Methods and apparatus for constructing 3D maps based on autonomous vehicles

Abstract

This invention provides a method and apparatus for constructing a 3D map based on an autonomous vehicle, relating to the field of 3D map construction technology. The invention obtains the 2D position and elevation information of the boundary of a target area, and the trajectory and elevation information of a basic route; then, based on at least a portion of the elevation information of the boundary and at least a portion of the elevation information of the basic route, it performs elevation interpolation to obtain a 3D map of the target area; and in use, it determines the fixed and variable routes that the autonomous vehicle needs to travel within the target area, and directs the autonomous vehicle to travel along the fixed and variable routes to gradually approach the boundary. As the autonomous vehicle gradually approaches the boundary, the boundary of the 3D map is updated, ultimately enabling the construction and updating of a 3D map without the use of LiDAR, visual sensors, or other similar devices, meeting the needs of autonomous vehicles for operation and transportation.

Description

Technical Field

[0001] This invention relates to the field of 3D map construction technology, and specifically to a method, apparatus, computer-readable storage medium, and electronic device for constructing 3D maps based on unmanned vehicles. Background Technology

[0002] In unmanned driving scenarios in open-pit coal mines, the construction of 3D maps is crucial, serving as a prerequisite for unmanned vehicles to operate and transport goods.

[0003] However, most existing unmanned driving systems in open-pit coal mines focus on the earthwork stripping and transportation process. The specific solutions mostly rely on LiDAR, visual sensors, and other sensors for real-time perception to determine the driving area and ensure driving safety.

[0004] However, the above-mentioned solution cannot be applied to the coal mining and transportation operation. This is because the coal has low reflectivity to lidar within the coal mining area, rendering lidar's sensing capability ineffective. At the same time, the large amount of coal dust in the coal mining area makes it difficult to segment and identify the road surface, retaining wall, and other elements visually. Furthermore, as the mining and loading equipment operates, the actual boundaries of the work area will change, so the 3D map of the work area needs to be updated in a timely manner. As a result, it is difficult to construct and update the 3D map using traditional methods in the coal mining and transportation process. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] To address the shortcomings of existing technologies, this invention provides a method, apparatus, computer-readable storage medium, and electronic device for constructing three-dimensional maps based on unmanned vehicles, solving the problem of difficulties in constructing and updating three-dimensional maps using traditional methods in the coal mining and transportation process.

[0007] (II) Technical Solution

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] Firstly, a method for constructing 3D maps based on autonomous vehicles is provided, the method comprising:

[0010] Obtain the two-dimensional location information of the boundary of the target area and the elevation information of the boundary.

[0011] Obtain the trajectory information and elevation information of the basic routes within the target area;

[0012] A three-dimensional map of the target area is obtained by interpolating the elevation of the boundary and the trajectory information based on at least part of the elevation information of the boundary and at least part of the elevation information of the basic route.

[0013] Based on the three-dimensional map and the trajectory information of the basic route, the fixed route that the unmanned vehicle needs to travel within the target area is determined.

[0014] Based on the real-time status of the autonomous vehicle, the real-time location of the devices cooperating with the autonomous vehicle, or the current boundary of the 3D map, a variable route for the autonomous vehicle to travel within the target area is automatically generated using a local trajectory planning method.

[0015] The autonomous vehicle travels along the fixed route and the variable route to gradually approach the boundary. As the autonomous vehicle approaches the boundary, the boundary of the 3D map is updated.

[0016] Furthermore, updating the boundaries of the 3D map includes updating the location and elevation information of the 3D map.

[0017] Furthermore, the autonomous vehicle gradually approaching the boundary includes: the bounding box of the autonomous vehicle intersecting the boundary of the 3D map.

[0018] Furthermore, the two-dimensional position information of the boundary, the elevation information of the boundary, the trajectory information of the basic route, and the elevation information of the basic route are all obtained through a motion device with positioning function.

[0019] Furthermore, the basic route includes some or all of the fixed routes;

[0020] Furthermore, the fixed route includes at least a portion of the driving route of the unmanned vehicle from the entrance of the coal mining area to the loading position.

[0021] Furthermore, the method also includes:

[0022] When a motion device with positioning function travels within a 3D map, the elevation information within the 3D map is updated in real time based on the elevation information of the motion device with positioning function.

[0023] Furthermore, the motion device with positioning function is an unmanned vehicle with GPS positioning function.

