High-precision map construction method based on satellite map auxiliary vehicle-mounted sensor

Abstract

The invention relates to a high-precision map construction method based on a satellite map auxiliary vehicle-mounted sensor, and the method comprises the steps: U1, obtaining the multi-view image data information of a road in real time based on a vehicle-mounted camera, and obtaining the data information of a satellite map of the road and the data information of dynamic parameters of the vehicle in real time; and U2, based on the multi-view image data information of the road, the data information of the satellite map of the road and the data information of the dynamic parameters of the vehicle, fusing the data of the road and the vehicle by adopting an improved multi-modal feature level fusion algorithm to obtain feature level fused data information of the road. According to the invention, not only is the positioning precision of the vehicle in a complex environment and a long-distance detection task improved by integrating satellite map data, but also the dependence on an expensive or high-precision vehicle-mounted sensor is reduced, and a solution with higher cost benefit is realized by supplementing the satellite map data.

Description

Technical Field

[0001] The present invention relates to the technical field of high-precision map construction, and in particular to a high-precision map construction method based on satellite map-assisted vehicle-mounted sensors. Background Art

[0002] High-precision maps in autonomous driving systems are crucial for vehicle positioning, route planning and navigation.

[0003] In the prior art, a Chinese patent (application number: 202011318597.6, publication number: CN 112484725A) discloses a high-precision positioning and spatiotemporal situational safety method for intelligent vehicles based on multi-sensor fusion, and the method is as follows: Part I, high-precision positioning method, the method is as follows: Step 1, preprocessing; Step 2, visual inertial odometer front end and initialization; Step 3, visual inertial odometer back end optimization; Step 4, global pose graph optimization. This technology may have reduced performance in complex scenes and long-distance map construction tasks due to the limitations of on-board sensors.

[0004] In the prior art, a Chinese patent (application number: 202310355752.9, publication number: CN 116452762A) discloses a method for constructing a map model, a positioning method and a device. The method for constructing a map model is applied to a vehicle, and the method includes: collecting road feature data using an on-board sensor; determining the target road where the vehicle is currently located according to the on-board positioning device; constructing a map model according to the road feature data and an ordinary map used for on-board navigation, and the map model records the association between the target road in the ordinary map and the road feature data. This technology may rely on accurate sensor data, and has high requirements for the performance and stability of the sensor, and may not be able to guarantee the accuracy of the data in some cases. Summary of the invention

[0005] In view of the above shortcomings of the prior art, the present invention provides a high-precision map construction method based on satellite maps assisted by vehicle-mounted sensors. It not only improves the positioning accuracy of vehicles in complex environments and long-distance detection tasks by integrating satellite map data, but also reduces the dependence on expensive or high-precision vehicle-mounted sensors. By supplementing satellite map data, a more cost-effective solution is achieved.

[0006] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows: a method for constructing a high-precision map based on satellite map-assisted vehicle-mounted sensors, the method comprising:

[0007] U1. The vehicle is driving on the road, and the vehicle camera obtains the multi-view image data information of the road in real time, the satellite map data information of the road and the dynamic parameter data information of the vehicle in real time;

[0008] U2. Based on the multi-view image data information of the road, the satellite map data information of the road and the dynamic parameter data information of the vehicle, an improved multi-modal feature-level fusion algorithm is used to fuse the road and vehicle data to obtain feature-level fusion data information of the road;

[0009] U3. Based on the feature-level fusion data information of the road, the satellite map data information of the road and the dynamic parameter data information of the vehicle, the BEV-level feature fusion algorithm of the road is used to fuse the road data to obtain the BEV-level fusion data information of the road;

[0010] U4. Based on the BEV-level fused data information of the road, a high-precision map generation model of the road is constructed, the high-precision map of the road is characterized, and the data information of the high-precision map of the road is obtained.

