WO2022012281A1 - 一种地图融合的方法及车辆、电子设备、存储介质 - Google Patents
一种地图融合的方法及车辆、电子设备、存储介质 Download PDFInfo
- Publication number
- WO2022012281A1 WO2022012281A1 PCT/CN2021/101578 CN2021101578W WO2022012281A1 WO 2022012281 A1 WO2022012281 A1 WO 2022012281A1 CN 2021101578 W CN2021101578 W CN 2021101578W WO 2022012281 A1 WO2022012281 A1 WO 2022012281A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- map
- map data
- target area
- road
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Definitions
- the present invention relates to the technical field of maps, and in particular, to a method for map fusion, a vehicle, an electronic device and a storage medium.
- Electronic maps are maps that are stored and consulted in the form of data, and have become an indispensable tool in people's daily travel. In order to obtain higher-precision maps, map data can be fused.
- weighted average is usually used for fusion.
- map data generally includes multiple road information and complex road relationships
- directly using weighted average for map fusion will change the road relationship. problems, such as road disconnects.
- a method for map fusion includes:
- the at least two map data are fused according to the map correction information.
- obtaining map correction information according to the target beam system mechanics model and the connection relationship information including:
- Map correction information is obtained according to the target beam system mechanics model, the connection relationship information, and the correction amount.
- obtaining map correction information according to the target beam system mechanics model, the connection relationship information, and the correction amount including:
- connection relationship information determines a total stiffness matrix for the target beam system mechanics model
- map correction information is obtained.
- connection relationship information to determine a total stiffness matrix for the target beam system mechanical model includes:
- connection relationship information determining a plurality of element stiffness matrices
- a total stiffness matrix for the target beam system mechanical model is determined.
- using the at least two map data to determine the correction amount for the road in the target area includes:
- a correction amount for the road in the target area is determined.
- the target beam system mechanics model includes a beam system mechanics model for the three-link.
- the target area is a parking lot.
- a vehicle comprising:
- a map data acquisition module for acquiring at least two map data for the target area
- a model and connection relationship determination module configured to determine a target beam system mechanics model for the target area, and use the at least two map data to determine connection relationship information for roads in the target area;
- a map correction information obtaining module used for obtaining map correction information according to the target beam system mechanics model and the connection relationship information
- a map data fusion module configured to fuse the at least two map data according to the map correction information.
- An electronic device comprising a processor, a memory and a computer program stored on the memory and capable of running on the processor, when the computer program is executed by the processor, the above-mentioned method for map fusion is realized .
- a computer-readable storage medium storing a computer program on the computer-readable storage medium, when the computer program is executed by a processor, implements the above-mentioned method for map fusion.
- the mechanical model of the target beam system for the target area is determined, and at least two map data are used to determine the connection relationship information for the roads in the target area, and According to the target beam system mechanics model and the connection relationship information, the map correction information is obtained, and at least two map data are fused according to the map correction information, so as to realize the fusion of the map by combining the beam system mechanics model and the connection relationship of the road, avoiding the need for
- the weighted average method is used for fusion, which leads to the problem of changing the road relationship, and there is no need to perform image processing operations on map data, which reduces the amount of calculation and ensures the accuracy of map fusion.
- FIG. 1 is a flow chart of steps of a method for map fusion provided by an embodiment of the present invention
- FIG. 2 is a flowchart of steps of another method for map fusion provided by an embodiment of the present invention.
- FIG. 3 is a flowchart of steps of yet another method for map fusion provided by an embodiment of the present invention.
- FIG. 5 is a schematic structural diagram of a map fusion vehicle according to an embodiment of the present invention.
- FIG. 1 a flowchart of steps of a method for map fusion provided by an embodiment of the present invention is shown, which may specifically include the following steps:
- Step 101 obtaining at least two map data for the target area
- the target area may be a parking lot, and the map data may be pre-stored in the vehicle, or generated in real time, or downloaded from the cloud.
- the target area may be determined, and then at least two map data for the target area may be acquired.
- the area that the vehicle enters may be determined as the target area, or the area designated by the user may be determined as the target area.
- the target area is determined to be a parking lot
- at least two maps for the parking lot may be obtained from map data pre-stored by the vehicle. map data.
- Step 102 Determine the target beam system mechanics model for the target area, and use the at least two map data to determine the connection relationship information for the roads in the target area;
- the mechanical model refers to an expression of the abstracted mechanical relationship according to the geometric characteristics of the research object
- the mechanical model of the beam system is a mechanical model of the beam system in the mechanical model.
- the target beam system mechanical model can include
- the connection relationship information of the road can be expressed as the connection relationship of the road, such as the connection at the end point of the road and the connection at the midpoint of the road.
- a topological map can be obtained according to the at least two map data, wherein the topological map refers to a statistical map in cartography, which maintains a correct relative positional relationship between points and lines without necessarily maintaining the shape of a graph
- An abstract map with correct area, distance and direction, and then the mechanical model of the target beam system for the target area can be determined in the topology map.
- the connection relationship information of roads in the target area can be determined in the topology map.
- At least two map data can also be used to determine matching road information in the target area, and then the connection relationship information of the roads in the target area can be determined according to the matched road information.
- Step 103 obtaining map correction information according to the target beam system mechanics model and the connection relationship information
- the map correction information may be displacement information, such as node displacement information, road displacement information, or angle information, such as road deflection angle information.
- the parameters in the target beam system mechanics model can be determined according to the connection relationship information, and then map correction information can be obtained through the calculation of the target beam system mechanics model.
- Step 104 fuse the at least two map data according to the map correction information.
- one of the at least two map data can be specified, and then the specified map data can be fused with the rest of the map data according to the map correction information, or the map data can be fused according to the map data in the topological map. Correct the information and fuse at least two map data.
- one of the at least two map data can be specified, and after obtaining the displacement information of all nodes, all nodes in the specified map data can be corrected according to the displacement information, and the The unmatched road information is added to the specified map data to obtain the fused map data.
- all the specified map data that match the rest of the map data can be modified according to the map correction information. The road is corrected to complete the fusion of at least two map data.
- the mechanical model of the target beam system for the target area is determined, and at least two map data are used to determine the connection relationship information for the roads in the target area, and According to the target beam system mechanics model and the connection relationship information, the map correction information is obtained, and at least two map data are fused according to the map correction information, so as to realize the fusion of the map by combining the beam system mechanics model and the connection relationship of the road, avoiding the need for
- the weighted average method is used for fusion, which leads to the problem of changing the road relationship, and there is no need to perform image processing operations on map data, which reduces the amount of calculation and ensures the accuracy of map fusion.
- FIG. 2 a flowchart of steps of another method for map fusion provided by an embodiment of the present invention is shown, which may specifically include the following steps:
- Step 201 obtaining at least two map data for the target area
- Step 202 determining the target beam system mechanics model for the target area, and using the at least two map data to determine the connection relationship information for the roads in the target area;
- Step 203 using the at least two map data to determine the correction amount for the road in the target area;
- the correction amount may include a displacement correction amount and an angle correction amount.
- At least two map data can be used to determine the road matched in the target area and the location information of the road, and then the matched road can be calculated according to the location information. Corrections for matching roads in the target area may be determined.
- a road matching one of the two map data can be determined, and then the location information of the matched road can be determined respectively, the fused location information of the matched road can be calculated in the topology map, and the fused location information can be calculated. With the unfused position information, the displacement correction amount and the angle correction amount of the matching road can be obtained.
- Step 204 obtaining map correction information according to the target beam system mechanics model, the connection relationship information, and the correction amount;
- the parameters in the mechanical model of the target beam system are determined according to the connection relationship information and the correction amount, and then the map correction information can be obtained by calculating the mechanical model of the target beam system.
- the correction amount can be determined as the parameter of the target beam system mechanics model, and then the target beam system mechanics model can be combined with the connection relationship information. The calculation of , obtains the map correction information.
- Step 205 fuse the at least two map data according to the map correction information.