[0024] Secondly, an apparatus for constructing 3D maps based on autonomous vehicles is provided, the apparatus comprising:

[0025] The boundary information acquisition module is used to acquire the two-dimensional position information of the boundary of the target area and the elevation information of the boundary;

[0026] The basic route information acquisition module is used to acquire the trajectory information and elevation information of the basic routes within the target area;

[0027] An elevation difference module is used to perform elevation interpolation on the boundary and the trajectory information based on at least part of the elevation information of the boundary and at least part of the elevation information of the basic route to obtain a three-dimensional map of the target area.

[0028] The fixed route determination module is used to determine the fixed route that the unmanned vehicle needs to travel within the target area based on the trajectory information of the three-dimensional map and the basic route.

[0029] The variable route determination module is used to automatically generate a variable route for the autonomous vehicle to travel within the target area based on the real-time status of the autonomous vehicle, the real-time location of the equipment cooperating with the autonomous vehicle, or the current boundary of the three-dimensional map, using a local trajectory planning method.

[0030] The driverless vehicle travels along the fixed route and the variable route to gradually approach the boundary;

[0031] The map update module is used to update the boundary of the 3D map as the autonomous vehicle gradually approaches the boundary.

[0032] Thirdly, a computer-readable storage medium is provided that stores a computer program for constructing a three-dimensional map based on an autonomous vehicle, wherein the computer program causes a computer to execute the above-described method for constructing a three-dimensional map based on an autonomous vehicle.

[0033] Fourthly, an electronic device is provided, comprising:

[0034] One or more processors;

[0035] Memory; and

[0036] One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including methods for performing the above-described method for constructing a 3D map based on an autonomous vehicle.

[0037] (III) Beneficial Effects

[0038] This invention provides a method and apparatus for constructing 3D maps based on autonomous vehicles. Compared with existing technologies, it has the following advantages:

[0039] This invention acquires the two-dimensional location information and elevation information of the boundary of a target area, as well as the trajectory information and elevation information of a basic route within the target area. Then, based on at least a portion of the elevation information of the boundary and at least a portion of the elevation information of the basic route, it performs elevation interpolation on the boundary and the trajectory information to obtain a three-dimensional map of the target area. In use, it determines the fixed and variable routes that an autonomous vehicle needs to travel within the target area, and directs the autonomous vehicle to travel along the fixed and variable routes to gradually approach the boundary. As the autonomous vehicle gradually approaches the boundary, the boundary of the three-dimensional map is updated, ultimately enabling the construction and updating of a three-dimensional map without the use of LiDAR, visual sensors, or other similar devices, thus meeting the needs of autonomous vehicles for operation and transportation. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a flowchart of the present invention;

[0042] Figure 2 This is a schematic diagram of coal mining and transportation operations according to an embodiment of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are described clearly and completely. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] This application provides a method, apparatus, computer-readable storage medium, and electronic device for constructing 3D maps based on unmanned vehicles, which solves the problem that it is difficult to construct and update 3D maps using traditional methods in the coal mining and transportation process.

[0045] The technical solution in this application is to solve the above-mentioned technical problems, and the general idea is as follows:

[0046] In view of the characteristics of coal mining and transportation operations, this patent proposes an engineerable method for unmanned driving in coal mining and transportation operations, which has low requirements for sensors and is based on unmanned vehicles to build and update 3D maps.

[0047] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0048] Example 1:

[0049] like Figure 1 As shown, the present invention provides a method for constructing a 3D map based on an autonomous vehicle, the method comprising:

[0050] Obtain the two-dimensional location information of the boundary of the target area and the elevation information of the boundary.

[0051] Obtain the trajectory information and elevation information of the basic routes within the target area;

[0052] A three-dimensional map of the target area is obtained by interpolating the elevation of the boundary and the trajectory information based on at least part of the elevation information of the boundary and at least part of the elevation information of the basic route.

[0053] Based on the three-dimensional map and the trajectory information of the basic route, the fixed route that the unmanned vehicle needs to travel within the target area is determined.

[0054] Based on the real-time status of the autonomous vehicle, the real-time location of the devices cooperating with the autonomous vehicle, or the current boundary of the 3D map, a variable route for the autonomous vehicle to travel within the target area is automatically generated using a local trajectory planning method.

[0055] The autonomous vehicle travels along the fixed route and the variable route to gradually approach the boundary. As the autonomous vehicle approaches the boundary, the boundary of the 3D map is updated.

