005] Therefore, there is currently no effective solution to the problem of how to maintain a high degree of consistency between the static scene model in the scene simulation software and the map model in the GMS system; that is, how to maintain a high degree of consistency between the operating range and positioning of the simulated vehicle in the scene simulation software and the GMS system. Summary of the Invention

[0006] The main objective of this invention is to provide a method and apparatus for determining the boundaries of a model region, thereby solving the technical problem of inconsistency between the boundaries of static scene models in scene simulation software of simulation platforms and map model regions in GMS systems in related technologies.

[0007] To achieve the above objectives, according to one aspect of the present invention, a method for determining the boundary of a model region is provided. The invention includes: acquiring a scene simulation model, wherein the scene simulation model is a simulation model corresponding to a target region of a mining area, the scene simulation model including a first scene simulation model and a second scene simulation model, the region boundary in the first scene simulation model being unknown, the region boundary in the second scene simulation model being known, and the region boundary being the boundary between the working area and the non-working area of ​​the mining area; importing the scene simulation model into scene simulation software, and configuring a simulation vehicle for the scene simulation model, wherein the simulation vehicle is equipped with a virtual GPS positioning function and a camera model; controlling the simulation vehicle to circle around the scene simulation model once, and controlling the simulation vehicle to collect circumference data corresponding to one circumference during the circumference process; and determining the region boundary of the scene simulation model and / or the region boundary of the ground map model based on the circumference data.

[0008] Furthermore, when the scene simulation model is the second scene simulation model, obtaining the scene simulation model includes: obtaining target mapping data, wherein the target mapping data is the data corresponding to the target area of ​​the mining area collected by the UAV; and constructing the second scene simulation model based on the mapping data.

[0009] Furthermore, when the scene simulation model is the first scene simulation model, before acquiring the scene simulation model, the method further includes: acquiring target mapping data, wherein the target mapping data is data corresponding to the target area of ​​the mining area collected by the UAV; and constructing a ground map model based on the target mapping data, wherein the ground map model contains area boundary information corresponding to the area boundary.

[0010] Furthermore, the simulation vehicle is controlled to circle the scene simulation model once, and the simulation vehicle is controlled to collect the corresponding detour data during the detour, including: obtaining the detour path corresponding to the detour of the simulation vehicle in the scene simulation model based on the ground map model, wherein the coordinate system corresponding to the detour path is the coordinate system in the ground map model; controlling the simulation vehicle to detour according to the detour path, and controlling the simulation vehicle to collect the positioning coordinate information corresponding to the detour path during the detour; and determining the positioning coordinate information as detour data.

[0011] Furthermore, based on the detour data, the regional boundaries of the scene simulation model and / or the regional boundaries of the ground map model are determined, including: converting the positioning coordinate information into target positioning coordinate information, wherein the coordinate system of the target positioning coordinate information is the coordinate system corresponding to the scene simulation model; and determining the regional boundaries corresponding to the scene simulation model based on the target positioning coordinate information.

[0012] Furthermore, the simulation vehicle is controlled to circle around the scene simulation model, and the simulation vehicle is controlled to collect the corresponding circumference data during the circumference process, including: acquiring the data collected by the camera model and extracting the area boundary GPS positioning data contained in the data; and identifying the area boundary GPS positioning data as circumference data.

[0013] Further, based on the detour data, the regional boundaries of the scene simulation model and / or the regional boundaries of the ground map model are determined, including: importing the regional boundary GPS positioning data into the scene simulation software to construct a second scene simulation model, and determining the regional boundaries in the second scene simulation model based on the regional boundary GPS positioning data; importing the regional boundary GPS positioning data into the GMS system map management module to construct a ground map model, and determining the regional boundaries in the ground map model based on the regional boundary GPS positioning data, wherein the regional boundaries in the ground map model are consistent with the regional boundaries in the scene simulation model.

[0014] To achieve the above objectives, according to another aspect of the present invention, an apparatus for determining the boundary of a model region is provided. The apparatus includes: an acquisition unit for acquiring a scene simulation model, wherein the scene simulation model is a simulation model corresponding to a target area of ​​a mining area, the scene simulation model including a first scene simulation model and a second scene simulation model, the region boundary in the first scene simulation model is unknown, the region boundary in the second scene simulation model is known, and the region boundary is the boundary between the working area and the non-working area of ​​the mining area; a configuration unit for importing the scene simulation model into scene simulation software and configuring a simulation vehicle for the scene simulation model, wherein the simulation vehicle is configured with virtual GPS positioning function and a camera model; a control unit for controlling the simulation vehicle to circle around the scene simulation model once, and controlling the simulation vehicle to collect circumference data corresponding to one circumference during the circumference process; and a determination unit for determining the region boundary of the scene simulation model and / or the region boundary of the ground map model based on the circumference data.

