WO2022170815A1 - 仿真高精度地图生成方法、装置和计算机可读存储介质 - Google Patents

仿真高精度地图生成方法、装置和计算机可读存储介质 Download PDF

Info

Publication number
WO2022170815A1
WO2022170815A1 PCT/CN2021/132775 CN2021132775W WO2022170815A1 WO 2022170815 A1 WO2022170815 A1 WO 2022170815A1 CN 2021132775 W CN2021132775 W CN 2021132775W WO 2022170815 A1 WO2022170815 A1 WO 2022170815A1
Authority
WO
WIPO (PCT)
Prior art keywords
lane
map
segment
primitives
primitive
Prior art date
Application number
PCT/CN2021/132775
Other languages
English (en)
French (fr)
Inventor
吴茜
缪若琳
赵凌
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2022170815A1 publication Critical patent/WO2022170815A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/28Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
    • G01C21/30Map- or contour-matching
    • G01C21/32Structuring or formatting of map data
    • GPHYSICS
    • G09EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09BEDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B29/00Maps; Plans; Charts; Diagrams, e.g. route diagram

Definitions

  • the present application relates to the technical field of intelligent transportation, and in particular, to a method, device and computer-readable storage medium for generating a simulated high-precision map.
  • the autonomous driving simulation system is an important module for the study of autonomous driving.
  • the autonomous driving software can be developed and tested through the autonomous driving simulation system, which can reduce the cost and risk of real vehicle testing.
  • HD Maps high-definition maps
  • the present application provides a simulation high-precision map generation method, device and computer-readable storage medium, which are used to select a plurality of primitives that meet the requirements from a primitive library, and splicing the plurality of primitives to generate a simulation high-precision map Therefore, the manpower in the process of generating the simulated high-precision map can be saved, the speed of generating the simulated high-precision map can be accelerated, and the cost of the simulated high-precision map can also be reduced.
  • the present application provides a method for generating a simulated high-precision map, in which a requirement for generating a high-precision map is obtained.
  • a requirement for generating a high-precision map is obtained.
  • multiple primitives that meet the requirements are selected from the primitive library, and a simulated high-precision map is generated by splicing multiple primitives.
  • Primitives are high-resolution map fragments with categorical labels.
  • multiple primitives are stored in the primitive library in advance, if there is a need, multiple primitives that meet the requirements can be selected from the primitive library, and multiple primitives can be spliced to generate a simulated high-precision map, thereby The manpower in the process of generating the simulated high-precision map can be saved, the speed of generating the simulated high-precision map can be accelerated, and the cost of the simulated high-precision map can also be reduced.
  • a high-precision map segment conforming to the classification label is segmented from an existing high-precision map; and the segmented high-precision map segment is added to the primitive library as a primitive.
  • the existing high-precision map may refer to an existing high-precision map obtained according to the collected data of the actual road. The primitives obtained in this way can be more in line with the actual road construction specifications.
  • a vector map segment that conforms to the classification label is segmented from an existing vector map; by performing image detection on a satellite cloud image corresponding to the vector map segment, a high-precision image corresponding to the vector map segment is obtained. map information; converting vector map fragments into high-precision map fragments using high-precision map information; and adding the high-precision map fragments obtained by the conversion into the primitive library as primitives. Since the lane-level information corresponding to the vector map segment can be determined based on the satellite cloud image, the high-precision map segment corresponding to the vector map segment is determined. In this way, the diversity of access to primitives can be increased.
  • selecting a plurality of primitives from the primitive library that meets the requirements includes: according to requirements, determining at least one classification label required for generating a simulated high-precision map, and each of the at least one classification label The number of primitives corresponding to each classification label; according to the number of primitives, multiple primitives with at least one classification label are selected from the primitive library.
  • the user can select the required primitive based on the classification label, thereby simplifying the user's operation, improving the convenience of the simulation high-precision map generation process, and contributing to the popularization and use of the scheme.
  • the user can also input the number of primitives, the convenience of the user's input needs is improved, and when a large number of the same primitives are required, the user's operation can be simplified by inputting the requirements by inputting the quantity.
  • the number of primitives corresponding to the classification label required to generate a simulated high-precision map is determined according to requirements is greater than 1 : selecting a plurality of primitives with at least one classification label from the primitive library according to the number of primitives, including: randomly selecting a plurality of primitives with a classification label from the primitive library according to the number of primitives.
  • Selecting a plurality of primitives with at least one classification label in the metabase includes: selecting a plurality of primitives with a classification label from the primitive library by sampling with replacement according to the number of primitives.
  • the plurality of primitives can include two primitives that belong to the same primitive in the primitive library, so that when the number of primitives stored in a classification label is less than the required number , it is still possible to select the desired number of primitives.
  • the plurality of primitives include a first primitive and a second primitive, the first primitive includes a first road segment, and the second primitive includes a second road segment, by splicing the plurality of primitives
  • Generating a simulated high-resolution map includes: generating a transition road segment between the first road segment and the second road segment, the transition road segment includes at least one transition lane, and the at least one transition lane is used to connect at least one first road segment in the first road segment. establishing a link relationship between at least one first lane and at least one transition lane; establishing a link relationship between at least one second lane and at least one transition lane. Since the two primitives are spliced by the transition road segment, the splicing of the two primitives can also be realized when the lanes or driving directions of the two primitives are somewhat different.
  • generating a simulated high-precision map by splicing a plurality of primitives further includes: determining at least one exit lane of at least one first lane; determining at least one entry lane of at least one second lane; at least one A transition lane is used to connect at least one exit lane with at least one entry lane.
  • the lane information on the spliced simulated high-precision map can be matched, thereby laying a foundation for the simulated vehicle to run on the simulated high-precision map.
  • the number of at least one exit lane is different from the number of at least one entry lane
  • the transition road segment includes a lane segment for merging two lanes into one lane. In this way, two road segments with different numbers of lanes can be spliced together through the transition road segment.
  • the orientation of at least one exit lane is different from the orientation of at least one entry lane
  • the at least one transition lane includes a curved lane. In this way, two road segments with different lane orientations can be spliced by transitioning the road segment.
  • the classification label is used to identify at least one of the following contents of the high-resolution map segment: geometric topology information of roads in the high-resolution map segment; usage information of lanes in the high-resolution map segment; or, Type information for the site in the HD map fragment.
  • the user can obtain some primitives that are usually used in the simulation environment based on the set classification labels, and this way of setting the classification labels can better match the actual needs in the field of automatic driving simulation.
  • the geometric topology information includes at least one of a curve, a straight road, a roundabout, an intersection, a T-junction, an L-shaped intersection, a U-shaped intersection or a ramp.
  • the usage information of the lane includes at least one of: a bus lane, a pedestrian crossing, a bicycle lane, an expressway, a temporary parking lane, or an emergency parking lane.
  • the type information of the venue includes at least one of city roads, expressways, and parking lots. This way of setting classification labels can better match the actual needs in the field of autonomous driving simulation.
  • the present application also provides a map generation device.
  • the map generating apparatus may be a communication chip, a terminal device side device, or a network device side device.
  • the map generating apparatus can be a chip used for network equipment; for another example, it can be used as a chip used in terminal equipment.
  • a map generating apparatus including an acquiring unit and a processing unit, so as to execute any one of the implementations of the first aspect above.
  • the acquisition unit is used to perform functions related to transmission and reception.
  • the obtaining unit includes a receiving unit and a sending unit.
  • the map generating device is a communication chip, and the acquiring unit may be an input and output circuit or port of the chip.
  • the acquisition unit may be a transmitter and a receiver, or the acquisition unit may be a transmitter and a receiver.
  • the map generating apparatus further includes various modules that can be used to execute any one of the implementations of the first aspect above.
  • a map generating apparatus is provided, where the map generating apparatus is the above-mentioned terminal device or network device. Includes processor and memory. Optionally, it also includes a transceiver, the memory is used to store a computer program or instruction, the processor is used to call and run the computer program or instruction from the memory, and when the processor executes the computer program or instruction in the memory, make the computer program or instruction in the memory.
  • the map generating apparatus executes any one of the embodiments of the above-mentioned first aspect.
  • processors there are one or more processors and one or more memories.
  • the memory may be integrated with the processor, or the memory may be provided separately from the processor.
  • the transceiver may include a transmitter (transmitter) and a receiver (receiver).
  • a map generating apparatus including a processor.
  • the processor coupled to the memory, is operable to perform the method of any of the possible implementations of the first aspect.
  • the map generating apparatus further includes a memory.
  • the map generating apparatus further includes a communication interface, and the processor is coupled to the communication interface.
  • the map generating apparatus is a terminal device.
  • the communication interface may be a transceiver, or an input/output interface.
  • the transceiver may be a transceiver circuit.
  • the input/output interface may be an input/output circuit.
  • the map generating apparatus is a network device.
  • the communication interface may be a transceiver, or an input/output interface.
  • the transceiver may be a transceiver circuit.
  • the input/output interface may be an input/output circuit.
  • the map generating apparatus is a chip or a system of chips.
  • the communication interface may be an input/output interface, an interface circuit, an output circuit, an input circuit, a pin or a related circuit, etc. on the chip or a chip system.
  • a processor may also be embodied as a processing circuit or a logic circuit.
  • a computer program product includes: a computer program (also referred to as code, or instruction), which, when the computer program is executed, enables the computer to execute any one of the above-mentioned first aspects. method in method.
  • a computer-readable storage medium where the computer-readable medium stores a computer program (also referred to as code, or instruction) when it runs on a computer, causing the computer to execute any one of the above-mentioned first aspects. method in one possible implementation.
  • a computer program also referred to as code, or instruction
  • a system-on-chip may include a processor.
  • the processor coupled to the memory, is operable to perform any of the first aspects.
  • the chip system further includes a memory.
  • Memory used to store computer programs (also called code, or instructions).
  • the processor is used to call and run the computer program from the memory, so that the device installed with the chip system executes the method in any possible implementation manner of the first aspect.
  • FIG. 1 provides a schematic flowchart of a method for generating a simulated high-precision map according to an embodiment of the present application
  • FIG. 6 is a schematic structural diagram of a map generating apparatus provided by an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of another map generation apparatus provided by an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of another map generating apparatus according to an embodiment of the present application.
  • the embodiment of the present application provides a method for generating a simulated high-precision map, and the simulated high-precision map generated by the method can be applied to an automatic driving simulation system.
  • Vehicles in the autonomous driving simulation system can realize traffic services based on simulated high-precision maps.
  • the traffic service in the embodiment of the present application may be various automatic driving and assisted driving services, for example, route planning, and providing driving risk warning for manual driving.
  • the above traffic services are just examples.
  • the simulated high-precision map provided by the embodiment of the present application can also provide technical preparation for the communication (vehicle to everything, V2X) between the vehicle and other devices, such as vehicle to vehicle (V2V), vehicle Road communication (vehicle to installation, V2I).
  • V2X vehicle to everything
  • V2V vehicle to vehicle
  • V2I vehicle Road communication
  • the method for generating a high-precision map may be performed by a map generating apparatus, and the map generating apparatus may be a network-side device or a terminal device, or a chip inside the network-side device or a chip inside the terminal device.
  • the network side device includes a computing platform or a server, and the specific deployment form of the computing platform and the server is not limited in this application. For example, it may be a cloud deployment or an independent computer device or chip.
  • the terminal device includes a hardware device that supports scientific operations, and may include, for example, a personal computer, a server, a mobile phone terminal, an embedded device, and the like.
  • FIG. 1 exemplarily shows a schematic flowchart of a method for generating a simulated high-precision map provided by an embodiment of the present application. As shown in FIG. 1 , the method includes:
  • the map generating apparatus acquires a requirement for generating a high-precision map.