- the mechanical model of the target beam system for the target area is determined, and at least two map data are used to determine the connection relationship information for the roads in the target area, using At least two map data, determine the correction amount for the road in the target area, realize the fusion of the map by combining the connection relationship information, the correction amount, and the mechanical model of the target beam system, avoiding the use of weighted average fusion to cause road changes
- FIG. 3 a flowchart of steps of a method for map fusion provided by an embodiment of the present invention is shown, which may specifically include the following steps:
- Step 301 obtaining at least two map data for the target area
- Step 302 determining the target beam system mechanics model for the target area, and using the at least two map data to determine the connection relationship information for the roads in the target area;
- Step 303 determining maturity information for the at least two map data
- the maturity information may be the fusion times of map data.
- the maturity information of at least two map data can be determined, such as determining the fusion times of the map data.
- map data A is map data that has not been fused
- the maturity information is 0
- map data B is map data that has been fused.
- the map data fused twice, the maturity information is 2.
- Step 304 using the maturity information to determine elasticity information for nodes in the target area and stiffness information for roads in the target area;
- the node can be the point connected by the road in the target area
- the elasticity information of the node can be expressed as the degree of node displacement when the road is merged
- the stiffness information of the road can be expressed as the degree of road deflection.
- elasticity information for nodes in the target area corresponding to the maturity information may be determined, and stiffness information for roads in the target area corresponding to the maturity information may be determined.
- the elasticity information of the nodes and the stiffness information of the road may be preset values and correspond to different maturity information, or may be values input by the user according to the maturity information. information obtained by calculation.
- the elasticity information and stiffness information corresponding to different maturity information can be preset.
- the corresponding elasticity information can be set to 1
- the stiffness information can be set to 1.
- the corresponding elasticity information can be set to 1.
- the maturity information can be used to determine that the elasticity information for the nodes in the target area is 1, and it is determined that the stiffness information for the roads in the target area is 1.
- Step 305 combining the elasticity information and the stiffness information, determine a correction amount for the road in the target area.
- At least two map data can be used to determine the matching road in the target area and the position information of the road, and then the position information of the road can be calculated in combination with the elasticity information and the stiffness information.
- the elasticity information and stiffness information are calculated on the road's position information in the topology map to determine the correction amount for the road in the target area.
- At least two map data may be used to determine matching roads in the at least two map data, and then one of the matching roads may be determined.
- the elasticity information of the nodes of the road is 1, and the stiffness information of the road is 2
- the displacement correction of the node can be calculated based on the elasticity information of the node
- the angle correction of the road can be calculated based on the stiffness information of the road, and then the correction of the road can be determined according to the displacement correction and the angle correction.
- step 305 may further include the following sub-steps:
- Sub-step 11 obtaining the topological map data for the target area
- At least two map data can be used to determine the matching road in the target area and the location information of the road, and then the topological map data for the target area can be determined according to the location information.
- Sub-step 12 combining the elasticity information, the stiffness information, and the topological map data, determine a correction amount for the road in the target area.
- the road can be calculated in the topological map in combination with the elasticity information and the stiffness information to determine the correction amount for the road in the target area.
- sub-step 12 may further include:
- first road information for the road in the target area is determined; in the topological map data, the elasticity information and the stiffness information are combined to determine the first road information for the road in the target area. Second road information of the road; using the first road information and the second road information to obtain a correction amount for the road in the target area.
- position information such as coordinate information, of roads in the target area can be determined in the map data.
- the location information of the corresponding road can be determined in the topological map data, and then the location information can be calculated in combination with the elasticity information and the stiffness information in the topological map data to obtain the corrected road. location information.
- the uncorrected location information and the corrected location information can be calculated in the topological map data, and then the difference between the corrected location information and the corrected location information can be determined.
- the displacement correction amount and the angle correction amount can be determined according to the displacement correction amount and the angle correction amount for the road in the target area.
- the topological map is an abstract map that maintains the correct relative position relationship between points and lines, but does not necessarily maintain the correct shape, area, distance, and direction of the graph, and then calculates the location information of the road in the topological map, only need to Considering the relative positional relationship of the road without considering other details in the map, the amount of calculation can be reduced, and the positional information of the road in the map data will not be changed.
- Step 306 obtaining map correction information according to the target beam system mechanics model, the connection relationship information, and the correction amount;
- Step 307 fuse the at least two map data according to the map correction information.
- the mechanical model of the target beam system for the target area is determined, and at least two map data are used to determine the connection relationship information for the roads in the target area
- the maturity information is used to determine the elasticity information for the nodes in the target area and the stiffness information for the road in the target area, and combine the elasticity information and the stiffness information to determine the correction for the road in the target area.
- the mechanical model of the target beam system the connection relationship information, and the correction amount, the map correction information is obtained, and at least two map data are fused according to the map correction information, so that the maturity information is used to determine the correction amount, and then the connection relationship is combined.
- the information, correction amount, and the mechanical model of the target beam system are fused to the map, which avoids the problem of changing the road relationship caused by the weighted average fusion, and does not need to perform image processing operations on the map data, which reduces the amount of calculation and ensures that accuracy of map fusion.
- FIG. 4 a flowchart of steps of another method for map fusion provided by an embodiment of the present invention is shown, which may specifically include the following steps:
- Step 401 obtaining at least two map data for the target area
- Step 402 determining the target beam system mechanics model for the target area, and using the at least two map data to determine the connection relationship information for the roads in the target area;
- Step 403 using the at least two map data to determine the correction amount for the road in the target area;
- Step 404 using the connection relationship information to determine a total stiffness matrix for the target beam system mechanics model
- the total stiffness matrix may be a matrix that establishes the basic equation of the displacement method of the overall structure.
- connection relationship information and the correction amount are determined.
- the overall structure of the road in the target area can be determined according to the connection relationship information, and then the total stiffness matrix of the target beam system mechanics model can be determined.
- connection relationship information can determine the overall structure of roads in different areas, and then can determine the corresponding total stiffness matrix. For example, when it is determined that the target area includes two matching roads, and the two roads are in it When one end is connected, the overall structure of the road can be determined as a three-link structure, and then the beam system mechanics model for the three-link corresponding to the connection relationship information can be determined.
- step 404 further includes the following sub-steps:
- Sub-step 21 using the connection relationship information to determine a plurality of element stiffness matrices
- the total stiffness matrix can be formed by the element stiffness matrix according to the stiffness integration rule, and the element stiffness matrix can be an important coefficient matrix calculated by the finite element method, which is characterized by the relationship between the force and the deformation of the element body.
- connection relationship information and the correction amount are determined, since multiple matching roads in the target area can be determined, the connection relationship information can be used to determine multiple coordinate systems for the matching roads, and then multiple coordinate systems for the matching roads can be determined through the coordinate system.
- the element stiffness matrix of the road is
- the coordinate system corresponding to multiple matching roads can be determined according to the connection relationship information, and since the roads in the map data can include multiple nodes, the coordinate information of the nodes can be determined, and the coordinate system can also be determined according to the coordinate system.
- the coordinate information and/or the angle information may be calculated, such as multiplied or added, to obtain a plurality of element stiffness matrices for the road.
- the coordinate information and the angle information can be determined as parameters of the element stiffness matrix, and then a plurality of road-specific element stiffness matrices can be obtained by multiplying the coordinate information and the angle information with the element stiffness matrix.
- the element stiffness matrix can be the following matrix:
- K ⁇ can be expressed as the element stiffness matrix
- E can be expressed as the elastic information of the nodes
- A can be expressed as the stiffness information of the road
- l can be expressed as the length of the road
- I can be expressed as the inertia moment of the road
- the inertia moment can be expressed by Coordinate information is determined.
- Sub-step 22 using the at least two map data to determine a coordinate transformation matrix
- the overall structure of the road matching the target area can be determined according to at least two map data, and then the global coordinate system can be determined according to the overall structure, and the coordinate system of the road and the global coordinate system can be combined. Determine the coordinate transformation matrix.
- the global coordinate system is the coordinate system in which the most nodes fall on the coordinate axis.
- the global coordinate system can be determined according to the overall structure of the road, and the relative positional relationship information between the road coordinate system and the global coordinate system can be calculated by geometric methods, such as the angle between the road coordinate system and the global coordinate system. information, and then the coordinate transformation matrix can be determined according to the position relationship information.