[0011] Furthermore, in step U2, the step of fusing the road and vehicle data using the improved multi-modal feature-level fusion algorithm includes:

[0012] U21. Based on the multi-view image data information of the road, construct an image feature extraction function Q1 of the road,

[0013]

[0014] Among them, x1 is the multi-vision image data information of the road, α1, α2 and α3 are image feature extraction factors of the road, and feature extraction is performed on the multi-vision image of the road to obtain feature data information of the multi-vision image of the road;

[0015] U22. Based on the data information of the satellite map of the road, construct a feature extraction function Q2 of the satellite map of the road,

[0016]

[0017] Among them, x2 is the data information of the satellite map of the road, β1, β2 and β3 are the feature extraction parameters of the satellite map of the road, and the feature extraction is performed on the satellite map of the road to obtain the feature data information of the satellite map of the road;

[0018] U23. Based on the data information of the dynamic parameters of the vehicle, construct a feature extraction function Q3 of the dynamic parameters of the vehicle,

[0019]

[0020] Among them, x3 is the data information of the satellite map of the road, γ1, γ2 and γ3 are the feature extraction factors of the dynamic parameters of the vehicle, and the feature extraction of the dynamic parameters of the vehicle is performed to obtain the feature data information of the dynamic parameters of the vehicle;

[0021] U24. Establishing a road and vehicle feature-level fusion function W based on the feature data information of the dynamic parameters of the vehicle, the feature data information of the satellite map of the road, and the feature data information of the multi-visual image of the road,

[0022]

[0023] Among them, q1 is the feature data information of the multi-visual image of the road, q2 is the feature data information of the satellite map of the road, q3 is the feature data information of the dynamic parameters of the vehicle, δ1, δ2 and δ3 are the feature-level fusion parameters of the road. The data of the road and the vehicle are fused to obtain the feature-level fusion data information of the road.

[0024] Furthermore, the feature-level fusion parameters δ1, δ2 and δ3 of the road are:

[0025]

[0026] Among them, q1 is the feature data information of the multi-visual image of the road, q2 is the feature data information of the satellite map of the road, and q3 is the feature data information of the dynamic parameters of the vehicle.

[0027] Furthermore, the constraints of the feature extraction factors γ1, γ2 and γ3 of the dynamic parameters of the vehicle are:

[0028]

[0029] Furthermore, the constraint function f of the road image feature extraction factors α1, α2 and α3 is,

[0030]

[0031] The value range of the constraint function f is (1,2).

[0032] Furthermore, in step U3, the method of fusing the road data using the BEV-level feature fusion algorithm of the road includes:

[0033] U31. Based on the data information of the satellite map of the road and the data information of the dynamic parameters of the vehicle, a coordinate alignment function R of the road is established.

[0034]

[0035] Wherein, y1 is the data information of the satellite map of the road, y2 is the data information of the dynamic parameters of the vehicle, η1, η2 and η3 are the coordinate alignment factors of the road, the satellite map of the road and the dynamic parameters of the vehicle are aligned, and the road coordinate alignment matrix is ​​constructed to obtain the data information of the road coordinate alignment matrix;

[0036] U32. Based on the data information of the road coordinate alignment matrix and the data information of the feature-level fusion of the road, a BEV-level feature fusion function P of the road is established.

[0037]

[0038] Among them, z1 is the data information of the road coordinate alignment matrix, z2 is the data information of the feature-level fusion of the road, λ1, λ2 and λ3 are the weight coefficients of the BEV-level feature fusion of the road;

[0039] U33. Based on the BEV-level feature fusion function P of the road, the road data is fused to obtain BEV-level fused data information of the road.

[0040] Furthermore, the constraints of the weight coefficients λ1, λ2 and λ3 of the BEV-level feature fusion of the road are:

[0041]

[0042] Furthermore, in step U4, the high-precision map generation model of the road is constructed to characterize the high-precision map of the road, including:

[0043] U41. Based on the BEV-level fusion data information of the road, construct a BEV-level fusion data set of the road;

[0044] U42. Input the BEV-level fused data set of the road into the high-precision map generation model of the road for training and learning, and determine the generation function S of the high-precision map of the road,

[0045]

[0046] Among them, r is the BEV-level fusion dataset of the road, μ1, μ2 and μ3 are the generation factors of the high-precision map of the road, and the trained high-precision map generation model of the road is obtained;

[0047] U43. Based on the trained high-precision map generation model of the road, the BEV-level fusion data information of the road is input, the high-precision map of the road is characterized, and the data information of the high-precision map of the road is obtained.