  • the user can input a requirement, and the format of the requirement is not limited, for example, it can be a table, a program segment, a piece of text, a file, a voice, and so on.
  • the map generating apparatus selects a plurality of primitives that meet the requirements from the primitive library according to requirements, and the primitives are high-precision map segments with classification labels.
  • a primitive can also be understood as a high-precision map file corresponding to a segment of a high-precision map.
  • the map generating device generates a simulated high-precision map by splicing multiple primitives.
  • multiple primitives are stored in the primitive library in advance, if there is a need, multiple primitives that meet the requirements can be selected from the primitive library, and multiple primitives can be spliced to generate a simulated high-precision map, thereby The manpower in the process of generating the simulated high-precision map can be saved, the speed of generating the simulated high-precision map can be accelerated, and the cost of the simulated high-precision map can also be reduced.
  • the first method is to obtain primitives according to an existing high-precision map.
  • High-resolution maps include road-level information and lane-level information.
  • the lane-level information is used to indicate the information of the lanes in the road network environment, such as lane curvature, lane heading, lane axis, lane width, lane markings, lane speed limit, lane segmentation and lane merging and other information.
  • the conditions of the lane lines between the lanes dotted line, solid line, single line and double line
  • the color of the lane line (white, yellow)
  • the road isolation belt, the isolation belt material, the road arrow, the text content and the location, etc. can also be Included in lane-level information.
  • a high-precision map segment that conforms to the classification label can be segmented from an existing high-precision map, and the segmented high-precision map segment (a high-precision map segment can also be understood as a file of a high-precision map segment) is used as the Primitives are added to the primitive library.
  • the existing high-precision map may refer to an existing high-precision map obtained according to the collected data of the actual road.
  • the existing high-precision map is detected, and one or more high-precision map fragments including "crossroads” are cut, and the obtained high-precision map fragments are used as Primitives, join the primitive library.
  • the second method is to obtain primitives according to the existing vector map and satellite cloud image.
  • Vector maps such as open source vector maps, include road-level information.
  • road-level information can provide users with navigation information to meet the navigation requirements of driving routes.
  • the road-level information may include: the number of lanes on the current road, speed limit information on the current road, and turning information.
  • the satellite cloud in the embodiment of the present application can be understood as a satellite map, and lane-level information, such as lane width, lane number, lane driving direction, lane usage information, etc., can be identified through the satellite cloud. Therefore, the lane-level information corresponding to the vector map segment can be determined based on the satellite cloud image, thereby determining the high-precision map segment corresponding to the vector map segment.
  • vector map segments that conform to the classification labels may be segmented from the existing vector map.
  • high-precision map information corresponding to the vector map segments is obtained. Convert the vector map fragments into high-precision map fragments by using high-precision map information; and add the high-precision map fragments obtained by the conversion into the primitive library as primitives.
  • Parameter item a1 type information of the venue in the high-precision map segment
  • Parameter item a2 the geometric topology information of the road in the high-precision map segment; or,
  • Parameter item a3 usage information of lanes in the high-resolution map segment.
  • Parameter item a1 The classification label is used to identify the type information of the venue in the high-precision map segment.
  • the type information of the venue may include several preset types, such as city roads, expressways and parking lots. Sites can be classified according to their type information in the hypermap segment.
  • the classification label of the high-precision map segment includes a parking lot.
  • the classification label of the high-precision map segment includes a highway.
  • Parameter item a2 The classification label is used to identify the geometric topology information of the road in the high-precision map segment.
  • Geometric information refers to the position information of an object in three-dimensional Euclidean space.
  • the geometric information reflects the size and position of the object, such as the coordinate value of the vertex, the specific coefficient in the mathematical expression of the surface, etc.
  • Topological information refers to the number and type of topological elements (Vertex, Edge, and Surface) of an object, as well as information about the mutual relationship between them.
  • the geometric topology information of the road in the high-precision map segment in the embodiment of the present application may include at least one of a curve, a straight road, a roundabout, an intersection, a T-shaped intersection, an L-shaped intersection, a U-shaped intersection, or a ramp.
  • the road is an arc with a certain curvature.
  • the geometric shape of the road is straight.
  • the geometric topology information of the road is "roundabout", the geometric shape of the road is a circle, and the roundabout in the road segment r6 has an exit and an entrance.
  • the geometric shape of the road is T-shaped.
  • the geometric shape of the road is a cross.
  • the geometric shape of the road is L-shaped.
  • the geometric shape of the road is U-shaped.
  • the classification label used to identify the type information of the venue in the high-precision map segment may be referred to as the first-level classification label, and the geometric topology information used to identify the road in the high-precision map segment may be referred to as the second-level classification label.
  • Category labels used to identify the type information of the venue in the high-precision map segment.
  • FIG. 2 exemplarily shows a schematic diagram of classification label setting.
  • three first-level classification labels can be set, namely: “city road”, “highway” and “parking lot”.
  • a secondary classification label can be set under the primary classification label, for example, the secondary classification label under the primary classification label "urban road” can include at least one of the following: curve, straight road, roundabout, intersection, T-junction , at least one of L-junction, U-junction or ramp.
  • the secondary classification label under the primary classification label "highway" may include at least one of the following: a curve, a straight road, or a ramp.
  • a high-precision map segment can correspond to a first-level classification label, such as a high-precision map segment whose classification label is a parking lot.
  • a high-precision map segment may also correspond to a first-level classification label and at least one second-level classification label.
  • a road in a high-precision map segment is a straight road under an urban road, and the classification label of the high-precision map segment may include: city Roads and straights.
  • one or more tertiary labels may be set under the secondary labels, and the tertiary labels may be key parameter items capable of identifying geometric topology information.
  • the tertiary classification label corresponding to the secondary classification label "curve” may be: curvature, and then multiple high-precision map segments corresponding to curves with different curvatures may be stored under the secondary classification label "curve”.
  • the tertiary classification label corresponding to the secondary classification label "roundabout” can be: the radius of the roundabout, and then multiple high-precision map fragments corresponding to roundabouts with different radii can be stored under the secondary classification label "roundabout”.
  • the tertiary classification label corresponding to the secondary classification label "U-shaped junction” can be: the opening size of the U-shaped junction, and then the corresponding U-shaped junctions with different opening sizes can be stored under the secondary classification label "U-shaped junction". of high-resolution map fragments.
  • the tertiary classification label corresponding to the secondary classification label "ramp” can be: the type of the ramp, and then multiple high-precision map fragments corresponding to different types of ramps can be stored under the secondary classification label "ramp".
  • the type of ramp can include at least one of the following:
  • auxiliary connecting sections entering and leaving the main line can be "level crossing ramps” or “interchange ramps”.
  • On-ramp and off-ramp Access to and from the elevated road, the auxiliary access ramp for driving up or down, usually "interchange ramp”.
  • Non-directional Ramp/Road Set the left-turn lane on the right, and set up a loop to connect to other roads.
  • the corresponding high-precision map segment under a three-level classification label may be one or multiple.
  • the high-precision map segment corresponding to the same curvature may be one or multiple. This application implements the Examples are not limited.
  • Parameter item a3 The classification label is used to identify the usage information of the lane in the high-resolution map segment.
  • the usage information of the lane may include at least one of: a bus lane, a pedestrian crossing, a bicycle lane, an expressway, a temporary parking lane, or an emergency parking lane.
  • the usage information of lanes can also be called secondary classification labels, and a high-resolution map segment can include one or more secondary classification labels.
  • a road in a high-precision map segment is a straight road
  • one lane in the road of the high-precision map segment is a bus lane
  • the classification label of the high-precision map segment may include: straight road and bus lane.
  • the classification label of the high-precision map segment may also include an urban road.
  • the lane When the usage information of a lane is "bus lane", the lane is mainly used for bus driving. Specifically, it can be only used for bus driving at all times, or it can be within a specified time period (such as morning rush hour and bus driving). During the evening rush hour) only for buses.
  • the lane can only allow bicycles to travel.
  • the lane When the usage information of a lane is "express road", the lane has requirements for the speed of the vehicle, for example, the speed of the vehicle driving in the lane must not be lower than 80 kilometers per hour.
  • the lane is a lane for pedestrians.
  • the lane can only be used in an emergency, for example, a traffic police vehicle can be driven, so as to quickly deal with various traffic accidents on the road.
  • the lane When the usage information of a lane is "temporary parking lane", the lane can only be used for temporary parking, and cannot be used for long-term parking.
  • classification label items are only examples. In practical applications, other classification label items can also be set according to the road information in the high-precision map segment. For example, at least one of the following contents can also be set as the classification label. Items: lane height limit, lane maximum speed limit, presence or absence of electronic eyes, lane restricted direction, prohibited time period of restricted direction, lane restricted vehicle type, and restricted vehicle prohibited time period, etc.
  • the map generating apparatus may determine at least one classification label required for generating a simulated high-precision map and the number of primitives corresponding to each classification label in the at least one classification label according to requirements.
  • a plurality of primitives with at least one classification label are selected from the primitive library according to the primitive number.
  • a requirement could be a program entered by the user as follows:
  • the classification labels required to generate a simulated high-resolution map include: 1 roundabout and 1 intersection.
  • the number of primitives corresponding to each classification label is included.
  • the primitives satisfying the category label can be randomly selected from the primitive library.
  • the number of primitives of the classification label to be selected from the primitive library is greater than 1, for example, it can be randomly selected.
  • multiple primitives that satisfy the classification label can be selected from the primitive library by means of sampling with replacement.
  • Samling with replacement is one of the operations of simple random sampling. Number the sampling units in the population from 1 to K, and return each number to the population. For any drawing, since the overall capacity remains unchanged, the chances of K numbers being drawn are equal.
  • the classification label of the primitive to be selected is "roundabout", and the number of primitives corresponding to the classification label "roundabout” is "2"
  • One primitive is extracted from the primitives, and then another primitive is extracted from all primitives corresponding to the classification label "Round Island" of the primitive library.
  • the two primitives selected by sampling with replacement may be the same, or they may be two different primitives.
  • the splicing order of the multiple primitives may be randomly generated, or may be specified by the user, for example, the acquired requirements include instructions for indicating Indication information of the splicing order of at least two primitives in the plurality of primitives.
  • the first primitive includes a first road segment
  • the second primitive includes a second road segment
  • the first road segment and the second road segment can be spliced.
  • FIG. 3 exemplarily shows a schematic structural diagram of splicing a first primitive and a second primitive
  • FIG. 3 shows a schematic diagram of a roundabout 301 (the roundabout 301 can be a first primitive)
  • FIG. 3 shows the intersection 302 (the intersection 302 can be the second primitive)
  • FIG. 3 shows that the map generation device performs the first primitive and the second primitive
  • a schematic diagram of the obtained simulated high-precision map As shown in FIG. 3 , the first road segment and the second road segment can be spliced according to the driving direction of the lane in the high-precision map segment, without generating a transition road segment.
  • the exit lanes in the first road segment may be compared with Entry lane stitching in the second road segment.
  • the two first lanes have different orientations
  • there are two second lanes in the second road segment the two second lanes are Orientation is different. Then the exit lane in the first road segment is spliced with the entry lane in the second road segment, and the entry lane in the first road segment is spliced with the exit lane in the second road segment.
  • the map generating means may generate a transition road segment between the first road segment and the second road segment.
  • the transition road segment includes at least one transition lane for connecting at least one first lane in the first road segment with at least one second lane in the first road segment.
  • a link relationship between at least one first lane and at least one transition lane is established.
  • a link relationship between the at least one second lane and the at least one transition lane is established.
  • the map generating device may determine at least one exit lane of the at least one first lane. At least one entry lane of the at least one second lane is determined. At least one transition lane is used to connect at least one exit lane with at least one entry lane.