- the coordinate transformation matrix can be the following matrix:
- T can be expressed as a coordinate transformation matrix
- ⁇ can be expressed as the angle information between the coordinate system of the road and the global coordinate system.
- Sub-step 23 combining the plurality of element stiffness matrices and the coordinate transformation matrix to obtain global coordinate information
- multiple element stiffness matrices can be transformed through the coordinate transformation matrix, and then the element stiffness matrices in multiple global coordinate systems can be obtained to obtain global coordinate information.
- the element stiffness matrix in the global coordinate system can be obtained by the following formula:
- K can be expressed as the element stiffness matrix in the global coordinate system
- K ⁇ can be expressed as the element stiffness matrix
- T can be expressed as a coordinate transformation matrix
- T′ can be expressed as an inverse coordinate transformation matrix
- Sub-step 24 using the global coordinate information to determine a total stiffness matrix for the target beam system mechanical model.
- the global coordinate information can be calculated, and then the total stiffness matrix of the mechanical model of the target beam system can be determined.
- the nodes at the road connection are coincident nodes.
- the coincident global coordinate information can be obtained, and the coincidence can be determined.
- the global coordinate information can be calculated by summing the coincident global coordinate information, and the total stiffness matrix can be determined according to the calculated global coordinate information.
- the total stiffness matrix can be determined by the following formula:
- K 1 can be expressed as the element stiffness matrix under the first global coordinate system
- K 2 can be expressed as the element stiffness matrix under the second global coordinate system
- K 3 can be expressed as the element stiffness matrix under the third global coordinate system
- the superscripts 1, 2, 3, and 4 can be expressed as four different nodes in the road information respectively
- the subscripts 11, 12, 22, 23, 33, 34, and 44 can be expressed as the road information between the two nodes.
- Step 405 using the correction amount to determine the nodal force parameters for the target beam system mechanics model
- the correction amount can include the displacement correction amount and the angle correction amount
- the displacement correction amount in the correction amount can be used to represent the coordinate parameter of the node force
- the angle correction amount in the correction amount can be used.
- the amount is expressed as the direction parameter of the nodal force, so that the coordinate parameter and the direction parameter are determined as the nodal force parameter for the target beam system mechanical model.
- Step 406 combining the total stiffness matrix, the nodal force parameters, and the mechanical model of the target beam system to obtain map correction information
- the total stiffness matrix and the correction amount After the total stiffness matrix and the correction amount are determined, the total stiffness matrix, the nodal force parameters, and the mechanical model of the target beam system can be calculated by formulas, and then the nodal displacement information of all nodes can be calculated, and the map can be calculated according to the node displacement information. Correction information of all matching roads in the data to obtain map correction information, that is, displacement information of nodes.
- map correction information can be obtained by the following formula:
- ⁇ 1 can be expressed as the rotation of node 1 in the global coordinate system.
- the angle, ⁇ 2 can be expressed as the angle
- the map correction information can be obtained by the following formula:
- F can be expressed as a node force parameter
- k can be expressed as a fixed elastic coefficient
- the elastic coefficient can be set by the user or calculated
- e and l can be constants
- v can be expressed as the node displacement in the global coordinate system
- the subscripts 1, 2, 3, and 4 may represent different nodes respectively, and may further represent the node force parameters and/or elastic coefficients and/or displacements in the global coordinate system of different nodes.
- Step 407 fuse the at least two map data according to the map correction information.
- the mechanical model of the target beam system for the target area is determined, and at least two map data are used to determine the connection relationship information for the roads in the target area, using At least two map data, determine the correction amount for the road in the target area, use the connection relationship information to determine the total stiffness matrix for the target beam system mechanical model, use the correction amount to determine the nodal force parameters for the target beam system mechanical model, combine The total stiffness matrix, nodal force parameters, and the mechanical model of the target beam system are used to obtain map correction information.
- map correction information at least two map data are fused to realize the combination of global coordinate information, total stiffness matrix, nodal force parameters, and
- the mechanical model of the target beam system fuses the map, which avoids the problem of changing the road relationship caused by the weighted average fusion, and does not need to perform image processing operations on the map data, which reduces the amount of calculation and ensures the accuracy of map fusion.
- FIG. 5 a schematic structural diagram of a map fusion vehicle provided by an embodiment of the present invention is shown, which may specifically include the following modules:
- a map data acquisition module 501 for acquiring at least two map data for the target area
- a model and connection relationship determination module 502 configured to determine a target beam system mechanics model for the target area, and use the at least two map data to determine connection relationship information for roads in the target area;
- the map correction information obtaining module 503 is used for obtaining map correction information according to the target beam system mechanics model and the connection relationship information;
- the map data fusion module 504 is configured to fuse the at least two map data according to the map correction information.
- the map correction information obtaining module 503 further includes:
- a correction amount determination sub-module configured to use the at least two map data to determine the correction amount for the road in the target area
- the map correction information obtaining sub-module is used for obtaining map correction information according to the target beam system mechanics model, the connection relationship information, and the correction amount.
- the map correction information obtaining submodule further includes:
- a total stiffness matrix determining unit configured to use the connection relationship information to determine a total stiffness matrix for the target beam system mechanical model
- a nodal force parameter determining unit configured to use the correction amount to determine nodal force parameters for the target beam system mechanics model
- the combining unit is used for combining the total stiffness matrix, the nodal force parameters, and the mechanical model of the target beam system to obtain map correction information.
- the total stiffness matrix determining unit further includes:
- an element stiffness matrix determining subunit used for determining a plurality of element stiffness matrices by using the connection relationship information
- a coordinate transformation matrix determination subunit configured to determine a coordinate transformation matrix by using the at least two map data
- a global coordinate information determination subunit used for combining the plurality of unit stiffness matrices and the coordinate transformation matrix to obtain global coordinate information
- the total stiffness matrix determination subunit of the target beam system mechanical model is configured to use the global coordinate information to determine the total stiffness matrix for the target beam system mechanical model.
- the correction amount determination sub-module further includes:
- a maturity information determination unit configured to determine maturity information for the at least two map data
- an elasticity information and stiffness information determining unit configured to use the maturity information to determine elasticity information for nodes in the target area and stiffness information for roads in the target area;
- a road correction amount determination unit configured to combine the elasticity information and the stiffness information to determine a correction amount for the road in the target area.
- the mechanical model of the target beam system for the target area is determined, and at least two map data are used to determine the connection relationship information for the roads in the target area, and According to the mechanical model of the target beam system and the connection relationship information, the map correction information is obtained, and at least two map data are fused according to the map correction information, which realizes the fusion of the map combined with the connection relationship information of the road, and avoids the road breakage after fusion.
- the operation of map optimization is reduced, the amount of calculation is reduced, and the accuracy of map fusion is guaranteed.
- An embodiment of the present invention also provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor.
- a computer program stored in the memory and capable of running on the processor.
- An embodiment of the present invention also provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the above method for map fusion is implemented.
- the description is relatively simple, and the relevant part may refer to the partial description of the method embodiment.
- embodiments of the present invention may be provided as a method, an apparatus, or a computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media having computer-usable program code embodied therein, including but not limited to disk storage, CD-ROM, optical storage, and the like.
- Embodiments of the present invention are described with reference to flowcharts and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the present invention. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing terminal equipment to produce a machine that causes the instructions to be executed by the processor of the computer or other programmable data processing terminal equipment Means are created for implementing the functions specified in the flow or flows of the flowcharts and/or the blocks or blocks of the block diagrams.
- These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal equipment to operate in a particular manner, such that the instructions stored in the computer readable memory result in an article of manufacture comprising instruction means, the The instruction means implement the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.