[0048] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a high-precision map construction system based on satellite map-assisted vehicle-mounted sensors, including a computer device, which is programmed or configured to execute the steps of the high-precision map construction method based on satellite map-assisted vehicle-mounted sensors as described in any one of the claims.

[0049] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the high-precision map construction methods based on satellite maps assisted vehicle-mounted sensors.

[0050] The present invention has the following positive effects:

[0051] 1. The present invention fuses the road and vehicle data by adopting an improved multimodal feature-level fusion algorithm, and fuses the road data by combining the BEV-level feature fusion algorithm of the road. It not only improves the positioning accuracy of the vehicle in complex environments and long-distance detection tasks by integrating satellite map data, but also reduces the dependence on expensive or high-precision vehicle-mounted sensors, and achieves a more cost-effective solution by supplementing satellite map data.

[0052] 2. The present invention characterizes the high-precision map of the road by constructing a high-precision map generation model for the road. Not only can the high-precision map be constructed and updated more quickly by utilizing satellite map data, especially in a dynamically changing environment, but also in complex scenarios such as traffic congestion, multiple lanes, and multiple intersections, the high-precision map assisted by satellite maps can provide more accurate decision support. By reducing the need for professional data collection vehicles or high-precision sensors, the cost of producing and maintaining high-precision maps is reduced, so that the autonomous driving system can better adapt to different geographical and climatic conditions because satellite maps provide a wider geographical coverage. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0054] Figure 2 It is a flowchart of the improved multi-modal feature-level fusion algorithm of the present invention;

[0055] Figure 3 It is a flowchart of the BEV-level feature fusion algorithm of the road of the present invention;

[0056] Figure 4 A schematic diagram of the process of constructing a high-precision map generation model for roads according to the present invention. DETAILED DESCRIPTION

[0057] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0058] Example 1: Figure 1 As shown, a method for constructing a high-precision map based on satellite maps assisted by vehicle-mounted sensors, the method comprising:

[0059] U1. The vehicle is driving on the road, and the vehicle camera obtains the multi-view image data information of the road in real time, the satellite map data information of the road and the dynamic parameter data information of the vehicle in real time;

[0060] U2. Based on the multi-view image data information of the road, the satellite map data information of the road and the dynamic parameter data information of the vehicle, an improved multi-modal feature-level fusion algorithm is used to fuse the road and vehicle data to obtain feature-level fusion data information of the road;

[0061] U3. Based on the feature-level fusion data information of the road, the satellite map data information of the road and the dynamic parameter data information of the vehicle, the BEV-level feature fusion algorithm of the road is used to fuse the road data to obtain the BEV-level fusion data information of the road;

[0062] U4. Based on the BEV-level fused data information of the road, a high-precision map generation model of the road is constructed, the high-precision map of the road is characterized, and the data information of the high-precision map of the road is obtained.

[0063] In this embodiment, if Figure 2 As shown, in step U2, the use of an improved multi-modal feature-level fusion algorithm to fuse the road and vehicle data includes:

[0064] U21. Based on the multi-view image data information of the road, construct an image feature extraction function Q1 of the road,

[0065]

[0066] Among them, x1 is the multi-vision image data information of the road, α1, α2 and α3 are image feature extraction factors of the road, and feature extraction is performed on the multi-vision image of the road to obtain feature data information of the multi-vision image of the road;

[0067] U22. Based on the data information of the satellite map of the road, construct a feature extraction function Q2 of the satellite map of the road,

[0068]