[0015] This invention employs the following steps: obtaining a scene simulation model, wherein the scene simulation model is a simulation model corresponding to the target area of ​​the mining area, the scene simulation model includes a first scene simulation model and a second scene simulation model, the area boundary in the first scene simulation model is unknown, the area boundary in the second scene simulation model is known, and the area boundary is the boundary between the working area and the non-working area of ​​the mining area; importing the scene simulation model into scene simulation software, and configuring a simulation vehicle for the scene simulation model, wherein the simulation vehicle is equipped with virtual GPS positioning function and a camera model; controlling the simulation vehicle to circle around the scene simulation model, and controlling the simulation vehicle to collect the corresponding circumference data during the circumference; based on the circumference data, determining the area boundary of the scene simulation model and / or the area boundary of the ground map model, thereby solving the technical problem of inconsistent area boundaries between the static scene model in the scene simulation software of the simulation platform and the map model in the GMS system in related technologies, thus achieving the effect of reducing the testing time and testing cost of autonomous driving technology. Attached Figure Description

[0016] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0017] Figure 1 This is a flowchart of a method for determining the boundary of a model region according to an embodiment of the present invention;

[0018] Figure 2 This is a flowchart of the static scene restoration scheme provided in this application;

[0019] Figure 3 This is a flowchart of the method for determining the boundary of a model region using coordinate data to obtain boundary information, as provided in this application.

[0020] Figure 4 This is a flowchart of the method for determining the boundary of a model region using GPS positioning data to obtain boundary information, as provided in this application; and

[0021] Figure 5 This is a schematic diagram of a device for determining the boundary of a model region according to an embodiment of the present invention. Detailed Implementation

[0022] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of the invention described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application:

[0026] GMS: General Motors Global Manufacturing System.

[0027] According to an embodiment of the present invention, a method for determining the boundary of a model region is provided.

[0028] Figure 1 This is a flowchart of a method for determining the boundary of a model region according to an embodiment of the present invention. Figure 1 As shown, the invention includes the following steps:

[0029] Step S101: Obtain the scene simulation model, wherein the scene simulation model is the simulation model corresponding to the target area of ​​the mining area. The scene simulation model includes a first scene simulation model and a second scene simulation model. The area boundary in the first scene simulation model is unknown, while the area boundary in the second scene simulation model is known. The area boundary is the boundary between the working area and the non-working area of ​​the mining area.

[0030] Step S102: Import the scene simulation model into the scene simulation software and configure the simulation vehicle for the scene simulation model. The simulation vehicle is equipped with virtual GPS positioning function and camera model.

[0031] Step S103: Control the simulation vehicle to circle around the scene simulation model once, and control the simulation vehicle to collect the circling data corresponding to the circle during the circling process;

[0032] Step S104: Based on the detour data, determine the area boundaries of the scene simulation model and / or the area boundaries of the ground map model.

[0033] The aforementioned solution comprises two parts: scene data acquisition and static scene reconstruction. For example... Figure 2 As shown, Figure 2 This is a flowchart of the static scene restoration scheme provided in this application. Based on the collected mining area scene data, scene extraction is used to generate a mining area operation zone scene model and a non-operation zone scene model, thus achieving static scene restoration. The data from the static scene restoration is used to generate a map model required by the Ground Management and Monitoring System (GMS) through map editing, and a static scene model required by the scene simulation software through scene editing.

[0034] This application also provides a map model, which is part of other modules in the GMS system, including scheduling, path planning, map planning, and front-end display modules, providing high-precision map information support. The scene model is part of other modules in the scene simulation software, including vehicle modules such as mining trucks, water trucks, and electric shovels, providing high-precision road network and positioning information support; and providing high-precision environmental perception information support for sensor modules. The scene simulation software feeds back the real-time vehicle position and attitude information of all vehicles in the scene model to the GMS through an onboard autonomous driving computing platform. Based on the vehicle's pose information in the map model, the GMS issues scheduling and planning commands to the onboard autonomous driving computing platform. Furthermore, the onboard autonomous driving computing platform issues vehicle control commands to all virtual vehicle models in the scene simulation software based on the scheduling and planning information.

[0035] As described above, this application constructs a simulation model of the corresponding work scenario in the mining area, imports the simulation model into the simulation software, runs a simulation vehicle, and the simulation vehicle circles the simulation scenario once. Based on the data collected after the circle, a scene simulation model or map model with the boundaries of the working area and the non-working area is reconstructed.