[0056] Theoretically, this invention can be used in any region without any restrictions. However, it is generally used in areas that cannot be acquired by lidar or in scenarios where the elevation accuracy of the 3D map is not critical.

[0057] The beneficial effects of this embodiment are:

[0058] This invention obtains the two-dimensional location information and elevation information of the boundary of a target area, as well as the trajectory information and elevation information of a basic route within the target area. Then, based on at least a portion of the elevation information of the boundary and at least a portion of the elevation information of the basic route, it performs elevation interpolation on the boundary and the trajectory information to obtain a three-dimensional map of the target area. In use, it determines the fixed and variable routes that the autonomous vehicle needs to travel within the target area, and directs the autonomous vehicle to travel along the fixed and variable routes to gradually approach the boundary. As the autonomous vehicle gradually approaches the boundary, the boundary of the three-dimensional map is updated, ultimately enabling the construction and updating of a three-dimensional map without the use of LiDAR, visual sensors, or other similar devices, thus meeting the needs of autonomous vehicles for operation and transportation.

[0059] like Figure 2 As shown, the implementation process of this invention will be described in detail below using a coal mining and transportation operation scenario as an example:

[0060] Definitions:

[0061] Coal mining area: This refers to the area where coal mining operations take place (also called the loading area). Within this area, mining and loading equipment (such as excavators, electric shovels, etc.) extracts coal and loads it onto transportation equipment (such as manned trucks and unmanned mining cars), which then transports it to the unloading area.

[0062] Waiting position: When other transport equipment enters the coal mining area, it waits at the waiting position when the loading equipment is already being loaded by other transport equipment.

[0063] Loading position: The stopping position of the transport equipment when the loading equipment loads coal into the transport equipment;

[0064] Work process:

[0065] (1) Select a suitable area as the coal mining area according to the production plan;

[0066] (2) For the selected coal mining area, use the above method to generate a three-dimensional map of the coal mining area;

[0067] (3) For other areas such as roads and unloading areas, high-precision three-dimensional maps are generated by using lidar data collection.

[0068] (4) The transportation equipment automatically cycles between the coal mining area, roads and unloading areas, and automatically updates the three-dimensional map of the coal mining area according to the vehicle's position when loading at the loading position.

[0069] S1. Obtain the two-dimensional location information of the boundary of the target area and the elevation information of the boundary, and obtain the trajectory information of the basic route within the target area and the elevation information of the basic route.

[0070] In practice, the target area is the coal mining operation area, which includes a variable area and a fixed area. The variable area can be the area surrounding the mining equipment, while the fixed area can be the area within the coal mining operation area from when the vehicle enters the coal mining operation area to when it is ready to be loaded.

[0071] In this embodiment, the method for obtaining the two-dimensional location information of the target area boundary is not limited. For example, the boundary two-dimensional location information can be obtained by mapping the coordinates of the boundary of the coal mining area in the CAD drawing of the coal mining area. When there is no CAD drawing, the following method can also be used to obtain the information:

[0072] S101. Move the motion device with positioning function along the boundary of the target area to obtain the two-dimensional position information of the boundary of the target area.

[0073] In specific implementation, this embodiment does not limit the form of the motion device with positioning function. For example, it can be a data collection vehicle carrying a GPS device, and the data collection vehicle can be an unmanned vehicle. In this way, the data collection vehicle can drive along the boundary of the coal mining operation area and obtain the two-dimensional information position of the boundary of the coal mining operation area based on the GPS positioning data during the driving process.

[0074] In addition, obtaining the trajectory information and elevation information of the basic route within the target area may specifically include the following steps:

[0075] S102. Use the travel route of the motion device with positioning function in the coal mining area as the basic route.

[0076] S103. Obtain the trajectory information of the moving device with positioning function in the coal mining operation area and the elevation information of the basic route.

[0077] In practical implementation, the motion device with positioning function travels along the basic route, and GPS is used to obtain the positioning data corresponding to the preset path, thus providing the corresponding trajectory and elevation information. Similarly, this embodiment does not limit the method of obtaining the basic route; only one feasible method is given below:

[0078] Based on the road and workface conditions at the coal mining site, on-site production personnel determine a suitable route for unmanned vehicles as the basic route. Considering the potential for significant changes in the loading area, the basic route can be the route taken by a positioning device from the entrance of the coal mining area to the loading position. Of course, if the coal mining area is large or there are areas with significant elevation changes, data collection vehicles are also needed to collect data for subsequent elevation interpolation to obtain a more accurate 3D map.