Abstract
一种地图融合的方法及车辆、电子设备、存储介质，所述方法包括：通过获取针对目标区域的至少两个地图数据（101），确定针对目标区域的目标梁系力学模型，并采用所述至少两个地图数据，确定针对所述目标区域中道路的连接关系信息（102），并根据所述目标梁系力学模型和所述连接关系信息，得到地图修正信息（103），按照所述地图修正信息，对所述至少两个地图数据进行融合（104）。通过上述方法，实现了结合梁系力学模型和道路的连接关系对地图进行融合，避免了采用加权平均的方式进行融合而导致改变道路关系的问题，且无需对地图数据进行图像处理的操作，减少了计算量，保证了地图融合的精度。
Description
交叉引用
本申请要求2020年7月16日递交的发明名称为“一种地图融合的方法及车辆、电子设备、存储介质”的申请号为202010688817.8的在先申请优先权，上述在先申请的内容以引入的方式并入本文本中。
本发明涉及地图技术领域，特别是涉及一种地图融合的方法及车辆、电子设备、存储介质。
电子地图是以数据形式存储和查阅的地图，已经成为了人们日常出行中必不可少的工具，而为了获取更高精度的地图，可以对地图数据进行融合。
在地图数据融合的过程中，通常会采用加权平均的方式进行融合，然而，由于地图数据一般都包括多个道路信息以及复杂的道路关系，直接采用加权平均的方式进行地图融合会出现改变道路关系的问题，如出现道路断开的情况。
在现有技术中，为了避免采用加权平均的方式进行地图融合所造成的影响，通常会对融合后的地图数据进行图像处理，甚至需要人工处理，而且采用对地图数据进行图像处理的操作会增加计算量，且不能保证地图融合的精度。
发明内容
鉴于上述问题，提出了以便提供克服上述问题或者至少部分地解决上述问题的一种地图融合的方法及车辆、电子设备、存储介质，包括：
一种地图融合的方法，所述方法包括：
获取针对目标区域的至少两个地图数据；
确定针对所述目标区域的目标梁系力学模型，并采用所述至少两个地图数据，确定针对所述目标区域中道路的连接关系信息；
根据所述目标梁系力学模型和所述连接关系信息，得到地图修正信息；
按照所述地图修正信息，对所述至少两个地图数据进行融合。
可选地，所述根据所述目标梁系力学模型和所述连接关系信息，得到地图修正信息，包括：
采用所述至少两个地图数据，确定针对所述目标区域中道路的修正量；
根据所述目标梁系力学模型、所述连接关系信息，以及所述修正量，得到地图修正信息。
可选地，所述根据所述目标梁系力学模型、所述连接关系信息，以及所述修正量，得到地图修正信息，包括：
采用所述连接关系信息，确定针对所述目标梁系力学模型的总刚度矩阵；
采用所述修正量，确定针对所述目标梁系力学模型的节点力参数；
结合所述总刚度矩阵、所述节点力参数，以及所述目标梁系力学模型，得到地图修正信息。
可选地，所述采用所述连接关系信息，确定针对所述目标梁系力学模型的总刚度矩阵，包括：
采用所述连接关系信息，确定多个单元刚度矩阵；
采用所述至少两个地图数据，确定坐标转换矩阵；
结合所述多个单元刚度矩阵和所述坐标转换矩阵，得到全局坐标信息；
采用所述全局坐标信息，确定针对所述目标梁系力学模型的总刚度矩阵。
可选地，所述采用所述至少两个地图数据，确定针对所述目标区域中道路的修正量，包括：
确定针对所述至少两个地图数据的成熟度信息；
采用所述成熟度信息，确定针对所述目标区域中节点的弹性信息和针对所述目标区域中道路的刚度信息；
结合所述弹性信息和所述刚度信息，确定针对所述目标区域中道路的修正量。
可选地，所述目标梁系力学模型包括针对三连杆的梁系力学模型。
可选地，所述目标区域为停车场。
一种车辆，所述车辆包括：
地图数据获取模块，用于获取针对目标区域的至少两个地图数据；
模型和连接关系确定模块，用于确定针对所述目标区域的目标梁系力学模型，并采用所述至少两个地图数据，确定针对所述目标区域中道路的连接关系信息；
地图修正信息得到模块，用于根据所述目标梁系力学模型和所述连接关系信息，得到地图修正信息；
地图数据融合模块，用于按照所述地图修正信息，对所述至少两个地图数据进行融合。
一种电子设备，包括处理器、存储器及存储在所述存储器上并能够在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行时实现如上所述的地图融合的方法。
一种计算机可读存储介质，所述计算机可读存储介质上存储计算机程序，所述计算机程序被处理器执行时实现如上所述的地图融合的方法。
本发明实施例具有以下优点：
在本发明实施例中，通过获取针对目标区域的至少两个地图数据，确定针对目标区域的目标梁系力学模型，并采用至少两个地图数据，确定针对目标区域中道路的连接关系信息，并根据目标梁系力学模型和连接关系信息，以得到地图修正信息，按照地图修正信息，对至少两个地图数据进行融合，实现了结合梁系力学模型和道路的连接关系对地图进行融合，避免了采用加权平均的方式进行融合而导致改变道路关系的问题，且无需对地图数据进行图像处理的操作，减少了计算量，保证了地图融合的精度。
为了更清楚地说明本发明的技术方案，下面将对本发明的描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本发明一实施例提供的一种地图融合的方法的步骤流程图；
图2是本发明一实施例提供的另一种地图融合的方法的步骤流程图；
图3是本发明一实施例提供的再一种地图融合的方法的步骤流程图；
图4是本发明一实施例提供的又一种地图融合的方法的步骤流程图；
图5是本发明一实施例提供的一种地图融合的车辆的结构示意图。
为使本发明的上述目的、特征和优点能够更加明显易懂，下面结合附图和具体实施方式对本发明作进一步详细的说明。显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
参照图1，示出了本发明一实施例提供的一种地图融合的方法的步骤流程图，具体可以包括如下步骤：
步骤101，获取针对目标区域的至少两个地图数据；
其中，目标区域可以为停车场，地图数据可以是预先存储在车辆中的，也可以实时生成的，还可以是从云端下载的。
在地图融合的过程中，可以确定目标区域，进而可以获取针对目标区域的至少两个地图数据。
例如，可以确定车辆进入的区域为目标区域，也可以确定用户指定的区域为目标区域，当确定目标区域为停车场时，可以从车辆预先存储的地图数据中，获取针对该停车场的至少两个地图数据。
步骤102，确定针对所述目标区域的目标梁系力学模型，并采用所述至少两个地图数据，确定针对所述目标区域中道路的连接关系信息；
其中，力学模型是指根据所研究对象的几何特性等，抽象出来的力学关系的一种表达，而梁系力学模型是力学模型中的一种梁体系的力学模型，目标梁系力学模型可以包括针对三连杆的梁系力学模型，道路的连接关系信息可以表示为道路的连接关系，如在道路的端点连接、在道路的中点连接。
在获取至少两个地图数据后，可以根据至少两个地图数据获得拓扑地图，其中，拓扑地图是指地图学中一种统计地图，一种保持点与线相对位置关系正确而不一定保持图形形状与面积、距离、方向正确的抽象地图，进而可以在拓扑地图中确定针对目标区域的目标梁系力学模型，如确定针对停车场的目标梁系力学模型，可以采用至少两个地图数据，确定针对目标区域中道路的连接关系信息。
在实际应用中，还可以采用至少两个地图数据，确定针对目标区域中匹配的道路信息，进而可以根据匹配的道路信息确定目标区域中道路的连接关系信息。
步骤103，根据所述目标梁系力学模型和所述连接关系信息，得到地图修正信息；
其中，地图修正信息可以是位移信息，如节点的位移信息、道路的位移信息，也可以是角度信息，如道路偏转的角度信息。
在确定目标梁系力学模型和道路的连接关系信息后，可以根据连接关系信息确定目标梁系力学模型中的参数，进而可以通过目标梁系力学模型的计算，可以得到地图修正信息。
步骤104，按照所述地图修正信息，对所述至少两个地图数据进行融合。
在得到地图修正信息后，可以指定至少两个地图数据中其中一个地图数据，进而可以按照地图修正信息，将该指定的地图数据与其余的地图数据进行融合，也可以是在拓扑地图中按照地图修正信息，对至少两个地图数据进行融合。
例如，在地图融合时，可以指定至少两个地图数据中其中一个地图数据，进而可以在得到所有节点的位移信息后，进而可以根据该位移信息对指定的地图数据中所有节点进行修正，并将未匹配的道路信息加入到该指定的地图数据，以得到融合后的地图数据，而在地图融合的过程中，可以按照地图修正信息，对该指定的地图数据中所有与其余的地图数据匹配的道路进行修正，以完成至少两个地图数据的融合。
在本发明实施例中，通过获取针对目标区域的至少两个地图数据，确定针对目标区域的目标梁系力学模型，并采用至少两个地图数据，确定针对目标区域中道路的连接关系信息，并根据目标梁系力学模型和连接关系信息，以得到地图修正信息，按照地图修正信息，对至少两个地图数据进行融合，实现了结合梁系力学模型和道路的连接关系对地图进行融合，避免了采用加权平均的方式进行融合而导致改变道路关系的问题，且无需对地图数据进行图像处理的操作，减少了计算量，保证了地图融合的精度。
参照图2，示出了本发明一实施例提供的另一种地图融合的方法的步骤流程图，具体可以包括如下步骤：