[0036] This invention provides a method for determining the boundary of a model region. The method involves acquiring a scene simulation model, which is a simulation model corresponding to the target area of ​​a mining area. The scene simulation model includes a first scene simulation model and a second scene simulation model. The boundary of the region in the first scene simulation model is unknown, while the boundary of the region in the second scene simulation model is known. The boundary of the region is the boundary between the working area and the non-working area of ​​the mining area. The scene simulation model is imported into scene simulation software, and a simulation vehicle is configured for the scene simulation model. The simulation vehicle is equipped with virtual GPS positioning and a camera model. The simulation vehicle is controlled to circle the scene simulation model once, and the circumference data corresponding to the circle is collected during the circumference. Based on the circumference data, the boundary of the scene simulation model and / or the boundary of the ground map model are determined. This method solves the technical problem of inconsistent boundary of the static scene model in the scene simulation software of the simulation platform and the map model in the GMS system in related technologies, thereby reducing the testing time and cost of autonomous driving technology.

[0037] In one optional embodiment, when the scene simulation model is a second scene simulation model, obtaining the scene simulation model includes: obtaining target mapping data, wherein the target mapping data is data corresponding to the target area of ​​the mining area collected by the UAV; and constructing the second scene simulation model based on the mapping data.

[0038] As mentioned above, since the boundary lines of the working area and the non-working area are known in the second scenario simulation model, the data collected by the UAV can be directly used for mapping to construct the simulation model. This solves the technical problem of how to construct a simulation model when the boundary of the simulation process is known, and achieves the technical effect of constructing simulation models for different boundary line situations.

[0039] In an optional embodiment, when the scene simulation model is a first scene simulation model, before acquiring the scene simulation model, the method further includes: acquiring target mapping data, wherein the target mapping data is data corresponding to the target area of ​​the mining area collected by the UAV; and constructing a ground map model based on the target mapping data, wherein the ground map model contains area boundary information corresponding to the area boundary.

[0040] The above-mentioned method processes radar point cloud data and video collected by UAVs, preprocesses the data to construct 2D or 3D models of non-operational areas and operation areas, and builds map models (navigation maps) after data collection. The data is divided into two parts: map model creation and simulation model creation. The scene model corresponds to the actual scene; the boundaries in the actual map must correspond to the boundaries of the scene model. New models are constructed using pre-existing models. This method solves the technical problem of how to build models using UAV mapping data, achieving the technical effect of accurately building map models.

[0041] In one optional embodiment, controlling the simulated vehicle to circle around the scene simulation model, and controlling the simulated vehicle to collect the corresponding detour data during the detour, includes: obtaining the detour path corresponding to the simulated vehicle's detour in the scene simulation model based on the ground map model, wherein the coordinate system corresponding to the detour path is the coordinate system in the ground map model; controlling the simulated vehicle to detour according to the detour path, and controlling the simulated vehicle to collect the positioning coordinate information corresponding to the detour path during the detour; and determining the positioning coordinate information as detour data.

[0042] As described above, a simple planar scene model is established in the scene simulation model, and a simulated vehicle with virtual GPS positioning function is configured. The simulated vehicle can accept GMS scheduling and planning. Through the GMS simulation backend, the simulated vehicle in the simulation system is driven to run along a specified path around the boundary of the GMS map. This solves the technical problem of not being able to determine the boundary in the scene simulation model and achieves the technical effect of obtaining the boundary through the scene simulation model.

[0043] In one optional embodiment, determining the regional boundary of the scene simulation model and / or the regional boundary of the ground map model based on the detour data includes: converting the positioning coordinate information into target positioning coordinate information, wherein the coordinate system of the target positioning coordinate information is the coordinate system corresponding to the scene simulation model; and determining the regional boundary corresponding to the scene simulation model based on the target positioning coordinate information.

[0044] As described above, the virtual GPS positioning function of the simulated vehicle outputs the positioning coordinates of the simulated vehicle's circumference. Based on these coordinates, the boundary lines of the simulation models of the work area and non-work area are obtained, ensuring consistency with the map model in the GMS system. This solves the technical problem of inconsistent boundary lines between the scene simulation model and the map model in the GMS system, achieving the technical effect of determining the boundary lines of the work area.