[0069] Among them, x2 is the data information of the satellite map of the road, β1, β2 and β3 are the feature extraction parameters of the satellite map of the road, and the feature extraction is performed on the satellite map of the road to obtain the feature data information of the satellite map of the road;

[0070] U23. Based on the data information of the dynamic parameters of the vehicle, construct a feature extraction function Q3 of the dynamic parameters of the vehicle,

[0071]

[0072] Among them, x3 is the data information of the satellite map of the road, γ1, γ2 and γ3 are the feature extraction factors of the dynamic parameters of the vehicle, and the feature extraction of the dynamic parameters of the vehicle is performed to obtain the feature data information of the dynamic parameters of the vehicle;

[0073] U24. Establishing a road and vehicle feature-level fusion function W based on the feature data information of the dynamic parameters of the vehicle, the feature data information of the satellite map of the road, and the feature data information of the multi-visual image of the road,

[0074]

[0075] Among them, q1 is the feature data information of the multi-visual image of the road, q2 is the feature data information of the satellite map of the road, q3 is the feature data information of the dynamic parameters of the vehicle, δ1, δ2 and δ3 are the feature-level fusion parameters of the road. The data of the road and the vehicle are fused to obtain the feature-level fusion data information of the road.

[0076] In this embodiment, the feature-level fusion parameters δ1, δ2 and δ3 of the road are:

[0077]

[0078] Among them, q1 is the feature data information of the multi-visual image of the road, q2 is the feature data information of the satellite map of the road, and q3 is the feature data information of the dynamic parameters of the vehicle.

[0079] In this embodiment, the constraint conditions of the feature extraction factors γ1, γ2 and γ3 of the dynamic parameters of the vehicle are:

[0080]

[0081] In this embodiment, the constraint function f of the road image feature extraction factors α1, α2 and α3 is,

[0082]

[0083] The value range of the constraint function f is (1,2).

[0084] Example 2: Based on the high-precision map construction method based on satellite map-assisted vehicle-mounted sensors in Example 1, the present invention is further illustrated and described below.

[0085] like Figure 1 As shown, a method for constructing a high-precision map based on satellite maps assisted by vehicle-mounted sensors, the method comprising:

[0086] U1. The vehicle is driving on the road, and the vehicle camera obtains the multi-view image data information of the road in real time, the satellite map data information of the road and the dynamic parameter data information of the vehicle in real time;

[0087] U2. Based on the multi-view image data information of the road, the satellite map data information of the road and the dynamic parameter data information of the vehicle, an improved multi-modal feature-level fusion algorithm is used to fuse the road and vehicle data to obtain feature-level fusion data information of the road;

[0088] U3. Based on the feature-level fusion data information of the road, the satellite map data information of the road and the dynamic parameter data information of the vehicle, the BEV-level feature fusion algorithm of the road is used to fuse the road data to obtain the BEV-level fusion data information of the road;

[0089] U4. Based on the BEV-level fused data information of the road, a high-precision map generation model of the road is constructed, the high-precision map of the road is characterized, and the data information of the high-precision map of the road is obtained.

[0090] In this embodiment, if Figure 3 As shown, in step U3, the method of fusing the road data using the BEV-level feature fusion algorithm of the road includes:

[0091] U31. Based on the data information of the satellite map of the road and the data information of the dynamic parameters of the vehicle, a coordinate alignment function R of the road is established.

[0092]

[0093] Wherein, y1 is the data information of the satellite map of the road, y2 is the data information of the dynamic parameters of the vehicle, η1, η2 and η3 are the coordinate alignment factors of the road, the satellite map of the road and the dynamic parameters of the vehicle are aligned, and the road coordinate alignment matrix is ​​constructed to obtain the data information of the road coordinate alignment matrix;

[0094] U32. Based on the data information of the road coordinate alignment matrix and the data information of the feature-level fusion of the road, a BEV-level feature fusion function P of the road is established.

[0095]

[0096] Among them, z1 is the data information of the road coordinate alignment matrix, z2 is the data information of the feature-level fusion of the road, λ1, λ2 and λ3 are the weight coefficients of the BEV-level feature fusion of the road;

[0097] U33. Based on the BEV-level feature fusion function P of the road, the road data is fused to obtain BEV-level fused data information of the road.