  • Transition road segments are generated based on the number and lane orientations of the exit lanes of the first road segment and the number and lane orientations of the entry lanes of the second road segment. Several possible examples are listed below.
  • Example 1 the number of exit lanes of the first road segment and the number of entry lanes of the second road segment are different, and the transition road segment includes a lane segment for merging multiple (eg, two) lanes into one lane.
  • FIG. 4 exemplarily shows a possible structural schematic diagram of splicing the first primitive and the second primitive.
  • the two primitives that need to be spliced are respectively (a) in FIG. 4 . ), and the second primitive 401 shown in FIG. 4(b), and the first primitive 402 shown in FIG. 4(b).
  • the second primitive 401 is a double lane
  • the first primitive 402 is a single lane.
  • the entry lane of the second primitive 401 may be determined according to the lane information of the second primitive 401
  • the exit lane of the first primitive 402 may be determined according to the lane information of the first primitive 402 .
  • the entry lane connection of the second primitive 401 is responsible for solving the transition of the number of lanes changed (increased/decreased number of lanes).
  • Example 2 in a possible implementation, the orientation of at least one exit lane of the first road segment is different from the orientation of at least one entry lane of the second road segment, and at least one transition lane in the transition road segment includes a curved lane.
  • FIG. 5 exemplarily shows a schematic diagram of another possible splicing of the first primitive and the second primitive.
  • the two primitives that need to be spliced are respectively shown in (a) of FIG. 5 .
  • the second primitive 501 shown in FIG. 5 and the first primitive 502 shown in (b) of FIG. 5 .
  • the driving direction of the vehicle of the second primitive 501 is different from the driving direction of the vehicle of the first primitive 502 by 90 degrees, then a transition lane (a curve) in the transition road segment is generated, as shown in (c) of FIG. 5 .
  • the transition road segment 503 is used to connect the second primitive 501 and the first primitive 502 .
  • the method for generating a high-precision map provided by the embodiment of the present application can construct a large number of high-precision maps that meet the requirements of simulation testing, and has the characteristics of wide coverage and rich road conditions, and can easily cover the full simulation testing requirements.
  • the high-precision maps generated in the embodiments of the present application conform to real roads
  • the construction specification is reasonable.
  • relatively real high-precision maps, without on-site mapping, reduce labor costs, improve generation efficiency, relatively low accuracy, and do not synchronize with real roads, can be generated in large quantities under the premise of meeting simulation test requirements to meet the needs of simulation.
  • a user-customized high-precision map can be automatically generated according to the user's intention, so as to better match the simulation requirements.
  • “at least one” refers to one or more, and “multiple” refers to two or more.
  • “And/or”, which describes the association relationship of the associated objects, indicates that there can be three kinds of relationships, for example, A and/or B, which can indicate: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A, B can be singular or plural.
  • the character “/” generally indicates that the associated objects are an “or” relationship.
  • “At least one item(s) below” or similar expressions thereof refer to any combination of these items, including any combination of single item(s) or plural items(s).
  • At least one item (a) of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, c may be single or multiple .
  • ordinal numbers such as “first” and “second” mentioned in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, sequence, priority or importance of multiple objects degree.
  • first data type and the second data type are only used to distinguish different data types, but do not indicate the difference in priority or importance of the two data types.
  • each network element in the above-mentioned implementation includes corresponding hardware structures and/or software modules for executing each function.
  • the present invention can be implemented in hardware or a combination of hardware and computer software in conjunction with the units and algorithm steps of each example described in the embodiments disclosed herein. Whether a function is performed by hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of the present invention.
  • FIG. 6 provides a schematic structural diagram of a map generating apparatus that can execute the simulation map generating method shown in FIG. 1 according to an embodiment of the present application.
  • the map generating apparatus may be a device or terminal on the network device side.
  • the device on the device side may also be a chip or circuit, for example, a chip or circuit that can be provided on the network device side, or a chip or circuit that can be provided on the terminal device side.
  • the map generating apparatus 1301 may further include a bus system, wherein the processor 1302, the memory 1304, and the transceiver 1303 may be connected through the bus system.
  • the above-mentioned processor 1302 may be a chip.
  • the processor 1302 may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), or a system on chip (SoC). It can be a central processing unit (CPU), a network processor (NP), a digital signal processing circuit (DSP), or a microcontroller (microcontroller). unit, MCU), it can also be a programmable logic device (PLD) or other integrated chips.
  • FPGA field programmable gate array
  • ASIC application specific integrated circuit
  • SoC system on chip
  • SoC system on chip
  • SoC system on chip
  • MCU microcontroller
  • MCU programmable logic device
  • PLD programmable logic device
  • each step of the above-mentioned method can be completed by an integrated logic circuit of hardware in the processor 1302 or an instruction in the form of software.
  • the steps of the methods disclosed in conjunction with the embodiments of the present application may be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor 1302 .
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory 1304, and the processor 1302 reads the information in the memory 1304, and completes the steps of the above method in combination with its hardware.
  • processor 1302 in this embodiment of the present application may be an integrated circuit chip, which has a signal processing capability.
  • each step of the above method embodiments may be completed by a hardware integrated logic circuit in a processor or an instruction in the form of software.
  • the aforementioned processors may be general purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components .
  • DSPs digital signal processors
  • ASICs application specific integrated circuits
  • FPGAs field programmable gate arrays
  • the methods, steps, and logic block diagrams disclosed in the embodiments of this application can be implemented or executed.
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the steps of the method disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.
  • the memory 1304 in this embodiment of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically programmable Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
  • Volatile memory may be random access memory (RAM), which acts as an external cache.
  • RAM random access memory
  • DRAM dynamic random access memory
  • SDRAM synchronous DRAM
  • SDRAM double data rate synchronous dynamic random access memory
  • ESDRAM enhanced synchronous dynamic random access memory
  • SLDRAM synchronous link dynamic random access memory
  • direct rambus RAM direct rambus RAM
  • the map generating apparatus may include a processor 1302 , a transceiver 1303 and a memory 1304 .
  • the memory 1304 is used for storing instructions
  • the processor 1302 is used for executing the instructions stored in the memory 1304, so as to realize the correlation of the map generating apparatus in any one or any of the corresponding methods shown in FIG. 1 to FIG. 5 above. Program.
  • the transceiver 1303 is used to obtain the requirement for generating a high-precision map.
  • the processor 1302 is configured to select a plurality of primitives that meet the requirements from the primitive library according to requirements, and the primitives are high-precision map fragments with classification labels; and generate a simulated high-precision map by splicing multiple primitives.
  • the processor 1302 is configured to segment the high-precision map segments conforming to the classification labels from the existing high-precision maps; and add the segmented high-precision map segments as primitives to the primitive library .
  • the processor 1302 is configured to segment the vector map segments conforming to the classification labels from the existing vector maps; obtain the vector map segments corresponding to the vector map segments by performing image detection on the satellite cloud images corresponding to the vector map segments Corresponding high-precision map information; using the high-precision map information to convert the vector map fragments into high-precision map fragments; and adding the high-precision map fragments obtained by the conversion as primitives into the primitive library.
  • the processor 1302 is specifically configured to: determine, according to requirements, at least one classification label required for generating a simulated high-precision map, and the number of primitives corresponding to each classification label in the at least one classification label; A plurality of primitives with at least one classification label are selected from the primitive library according to the primitive number.
  • the plurality of primitives include a first primitive and a second primitive, the first primitive includes a first road segment, and the second primitive includes a second road segment, the processor 1302 specifically uses In: generating a transition road segment between the first road segment and the second road segment, the transition road segment includes at least one transition lane, and the at least one transition lane is used to connect at least one first lane in the first road segment with the first road at least one second lane in the segment; establishing a link relationship between at least one first lane and at least one transition lane; establishing a link relationship between at least one second lane and at least one transition lane.
  • the processor 1302 is further configured to: determine at least one exit lane of at least one first lane; determine at least one entry lane of at least one second lane; at least one transition lane is used to connect at least one Exit lanes and at least one entry lane.
  • FIG. 7 is a schematic structural diagram of a map generating apparatus provided by an embodiment of the present application.
  • the map generating apparatus 1401 may include a communication interface 1403 , a processor 1402 and a memory 1404 .
  • the communication interface 1403 is used for inputting and/or outputting information; the processor 1402 is used for executing a computer program or instruction, so that the map generating device 1401 realizes the map generating device 1401 in the related scheme of the above-mentioned FIGS.
  • the communication interface 1403 can implement the solution implemented by the transceiver 1303 in FIG. 6, the processor 1402 can implement the solution implemented by the processor 1302 in FIG. 6, and the memory 1404 can implement the memory 1304 in FIG. 6.
  • the implemented solution will not be repeated here.
  • FIG. 8 is a schematic diagram of a map generating apparatus that can implement the method for generating a simulated map as shown in FIG. 1 according to an embodiment of the present application.
  • the map generating apparatus 1501 may be a network
  • the device on the device side and the device on the terminal device side can also be a chip or circuit, such as a chip or circuit of a device that can be provided on the network device side, or a chip or circuit of a device that can be provided on the terminal device side.
  • the obtaining unit 1503 is configured to obtain the requirement for generating a high-precision map.
  • the processing unit 1502 is configured to select a plurality of primitives that meet the requirements from the primitive library according to requirements, and the primitives are high-precision map fragments with classification labels; and generate a simulated high-precision map by splicing multiple primitives.
  • each unit in the above-mentioned map generating apparatus 1501 may refer to the implementation of the corresponding method embodiments, which will not be repeated here.
  • the above division of the units of the map generating apparatus is only a division of logical functions, and may be fully or partially integrated into a physical entity in actual implementation, or may be physically separated.
  • the obtaining unit 1503 may be implemented by the transceiver 1303 shown in FIG. 6 above, and the processing unit 1502 may be implemented by the processor 1302 shown in FIG. 6 above.
  • the present application also provides a computer program product, the computer program product includes: computer program code or instructions, when the computer program code or instructions are run on a computer, the computer is made to execute FIG. 1 To the method of any one of the embodiments shown in FIG. 5 .
  • the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores program codes, and when the program codes are run on a computer, the computer is made to execute FIG. 1 to FIG. 5 .
  • the present application further provides a chip system, where the chip system may include a processor.
  • the processor is coupled to the memory and can be used to execute the method of any one of the embodiments shown in FIGS. 1 to 5 .
  • the chip system further includes a memory. Memory, used to store computer programs (also called code, or instructions).
  • the processor is used to call and run the computer program from the memory, so that the device installed with the chip system executes the method of any one of the embodiments shown in FIG. 1 to FIG. 5 .
  • a computer program product includes one or more computer instructions.
  • the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device.
  • Computer instructions may be stored on or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server, or data center over a wire (e.g.
  • coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless means to transmit to another website site, computer, server or data center.
  • a computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, a data center, or the like that includes an integration of one or more available media.
  • Useful media may be magnetic media (eg, floppy disk, hard disk, magnetic tape), optical media (eg, high-density digital video disc (DVD)), or semiconductor media (eg, solid state disc (SSD)) )Wait.
  • the map generating device in the above-mentioned various device embodiments corresponds to the map generating device in the method embodiments, and corresponding steps are performed by corresponding modules or units, for example, the acquiring unit (transceiver) performs the receiving or sending steps in the method embodiments, except Steps other than sending and receiving can be performed by a processing unit (processor).
  • a processing unit for functions of specific units, reference may be made to corresponding method embodiments.
  • the number of processors may be one or more.
  • the disclosed system, apparatus and method may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of units is only a logical function division.
  • there may be other division methods for example, multiple units or components may be combined or integrated. to another system, or some features can be ignored, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • Units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Mathematical Physics (AREA)
  • Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Processing Or Creating Images (AREA)