[0045] like Figure 3 As shown, Figure 3This is a flowchart of the method for determining the boundary of a model area using coordinate data to obtain boundary information provided in this application. First, a scene model of the simulation system is established using UAV mapping data. A simple planar scene model is then established in the simulation system, and a simulation vehicle is configured. Through the GMS simulation backend, a path around the GMS map boundary is specified for the simulation vehicle. The virtual GPS positioning function of the simulation vehicle outputs the positioning coordinate information of the vehicle after one revolution. The positioning coordinate information is then transformed to establish the initial position coordinate conversion relationship between the simulation vehicle in the map model and the scene model. Based on the transformed positioning coordinate information, the boundary lines of the work area scene model and the non-work area scene model in the simulation system are obtained.

[0046] In one optional embodiment, the simulated vehicle is controlled to circle around the scene simulation model, and the simulated vehicle is controlled to collect the corresponding circumference data during the circumference process, including: acquiring the data collected by the camera model, and extracting the area boundary GPS positioning data contained in the data; and determining the area boundary GPS positioning data as circumference data.

[0047] As mentioned above, when a scene simulation model is established using UAV mapping data, but the boundary lines between the operation area scene simulation model and the non-operation area scene simulation model in the scene simulation model have not yet been manually defined, it is necessary to further establish a GMS system map model to ensure the consistency of the boundary lines between the operation area scene model and the non-operation area scene model in the scene simulation model and the GMS map model.

[0048] The scene simulation model is imported into scene simulation software. A simulation vehicle capable of accepting GMS scheduling and driving simulator control, and possessing virtual GPS positioning capabilities, is configured. A camera model is installed on the simulation vehicle, enabling it to transmit camera data back to the driving simulator. The driver can clearly observe the scene boundaries through video data. The driver then drives the simulation vehicle along the scene boundaries in the driving simulator, saving the virtual GPS positioning data. This solves the problem of determining boundary lines using video information from the scene simulation model, achieving the technical effect of defining the boundary lines of the working area.

[0049] In one optional embodiment, determining the regional boundaries of the scene simulation model and / or the regional boundaries of the ground map model based on the detour data includes: importing the regional boundary GPS positioning data into the scene simulation software to construct a second scene simulation model, and determining the regional boundaries in the second scene simulation model based on the regional boundary GPS positioning data; importing the regional boundary GPS positioning data into the GMS system map management module to construct a ground map model, and determining the regional boundaries in the ground map model based on the regional boundary GPS positioning data, wherein the regional boundaries in the ground map model are consistent with the regional boundaries in the scene simulation model.

[0050] As described above, virtual GPS positioning data is imported into the scene simulation software and the GMS system map management module to create scene simulation models and map models, thereby ensuring the consistency of the boundary lines between the work area and non-work area in the scene simulation model and the map model in the GMS system. This solves the technical problem of inconsistent boundary lines between the scene simulation model and the map model in the GMS system, achieving the technical effect of determining the boundary lines of the work area.

[0051] like Figure 4 As shown, Figure 4 This is a flowchart of the method for determining the boundary of a model area using GPS positioning data provided in this application. First, a ground system scene simulation model is established using UAV mapping data. Then, the scene simulation model of the simulation system is imported into the scene simulation software. A simulation vehicle is configured, and the simulation vehicle is driven around the scene boundary using a driving simulator. The simulation vehicle is equipped with virtual GPS positioning function, the virtual GPS positioning data is saved, and the positioning coordinate information is transformed. Then, the transformed virtual GPS positioning data is imported into the scene simulation software as the boundary line between the working area and the non-working area in the simulation system scene model, or the transformed virtual GPS positioning data is imported into GMS map management software as the boundary line between the working area and the non-working area in the GMS system map model.

[0052] This invention provides a method for determining the boundary of a model region. The method involves acquiring a scene simulation model, which is a simulation model corresponding to the target area of ​​a mining area. The scene simulation model includes a first scene simulation model and a second scene simulation model. The boundary of the region in the first scene simulation model is unknown, while the boundary of the region in the second scene simulation model is known. The boundary of the region is the boundary between the working area and the non-working area of ​​the mining area. The scene simulation model is imported into scene simulation software, and a simulation vehicle is configured for the scene simulation model. The simulation vehicle is equipped with virtual GPS positioning and a camera model. The simulation vehicle is controlled to circle the scene simulation model once, and the circumference data corresponding to the circle is collected during the circumference. Based on the circumference data, the boundary of the scene simulation model and / or the boundary of the ground map model are determined. This method solves the technical problem of inconsistent boundary of the static scene model in the scene simulation software of the simulation platform and the map model in the GMS system in related technologies, thereby reducing the testing time and cost of autonomous driving technology.