[0079] S2. Based on at least some elevation information of the boundary and at least some elevation information of the basic route, perform elevation interpolation on the boundary and the trajectory information to obtain a three-dimensional map of the target area.

[0080] In practice, the elevation information of at least some of the boundaries, basic routes, and areas with significant elevation changes obtained through the above two steps is used to interpolate the elevation of the entire two-dimensional map to obtain three-dimensional map data with elevation information.

[0081] Interpolation methods can include global interpolation, block interpolation, and inverse distance weighted interpolation, with inverse distance weighted interpolation being a commonly used method. Its main principle is to calculate the distance between each point for which elevation data is desired and its surrounding existing elevation data points, and then use the power of the inverse of that distance as the weight to determine the final weight of the desired point.

[0082] S3. Based on the trajectory information of the three-dimensional map and the basic route, determine the fixed route that the autonomous vehicle needs to travel in the target area; based on the real-time status of the autonomous vehicle, the real-time location of the equipment cooperating with the autonomous vehicle, or the current boundary of the three-dimensional map, automatically generate the variable route that the autonomous vehicle travels in the target area through a local trajectory planning method.

[0083] Specifically, when the positioning device is an unmanned mining vehicle, the driving route can be divided based on the variable and fixed areas of the coal mining area, and then divided into variable routes and fixed routes.

[0084] Fixed routes can be the same as the vehicle's journey from the entrance of the coal mining area to the loading position, while variable routes can be the same as the route from the loading position to the loading point. Since fixed routes remain largely unchanged, they can serve as part of the autonomous vehicle's route. Variable routes, on the other hand, can be automatically generated by the vehicle or the dispatch platform based on the vehicle's real-time status, the location of equipment cooperating with the autonomous vehicle (such as mining and loading equipment), and map boundaries, using local trajectory planning methods. When the autonomous vehicle approaches the mining and loading equipment located at the map boundary along both fixed and variable routes, since the map is not a high-precision map generated from radar data, various sensors, such as ultrasonic radar and millimeter-wave radar, are still required for safety assurance. These sensors, in addition to obstacle avoidance, can also roughly determine the location of the coal mine loading retaining walls when the vehicle enters the loading position; this data can be used for subsequent automatic map updates.

[0085] S4. Update the 3D map.

[0086] In practice, as operations progress, the map boundaries near the loading positions of the mining and loading equipment will change. To achieve continuous mining and transportation operations in the coal mine, the map needs to be continuously updated. The solution includes updating the elevation information of the internal areas of the 3D map and updating the boundaries of the 3D map.

[0087] 1) Update elevation information for areas within the 3D map:

[0088] The elevation information of the 3D map is updated in real time based on the elevation information of the acquired motion device with positioning function.

[0089] Specifically, if the motion device with positioning function is an unmanned data collection vehicle, the data collection vehicle will collect GPS data in real time when it is driving in the 3D map, and the latest elevation data can be obtained from it to replace the original elevation data of that location in the 3D map.

[0090] 2) Updating the boundaries of the 3D map:

[0091] First, the elevation information and bounding box position information of the motion device with positioning function are obtained; when the bounding box intersects with the boundary of the 3D map, it indicates that the actual position of the motion device exceeds the boundary of the 3D map, so the boundary of the 3D map can be updated at this time; finally, the elevation information of the boundary can also be updated based on the elevation information of the motion device with positioning function obtained in real time.

[0092] One specific scenario is:

[0093] The motion device with positioning capabilities is a data acquisition vehicle. This unmanned vehicle travels along the fixed route and the variable route to gradually approach the boundary. Before entering the loading position, it interacts with the data acquisition equipment to obtain a suitable loading position, such as a location previously excavated by the data acquisition equipment. The boundary of this area will expand outwards, requiring boundary updates. Throughout the vehicle's journey to the loading position, the vehicle continuously assesses its position relative to the map boundary. If the vehicle's bounding box intersects with the map boundary, the map boundary is updated directly, and the vehicle's elevation information is filled into the updated boundary area.

[0094] Example 2:

[0095] An apparatus for constructing 3D maps based on autonomous vehicles, the apparatus comprising:

[0096] The boundary information acquisition module is used to acquire the two-dimensional position information of the boundary of the target area and the elevation information of the boundary;

[0097] The basic route information acquisition module is used to acquire the trajectory information and elevation information of the basic routes within the target area;

[0098] An elevation difference module is used to perform elevation interpolation on the boundary and the trajectory information based on at least part of the elevation information of the boundary and at least part of the elevation information of the basic route to obtain a three-dimensional map of the target area.