Abstract

一种仿真高精度地图生成方法、装置(1301,1401,1501)和计算机可读存储介质,用于生成自动驾驶仿真系统中使用的仿真高精度地图。地图生成装置(1301,1401,1501)获取生成高精度地图的需求(S101)。根据需求,从基元库中选择满足需求的多个基元,基元为具有分类标签的高精度地图片段(S102)。通过拼接多个基元生成仿真高精度地图 (S103)。由于预先在基元库中存储多个基元,因此有需求的情况下可以从基元库中选择满足需求的多个基元,并对多个基元进行拼接从而生成仿真高精度地图,从而可以节省仿真高精度地图生成过程中的人力,且可以加快仿真高精度地图生成的速度,也可以降低仿真高精度地图的成本。

Description

仿真高精度地图生成方法、装置和计算机可读存储介质
相关申请的交叉引用
本申请要求在2021年02月09日提交中国专利局、申请号为202110176442.1、申请名称为“仿真高精度地图生成方法、装置和计算机可读存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及智能交通技术领域,尤其涉及一种仿真高精度地图生成方法、装置和计算机可读存储介质。
背景技术
自动驾驶仿真系统是研究自动驾驶的重要模块,可以通过自动驾驶仿真系统对自动驾驶软件进行开发和测试,如此,可以减少实车测试的开销和风险。
在真实的自动驾驶场景中,需要依赖于高精度地图(High Definition Map,HD Map)为自动驾驶车辆提供路段内车道级别规划和自车定位辅助。同样的,在自动驾驶仿真系统中也需要依赖高精度地图,以便使自动驾驶仿真系统具有模拟真实道路的能力,进而使自动驾驶仿真系统可以基于模拟的道路进行自动驾驶软件进行开发和测试。
为了获取自动驾驶仿真系统中使用的高精度地图,一种方式是可以向专业制图公司购买,但高精度地图造价高昂,该方式会加大自动驾驶的研究成本。另一种方式是通过实车采集数据,并根据采集的数据绘制地图。但是该方式耗时周期长,人力投入大,同样费时费力。
发明内容
本申请提供一种仿真高精度地图生成方法、装置和计算机可读存储介质,用于从基元库中选择出满足需求的多个基元,并对多个基元进行拼接从而生成仿真高精度地图,从而可以节省仿真高精度地图生成过程中的人力,且可以加快仿真高精度地图生成的速度,也可以降低仿真高精度地图的成本。
第一方面,本申请提供一种仿真高精度地图生成方法,该方法中获取生成高精度地图的需求。根据需求,从基元库中选择满足需求的多个基元,通过拼接多个基元生成仿真高精度地图。基元为具有分类标签的高精度地图片段。由于预先在基元库中存储多个基元,因此有需求的情况下可以从基元库中选择满足需求的多个基元,并对多个基元进行拼接从而生成仿真高精度地图,从而可以节省仿真高精度地图生成过程中的人力,且可以加快仿真高精度地图生成的速度,也可以降低仿真高精度地图的成本。
在一种可能地实施方式中,从已有的高精度地图中分割出符合分类标签的高精度地图片段;以及将通过分割得到的高精度地图片段作为基元加入基元库。已有的高精度地图可以是指现有的,且根据实际道路的采集数据得到的高精度地图。通过此方式获得的基元可以更加符合现实中的道路建造规范。
在另一种可能地实施方式中,从已有的矢量地图中分割出符合分类标签的矢量地图片段;通过对与矢量地图片段对应的卫星云图进行图像检测,获取与矢量地图片段对应的高精度地图信息;利用高精度地图信息将矢量地图片段转换为高精度地图片段;以及将通过转换得到的高精度地图片段作为基元加入基元库。由于基于卫星云图可以确定出矢量地图片段对应的车道级信息,从而确定出矢量地图片段对应的高精度地图片段。如此,可以增加获取基元的途径的多样性。
在一种可能地实施方式中,根据需求,从基元库中选择满足需求的多个基元包括:根据需求,确定生成仿真高精度地图需要的至少一个分类标签,以及至少一个分类标签中每个分类标签所对应的基元数量;根据基元数量从基元库中选择具有至少一个分类标签的多个基元。如此,可以使用户基于分类标签选择所需的基元,从而可以简化用户的操作,可以提高仿真高精度地图生成过程的便利性,可以有助于该方案的推广使用。另一方面,由于用户还可以输入基元的数量,如此提高用户输入需要的便利性,且在需要大量同一种基元的情况下,通过输入数量的方式输入需求,可以简化用户的操作。
为了提高方案的灵活性,在一种可能地实施方式中,针对至少一个分类标签中的一个分类标签,在根据需求确定生成仿真高精度地图需要的分类标签对应的基元数量大于1的情况下:根据基元数量从基元库中选择具有至少一个分类标签的多个基元,包括:根据基元数量,随机从基元库中选择具有分类标签的多个基元。
另一种可能地实施方式中,针对至少一个分类标签中的一个分类标签,在根据需求确定生成仿真高精度地图需要的分类标签对应的基元数量大于1的情况下:根据基元数量从基元库中选择具有至少一个分类标签的多个基元,包括:根据基元数量,通过有放回抽样从基元库中选择具有分类标签的多个基元。通过有放回抽样选择基元,多个基元中的可以包括属于基元库中同一个基元的两个基元,从而当一个分类标签中存储的基元的数量小于所需的数量时,仍然可以选择出满足所需数量的基元。
在一种可能地实施方式中,多个基元包括第一基元和第二基元,第一基元包括第一道路片段,第二基元包括第二道路片段,通过拼接多个基元生成仿真高精度地图包括:生成第一道路片段和第二道路片段之间的过渡道路片段,过渡道路片段包括至少一个过渡车道,至少一个过渡车道用于连接第一道路片段中的至少一个第一车道与第一道路片段中的至少一个第二车道;建立至少一个第一车道与至少一个过渡车道的链接关系;建立至少一个第二车道与至少一个过渡车道的链接关系。由于通过过渡道路片段对两个基元进行拼接,因此当两个基元的车道或行驶方向有些出入时,也可以实现两个基元的拼接。
在一种可能地实施方式中,通过拼接多个基元生成仿真高精度地图,还包括:确定至少一个第一车道的至少一个出口车道;确定至少一个第二车道的至少一个入口车道;至少一个过渡车道用于连接至少一个出口车道与至少一个入口车道。如此,可以使拼接后的仿真高精度地图上车道信息相匹配,从而为仿真车辆在仿真高精度地图上运行奠定基础。
在一种可能地实施方式中,至少一个出口车道的数量与至少一个入口车道的数量不相同,过渡道路片段包括用于将两条车道并入一条车道的车道片段。如此,可以通过过渡道路片段将车道数量不同的两个道路片段进行拼接。
在一种可能地实施方式中,至少一个出口车道的朝向与至少一个入口车道的朝向不同,至少一个过渡车道包括曲线车道。如此,可以通过过渡道路片段将车道朝向不同的两个道路片段进行拼接。
在一种可能地实施方式中,分类标签用于标识高精度地图片段的以下内容中的至少一项:高精度地图片段中道路的几何拓扑信息;高精度地图片段中车道的用途信息;或,高精度地图片段中场地的类型信息。如此,可以使用户基于所设置的分类标签获取仿真环境下通常会使用到的一些基元,这种设置分类标签的方式可以更加匹配自动驾驶仿真领域的实际需求。
在一种可能地实施方式中,几何拓扑信息包括:弯道、直道、环岛、十字路口、丁字路口、L型路口、U型路口或匝道中的至少一项。在一种可能地实施方式中,车道的用途信息包括:公交专用道、人行横道、自行车专用道、快速路、临时停车道或紧急停车道中的至少一项。在一种可能地实施方式中,场地的类型信息包括:城市道路、高速道路、停车场中的至少一项。这种设置分类标签的方式可以更加匹配自动驾驶仿真领域的实际需求。
相应于第一方面中的仿真高精度地图生成方法,本申请还提供了一种地图生成装置。地图生成装置可以为通信芯片、终端设备侧设备、或者网络设备侧设备。比如,地图生成装置可以为用于网络设备的芯片;再比如,可以作为可用于终端设备的芯片。
第二方面,提供了一种地图生成装置,包括获取单元和处理单元,以执行上述第一方面中的任一种实施方式。获取单元用于执行与发送和接收相关的功能。可选地,获取单元包括接收单元和发送单元。在一种设计中,地图生成装置为通信芯片,获取单元可以为芯片的输入输出电路或者端口。
在另一种设计中,获取单元可以为发射器和接收器,或者获取单元为发射机和接收机。
可选的,地图生成装置还包括可用于执行上述第一方面中任一种实施方式的各个模块。
第三方面,提供了一种地图生成装置,该地图生成装置为上述终端设备或网络设备。包括处理器和存储器。可选的,还包括收发器,该存储器用于存储计算机程序或指令,该处理器用于从存储器中调用并运行该计算机程序或指令,当处理器执行存储器中的计算机程序或指令时,使得该地图生成装置执行上述第一方面中的任一种实施方式。
可选的,处理器为一个或多个,存储器为一个或多个。
可选的,存储器可以与处理器集成在一起,或者存储器与处理器分离设置。
可选的,收发器中可以包括,发射机(发射器)和接收机(接收器)。
第四方面,提供了一种地图生成装置,包括处理器。该处理器与存储器耦合,可用于执行第一方面中任一种可能实现方式中的方法。可选地,该地图生成装置还包括存储器。可选地,该地图生成装置还包括通信接口,处理器与通信接口耦合。
在一种实现方式中,该地图生成装置为终端设备。当该地图生成装置为终端设备时,通信接口可以是收发器,或,输入/输出接口。可选地,收发器可以为收发电路。可选地,输入/输出接口可以为输入/输出电路。
在另一种实现方式中,该地图生成装置为网络设备。当该地图生成装置为网络设备时,通信接口可以是收发器,或,输入/输出接口。可选地,收发器可以为收发电路。可选地,输入/输出接口可以为输入/输出电路。
在又一种实现方式中,该地图生成装置为芯片或芯片系统。当该地图生成装置为芯片或芯片系统时,通信接口可以是该芯片或芯片系统上的输入/输出接口、接口电路、输出电路、输入电路、管脚或相关电路等。处理器也可以体现为处理电路或逻辑电路。
第五方面,提供了一种计算机程序产品,计算机程序产品包括:计算机程序(也可以 称为代码,或指令),当计算机程序被运行时,使得计算机执行上述第一方面中任一种可能实现方式中的方法。
第六方面,提供了一种计算机可读存储介质,计算机可读介质存储有计算机程序(也可以称为代码,或指令)当其在计算机上运行时,使得计算机执行上述第一方面中任一种可能实现方式中的方法。
第七方面,提供了一种芯片系统,该芯片系统可以包括处理器。该处理器与存储器耦合,可用于执行第一方面中任一方面。可选地,该芯片系统还包括存储器。存储器,用于存储计算机程序(也可以称为代码,或指令)。处理器,用于从存储器调用并运行计算机程序,使得安装有芯片系统的设备执行第一方面中任一种可能实现方式中的方法。