[0053] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0054] This invention also provides an apparatus for determining the boundary of a model region. It should be noted that the apparatus for determining the boundary of a model region provided in this invention can be used to execute the method for determining the boundary of a model region provided in this invention. The following describes the apparatus for determining the boundary of a model region provided in this invention.

[0055] Figure 5 This is a schematic diagram of an apparatus for determining the boundary of a model region according to an embodiment of the present invention. Figure 5 As shown, the device includes: an acquisition unit 501, used to acquire a scene simulation model, wherein the scene simulation model is a simulation model corresponding to the target area of ​​the mining area, the scene simulation model includes a first scene simulation model and a second scene simulation model, the area boundary in the first scene simulation model is unknown, the area boundary in the second scene simulation model is known, and the area boundary is the boundary between the working area and the non-working area of ​​the mining area; a configuration unit 503, used to import the scene simulation model into the scene simulation software and configure a simulation vehicle for the scene simulation model, wherein the simulation vehicle is configured with virtual GPS positioning function and a camera model; a control unit 505, used to control the simulation vehicle to circle around the scene simulation model, and control the simulation vehicle to collect the circumference data corresponding to the circumference during the circumference; and a determination unit 507, used to determine the area boundary of the scene simulation model and / or the area boundary of the ground map model based on the circumference data.

[0056] In an optional embodiment, when the scene simulation model is a second scene simulation model, the acquisition unit 501 includes: a first acquisition subunit, used to acquire target mapping data, wherein the target mapping data is data corresponding to the target area of ​​the mining area collected by the UAV; and a first construction subunit, used to construct the second scene simulation model based on the mapping data.

[0057] In an optional embodiment, when the scene simulation model is a first scene simulation model, before acquiring the scene simulation model, the acquisition unit 501 further includes: a second acquisition subunit, used to acquire target mapping data, wherein the target mapping data is data corresponding to the target area of ​​the mining area collected by the UAV; and a second construction subunit, used to construct a ground map model based on the target mapping data, wherein the ground map model contains area boundary information corresponding to the area boundary.

[0058] In one optional embodiment, the control unit 505 includes: a third acquisition subunit, configured to acquire, based on a ground map model, a detour path corresponding to the detour of the simulated vehicle in the scene simulation model, wherein the coordinate system corresponding to the detour path is the coordinate system in the ground map model; a control subunit, configured to control the simulated vehicle to detour according to the detour path, and control the simulated vehicle to collect positioning coordinate information corresponding to the detour path during the detour process; and a first determination subunit, configured to determine the positioning coordinate information as detour data.

[0059] In an optional embodiment, the determining unit 507 includes: a transformation subunit, used to convert the positioning coordinate information into target positioning coordinate information, wherein the coordinate system of the target positioning coordinate information is the coordinate system corresponding to the scene simulation model; and a second determining subunit, used to determine the area boundary corresponding to the scene simulation model based on the target positioning coordinate information.

[0060] In an optional embodiment, the determining unit 507 includes: a fourth acquisition subunit, configured to acquire data collected by the camera model and extract the area boundary GPS positioning data contained in the data; and a third determining subunit, configured to determine the area boundary GPS positioning data as detour data.

[0061] In one optional embodiment, the determining unit 507 includes: a second construction subunit, configured to import the area boundary GPS positioning data into the scene simulation software to construct a second scene simulation model, and determine the area boundary in the second scene simulation model based on the area boundary GPS positioning data; and a third construction subunit, configured to import the area boundary GPS positioning data into the GMS system map management module to construct a ground map model, and determine the area boundary in the ground map model based on the area boundary GPS positioning data, wherein the area boundary in the ground map model is consistent with the area boundary in the scene simulation model.

[0062] This invention provides an apparatus for determining the boundary of a model region. An acquisition unit 501 acquires a scene simulation model, which is a simulation model corresponding to the target area of ​​a mining area. The scene simulation model includes a first scene simulation model and a second scene simulation model. The boundary of the region in the first scene simulation model is unknown, while the boundary of the region in the second scene simulation model is known. The boundary of the region is the boundary between the working area and the non-working area of ​​the mining area. A configuration unit 503 imports the scene simulation model into scene simulation software and configures a simulation vehicle for the scene simulation model. The simulation vehicle is equipped with virtual GPS positioning and a camera model. A control unit 505 controls the simulation vehicle to circle around the scene simulation model and collects the corresponding circumference data during the circumference. A determination unit 507 determines the boundary of the scene simulation model and / or the boundary of the ground map model based on the circumference data. This solves the technical problem of inconsistent boundary between the static scene model in the scene simulation software of the simulation platform and the map model in the GMS system in related technologies, thereby reducing the testing time and cost of autonomous driving technology.