[0099] The fixed route determination module is used to determine the fixed route that the unmanned vehicle needs to travel within the target area based on the trajectory information of the three-dimensional map and the basic route.

[0100] The variable route determination module is used to automatically generate a variable route for the autonomous vehicle to travel within the target area based on the real-time status of the autonomous vehicle, the real-time location of the equipment cooperating with the autonomous vehicle, or the current boundary of the three-dimensional map, using a local trajectory planning method.

[0101] The driverless vehicle travels along the fixed route and the variable route to gradually approach the boundary;

[0102] The map update module is used to update the boundary of the 3D map as the autonomous vehicle gradually approaches the boundary.

[0103] Example 3:

[0104] A computer-readable storage medium storing a computer program for constructing a 3D map based on an autonomous vehicle, wherein the computer program causes a computer to perform the following steps:

[0105] Obtain the two-dimensional location information of the boundary of the target area and the elevation information of the boundary.

[0106] Obtain the trajectory information and elevation information of the basic routes within the target area;

[0107] A three-dimensional map of the target area is obtained by interpolating the elevation of the boundary and the trajectory information based on at least part of the elevation information of the boundary and at least part of the elevation information of the basic route.

[0108] Based on the three-dimensional map and the trajectory information of the basic route, the fixed route that the unmanned vehicle needs to travel within the target area is determined.

[0109] Based on the real-time status of the autonomous vehicle, the real-time location of the devices cooperating with the autonomous vehicle, or the current boundary of the 3D map, a variable route for the autonomous vehicle to travel within the target area is automatically generated using a local trajectory planning method.

[0110] The autonomous vehicle travels along the fixed route and the variable route to gradually approach the boundary. As the autonomous vehicle approaches the boundary, the boundary of the 3D map is updated.

[0111] Example 4:

[0112] An electronic device, comprising:

[0113] One or more processors;

[0114] Memory; and

[0115] One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including steps for performing the following:

[0116] Obtain the two-dimensional location information of the boundary of the target area and the elevation information of the boundary.

[0117] Obtain the trajectory information and elevation information of the basic routes within the target area;

[0118] A three-dimensional map of the target area is obtained by interpolating the elevation of the boundary and the trajectory information based on at least part of the elevation information of the boundary and at least part of the elevation information of the basic route.

[0119] Based on the three-dimensional map and the trajectory information of the basic route, the fixed route that the unmanned vehicle needs to travel within the target area is determined.

[0120] Based on the real-time status of the autonomous vehicle, the real-time location of the devices cooperating with the autonomous vehicle, or the current boundary of the 3D map, a variable route for the autonomous vehicle to travel within the target area is automatically generated using a local trajectory planning method.

[0121] The autonomous vehicle travels along the fixed route and the variable route to gradually approach the boundary. As the autonomous vehicle approaches the boundary, the boundary of the 3D map is updated.

[0122] It is understood that the apparatus, computer-readable storage medium, and electronic device for constructing three-dimensional maps based on autonomous vehicles provided in the embodiments of the present invention correspond to the method for constructing three-dimensional maps based on autonomous vehicles described above. The explanations, examples, and beneficial effects of the relevant contents can be referred to the corresponding contents in the method for constructing three-dimensional maps based on autonomous vehicles, and will not be repeated here.

[0123] In summary, compared with the prior art, the present invention has the following beneficial effects:

[0124] This invention obtains a three-dimensional map of the target area by acquiring the two-dimensional location information and elevation information of the boundary of the target area, and the trajectory information and elevation information of the basic route within the target area; then, based on at least part of the elevation information of the boundary and at least part of the elevation information of the basic route, it performs elevation interpolation on the boundary and the trajectory information.

[0125] In operation, a fixed and variable route for the autonomous vehicle to travel within the target area is first determined. The autonomous vehicle then travels along the fixed and variable routes to gradually approach the boundary. As the autonomous vehicle approaches the boundary, the boundary of the 3D map is updated. Ultimately, this allows for the construction and updating of a 3D map without the need for devices such as LiDAR and visual sensors, meeting the needs of autonomous vehicles for operation and transportation.