附图说明
图1为本申请实施例提供一种仿真高精度地图生成方法的流程示意图;
图2为本申请实施例提供一种分类标签设置的示意图;
图3为本申请实施例提供一种第一基元和第二基元进行拼接的结构示意图;
图4为本申请实施例提供一种可能地的第一基元和第二基元拼接的示意图;
图5为本申请实施例提供又一种可能地的第一基元和第二基元拼接的示意图;
图6为本申请实施例提供的一种地图生成装置的结构示意图;
图7为本申请实施例提供的另一种地图生成装置的结构示意图;
图8为本申请实施例提供的另一种地图生成装置的结构示意图。
具体实施方式
下面将结合附图,对本申请实施例进行详细描述。
首先,对本申请实施例的应用场景进行介绍。本申请实施例提供一种仿真高精度地图的生成方法,通过该方法生成的仿真高精度地图可以应用于自动驾驶仿真系统。自动驾驶仿真系统中的车辆可以基于仿真高精度地图实现交通业务。本申请实施例交通业务可以是各种自动驾驶、辅助驾驶的业务,例如:路径规划、为人工驾驶提供行驶风险预警。以上交通业务仅是举例。在自动驾驶仿真系统中,本申请实施例提供的仿真高精度地图也可以为车辆与其他装置的通讯(vehicle to everything,V2X)提供技术准备,如车车通讯(vehicle to vehicle,V2V)、车路通讯(vehicle to installation,V2I)。
本申请实施例提供的高精度地图的生成方法可以由地图生成装置来执行,地图生成装置可以为网络侧设备或者终端设备,也可以为网络侧设备内部的芯片或者终端设备内部的芯片。该网络侧设备包括计算平台或服务器,计算平台和服务器的具体部署形态本申请不做限定,比如可以是云端部署,还可以是独立的计算机设备或芯片等。该终端设备包括具有支持科学运算的硬件设备,例如可以包括如个人计算机、服务器、手机移动终端、嵌入式设备等。
基于上述内容,图1示例性示出了本申请实施例提供一种仿真高精度地图生成方法的流程示意图,如图1所示,该方法包括:
S101,地图生成装置获取生成高精度地图的需求。
一种可能地实施方式中,用户可以输入需求,该需求的格式不限定,比如可以是表格、程序段、一段文字、文件、语音等等。
S102,地图生成装置根据需求,从基元库中选择满足需求的多个基元,基元为具有分类标签的高精度地图片段。
一种可能地实施方式中,一个基元也可以理解为一段高精度地图片段对应的高精度地图文件。
S103,地图生成装置通过拼接多个基元生成仿真高精度地图。
由于预先在基元库中存储多个基元,因此有需求的情况下可以从基元库中选择满足需求的多个基元,并对多个基元进行拼接从而生成仿真高精度地图,从而可以节省仿真高精度地图生成过程中的人力,且可以加快仿真高精度地图生成的速度,也可以降低仿真高精度地图的成本。
下面介绍几种可能的获取基元库中基元的方式。
方式一,根据已有的高精度地图获取基元。
高精度地图包括道路级的信息和车道级的信息。其中,车道级信息用于指示路网环境中的车道的信息,例如,车道曲率、车道航向、车道中轴线、车道宽度、车道标线、车道限速、车道分割以及车道合并等信息。另外,车道之间的车道线情况(虚线、实线、单线和双线)、车道线颜色(白色、黄色)、道路隔离带、隔离带材质、道路箭头、文字内容和所在位置等也都可以包括在车道级信息中。
具体来说,可以从已有的高精度地图中分割出符合分类标签的高精度地图片段,将通过分割得到的高精度地图片段(高精度地图片段也可以理解为高精度地图片段的文件)作为基元加入基元库。已有的高精度地图可以是指现有的,且根据实际道路的采集数据得到的高精度地图。
举个例子,一个分类标识为“十字路口”,对已有的高精度地图进行检测,将包括有“十字路口”的一个或多个高精度地图片段切割,将得到的高精度地图片段其作为基元,加入基元库。
方式二,根据已有的矢量地图和卫星云图获取基元。
矢量地图,比如开源矢量地图,包括道路级的信息。其中,道路级的信息可以为用户提供导航信息,满足开车路线的导航需求。例如,道路级的信息可以包括:当前道路的车道数量、当前道路的限速信息、转弯信息。
本申请实施例中的卫星云可以理解为卫星地图,通过卫星云可以识别车道级信息,例如车道宽度、车道数量、车道行驶方向、车道用途信息等。因此基于卫星云图可以确定出矢量地图片段对应的车道级信息,从而确定出矢量地图片段对应的高精度地图片段。
一种可能地实施方式中,可以从已有的矢量地图中分割出符合分类标签的矢量地图片段。通过对与矢量地图片段对应的卫星云图进行图像检测,获取与矢量地图片段对应的高精度地图信息。利用高精度地图信息将矢量地图片段转换为高精度地图片段;以及将通过转换得到的高精度地图片段作为基元加入基元库。
本申请实施例中的分类标签用于标识高精度地图片段的以下内容中的至少一项:
参数项a1:高精度地图片段中场地的类型信息;
参数项a2:高精度地图片段中道路的几何拓扑信息;或,
参数项a3:高精度地图片段中车道的用途信息。
下面对各个参数项分别进行介绍。
参数项a1:分类标签用于标识高精度地图片段中场地的类型信息。
一种可能地实施方式中,场地的类型信息可以包括几种预设的类型,比如:城市道路、高速道路和停车场。可以根据高精度地图片段中场地的类型信息为其添加分类标签。
举个例子,一个高精度地图片段中包括停车场,则该高精度地图片段的分类标签包括停车场。再举个例子,一个高精度地图片段中的道路属于高速道路,则该高精度地图片段的分类标签包括高速道路。
参数项a2:分类标签用于标识高精度地图片段中道路的几何拓扑信息。
几何元素之间可以由两种重要的信息表示。一是几何信息,另一是拓扑信息。几何信息,是指一个物体在三维欧氏空间中的位置信息。几何信息反映物体的大小和位置,例如顶点的坐标值、曲面数学表达式中的具体系数等。拓扑信息,是指物体的拓扑元素(顶点Vertex、边Edge和表面Face)的个数、类型以及它们之间的相互关系信息。
本申请实施例中高精度地图片段中道路的几何拓扑信息可以包括:弯道、直道、环岛、十字路口、丁字路口、L型路口、U型路口或匝道中的至少一项。
道路的几何拓扑信息为“弯道”,则该道路为具有一定曲率的弧形。
道路的几何拓扑信息为“直道”,则该道路的几何形状为直线形。
道路的几何拓扑信息为“环岛”,则该道路的几何形状为圆形,且该路段r6中环岛具有出口和入口。
道路的几何拓扑信息为“丁字路口”,则该道路的几何形状为丁字形。
道路的几何拓扑信息为“十字路口”,则该道路的几何形状为十字形。
道路的几何拓扑信息为“L型路口”,则该道路的几何形状为L形。
道路的几何拓扑信息为“U型路口”,则该道路的几何形状为U形。
一种可能地实施方式中,可以将用于标识高精度地图片段中场地的类型信息的分类标签称为一级分类标签,将用于标识高精度地图片段中道路的几何拓扑信息称为二级分类标签。
图2示例性示出了分类标签设置的示意图,如图2所示,比如可以设置3个一级分类标签,分别为:“城市道路”、“高速道路”和“停车场”。在一级分类标签下可以设置二级分类标签,比如一级分类标签“城市道路”下的二级分类标签可以包括以下内容中的至少一项:弯道、直道、环岛、十字路口、丁字路口、L型路口、U型路口或匝道中的至少一项。
再比如,一级分类标签“高速道路”下的二级分类标签可以包括以下内容中的至少一项:弯道、直道或匝道。
一个高精度地图片段可以对应一个一级分类标签,比如分类标签为停车场的一个高精度地图片段。一个高精度地图片段也可以对应一个一级分类标签和至少一个二级分类标签,比如一个高精度地图片段中的道路为城市道路下的直道,则该高精度地图片段的分类标签可以包括:城市道路和直道。
一种可能地实施方式中,可以在二级标签下设置一个或多个三级标签,三级标签可以为能够标识出几何拓扑信息的关键参数项。下面列举几种三级分类标识的示例:
比如二级分类标签“弯道”对应的三级分类标签可以为:曲率,继而可以在二级分类标签“弯道”下存储多个不同曲率的弯道对应的高精度地图片段。
比如二级分类标签“环岛”对应的三级分类标签可以为:环岛的半径,继而可以在二级分类标签“环岛”下存储多个不同半径的环岛对应的高精度地图片段。
比如二级分类标签“U型路口”对应的三级分类标签可以为:U型路口的开口尺寸,继而可以在二级分类标签“U型路口”下存储多个不同开口尺寸的U型路口对应的高精度地图片段。
比如二级分类标签“匝道”对应的三级分类标签可以为:匝道的类型,继而可以在二级分类标签“匝道”下存储多个不同类型的匝道对应高精度地图片段。
匝道的类型可以包括以下内容中的至少一项:
进口、出口匝道:进出主干线的附属接驳路段,可以是“平交匝道”,或是“立交匝道”。
上、下匝道:进出高架道路,向上或向下行车的附属接驳斜道,通常为“立交匝道”。
直接式匝道(Directional Ramp/Road):将右转车道设于右方。
非直接式匝道(Non-directional Ramp/Road):将左转车道设于右方,设置环道(loop)衔接其他公路。
半直接式匝道(Semi-Directional Ramp/Road):与非直接式匝道相似,但不用环道,改以路线较长、起伏较大的高架道路作为连接匝道。
回转匝道(U-Turn Ramp/Road):U型转向的匝道。
注:以上名词以靠右行驶的道路设计为基础。
需要说明的是,一个三级分类标签下对应的高精度地图片段可以为一个,也可以为多个,比如同一个曲率对应的高精度地图片段可以为一个,也可以为多个,本申请实施例不做限制。
参数项a3:分类标签用于标识高精度地图片段中车道的用途信息。
车道的用途信息可以包括:公交专用道、人行横道、自行车专用道、快速路、临时停车道或紧急停车道中的至少一项。
车道的用途信息也可以称为二级分类标签,一个高精度地图片段可以包括一个或多个二级分类标签。比如,一个高精度地图片段中的道路为直道,且该高精度地图片段的道路中有一个车道为公交专用道,则该高精度地图片段的分类标签可以包括:直道和公交专用道。当该高精度地图片段的道路为城市道路,则该高精度地图片段的分类标签还可以包括城市道路。
当一个车道的用途信息为“公交专用道”,则该车道主要供公交车行驶,具体来说,可以是全时段仅供公交车行驶,也可以是在指定的时间段内(比如早高峰和晚高峰的时间段)仅供公交车行驶。
当一个车道的用途信息为“自行车专用道”,则该车道仅可以使自行车进行行驶。