[0063] The device for determining the boundary of a model region includes a processor and a memory. The aforementioned acquisition unit 501 and the like are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0064] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can resolve technical issues related to inconsistencies between the static scene model in the scene simulation software of the simulation platform and the map model region boundaries in the GMS system.

[0065] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0066] This invention provides a storage medium storing a program that, when executed by a processor, implements the method for determining the boundary of a model region.

[0067] This invention provides a processor for running a program, wherein the program executes the method for determining the boundary of a model region.

[0068] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring a scene simulation model, wherein the scene simulation model is a simulation model corresponding to a target area of ​​a mining area, the scene simulation model includes a first scene simulation model and a second scene simulation model, the area boundary in the first scene simulation model is unknown, and the area boundary in the second scene simulation model is known, the area boundary being the boundary between the working area and the non-working area of ​​the mining area; importing the scene simulation model into scene simulation software and configuring a simulation vehicle for the scene simulation model, wherein the simulation vehicle is equipped with virtual GPS positioning and a camera model; controlling the simulation vehicle to circle around the scene simulation model, and controlling the simulation vehicle to collect circumference data corresponding to the circumference during the circumference; and determining the area boundary of the scene simulation model and / or the area boundary of the ground map model based on the circumference data.

[0069] Furthermore, when the scene simulation model is the second scene simulation model, obtaining the scene simulation model includes: obtaining target mapping data, wherein the target mapping data is the data corresponding to the target area of ​​the mining area collected by the UAV; and constructing the second scene simulation model based on the mapping data.

[0070] Furthermore, when the scene simulation model is the first scene simulation model, before acquiring the scene simulation model, the method further includes: acquiring target mapping data, wherein the target mapping data is data corresponding to the target area of ​​the mining area collected by the UAV; and constructing a ground map model based on the target mapping data, wherein the ground map model contains area boundary information corresponding to the area boundary.

[0071] Furthermore, the simulation vehicle is controlled to circle the scene simulation model once, and the simulation vehicle is controlled to collect the corresponding detour data during the detour, including: obtaining the detour path corresponding to the detour of the simulation vehicle in the scene simulation model based on the ground map model, wherein the coordinate system corresponding to the detour path is the coordinate system in the ground map model; controlling the simulation vehicle to detour according to the detour path, and controlling the simulation vehicle to collect the positioning coordinate information corresponding to the detour path during the detour; and determining the positioning coordinate information as detour data.

[0072] Furthermore, based on the detour data, the regional boundaries of the scene simulation model and / or the regional boundaries of the ground map model are determined, including: converting the positioning coordinate information into target positioning coordinate information, wherein the coordinate system of the target positioning coordinate information is the coordinate system corresponding to the scene simulation model; and determining the regional boundaries corresponding to the scene simulation model based on the target positioning coordinate information.

[0073] Furthermore, the simulation vehicle is controlled to circle around the scene simulation model, and the simulation vehicle is controlled to collect the corresponding circumference data during the circumference process, including: acquiring the data collected by the camera model and extracting the area boundary GPS positioning data contained in the data; and identifying the area boundary GPS positioning data as circumference data.

[0074] Further, based on the detour data, the regional boundaries of the scene simulation model and / or the regional boundaries of the ground map model are determined, including: importing the regional boundary GPS positioning data into the scene simulation software to construct a second scene simulation model, and determining the regional boundaries in the second scene simulation model based on the regional boundary GPS positioning data; importing the regional boundary GPS positioning data into the GMS system map management module to construct a ground map model, and determining the regional boundaries in the ground map model based on the regional boundary GPS positioning data, wherein the regional boundaries in the ground map model are consistent with the regional boundaries in the scene simulation model.

[0075] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0076] This invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program with the following method steps: acquiring a scene simulation model, wherein the scene simulation model is a simulation model corresponding to the target area of ​​the mining area, the scene simulation model includes a first scene simulation model and a second scene simulation model, the area boundary in the first scene simulation model is unknown, the area boundary in the second scene simulation model is known, and the area boundary is the boundary between the working area and the non-working area of ​​the mining area; importing the scene simulation model into scene simulation software, and configuring a simulation vehicle for the scene simulation model, wherein the simulation vehicle is configured with virtual GPS positioning function and a camera model; controlling the simulation vehicle to circle around the scene simulation model, and controlling the simulation vehicle to collect the circumference data corresponding to the circumference during the circumference; and determining the area boundary of the scene simulation model and / or the area boundary of the ground map model based on the circumference data.