[0098] In this embodiment, the constraints of the weight coefficients λ1, λ2 and λ3 of the BEV-level feature fusion of the road are:

[0099]

[0100] In this embodiment, in step U4, constructing a high-precision map generation model for the road and characterizing the high-precision map of the road includes:

[0101] U41. Based on the BEV-level fusion data information of the road, construct a BEV-level fusion data set of the road;

[0102] U42. Input the BEV-level fused data set of the road into the high-precision map generation model of the road for training and learning, and determine the generation function S of the high-precision map of the road,

[0103]

[0104] Among them, r is the BEV-level fusion dataset of the road, μ1, μ2 and μ3 are the generation factors of the high-precision map of the road, and the trained high-precision map generation model of the road is obtained;

[0105] U43. Based on the trained high-precision map generation model of the road, the BEV-level fusion data information of the road is input, the high-precision map of the road is characterized, and the data information of the high-precision map of the road is obtained.

[0106] In this embodiment, the present invention provides a high-precision map construction system based on satellite maps assisted by vehicle-mounted sensors, including a computer device that is programmed or configured to execute the steps of the high-precision map construction method based on satellite maps assisted by vehicle-mounted sensors as described in any one of the claims.

[0107] In this embodiment, the present invention provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the methods for constructing a high-precision map based on satellite maps assisted by vehicle-mounted sensors.

[0108] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0109] In summary, the present invention not only improves the positioning accuracy of vehicles in complex environments and long-distance detection tasks by integrating satellite map data, but also reduces the dependence on expensive or high-precision vehicle-mounted sensors, and achieves a more cost-effective solution through the supplementation of satellite map data.

[0110] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for constructing a high-precision map based on satellite maps assisted by vehicle-mounted sensors, characterized in that: The method comprises: U1. The vehicle is driving on the road, and the vehicle camera obtains the multi-view image data information of the road in real time, the satellite map data information of the road and the dynamic parameter data information of the vehicle in real time; U2. Based on the multi-view image data information of the road, the satellite map data information of the road and the dynamic parameter data information of the vehicle, an improved multi-modal feature-level fusion algorithm is used to fuse the road and vehicle data to obtain feature-level fusion data information of the road; U3. Based on the feature-level fusion data information of the road, the satellite map data information of the road and the dynamic parameter data information of the vehicle, the BEV-level feature fusion algorithm of the road is used to fuse the road data to obtain the BEV-level fusion data information of the road; U4. Based on the BEV-level fused data information of the road, a high-precision map generation model of the road is constructed, the high-precision map of the road is characterized, and the data information of the high-precision map of the road is obtained.

2. The method for constructing a high-precision map based on satellite map-assisted vehicle-mounted sensors according to claim 1, characterized in that: In step U2, the use of an improved multi-modal feature-level fusion algorithm to fuse the road and vehicle data includes: U21. Based on the multi-view image data information of the road, construct an image feature extraction function Q1 of the road, Among them, x1 is the multi-vision image data information of the road, α1, α2 and α3 are image feature extraction factors of the road, and feature extraction is performed on the multi-vision image of the road to obtain feature data information of the multi-vision image of the road; U22. Based on the data information of the satellite map of the road, construct a feature extraction function Q2 of the satellite map of the road, Among them, x2 is the data information of the satellite map of the road, β1, β2 and β3 are the feature extraction parameters of the satellite map of the road, and the feature extraction is performed on the satellite map of the road to obtain the feature data information of the satellite map of the road; U23. Based on the data information of the dynamic parameters of the vehicle, construct a feature extraction function Q3 of the dynamic parameters of the vehicle, Among them, x3 is the data information of the satellite map of the road, γ1, γ2 and γ3 are the feature extraction factors of the dynamic parameters of the vehicle, and the feature extraction of the dynamic parameters of the vehicle is performed to obtain the feature data information of the dynamic parameters of the vehicle; U24. Establishing a road and vehicle feature-level fusion function W based on the feature data information of the dynamic parameters of the vehicle, the feature data information of the satellite map of the road, and the feature data information of the multi-visual image of the road, Among them, q1 is the feature data information of the multi-visual image of the road, q2 is the feature data information of the satellite map of the road, q3 is the feature data information of the dynamic parameters of the vehicle, δ1, δ2 and δ3 are the feature-level fusion parameters of the road. The data of the road and the vehicle are fused to obtain the feature-level fusion data information of the road.