当一个车道的用途信息为“快速路”,则该车道对于车辆的行驶速度有要求,比如在该车道行驶的车辆的行驶速度需不低于每小时80公里。
当一个车道的用途信息为“人行横道”,则该车道为供行人通行的车道。
当一个车道的用途信息为“应急车道”,则该车道仅可以应急使用,比如可以使交通警察的车辆行驶,以便快速处理道路上的各种交通事故。
当一个车道的用途信息为“临时停车道”,则该车道仅可以临时停车使用,不可以长时间停车占用。
本申请实施例中,上述分类标签项仅仅是示例,在实际应用中还可以根据高精度地图 片段中的道路信息设置其他分类标签项,比如可以将以下内容中的至少一项也设置为分类标签项:车道限高、车道最高限速、有无电子眼、车道受限方向、受限方向的禁用时间段、车道受限车辆类型、和受限车辆的禁用时间段等。
一种可能地实施方式中,上述S102中,地图生成装置可以根据需求,确定生成仿真高精度地图需要的至少一个分类标签,以及至少一个分类标签中每个分类标签所对应的基元数量。根据基元数量从基元库中选择具有至少一个分类标签的多个基元。
举个例子,需求可以是用户输入的一段程序,如下所示:
Figure PCTCN2021132775-appb-000001
在该示例中,可以确定出生成仿真高精度地图所需的分类标签包括:1个环岛和1个十字路口。在该示例中包括有每个分类标签对应的基元数量。
针对至少一个分类标签下的一个分类标签,当需从基元库中选择的该分类标签的基元的数量等于1时,可以随机的从基元库中选择出满足该分类标签的基元。而当需从基元库中选择的该分类标签的基元的数量大于1时,比如可以随机选择。
再比如,可以通过有放回抽样方式,从基元库中选择出满足该分类标签的多个基元。“有放回抽样的方式”是简单随机抽样的操作方式之一。把总体中的抽样单位从1至K编号,每抽取一个号码后再将它放回总体。对于任意一次抽取而言,由于总体容量不变,所以K个号码被抽中的机会均等。
举个例子,比如需要选择的基元的分类标签为“环岛”,分类标签为“环岛”对应的基元数量为“2”,则可以先从基元库的分类标签“环岛”对应的所有基元中抽取一个基元,之后再从基元库的分类标签“环岛”对应的所有基元中再抽取一个基元。通过又放回抽样选择出的两个基元可能是同一个,也有可能是不同的两个基元。
本申请实施例中,S103中对选择出的多个基元进行拼接时,多个基元的拼接顺序可以是随机产生的,也可以是由用户指定的,比如获取的需求中包括用于指示多个基元中至少两个基元的拼接顺序的指示信息。
针对多个基元中的两个基元,对两个基元进行拼接的方式有多种,下面分别进行介绍。为了后续内容介绍清楚,下面以多个基元中的第一基元和第二基元为例进行介绍。其中,第一基元包括第一道路片段,第二基元包括第二道路片段。
方式一,无需生成过渡道路片段。
若第一道路片段包括的车道数量和第二道路片段的车道数量相同,且车道朝向(也可 以称为车道行驶方向)一致,则可以将第一道路片段和第二道路片段拼接。
图3示例性示出了一种对第一基元和第二基元进行拼接的结构示意图,如图3中的(a)示出了环岛301(环岛301可以为第一基元)的示意图,图3中的(b)示出了十字路口302(十字路口302可以为第二基元),图3中的(c)示出了地图生成装置对第一基元和第二基元进行拼接后,得到的仿真高精度地图的示意图。如图3所示,可以根据高精度地图片段中车道的行驶方向对第一道路片段和第二道路片段进行拼接,无需生成过渡道路片段。
若第一道路片段的至少一个第一车道中所有车道的行驶方向相同,且第二道路片段的至少一个第二车道中所有车道的行驶方向相同,则可以将第一道路片段中的出口车道与第二道路片段中的入口车道拼接。
又一种可能地实施方式中,若第一道路片段中存在两个第一车道,该两个第一车道朝向不同,且第二道路片段中存在两个第二车道,该两个第二车道朝向不同。则将第一道路片段中的出口车道与第二道路片段中的入口车道拼接,且将第一道路片段中的入口车道与第二道路片段中的出口车道拼接。
方式二,需生成过渡道路片段。
地图生成装置可以生成第一道路片段和第二道路片段之间的过渡道路片段。
过渡道路片段包括至少一个过渡车道,至少一个过渡车道用于连接第一道路片段中的至少一个第一车道与第一道路片段中的至少一个第二车道。建立至少一个第一车道与至少一个过渡车道的链接关系。建立至少一个第二车道与至少一个过渡车道的链接关系。
具体来说,地图生成装置可以确定至少一个第一车道的至少一个出口车道。确定至少一个第二车道的至少一个入口车道。至少一个过渡车道用于连接至少一个出口车道与至少一个入口车道。
根据第一道路片段的出口车道的数量和车道朝向、第二道路片段的入口车道的数量和车道朝向生成过渡道路片段。下面列举几种可能地示例。
示例一,第一道路片段的出口车道的数量和第二道路片段的入口车道的数量不相同,则过渡道路片段包括用于将多条(比如两条)车道并入一条车道的车道片段。
图4示例性示出了一种可能地的对第一基元和第二基元进行拼接的结构示意图,如图4所示,需要进行拼接的两个基元分别为图4中的(a)所示的第二基元401,以及图4中的(b)所示的第一基元402。其中,第二基元401为双车道,第一基元402为单车道。可以根据第二基元401的车道信息确定出第二基元401的入口车道处,且根据第一基元402的车道信息确定出第一基元402的出口车道处。在第二基元401和第一基元402之间生成如图4中的(c)所示的过渡道路片段403,过渡道路片段403一端与第一基元402的出口车道连接,另一端与第二基元401的入口车道连接,用于负责解决车道数目变更的过渡(车道数目增多/数目变少)。
示例二,一种可能地实施方式中,第一道路片段的至少一个出口车道的朝向与第二道路片段的至少一个入口车道的朝向不同,则过渡道路片段中的至少一个过渡车道包括曲线车道。
车道的朝向可以理解为车道行驶方向。图5示例性示出了又一种可能地的第一基元和第二基元拼接的示意图,如图5所示,需要进行拼接的两个基元分别为图5中的(a)所示的第二基元501,以及图5中的(b)所示的第一基元502。其中,第二基元501的车辆行驶方向与第一基元502的车辆行驶方向相差90度,则生成过渡道路片段中的过渡车道(一 段曲线),如图5中的(c)所示的过渡道路片段503用于连接第二基元501和第一基元502。
由于在自动驾驶仿真领域,对高精度地图的需求量巨大,如果依赖购买或人工标注等方式生成高精度地图,不仅成本高、周期长而且效率很低。因此对于能够快速地自动化生成仿真用虚拟高精度地图的技术有着强烈需求。而本申请实施例提供的高精度地图的生成方法可以构建出满足仿真测试要求的大量高精度地图,并且具有覆盖面广、路况丰富的特性,且可以较为容易的覆盖全仿真测试需求。
另一方面,由于本申请实施例中地图库中所存储的路段均是从已有的地图上截取的,即来源于真是的路况,因此本申请实施例中生成的高精度地图符合现实中道路建造规范,具备合理性。且相对真实高精度地图,无需实地测绘,降低了人力成本,提高了生成效率,精度相对较低,且不与现实道路同步,在满足仿真测试要求的前提下可以大量的生成,以满足对仿真地图的数量的需求。相较于已有的获取高精度地图的方式,在速度和效率上大幅领先。进一步,本申请实施例中还可以根据用户意图,自动化生成用户定制的高精度地图,从而更匹配仿真需求。
需要说明的是,本申请实施例提供的方案并不局限于仿真用虚拟高精度地图的生成,可以应用于其他仿真场景的生成,生成过程与之类似,不再赘述。
本申请实施例中的“至少一个”是指一个或者多个,“多个”是指两个或两个以上。“和/或”,描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B的情况,其中A,B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。“以下至少一项(个)”或其类似表达,是指的这些项中的任意组合,包括单项(个)或复数项(个)的任意组合。例如,a,b,或c中的至少一项(个),可以表示:a,b,c,a-b,a-c,b-c,或a-b-c,其中a,b,c可以是单个,也可以是多个。
以及,除非有特别说明,本申请实施例提及“第一”、“第二”等序数词是用于对多个对象进行区分,不用于限定多个对象的顺序、时序、优先级或者重要程度。例如,第一数据类型和第二数据类型,只是为了区分不同的数据类型,而并不是表示这两个数据类型的优先级或者重要程度等的不同。
需要说明的是,上述各个消息的名称仅仅是作为示例,随着通信技术的演变,上述任意消息均可能改变其名称,但不管其名称如何发生变化,只要其含义与本申请上述消息的含义相同,则均落入本申请的保护范围之内。
上述主要从各个网元之间交互的角度对本申请提供的方案进行了介绍。可以理解的是,上述实现各网元为了实现上述功能,其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到,结合本文中所公开的实施例描述的各示例的单元及算法步骤,本发明能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本发明的范围。
根据前述方法,图6为本申请实施例提供可执行如图1所示仿真地图生成方法的地图生成装置的结构示意图,如图6所示,该地图生成装置可以为网络设备侧的设备、终端设备侧的设备,也可以为芯片或电路,比如可设置于网络设备侧的芯片或电路,再比如可设 置于终端设备侧的芯片或电路。
进一步的,该地图生成装置1301还可以进一步包括总线系统,其中,处理器1302、存储器1304、收发器1303可以通过总线系统相连。
应理解,上述处理器1302可以是一个芯片。例如,该处理器1302可以是现场可编程门阵列(field programmable gate array,FPGA),可以是专用集成芯片(application specific integrated circuit,ASIC),还可以是系统芯片(system on chip,SoC),还可以是中央处理器(central processor unit,CPU),还可以是网络处理器(network processor,NP),还可以是数字信号处理电路(digital signal processor,DSP),还可以是微控制器(micro controller unit,MCU),还可以是可编程控制器(programmable logic device,PLD)或其他集成芯片。