[0077] Furthermore, when the scene simulation model is the second scene simulation model, obtaining the scene simulation model includes: obtaining target mapping data, wherein the target mapping data is the data corresponding to the target area of ​​the mining area collected by the UAV; and constructing the second scene simulation model based on the mapping data.

[0078] Furthermore, when the scene simulation model is the first scene simulation model, before acquiring the scene simulation model, the method further includes: acquiring target mapping data, wherein the target mapping data is data corresponding to the target area of ​​the mining area collected by the UAV; and constructing a ground map model based on the target mapping data, wherein the ground map model contains area boundary information corresponding to the area boundary.

[0079] Furthermore, the simulation vehicle is controlled to circle the scene simulation model once, and the simulation vehicle is controlled to collect the corresponding detour data during the detour, including: obtaining the detour path corresponding to the detour of the simulation vehicle in the scene simulation model based on the ground map model, wherein the coordinate system corresponding to the detour path is the coordinate system in the ground map model; controlling the simulation vehicle to detour according to the detour path, and controlling the simulation vehicle to collect the positioning coordinate information corresponding to the detour path during the detour; and determining the positioning coordinate information as detour data.

[0080] Furthermore, based on the detour data, the regional boundaries of the scene simulation model and / or the regional boundaries of the ground map model are determined, including: converting the positioning coordinate information into target positioning coordinate information, wherein the coordinate system of the target positioning coordinate information is the coordinate system corresponding to the scene simulation model; and determining the regional boundaries corresponding to the scene simulation model based on the target positioning coordinate information.

[0081] Furthermore, the simulation vehicle is controlled to circle around the scene simulation model, and the simulation vehicle is controlled to collect the corresponding circumference data during the circumference process, including: acquiring the data collected by the camera model and extracting the area boundary GPS positioning data contained in the data; and identifying the area boundary GPS positioning data as circumference data.

[0082] Further, based on the detour data, the regional boundaries of the scene simulation model and / or the regional boundaries of the ground map model are determined, including: importing the regional boundary GPS positioning data into the scene simulation software to construct a second scene simulation model, and determining the regional boundaries in the second scene simulation model based on the regional boundary GPS positioning data; importing the regional boundary GPS positioning data into the GMS system map management module to construct a ground map model, and determining the regional boundaries in the ground map model based on the regional boundary GPS positioning data, wherein the regional boundaries in the ground map model are consistent with the regional boundaries in the scene simulation model.

[0083] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0084] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0085] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0086] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0087] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0088] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory. Memory is an example of computer-readable media.

[0089] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media do not include transient computer-readable media, such as modulated data signals and carrier waves.

[0090] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0091] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] The above are merely embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A method for determining the boundary of a model region, characterized in that, include: Obtain a scene simulation model, wherein the scene simulation model is a simulation model corresponding to the target area of ​​the mining area, the scene simulation model includes a first scene simulation model and a second scene simulation model, the area boundary in the first scene simulation model is unknown, the area boundary in the second scene simulation model is known, and the area boundary is the boundary between the working area and the non-working area of ​​the mining area; The scene simulation model is imported into the scene simulation software, and a simulation vehicle is configured for the scene simulation model, wherein the simulation vehicle is equipped with virtual GPS positioning function and camera model; The simulation vehicle is controlled to circle the scene simulation model once, and the simulation vehicle is controlled to collect the circumference data corresponding to the circle once during the circumference process; Based on the detour data, the regional boundaries of the scene simulation model and / or the regional boundaries of the ground map model are redefined; When the scenario simulation model is the second scenario simulation model, obtaining the scenario simulation model includes: obtaining target mapping data, wherein the target mapping data is data corresponding to the target area of ​​the mining area collected by the UAV; and constructing the second scenario simulation model based on the mapping data. When the scene simulation model is the first scene simulation model, before acquiring the scene simulation model, the method further includes: acquiring target mapping data, wherein the target mapping data is data corresponding to the target area of ​​the mining area collected by the UAV; and constructing the ground map model based on the target mapping data, wherein the ground map model includes area boundary information corresponding to the area boundary. Controlling the simulated vehicle to circle the scene simulation model once, and controlling the simulated vehicle to collect the corresponding detour data during the detour, includes: obtaining the detour path corresponding to the simulated vehicle's circle in the scene simulation model based on the ground map model, wherein the coordinate system corresponding to the detour path is the coordinate system in the ground map model; controlling the simulated vehicle to circle according to the detour path, and controlling the simulated vehicle to collect the positioning coordinate information corresponding to the detour path during the detour; and determining the positioning coordinate information as the detour data. Based on the detour data, determining the regional boundary of the scene simulation model and / or the regional boundary of the ground map model includes: converting the positioning coordinate information into target positioning coordinate information, wherein the coordinate system of the target positioning coordinate information is the coordinate system corresponding to the scene simulation model; and determining the regional boundary corresponding to the scene simulation model based on the target positioning coordinate information. Controlling the simulated vehicle to circle once in the scene simulation model, and controlling the simulated vehicle to collect the corresponding circumference data during the circumference process, including: acquiring the data collected by the camera model, and extracting the area boundary GPS positioning data contained in the data; determining the area boundary GPS positioning data as the circumference data; Based on the detour data, determining the regional boundaries of the scene simulation model and / or the regional boundaries of the ground map model includes: importing the GPS positioning data of the regional boundaries into the scene simulation software to construct the second scene simulation model, and determining the regional boundaries in the second scene simulation model based on the GPS positioning data of the regional boundaries; importing the GPS positioning data of the regional boundaries into the GMS system map management module to construct the ground map model, and determining the regional boundaries in the ground map model based on the GPS positioning data of the regional boundaries, wherein the regional boundaries in the ground map model are consistent with the regional boundaries in the scene simulation model.