[0126] It should be noted that, through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the prior art, can be embodied in the form of software products. These computer software products can be stored in computer-readable storage media, such as ROM / RAM, magnetic disks, optical disks, etc., and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or certain portions of the embodiments. In this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, 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 a process, method, article, or apparatus. In the absence of further restrictions, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0127] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method of constructing a three-dimensional map based on an unmanned vehicle, characterized by, The method comprises: acquiring two-dimensional position information of a boundary of a target region and elevation information of the boundary, acquiring trajectory information of a basic route in the target region and elevation information of the basic route; based on at least part of the elevation information of the boundary and at least part of the elevation information of the basic route, performing elevation interpolation on the boundary and the trajectory information to obtain a three-dimensional map of the target region; based on the three-dimensional map and the trajectory information of the basic route, determining a fixed route that needs to be traveled by an unmanned vehicle in the target region, the fixed route being used to represent a travel route located in a fixed region; based on a real-time state of the unmanned vehicle, a real-time position of a device cooperating with the unmanned vehicle, or a boundary of the three-dimensional map at present, automatically generating a variable route that the unmanned vehicle travels in the target region by a local trajectory planning method, the variable route being used to represent a travel route located in a variable region; wherein the unmanned vehicle travels along the fixed route and the variable route to gradually approach the boundary; and when the unmanned vehicle gradually approaches the boundary, the boundary of the three-dimensional map is updated.

2. The method of claim 1, wherein, The updating of the boundary of the three-dimensional map comprises updating position information and elevation information of the three-dimensional map.

3. The method of claim 1, wherein, The gradual approaching of the unmanned vehicle to the boundary comprises intersection of a bounding box of the unmanned vehicle and the boundary of the three-dimensional map.

4. The method of claim 1, wherein, The two-dimensional position information of the boundary, the elevation information of the boundary, the trajectory information of the basic route, and the elevation information of the basic route are all acquired by a motion device with positioning function.

5. The method of claim 4, wherein, The basic route comprises part of the fixed route or all of the fixed route. The fixed route comprises at least part of a travel route of the unmanned vehicle from an entry of a coal mining operation region to a waiting position.

6. The method of claim 1, wherein, The method further comprises: when the motion device with positioning function travels in the three-dimensional map, the elevation information inside the three-dimensional map is updated in real time based on elevation information of the motion device with positioning function.

7. A method of constructing a three-dimensional map based on an unmanned vehicle as claimed in claim 4 or 6, characterized in that, The motion device with positioning function is an unmanned vehicle with GPS positioning function.

8. A device for constructing a three-dimensional map based on an unmanned vehicle, characterized in that, The device comprises: a boundary information acquisition module configured to acquire two-dimensional position information of a boundary of a target region and elevation information of the boundary; a basic route information acquisition module configured to acquire trajectory information of a basic route in the target region and elevation information of the basic route; an elevation difference module configured to perform elevation interpolation on the boundary and the trajectory information based on at least part of the elevation information of the boundary and at least part of the elevation information of the basic route to obtain a three-dimensional map of the target region; a fixed route determination module configured to determine a fixed route that needs to be traveled by an unmanned vehicle in the target region based on the three-dimensional map and the trajectory information of the basic route, the fixed route being used to represent a travel route located in a fixed region; and a variable route generation module configured to automatically generate a variable route that the unmanned vehicle travels in the target region based on a real-time state of the unmanned vehicle, a real-time position of a device cooperating with the unmanned vehicle, or a boundary of the three-dimensional map at present, the variable route being used to represent a travel route located in a variable region. A variable route determining module is configured to automatically generate a variable route for the unmanned vehicle to travel within the target area based on a real-time state of the unmanned vehicle, a real-time position of a device cooperating with the unmanned vehicle, or a boundary of the three-dimensional map at present, the variable route being used to represent a travel route within a variable area; wherein the unmanned vehicle travels along the fixed route and the variable route to gradually approach the boundary; A map updating module is configured to update the boundary of the three-dimensional map when the unmanned vehicle gradually approaches the boundary.

9. A computer-readable storage medium, characterized in that, A computer program product for constructing a three-dimensional map based on an unmanned vehicle, wherein the computer program product causes a computer to perform the method for constructing a three-dimensional map based on an unmanned vehicle according to any one of claims 1-7.

10. An electronic device, comprising: comprising: one or more processors; memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising programs for performing the method for constructing a three-dimensional map based on an unmanned vehicle according to any one of claims 1-7.

Images