在实现过程中,上述方法的各步骤可以通过处理器1302中的硬件的集成逻辑电路或者软件形式的指令完成。结合本申请实施例所公开的方法的步骤可以直接体现为硬件处理器执行完成,或者用处理器1302中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器,闪存、只读存储器,可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器1304,处理器1302读取存储器1304中的信息,结合其硬件完成上述方法的步骤。
应注意,本申请实施例中的处理器1302可以是一种集成电路芯片,具有信号的处理能力。在实现过程中,上述方法实施例的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器可以是通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成,或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器,闪存、只读存储器,可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器,处理器读取存储器中的信息,结合其硬件完成上述方法的步骤。
可以理解,本申请实施例中的存储器1304可以是易失性存储器或非易失性存储器,或可包括易失性和非易失性存储器两者。其中,非易失性存储器可以是只读存储器(read-only memory,ROM)、可编程只读存储器(programmable ROM,PROM)、可擦除可编程只读存储器(erasable PROM,EPROM)、电可擦除可编程只读存储器(electrically EPROM,EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory,RAM),其用作外部高速缓存。通过示例性但不是限制性说明,许多形式的RAM可用,例如静态随机存取存储器(static RAM,SRAM)、动态随机存取存储器(dynamic RAM,DRAM)、同步动态随机存取存储器(synchronous DRAM,SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM,DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM,ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM,SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM,DR RAM)。应注意,本文描述的系统和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
该地图生成装置可以包括处理器1302、收发器1303和存储器1304。该存储器1304用于存储指令,该处理器1302用于执行该存储器1304存储的指令,以实现如上图1至图 5中所示的任一项或任多项对应的方法中地图生成装置的相关方案。
一种可能的实施方式中,收发器1303用于获取生成高精度地图的需求。处理器1302,用于根据需求,从基元库中选择满足需求的多个基元,基元为具有分类标签的高精度地图片段;通过拼接多个基元生成仿真高精度地图。
在一种可能地实施方式中,处理器1302用于从已有的高精度地图中分割出符合分类标签的高精度地图片段;以及将通过分割得到的高精度地图片段作为基元加入基元库。
在一种可能地实施方式中,处理器1302用于从已有的矢量地图中分割出符合分类标签的矢量地图片段;通过对与矢量地图片段对应的卫星云图进行图像检测,获取与矢量地图片段对应的高精度地图信息;利用高精度地图信息将矢量地图片段转换为高精度地图片段;以及将通过转换得到的高精度地图片段作为基元加入基元库。
在一种可能地实施方式中,处理器1302,具体用于:根据需求,确定生成仿真高精度地图需要的至少一个分类标签,以及至少一个分类标签中每个分类标签所对应的基元数量;根据基元数量从基元库中选择具有至少一个分类标签的多个基元。
在一种可能地实施方式中,多个基元包括第一基元和第二基元,第一基元包括第一道路片段,第二基元包括第二道路片段,处理器1302,具体用于:生成第一道路片段和第二道路片段之间的过渡道路片段,过渡道路片段包括至少一个过渡车道,至少一个过渡车道用于连接第一道路片段中的至少一个第一车道与第一道路片段中的至少一个第二车道;建立至少一个第一车道与至少一个过渡车道的链接关系;建立至少一个第二车道与至少一个过渡车道的链接关系。
在一种可能地实施方式中,处理器1302,还用于:确定至少一个第一车道的至少一个出口车道;确定至少一个第二车道的至少一个入口车道;至少一个过渡车道用于连接至少一个出口车道与至少一个入口车道。
相关其他描述可以参见前述方法实施例的内容,在此不再赘述。该地图生成装置所涉及的与本申请实施例提供的技术方案相关的概念,解释和详细说明及其他步骤请参见前述方法或其他实施例中关于这些内容的描述,此处不做赘述。
根据前述方法,图7为本申请实施例提供的地图生成装置的结构示意图,如图7所示,地图生成装置1401可以包括通信接口1403、处理器1402和存储器1404。通信接口1403,用于输入和/或输出信息;处理器1402,用于执行计算机程序或指令,使得地图生成装置1401实现上述图1至图5的相关方案中地图生成装置1401实现上述图1至图5的相关方案中地图生成装置侧的方法。本申请实施例中,通信接口1403可以实现上述图6的收发器1303所实现的方案,处理器1402可以实现上述图6的处理器1302所实现的方案,存储器1404可以实现上述图6的存储器1304所实现的方案,在此不再赘述。
基于以上实施例以及相同构思,图8为本申请实施例提供的可实现如图1所示的仿真地图生成方法的地图生成装置的示意图,如图8所示,该地图生成装置1501可以为网络设备侧的设备、终端设备侧的设备,也可以为芯片或电路,比如可设置于网络设备侧的设备的芯片或电路,再比如可设置于终端设备侧的设备的芯片或电路。
获取单元1503,用于获取生成高精度地图的需求。处理单元1502,用于根据需求,从基元库中选择满足需求的多个基元,基元为具有分类标签的高精度地图片段;通过拼接多个基元生成仿真高精度地图。
该地图生成装置所涉及的与本申请实施例提供的技术方案相关的概念,解释和详细说 明及其他步骤请参见前述方法或其他实施例中关于这些内容的描述,此处不做赘述。
可以理解的是,上述地图生成装置1501中各个单元的功能可以参考相应方法实施例的实现,此处不再赘述。
应理解,以上地图生成装置的单元的划分仅仅是一种逻辑功能的划分,实际实现时可以全部或部分集成到一个物理实体上,也可以物理上分开。本申请实施例中,获取单元1503可以由上述图6的收发器1303实现,处理单元1502可以由上述图6的处理器1302实现。
根据本申请实施例提供的方法,本申请还提供一种计算机程序产品,该计算机程序产品包括:计算机程序代码或指令,当该计算机程序代码或指令在计算机上运行时,使得该计算机执行图1至图5所示实施例中任意一个实施例的方法。
根据本申请实施例提供的方法,本申请还提供一种计算机可读存储介质,该计算机可读介质存储有程序代码,当该程序代码在计算机上运行时,使得该计算机执行图1至图5所示实施例中任意一个实施例的方法。
根据本申请实施例提供的方法,本申请还提供一种芯片系统,该芯片系统可以包括处理器。该处理器与存储器耦合,可用于执行图1至图5所示实施例中任意一个实施例的方法。可选地,该芯片系统还包括存储器。存储器,用于存储计算机程序(也可以称为代码,或指令)。处理器,用于从存储器调用并运行计算机程序,使得安装有芯片系统的设备执行图1至图5所示实施例中任意一个实施例的方法。
在上述实施例中,可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时,可以全部或部分地以计算机程序产品的形式实现。计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行计算机指令时,全部或部分地产生按照本申请实施例的流程或功能。计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。计算机指令可以存储在计算机可读存储介质中,或者从一个计算机可读存储介质向另一个计算机可读存储介质传输,例如,计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line,DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。可用介质可以是磁性介质(例如,软盘、硬盘、磁带)、光介质(例如,高密度数字视频光盘(digital video disc,DVD))、或者半导体介质(例如,固态硬盘(solid state disc,SSD))等。
需要指出的是,本专利申请文件的一部分包含受著作权保护的内容。除了对专利局的专利文件或记录的专利文档内容制作副本以外,著作权人保留著作权。
上述各个装置实施例中地图生成装置和方法实施例中的地图生成装置对应,由相应的模块或单元执行相应的步骤,例如获取单元(收发器)执行方法实施例中接收或发送的步骤,除发送、接收外的其它步骤可以由处理单元(处理器)执行。具体单元的功能可以参考相应的方法实施例。其中,处理器可以为一个或多个。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统、装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露的系统、装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以 结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。
以上,仅为本申请的具体实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应以权利要求的保护范围为准。