2. An apparatus for determining the boundary of a model region, characterized in that, include: An acquisition unit is used to acquire a scene simulation model, wherein the scene simulation model is a simulation model corresponding to the target area of ​​the mining area, the scene simulation model includes a first scene simulation model and a second scene simulation model, the area boundary in the first scene simulation model is unknown, the area boundary in the second scene simulation model is known, and the area boundary is the boundary between the working area and the non-working area of ​​the mining area. A configuration unit is used to import the scene simulation model into the scene simulation software and configure a simulation vehicle for the scene simulation model, wherein the simulation vehicle is configured with a virtual GPS positioning function and a camera model. The control unit is used to control the simulated vehicle to circle once in the scene simulation model, and to control the simulated vehicle to collect the circling data corresponding to one circling during the circling process; The determining unit is used to redetermine the regional boundaries of the scene simulation model and / or the regional boundaries of the ground map model based on the detour data. The acquisition unit includes: a first acquisition subunit, used to acquire target mapping data, wherein the target mapping data is data corresponding to the target area of ​​the mining area collected by the UAV; and a first construction subunit, used to construct the second scene simulation model based on the mapping data. When the scene simulation model is the first scene simulation model, before acquiring the scene simulation model, the acquisition unit further includes: a second acquisition subunit for acquiring target mapping data, wherein the target mapping data is data corresponding to the target area of ​​the mining area collected by the UAV; and a second construction subunit for constructing the ground map model based on the target mapping data, wherein the ground map model includes area boundary information corresponding to the area boundary. The control unit includes: a third acquisition subunit, configured to acquire, based on the ground map model, a detour path corresponding to the detour of the simulated vehicle in the scene simulation model, wherein the coordinate system corresponding to the detour path is the coordinate system in the ground map model; a control subunit, configured to control the simulated vehicle to detour according to the detour path, and control the simulated vehicle to collect positioning coordinate information corresponding to the detour path during the detour; and a first determination subunit, configured to determine the positioning coordinate information as the detour data. The determining unit includes: a transformation subunit, used to convert the positioning coordinate information into target positioning coordinate information, wherein the coordinate system of the target positioning coordinate information is the coordinate system corresponding to the scene simulation model; and a second determining subunit, used to determine the region boundary corresponding to the scene simulation model based on the target positioning coordinate information. The determining unit includes: a fourth acquisition subunit, used to acquire data collected by the camera model and extract the regional boundary GPS positioning data contained in the data; and a third determining subunit, used to determine the regional boundary GPS positioning data as the detour data. The determining unit includes: a second construction subunit, used to import the GPS positioning data of the area boundary into the scene simulation software to construct the second scene simulation model, and to determine the area boundary in the second scene simulation model based on the GPS positioning data of the area boundary; and a third construction subunit, used to import the GPS positioning data of the area boundary into the GMS system map management module to construct the ground map model, and to determine the area boundary in the ground map model based on the GPS positioning data of the area boundary, wherein the area boundary in the ground map model is consistent with the area boundary in the scene simulation model.

3. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the method for determining the boundary of a model region as described in claim 1.

4. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein, when the program is executed, it controls the device where the non-volatile storage medium is located to perform the method for determining the boundary of a model region as described in claim 1.

5. A processor, characterized in that, The processor is used to run a program, wherein the program executes the method for determining the boundary of a model region as described in claim 1.

Images