步骤201，获取针对目标区域的至少两个地图数据；
步骤202，确定针对所述目标区域的目标梁系力学模型，并采用所述至少两个地图数据，确定针对所述目标区域中道路的连接关系信息；
步骤203，采用所述至少两个地图数据，确定针对所述目标区域中道路的修正量；
其中，修正量可以包括位移修正量、角度修正量。
在确定目标梁系力学模型和道路的连接关系信息后，可以采用至少两个地图数据，确定针对目标区域中匹配的道路以及道路的位置信息，进而可以根据该位置信息对匹配的道路进行计算，可以确定针对目标区域中匹配的道路的修正量。
例如，可以确定两个地图数据其中一个匹配的道路，进而可以分别确定该匹配的道路的位置信息，可以在拓扑地图中计算该匹配的道路融合后的位置信息，并计算该融合后的位置信息与未融合后的位置信息，可以得到该匹配的道路的位移修正量和角度修正量。
步骤204，根据所述目标梁系力学模型、所述连接关系信息，以及所述修正量，得到地图修正信息；
在确定修正量后，根据连接关系信息和修正量确定目标梁系力学模型中的参数，进而可以通过目标梁系力学模型的计算，可以得到地图修正信息。
例如，在得到其中一个匹配的道路的位移修正量和角度修正量后，可以将该修正量确定为目标梁系力学模型的参数，进而可以在结合该连接关系信息后，通过目标梁系力学模型的计算得到地图修正信息。
步骤205，按照所述地图修正信息，对所述至少两个地图数据进行融合。
在本发明实施例中，通过获取针对目标区域的至少两个地图数据，确定针对目标区域的目标梁系力学模型，并采用至少两个地图数据，确定针对目标区域中道路的连接关系信息，采用至少两个地图数据，确定针对目标区域中道路的修正量，实现了结合连接关系信息、修正量，以及目标梁系力学模型对地图进行融合，避免了采用加权平均的方式进行融合而导致改变道路关系的问题，且无需对地图数据进行图像处理的操作，减少了计算量，保证了地图融合的精度。
参照图3，示出了本发明一实施例提供的再一种地图融合的方法的步骤流程图，具体可以包括如下步骤：
步骤301，获取针对目标区域的至少两个地图数据；
步骤302，确定针对所述目标区域的目标梁系力学模型，并采用所述至少两个地图数据，确定针对所述目标区域中道路的连接关系信息；
步骤303，确定针对所述至少两个地图数据的成熟度信息；
其中，成熟度信息可以为地图数据的融合次数。
在确定目标梁系力学模型和道路的连接关系信息后，可以确定至少两个地图数据的成熟度信息，如确定地图数据的融合次数。
例如，可以确定地图数据A的融合次数为0，可以确定地图数据B的融合次数为2，则可以表示地图数据A为未进行融合的地图数据，成熟度信息为0，地图数据B为已进行两次融合的地图数据，成熟度信息为2。
步骤304，采用所述成熟度信息，确定针对所述目标区域中节点的弹性信息和针对所述目标区域中道路的刚度信息；
其中，节点可以为目标区域中道路连接的点，节点的弹性信息可以表示为道路融合时节点位移的程度，道路的刚度信息可以表示为道路偏转的程度。
在确定地图数据的成熟度信息后，可以确定针对目标区域中与成熟度信息对应的节点的弹性信息，以及确定针对目标区域中与成熟度信息对应的道路的刚度信息。
在实际应用中，节点的弹性信息和道路的刚度信息可以是预设的值，并且与不同的成熟度信息对应，也可以是用户根据成熟度信息所输入的值，还可以是通过对成熟度信息进行计算所获得的。
例如，可以预先设置不同的成熟度信息所对应的弹性信息和刚度信息，当成熟度信息为1时，可以设置对应的弹性信息为1，刚度信息为1，当成熟度信息为2时，可以设置对应的弹性信息为2，刚度信息为2。
当确定成熟度信息为1时，则可以采用该成熟度信息，确定针对目标区域中节点的弹性信息为1，且确定针对目标区域中道路的刚度信息为1。
步骤305，结合所述弹性信息和所述刚度信息，确定针对所述目标区域中道路的修正量。
在确定弹性信息和刚度信息后，可以采用至少两个地图数据，确定针对目标区域中匹配的道路以及道路的位置信息，进而可以结合弹性信息和刚度信息对道路的位置信息进行计算，也可以结合弹性信息和刚度信息在拓扑地图中对道路的位置信息进行计算，以确定针对目标区域中道路的修正量。
例如，可以采用至少两个地图数据，以确定至少两个地图数据中匹配的道路，进而 可以确定其中一个匹配的道路，当确定该道路的节点的弹性信息为1，该道路的刚度信息为2时，可以结合节点的弹性信息，计算节点的位移修正量，可以结合该道路的刚度信息，计算该道路的角度修正量，进而可以根据位移修正量和角度修正量确定该道路的修正量。
在本发明一实施例中，步骤305还可以包括如下子步骤：
子步骤11，获取针对所述目标区域的拓扑地图数据；
在确定弹性信息和刚度信息后，可以采用至少两个地图数据，确定针对目标区域中匹配的道路以及道路的位置信息，进而可以根据该位置信息确定针对目标区域的拓扑地图数据。
子步骤12，结合所述弹性信息、所述刚度信息，以及所述拓扑地图数据，确定针对所述目标区域中道路的修正量。
在获得拓扑地图数据后，可以结合弹性信息和刚度信息在拓扑地图中对道路进行计算，以确定针对目标区域中道路的修正量。
在本发明一实施例中，子步骤12还可以包括：
在所述至少两个地图数据中，确定针对所述目标区域中道路的第一道路信息；在所述拓扑地图数据中，结合所述弹性信息和所述刚度信息，确定针对所述目标区域中道路的第二道路信息；采用所述第一道路信息和所述第二道路信息，得到针对所述目标区域中道路的修正量。
在获得拓扑地图数据后，可以在地图数据中确定目标区域中道路的位置信息，如坐标信息。
在确定地图数据中的位置信息后，可以在拓扑地图数据中确定对应的道路的位置信息，进而可以在拓扑地图数据中结合弹性信息和刚度信息，对该位置信息进行计算，获得道路修正后的位置信息。
在获得拓扑地图数据中修正后的位置信息后，可以在拓扑地图数据中对修正前的位置信息与修正后的位置信息进行计算，进而可以确定修正前的位置信息与修正后的位置信息之间的位移修正量和角度修正量，可以根据位移修正量和角度修正量确定针对目标区域中道路的修正量。
在实际应用中，由于拓扑地图是一种保持点与线相对位置关系正确而不一定保持图 形形状与面积、距离、方向正确的抽象地图，进而在拓扑地图中计算道路的位置信息时，只需考虑道路的相对位置关系，而不需考虑地图中其他细节，可以减少计算量，而且不会改变地图数据中道路的位置信息。
步骤306，根据所述目标梁系力学模型、所述连接关系信息，以及所述修正量，得到地图修正信息；
步骤307，按照所述地图修正信息，对所述至少两个地图数据进行融合。
在本发明实施例中，通过获取针对目标区域的至少两个地图数据，确定针对目标区域的目标梁系力学模型，并采用至少两个地图数据，确定针对目标区域中道路的连接关系信息，确定针对至少两个地图数据的成熟度信息，采用成熟度信息，确定针对目标区域中节点的弹性信息和针对目标区域中道路的刚度信息，结合弹性信息和刚度信息，确定针对目标区域中道路的修正量，根据目标梁系力学模型、连接关系信息，以及修正量，得到地图修正信息，按照地图修正信息，对至少两个地图数据进行融合，实现了采用成熟度信息确定修正量，进而结合连接关系信息、修正量，以及目标梁系力学模型对地图进行融合，避免了采用加权平均的方式进行融合而导致改变道路关系的问题，且无需对地图数据进行图像处理的操作，减少了计算量，保证了地图融合的精度。
参照图4，示出了本发明一实施例提供的又一种地图融合的方法的步骤流程图，具体可以包括如下步骤：
步骤401，获取针对目标区域的至少两个地图数据；
步骤402，确定针对所述目标区域的目标梁系力学模型，并采用所述至少两个地图数据，确定针对所述目标区域中道路的连接关系信息；
步骤403，采用所述至少两个地图数据，确定针对所述目标区域中道路的修正量；
步骤404，采用所述连接关系信息，确定针对所述目标梁系力学模型的总刚度矩阵；
其中，总刚度矩阵可以是一种建立整体结构的位移法基本方程的矩阵。
在确定连接关系信息和修正量后，可以根据连接关系信息，确定目标区域中道路的整体结构，进而可以确定针对目标梁系力学模型的总刚度矩阵。
在实际应用中，不同的连接关系信息可以确定不同区域中道路的整体结构，进而可以确定对应的总刚度矩阵，例如，当确定目标区域中包括两个匹配的道路，且该两条道 路在其中一个端点处连接时，则可以确定道路的整体结构为三连杆结构，进而可以确定该连接关系信息对应的针对三连杆的梁系力学模型。
在本发明一实施例中，步骤404还包括以下子步骤：
子步骤21，采用所述连接关系信息，确定多个单元刚度矩阵；
其中，总刚度矩阵可以由单元刚度矩阵按照刚度集成规则而形成的，单元刚度矩阵可以为有限元方法计算的重要一个重要的系数矩阵，表征为单元体的受力与变形关系。
在确定连接关系信息和修正量后，由于可以确定针对目标区域中多个匹配的道路，可以采用连接关系信息，确定多个针对匹配的道路的坐标系，进而可以通过该坐标系确定多个针对道路的单元刚度矩阵。
在实际应用中，可以根据连接关系信息确定与多个匹配的道路对应的坐标系，且由于地图数据中的道路可以包括多个节点，进而可以确定节点的坐标信息，还可以根据该坐标系确定匹配的道路与坐标系之间的角度信息，可以通过对该坐标信息和/或角度信息进行计算，如相乘或相加，以得到多个针对道路的单元刚度矩阵。
具体的，可以将该坐标信息和角度信息确定为单元刚度矩阵的参数，进而可以通过将该坐标信息和角度信息与单元刚度矩阵相乘，以得到多个针对道路的单元刚度矩阵。