3. The method for constructing a high-precision map based on satellite map-assisted vehicle-mounted sensors according to claim 2 is characterized in that: The feature-level fusion parameters δ1, δ2 and δ3 of the road are: Among them, q1 is the feature data information of the multi-visual image of the road, q2 is the feature data information of the satellite map of the road, and q3 is the feature data information of the dynamic parameters of the vehicle.

4. The method for constructing a high-precision map based on satellite map-assisted vehicle-mounted sensors according to claim 2, characterized in that: The constraints of the feature extraction factors γ1, γ2 and γ3 of the vehicle's dynamic parameters are:

5. The method for constructing a high-precision map based on satellite maps assisted by vehicle-mounted sensors according to claim 2, characterized in that: The constraint function f of the image feature extraction factors α1, α2 and α3 of the road is, The value range of the constraint function f is (1,2).

6. The method for constructing a high-precision map based on satellite map-assisted vehicle-mounted sensors according to claim 1, characterized in that: In step U3, the method of fusing the road data using the BEV-level feature fusion algorithm of the road includes: U31. Based on the data information of the satellite map of the road and the data information of the dynamic parameters of the vehicle, a coordinate alignment function R of the road is established. Wherein, y1 is the data information of the satellite map of the road, y2 is the data information of the dynamic parameters of the vehicle, η1, η2 and η3 are the coordinate alignment factors of the road, the satellite map of the road and the dynamic parameters of the vehicle are aligned, and the road coordinate alignment matrix is ​​constructed to obtain the data information of the road coordinate alignment matrix; U32. Based on the data information of the road coordinate alignment matrix and the data information of the feature-level fusion of the road, a BEV-level feature fusion function P of the road is established. Among them, z1 is the data information of the road coordinate alignment matrix, z2 is the data information of the feature-level fusion of the road, λ1, λ2 and λ3 are the weight coefficients of the BEV-level feature fusion of the road; U33. Based on the BEV-level feature fusion function P of the road, the road data is fused to obtain BEV-level fused data information of the road.

7. The method for constructing a high-precision map based on satellite maps assisted by vehicle-mounted sensors according to claim 6, characterized in that: The constraints of the weight coefficients λ1, λ2 and λ3 of the BEV-level feature fusion of the road are:

8. The method for constructing a high-precision map based on satellite maps assisted by vehicle-mounted sensors according to claim 1, characterized in that: In step U4, the high-precision map generation model of the road is constructed to characterize the high-precision map of the road, including: U41. Based on the BEV-level fusion data information of the road, construct a BEV-level fusion data set of the road; U42. Input the BEV-level fused data set of the road into the high-precision map generation model of the road for training and learning, and determine the generation function S of the high-precision map of the road, Among them, r is the BEV-level fusion dataset of the road, μ1, μ2 and μ3 are the generation factors of the high-precision map of the road, and the trained high-precision map generation model of the road is obtained; U43. Based on the trained high-precision map generation model of the road, the BEV-level fusion data information of the road is input, the high-precision map of the road is characterized, and the data information of the high-precision map of the road is obtained.

9. A high-precision map construction system based on satellite maps and vehicle-mounted sensors, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the method for constructing a high-precision map based on satellite maps assisted by vehicle-mounted sensors as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that is programmed or configured to execute the high-precision map construction method based on satellite map-assisted vehicle-mounted sensors as described in any one of claims 1 to 8.

Images