Claims (22)

  1. 一种仿真高精度地图生成方法,其特征在于,包括:
    获取生成高精度地图的需求;
    根据所述需求,从基元库中选择满足所述需求的多个基元,所述基元为具有分类标签的高精度地图片段;
    通过拼接所述多个基元生成所述仿真高精度地图。
  2. 如权利要求1所述的方法,其特征在于,所述基元库中的基元是通过方式一或者方式二中的至少一种得到的;
    所述方式一包括:
    从已有的高精度地图中分割出符合所述分类标签的高精度地图片段;以及
    将通过所述分割得到的高精度地图片段作为基元加入所述基元库;
    所述方式二包括:
    从已有的矢量地图中分割出符合所述分类标签的矢量地图片段;
    通过对与所述矢量地图片段对应的卫星云图进行图像检测,获取与所述矢量地图片段对应的高精度地图信息;
    利用所述高精度地图信息将所述矢量地图片段转换为高精度地图片段;以及
    将通过所述转换得到的高精度地图片段作为基元加入所述基元库。
  3. 如权利要求1或2所述的方法,其特征在于,所述根据所述需求,从基元库中选择满足所述需求的多个基元包括:
    根据所述需求,确定生成所述仿真高精度地图需要的至少一个分类标签,以及所述至少一个分类标签中每个分类标签所对应的基元数量;
    根据所述基元数量从所述基元库中选择具有所述至少一个分类标签的所述多个基元。
  4. 如权利要求1-3任一项所述的方法,其特征在于,所述多个基元包括第一基元和第二基元,所述第一基元包括第一道路片段,所述第二基元包括第二道路片段,所述通过拼接所述多个基元生成所述仿真高精度地图包括:
    生成所述第一道路片段和所述第二道路片段之间的过渡道路片段,所述过渡道路片段包括至少一个过渡车道,所述至少一个过渡车道用于连接所述第一道路片段中的至少一个第一车道与所述第一道路片段中的至少一个第二车道;
    建立所述至少一个第一车道与所述至少一个过渡车道的链接关系;
    建立所述至少一个第二车道与所述至少一个过渡车道的链接关系。
  5. 如权利要求4所述的方法,其特征在于,所述通过拼接所述多个基元生成所述仿真高精度地图,还包括:
    确定所述至少一个第一车道的至少一个出口车道;
    确定所述至少一个第二车道的至少一个入口车道;
    所述至少一个过渡车道用于连接所述至少一个出口车道与所述至少一个入口车道。
  6. 如权利要求5所述的方法,其特征在于,所述至少一个出口车道的数量与所述至少一个入口车道的数量不相同,所述过渡道路片段包括用于将两条车道并入一条车道的车道片段。
  7. 如权利要求5所述的方法,其特征在于,所述至少一个出口车道的朝向与所述至少一个入口车道的朝向不同,所述至少一个过渡车道包括曲线车道。
  8. 如权利要求1-7任一项所述的方法,其特征在于,所述分类标签用于标识所述高精度地图片段的以下内容中的至少一项:
    所述高精度地图片段中道路的几何拓扑信息;
    所述高精度地图片段中车道的用途信息;或,
    所述高精度地图片段中场地的类型信息。
  9. 如权利要求8所述的方法,其特征在于,
    所述几何拓扑信息包括:弯道、直道、环岛、十字路口、丁字路口、L型路口、U型路口或匝道中的至少一项;
    所述车道的用途信息包括:公交专用道、人行横道、自行车专用道、快速路、临时停车道或紧急停车道中的至少一项;
    所述场地的类型信息包括:城市道路、高速道路、停车场中的至少一项。
  10. 一种仿真高精度地图生成装置,其特征在于,包括:
    获取单元,用于获取生成高精度地图的需求;
    处理单元,用于根据所述需求,从基元库中选择满足所述需求的多个基元,所述基元为具有分类标签的高精度地图片段;通过拼接所述多个基元生成所述仿真高精度地图。
  11. 如权利要求10所述的装置,其特征在于,所述处理单元用于通过方式一或者方式二中的至少一种得到所述基元库中的基元;
    所述方式一包括:
    从已有的高精度地图中分割出符合所述分类标签的高精度地图片段;以及
    将通过所述分割得到的高精度地图片段作为基元加入所述基元库;
    所述方式二包括:
    从已有的矢量地图中分割出符合所述分类标签的矢量地图片段;
    通过对与所述矢量地图片段对应的卫星云图进行图像检测,获取与所述矢量地图片段对应的高精度地图信息;
    利用所述高精度地图信息将所述矢量地图片段转换为高精度地图片段;以及
    将通过所述转换得到的高精度地图片段作为基元加入所述基元库。
  12. 如权利要求10或11所述的装置,其特征在于,所述处理单元,具体用于:
    根据所述需求,确定生成所述仿真高精度地图需要的至少一个分类标签,以及所述至少一个分类标签中每个分类标签所对应的基元数量;
    根据所述基元数量从所述基元库中选择具有所述至少一个分类标签的所述多个基元。
  13. 如权利要求10-12任意一项所述的装置,其特征在于,所述多个基元包括第一基元和第二基元,所述第一基元包括第一道路片段,所述第二基元包括第二道路片段,所述处理单元,具体用于:
    生成所述第一道路片段和所述第二道路片段之间的过渡道路片段,所述过渡道路片段包括至少一个过渡车道,所述至少一个过渡车道用于连接所述第一道路片段中的至少一个第一车道与所述第一道路片段中的至少一个第二车道;
    建立所述至少一个第一车道与所述至少一个过渡车道的链接关系;
    建立所述至少一个第二车道与所述至少一个过渡车道的链接关系。
  14. 如权利要求13所述的装置,其特征在于,所述处理单元,还用于:
    确定所述至少一个第一车道的至少一个出口车道;
    确定所述至少一个第二车道的至少一个入口车道;
    所述至少一个过渡车道用于连接所述至少一个出口车道与所述至少一个入口车道。
  15. 如权利要求14所述的装置,其特征在于,所述至少一个出口车道的数量与所述至少一个入口车道的数量不相同,所述过渡道路片段包括用于将两条车道并入一条车道的车道片段。
  16. 如权利要求14所述的装置,其特征在于,所述至少一个出口车道的朝向与所述至少一个入口车道的朝向不同,所述至少一个过渡车道包括曲线车道。
  17. 如权利要求10-16任一项所述的装置,其特征在于,所述分类标签用于标识所述高精度地图片段的以下内容中的至少一项:
    所述高精度地图片段中道路的几何拓扑信息;
    所述高精度地图片段中车道的用途信息;或,
    所述高精度地图片段中场地的类型信息。
  18. 如权利要求17所述的装置,其特征在于,
    所述几何拓扑信息包括:弯道、直道、环岛、十字路口、丁字路口、L型路口、U型路口或匝道中的至少一项;
    所述车道的用途信息包括:公交专用道、人行横道、自行车专用道、快速路、临时停车道或紧急停车道中的至少一项;
    所述场地的类型信息包括:城市道路、高速道路、停车场中的至少一项。
  19. 一种地图生成装置,其特征在于,包括处理器和存储器,所述存储器用于存储计算机可执行程序,所述处理器执行所述存储器中的计算机可执行程序,使得权利要求1-9中任一项所述的方法被执行。
  20. 一种地图生成装置,其特征在于,包括处理器和通信接口,
    所述通信接口,用于输入和/或输出信息;
    所述处理器,用于执行计算机可执行程序,使得权利要求1-9中任一项所述的方法被执行。
  21. 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存储有计算机可执行程序,所述计算机可执行程序在被处理器执行时,使得权利要求1-9中任一项所述的方法被执行。
  22. 一种计算机程序产品,其特征在于,当所述计算机程序产品在处理器上运行时,使得权利要求1-9中任一项所述的方法被执行。
PCT/CN2021/132775 2021-02-09 2021-11-24 仿真高精度地图生成方法、装置和计算机可读存储介质 WO2022170815A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110176442.1 2021-02-09
CN202110176442.1A CN114910086A (zh) 2021-02-09 2021-02-09 仿真高精度地图生成方法、装置和计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2022170815A1 true WO2022170815A1 (zh) 2022-08-18

Family

ID=82761696

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/132775 WO2022170815A1 (zh) 2021-02-09 2021-11-24 仿真高精度地图生成方法、装置和计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN114910086A (zh)
WO (1) WO2022170815A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115438517A (zh) * 2022-11-07 2022-12-06 阿里巴巴达摩院(杭州)科技有限公司 仿真地图生成方法、电子设备及计算机存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115438516B (zh) * 2022-11-07 2023-03-24 阿里巴巴达摩院(杭州)科技有限公司 仿真地图生成方法、电子设备及计算机存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110433495A (zh) * 2019-08-12 2019-11-12 网易(杭州)网络有限公司 游戏中虚拟场景的配置方法及装置、存储介质及电子设备
US20200175760A1 (en) * 2017-08-23 2020-06-04 Tencent Technology(Shenzhen) Company Limited Information interaction method based on virtual space scene, computer equipment and computer-readable storage medium
CN111524445A (zh) * 2019-02-01 2020-08-11 阿里巴巴集团控股有限公司 地图生成方法、装置、电子设备及可读存储介质
CN111553963A (zh) * 2020-04-13 2020-08-18 中国能源建设集团广东省电力设计研究院有限公司 一种基于地理信息的元网格生成方法及装置
US20200380083A1 (en) * 2019-05-28 2020-12-03 Applied Intuition, Inc. Simulated-driving-environment generation
CN112231430A (zh) * 2020-12-10 2021-01-15 中智行科技有限公司 一种地图数据管理方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200175760A1 (en) * 2017-08-23 2020-06-04 Tencent Technology(Shenzhen) Company Limited Information interaction method based on virtual space scene, computer equipment and computer-readable storage medium
CN111524445A (zh) * 2019-02-01 2020-08-11 阿里巴巴集团控股有限公司 地图生成方法、装置、电子设备及可读存储介质
US20200380083A1 (en) * 2019-05-28 2020-12-03 Applied Intuition, Inc. Simulated-driving-environment generation
CN110433495A (zh) * 2019-08-12 2019-11-12 网易(杭州)网络有限公司 游戏中虚拟场景的配置方法及装置、存储介质及电子设备
CN111553963A (zh) * 2020-04-13 2020-08-18 中国能源建设集团广东省电力设计研究院有限公司 一种基于地理信息的元网格生成方法及装置
CN112231430A (zh) * 2020-12-10 2021-01-15 中智行科技有限公司 一种地图数据管理方法及装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115438517A (zh) * 2022-11-07 2022-12-06 阿里巴巴达摩院(杭州)科技有限公司 仿真地图生成方法、电子设备及计算机存储介质

Also Published As

Publication number Publication date
CN114910086A (zh) 2022-08-16

Similar Documents

Publication Publication Date Title
US11192558B2 (en) Method, apparatus, and system for providing road curvature data
WO2022170815A1 (zh) 仿真高精度地图生成方法、装置和计算机可读存储介质
US9222786B2 (en) Methods and systems for creating digital transportation networks
CN102713521B (zh) 用gps踪迹产生、细化及扩充增量地图
US9377313B2 (en) Methods and systems for creating digital street network database
US8442767B2 (en) Method of operating a navigation system to provide route guidance
US9243925B2 (en) Generating a sequence of lane-specific driving directions
US10152635B2 (en) Unsupervised online learning of overhanging structure detector for map generation
US11170485B2 (en) Method, apparatus, and system for automatic quality assessment of cross view feature correspondences using bundle adjustment techniques
US11420649B2 (en) Method, apparatus, and computer program product for generating turn paths through an intersection
US10515293B2 (en) Method, apparatus, and system for providing skip areas for machine learning
CN112033420A (zh) 一种车道地图构建方法和装置
WO2011140859A1 (zh) 提供图形化实时交通信息的方法及系统
US11085791B2 (en) Method, apparatus, and computer program product for on-street parking localization
CN109523781B (zh) 一种基于卫星定位的路口预测方法
WO2022021982A1 (zh) 可行驶区域判定的方法、智能驾驶系统和智能汽车
US20200408534A1 (en) Method and apparatus for providing inferential location estimation using automotive sensors
US20230206625A1 (en) Method, apparatus, and system for pole extraction from optical imagery
KR102131012B1 (ko) 차량용 최적 경로 안내 시스템, 및 차량용 최적 경로 안내 시스템을 위한 경로 계산 서버
CN108898862A (zh) 红绿灯路口的确定方法、装置及电子设备
CN111337043B (zh) 一种路径的规划方法、装置、存储介质和电子设备
CN115131455A (zh) 地图生成方法和相关产品
CN116935656B (zh) 道路交通数据处理方法、装置、电子设备及存储介质
JP7358528B2 (ja) 公共交通ルートの決定方法及び装置
US20240155547A1 (en) Apparatus, method, and computer program product for radio model generation, mobile device positioning, and/or hash key generation for a radio model

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21925462

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21925462

Country of ref document: EP

Kind code of ref document: A1