其中，单元刚度矩阵可以为如下矩阵：
其中，K
ε可以表示为单元刚度矩阵，E可以表示为节点的弹性信息，A可以表示为道路的刚度信息，l可以表示为道路的长度，I可以表示为道路的惯性矩，惯性矩可以由坐标信息确定。
子步骤22，采用所述至少两个地图数据，确定坐标转换矩阵；
在确定多个单元刚度矩阵后，可以根据至少两个地图数据，确定针对目标区域中匹配的道路的整体结构，进而可以根据该整体结构确定全局坐标系，可以结合道路的坐标系与全局坐标系确定坐标转换矩阵。
其中，全局坐标系为最多节点落在坐标轴的坐标系。
在实际应用中，可以根据道路的整体结构确定全局坐标系，可以通过几何的方法计算道路的坐标系与全局坐标系相对的位置关系信息，如道路的坐标系与全局坐标系之间的夹角信息，进而可以根据该位置关系信息确定坐标转换矩阵。
其中，坐标转换矩阵可以为如下矩阵：
其中，T可以表示为坐标转换矩阵，φ可以表示为道路的坐标系与全局坐标系之间的夹角信息。
子步骤23，结合所述多个单元刚度矩阵和所述坐标转换矩阵，得到全局坐标信息；
在得到坐标转换矩阵后，可以将多个单元刚度矩阵通过该坐标转换矩阵进行坐标转换，进而可以得到多个全局坐标系下的单元刚度矩阵，以得到全局坐标信息。
具体的，全局坐标系下的单元刚度矩阵可以采用如下公式得到：
K＝T'K
eT
其中，K可以表示为全局坐标系下的单元刚度矩阵，K
ε可以表示为单元刚度矩阵，T可以表示为坐标转换矩阵，T′可以表示为逆坐标转换矩阵。
子步骤24，采用所述全局坐标信息，确定针对所述目标梁系力学模型的总刚度矩阵。
在得到全局坐标信息后，可以对全局坐标信息进行计算，进而可以确定针对目标梁系力学模型的总刚度矩阵。
在实际应用中，由于道路之间可以具有一定的连接关系，可以确定道路连接处的节点为重合的节点，则在对单元刚度矩阵进行坐标转换时，可以得到重合的全局坐标信息，可以确定重合的全局坐标信息，进而可以对重合的全局坐标信息进行求和计算，可以根 据计算后的全局坐标信息确定总刚度矩阵。
作为一示例，当目标梁系力学模型为针对三连杆的梁系力学模型时，总刚度矩阵可以通过如下公式确定：
其中，K
1可以表示为第一个全局坐标系下的单元刚度矩阵，K
2可以表示为第二个全局坐标系下的单元刚度矩阵，K
3可以第三个全局坐标系下的单元刚度矩阵，而上标的1、2、3、4可以分别表示为道路信息中四个不同的节点，下标的11、12、22、23、33、34、44可以表示为两个节点之间的道路信息。
步骤405，采用所述修正量，确定针对所述目标梁系力学模型的节点力参数；
在确定连接关系信息和修正量后，由于修正量可以包括位移修正量和角度修正量，进而可以采用修正量中的位移修正量来表示为节点力的坐标参数，可以采用修正量中的角度修正量来表示为节点力的方向参数，以将该坐标参数和方向参数确定为针对目标梁系力学模型的节点力参数。
步骤406，结合所述总刚度矩阵、所述节点力参数，以及所述目标梁系力学模型，得到地图修正信息；
在确定总刚度矩阵和修正量后，可以通过公式将总刚度矩阵、节点力参数，以及目标梁系力学模型进行计算，进而可以计算出所有节点的节点位移信息，可以根据该节点位移信息计算地图数据中所有匹配的道路的修正信息，以得到地图修正信息，即节点的位移信息。
具体的，地图修正信息可以通过如下公式得到：
单元梁的平衡方程：
其中，
可以表示为节点1在x轴方向的节点力参数，
可以表示为节点1在y轴方向的节点力参数，
可以表示为节点2在x轴方向的节点力参数，
可以表示为节点2在y轴方向的节点力参数，
可以表示为在节点1处的力矩，
可以表示为在节点2处的力矩，x
1可以表示为节点1在全局坐标系的x轴方向上的位移，x可以表示为节点2在全局坐标系的x轴方向上的位移，y
1可以表示为节点1在全局坐标系的y轴方向上的位移，y
2可以表示为节点2在全局坐标系的y轴方向上的位移，θ
1可以表示为节点1在全局坐标系中所转动的角度，θ
2可以表示为节点2在全局坐标系中所转动的角度。
作为一示例，当目标梁系力学模型为针对三连杆的梁系力学模型时，地图修正信息可以通过如下公式得到：
其中，F可以表示为节点力参数，k可以表示为固定的弹性系数，弹性系数可以由用户设置或经过计算得到，e和l可以为常数，v可以表示为节点在全局坐标系下的位移，而下标的1、2、3、4可以分别表示为不同的节点，进而可以表示不同节点的节点力参数和/或弹性系数和/或在全局坐标系下的位移。
步骤407，按照所述地图修正信息，对所述至少两个地图数据进行融合。
在本发明实施例中，通过获取针对目标区域的至少两个地图数据，确定针对目标区域的目标梁系力学模型，并采用至少两个地图数据，确定针对目标区域中道路的连接关系信息，采用至少两个地图数据，确定针对目标区域中道路的修正量，采用连接关系信息，确定针对目标梁系力学模型的总刚度矩阵，采用修正量，确定针对目标梁系力学模型的节点力参数，结合总刚度矩阵、节点力参数，以及目标梁系力学模型，得到地图修正信息，按照地图修正信息，对至少两个地图数据进行融合，实现了结合全局坐标信息、总刚度矩阵、节点力参数，以及目标梁系力学模型对地图进行融合，避免了采用加权平均的方式进行融合而导致改变道路关系的问题，且无需对地图数据进行图像处理的操作，减少了计算量，保证了地图融合的精度。
需要说明的是，对于方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本发明实施例并不受所描述的动作顺序的限制，因为依据本发明实施例，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作并不一定是本发明实施例所必须的。
参照图5，示出了本发明一实施例提供的一种地图融合的车辆的结构示意图，具体可以包括如下模块：
地图数据获取模块501，用于获取针对目标区域的至少两个地图数据；
模型和连接关系确定模块502，用于确定针对所述目标区域的目标梁系力学模型，并采用所述至少两个地图数据，确定针对所述目标区域中道路的连接关系信息；
地图修正信息得到模块503，用于根据所述目标梁系力学模型和所述连接关系信息，得到地图修正信息；
地图数据融合模块504，用于按照所述地图修正信息，对所述至少两个地图数据进行融合。
在本发明一实施例中，所述地图修正信息得到模块503还包括：
修正量确定子模块，用于采用所述至少两个地图数据，确定针对所述目标区域中道路的修正量；
地图修正信息获得子模块，用于根据所述目标梁系力学模型、所述连接关系信息，以及所述修正量，得到地图修正信息。
在本发明一实施例中，所述地图修正信息获得子模块还包括：
总刚度矩阵确定单元，用于采用所述连接关系信息，确定针对所述目标梁系力学模型的总刚度矩阵；
节点力参数确定单元，用于采用所述修正量，确定针对所述目标梁系力学模型的节点力参数；
结合单元，用于结合所述总刚度矩阵、所述节点力参数，以及所述目标梁系力学模型，得到地图修正信息。
在本发明一实施例中，所述总刚度矩阵确定单元还包括：
单元刚度矩阵确定子单元，用于采用所述连接关系信息，确定多个单元刚度矩阵；
坐标转换矩阵确定子单元，用于采用所述至少两个地图数据，确定坐标转换矩阵；
全局坐标信息确定子单元，用于结合所述多个单元刚度矩阵和所述坐标转换矩阵，得到全局坐标信息；
目标梁系力学模型的总刚度矩阵确定子单元，用于采用所述全局坐标信息，确定针对所述目标梁系力学模型的总刚度矩阵。
在本发明一实施例中，所述修正量确定子模块还包括：
成熟度信息确定单元，用于确定针对所述至少两个地图数据的成熟度信息；
弹性信息和刚度信息确定单元，用于采用所述成熟度信息，确定针对所述目标区域中节点的弹性信息和针对所述目标区域中道路的刚度信息；
道路的修正量确定单元，用于结合所述弹性信息和所述刚度信息，确定针对所述目标区域中道路的修正量。
在本发明实施例中，通过获取针对目标区域的至少两个地图数据，确定针对目标区域的目标梁系力学模型，并采用至少两个地图数据，确定针对目标区域中道路的连接关系信息，并根据目标梁系力学模型和连接关系信息，以得到地图修正信息，按照地图修正信息，对至少两个地图数据进行融合，实现了结合道路的连接关系信息对地图进行融合，避免了融合后道路断开的情况，减掉了对地图优化的操作，减少了计算量，保证了地图融合的精度。
本发明一实施例还提供了一种电子设备，可以包括处理器、存储器及存储在存储器上并能够在处理器上运行的计算机程序，计算机程序被处理器执行时实现如上地图融合的方法。
本发明一实施例还提供了一种计算机可读存储介质，计算机可读存储介质上存储计算机程序，计算机程序被处理器执行时实现如上地图融合的方法。
对于装置实施例而言，由于其与方法实施例基本相似，所以描述的比较简单，相关 之处参见方法实施例的部分说明即可。
本说明书中的各个实施例均采用递进的方式描述，每个实施例重点说明的都是与其他实施例的不同之处，各个实施例之间相同相似的部分互相参见即可。
本领域内的技术人员应明白，本发明实施例可提供为方法、装置、或计算机程序产品。因此，本发明实施例可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明实施例是参照根据本发明实施例的方法、终端设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理终端设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理终端设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理终端设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理终端设备上，使得在计算机或其他可编程终端设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程终端设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本发明实施例的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例做出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本发明实施例范围的所有变更和修改。
最后，还需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将 一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者终端设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者终端设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者终端设备中还存在另外的相同要素。
以上对所提供的一种地图融合的方法及车辆、电子设备、存储介质，进行了详细介绍，本文中应用了具体个例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的方法及其核心思想；同时，对于本领域的一般技术人员，依据本发明的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本发明的限制。
Claims (10)
- 一种地图融合的方法，其特征在于，所述方法包括：获取针对目标区域的至少两个地图数据；确定针对所述目标区域的目标梁系力学模型，并采用所述至少两个地图数据，确定针对所述目标区域中道路的连接关系信息；根据所述目标梁系力学模型和所述连接关系信息，得到地图修正信息；按照所述地图修正信息，对所述至少两个地图数据进行融合。
- 根据权利要求1所述的方法，其特征在于，所述根据所述目标梁系力学模型和所述连接关系信息，得到地图修正信息，包括：采用所述至少两个地图数据，确定针对所述目标区域中道路的修正量；根据所述目标梁系力学模型、所述连接关系信息，以及所述修正量，得到地图修正信息。
- 根据权利要求2所述的方法，其特征在于，所述根据所述目标梁系力学模型、所述连接关系信息，以及所述修正量，得到地图修正信息，包括：采用所述连接关系信息，确定针对所述目标梁系力学模型的总刚度矩阵；采用所述修正量，确定针对所述目标梁系力学模型的节点力参数；结合所述总刚度矩阵、所述节点力参数，以及所述目标梁系力学模型，得到地图修正信息。
- 根据权利要求3所述的方法，其特征在于，所述采用所述连接关系信息，确定针对所述目标梁系力学模型的总刚度矩阵，包括：采用所述连接关系信息，确定多个单元刚度矩阵；采用所述至少两个地图数据，确定坐标转换矩阵；结合所述多个单元刚度矩阵和所述坐标转换矩阵，得到全局坐标信息；采用所述全局坐标信息，确定针对所述目标梁系力学模型的总刚度矩阵。
- 根据权利要求2或3或4所述的方法，其特征在于，所述采用所述至少两个地图数据，确定针对所述目标区域中道路的修正量，包括：确定针对所述至少两个地图数据的成熟度信息；采用所述成熟度信息，确定针对所述目标区域中节点的弹性信息和针对所述目标区域中道路的刚度信息；结合所述弹性信息和所述刚度信息，确定针对所述目标区域中道路的修正量。
- 根据权利要求5所述的方法，其特征在于，所述结合所述弹性信息和所述刚度信息，确定针对所述目标区域中道路的修正量，包括：获取针对所述目标区域的拓扑地图数据；结合所述弹性信息、所述刚度信息，以及所述拓扑地图数据，确定针对所述目标区域中道路的修正量。
- 根据权利要求6所述的方法，其特征在于，所述结合所述弹性信息、所述刚度信息，以及所述拓扑地图数据，确定针对所述目标区域中道路的修正量，包括：在所述至少两个地图数据中，确定针对所述目标区域中道路的第一道路信息；在所述拓扑地图数据中，结合所述弹性信息和所述刚度信息，确定针对所述目标区域中道路的第二道路信息；采用所述第一道路信息和所述第二道路信息，得到针对所述目标区域中道路的修正量。
- 一种车辆，其特征在于，所述车辆包括：地图数据获取模块，用于获取针对目标区域的至少两个地图数据；模型和连接关系确定模块，用于确定针对所述目标区域的目标梁系力学模型，并采用所述至少两个地图数据，确定针对所述目标区域中道路的连接关系信息；地图修正信息得到模块，用于根据所述目标梁系力学模型和所述连接关系信息，得到地图修正信息；地图数据融合模块，用于按照所述地图修正信息，对所述至少两个地图数据进行融合。
- 一种电子设备，其特征在于，包括处理器、存储器及存储在所述存储器上并能够在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行时实现如权利要求1至7中任一项所述的地图融合的方法。
- 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储计算 机程序，所述计算机程序被处理器执行时实现如权利要求1至7中任一项所述的地图融合的方法。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP21786739.9A EP3968177A4 (en) | 2020-07-16 | 2021-06-22 | CARD AND VEHICLE MERGER METHOD, ELECTRONIC DEVICE, AND STORAGE MEDIA |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010688817.8A CN111831776B (zh) | 2020-07-16 | 2020-07-16 | 一种地图融合的方法及车辆、电子设备、存储介质 |
| CN202010688817.8 | 2020-07-16 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2022012281A1 true WO2022012281A1 (zh) | 2022-01-20 |
Family
ID=72923456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2021/101578 WO2022012281A1 (zh) | 2020-07-16 | 2021-06-22 | 一种地图融合的方法及车辆、电子设备、存储介质 |
Country Status (3)
| Country | Link |
|---|---|
| EP (1) | EP3968177A4 (zh) |
| CN (1) | CN111831776B (zh) |
| WO (1) | WO2022012281A1 (zh) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111831776B (zh) * | 2020-07-16 | 2022-03-11 | 广州小鹏自动驾驶科技有限公司 | 一种地图融合的方法及车辆、电子设备、存储介质 |
| CN112308810B (zh) * | 2020-11-05 | 2022-05-13 | 广州小鹏自动驾驶科技有限公司 | 一种地图融合的方法及装置、服务器、存储介质 |
| WO2023249550A2 (en) * | 2022-06-20 | 2023-12-28 | Grabtaxi Holdings Pte. Ltd. | Method and device for placing road objects on map using sensor information |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102374866A (zh) * | 2011-08-25 | 2012-03-14 | 光庭导航数据（武汉）有限公司 | 基于走行方向的有损道路形状融合方法 |
| CN107826105A (zh) * | 2017-10-31 | 2018-03-23 | 清华大学 | 半透明自动驾驶人工智能系统及车辆 |
| CN110083668A (zh) * | 2019-03-22 | 2019-08-02 | 纵目科技（上海）股份有限公司 | 一种高精度地图的数据管理系统、管理方法、终端和存储介质 |
| CN110986969A (zh) * | 2019-11-27 | 2020-04-10 | Oppo广东移动通信有限公司 | 地图融合方法及装置、设备、存储介质 |
| US20200167934A1 (en) * | 2018-11-27 | 2020-05-28 | GM Global Technology Operations LLC | Systems and methods for applying maps to improve object tracking, lane-assignment and classification |
| CN111831776A (zh) * | 2020-07-16 | 2020-10-27 | 广州小鹏车联网科技有限公司 | 一种地图融合的方法及车辆、电子设备、存储介质 |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7533010B2 (en) * | 2005-09-01 | 2009-05-12 | The Goodyear Tire & Rubber Company | Method and system for tread pattern noise optimization |
| US8725394B2 (en) * | 2007-10-09 | 2014-05-13 | Siemens Corporation | Multi-modal speed limit assistant |
| US20100299370A1 (en) * | 2007-12-28 | 2010-11-25 | Hans Ulrich Otto | Method and apparatus for combining a first partition from a first digital map database and a second partition from a second digital map database |
| EP3293486B1 (en) * | 2016-09-07 | 2019-04-24 | Ordnance Survey Limited | Method and system for improving spatial accuracy of map data |
| CN106564495B (zh) * | 2016-10-19 | 2018-11-06 | 江苏大学 | 融合空间和动力学特性的智能车辆安全驾驶包络重构方法 |
| CN110969837B (zh) * | 2018-09-30 | 2022-03-25 | 毫末智行科技有限公司 | 自动驾驶车辆的道路信息融合系统及方法 |
-
2020
- 2020-07-16 CN CN202010688817.8A patent/CN111831776B/zh active Active
-
2021
- 2021-06-22 WO PCT/CN2021/101578 patent/WO2022012281A1/zh unknown
- 2021-06-22 EP EP21786739.9A patent/EP3968177A4/en not_active Withdrawn
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102374866A (zh) * | 2011-08-25 | 2012-03-14 | 光庭导航数据（武汉）有限公司 | 基于走行方向的有损道路形状融合方法 |
| CN107826105A (zh) * | 2017-10-31 | 2018-03-23 | 清华大学 | 半透明自动驾驶人工智能系统及车辆 |
| US20200167934A1 (en) * | 2018-11-27 | 2020-05-28 | GM Global Technology Operations LLC | Systems and methods for applying maps to improve object tracking, lane-assignment and classification |
| CN110083668A (zh) * | 2019-03-22 | 2019-08-02 | 纵目科技（上海）股份有限公司 | 一种高精度地图的数据管理系统、管理方法、终端和存储介质 |
| CN110986969A (zh) * | 2019-11-27 | 2020-04-10 | Oppo广东移动通信有限公司 | 地图融合方法及装置、设备、存储介质 |
| CN111831776A (zh) * | 2020-07-16 | 2020-10-27 | 广州小鹏车联网科技有限公司 | 一种地图融合的方法及车辆、电子设备、存储介质 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP3968177A4 * |
Also Published As
| Publication number | Publication date |
|---|---|
| EP3968177A1 (en) | 2022-03-16 |
| EP3968177A4 (en) | 2022-07-27 |
| CN111831776A (zh) | 2020-10-27 |
| CN111831776B (zh) | 2022-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022012281A1 (zh) | 一种地图融合的方法及车辆、电子设备、存储介质 | |
| US20200132476A1 (en) | Method and apparatus for producing a lane-accurate road map | |
| JP2023509888A (ja) | 法線ベクトルに基づく点群平滑化フィルタリング方法 | |
| WO2019201135A1 (zh) | 基于全局路网特征的数据匹配方法、装置及存储介质 | |
| CN109855623B (zh) | 基于Legendre多项式和BP神经网络的地磁模型在线逼近方法 | |
| CN111222418A (zh) | 一种车道线的多道路片段的众包数据快速融合优化方法 | |
| CN109214314B (zh) | 一种车道线自动融合匹配算法 | |
| CN111462029A (zh) | 视觉点云与高精地图融合方法、装置和电子设备 | |
| CN112183171A (zh) | 一种基于视觉信标建立信标地图方法、装置 | |
| CN111209805B (zh) | 车道线众包数据的多道路片段数据的快速融合优化方法 | |
| JP2015161557A5 (zh) | ||
| CN111141296B (zh) | 车道线众包数据的多道路片段数据的预处理方法及系统 | |
| CN111047652A (zh) | 一种快速的多tof相机外参标定方法和装置 | |
| WO2022062355A1 (zh) | 一种融合定位方法及装置 | |
| CN111858785B (zh) | 地图离散型要素的匹配方法、装置、系统及存储介质 | |
| CN115435796B (zh) | 车辆的定位方法、装置和电子设备 | |
| Förstner | On weighting and choosing constraints for optimally reconstructing the geometry of image triplets | |
| CN114323007A (zh) | 一种载体运动状态估计方法及装置 | |
| CN112115930B (zh) | 位姿信息的确定方法和装置 | |
| CN111156948A (zh) | 用于3c玻璃面板检测的三维数据坐标校正方法及装置 | |
| JP7173310B2 (ja) | 経路探索装置、経路探索方法、及び経路探索プログラム | |
| CN112556726B (zh) | 一种车辆位置修正方法、装置、车辆及介质 | |
| JP2021169990A (ja) | 測位システム、方法及びプログラム | |
| CN117473455B (zh) | 多源定位数据的融合方法、装置和电子设备 | |
| CN112633043A (zh) | 一种车道线确定方法、装置、电子设备及存储介质 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| ENP | Entry into the national phase |
Ref document number: 2021786739 Country of ref document: EP Effective date: 20211021 |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21786739 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |