Method for generating road network map for driving plan of autonomous vehicle

Abstract

The present invention provides a method, a server, and a computer program for generating a road network map for a driving plan of an autonomous vehicle. The method for generating a road network map for a driving plan of an autonomous vehicle according to various embodiments of the present invention is executed by a computing device, and is characterized by including: a step of generating regional relevant road network data; a step of generating grid road network data for a short-term driving plan of the autonomous vehicle by using the generated road network data; and a step of generating a road intersection map for a long-term driving plan of the autonomous vehicle by using the generated grid road network data.

Description

Technical Field

[0001] Various embodiments of the present invention relate to a method, a server, and a computer program for generating a road network map for a driving plan of an autonomous vehicle, and more particularly, to a method for generating a road network map for short-term and long-term driving plans of an autonomous vehicle. Background Art

[0002] To facilitate users of vehicles, there is a trend of having various sensors and electronic devices, etc. (such as an Advanced Driver Assistance System (ADAS)), and in particular, the development of technologies for autonomous driving systems of vehicles is actively underway.

[0003] Among them, an autonomous driving system refers to a vehicle that recognizes the surrounding environment without the intervention of a driver and autonomously drives to a specific destination based on the recognized surrounding environment.

[0004] Generally, an autonomous driving system requires various pre-information to perform various purposes such as providing a path to an autonomous vehicle. In particular, road network data including information related to lanes and lane lines of roads is pre-information that can be applied to various modules included in an autonomous driving system, and is necessary data in this regard, so the process of generating road network data is essential.

[0005] Prior Art Documents

[0006] Patent Documents

[0007] Korean Patent Publication No. 10-2014-0126500 (October 31, 2014) Summary of the Invention

[0008] Problems to be Solved

[0009] The problem to be solved by the present invention is to provide a method, a server, and a computer program for generating a road network map for a driving plan of an autonomous vehicle that collect various information related to roads within a region to generate road network data, automatically generate grid road network data and road intersection diagrams using the same, and can construct a road network map for short-term and long-term driving plans of an autonomous vehicle.

[0010] The problems to be solved by the present invention are not limited to the problems mentioned above, and those skilled in the art to which the present invention pertains can clearly understand other problems not mentioned from the following description.

[0011] Solutions to the Problems

[0012] A method for generating a road network map for a driving plan of an autonomous vehicle according to an embodiment of the present invention for solving the above problems, which is executed by a computing device, may include: a step of generating region-related road network data; a step of generating grid road network data for a short-term driving plan of the autonomous vehicle by using the generated road network data; and a step of generating a road intersection map for a long-term driving plan of the autonomous vehicle by using the generated grid road network data.

[0013] In various embodiments, the step of generating the road network data may include: a step of generating a first road network representing a connection relationship between a first road located in the region and a second road connected to the first road; and a step of generating a second road network representing a connection relationship between a plurality of first lane lines included in the first road and a plurality of second lane lines included in the second road by using the generated first road network.

[0014] In various embodiments, the step of generating the first road network may include: a step of respectively charting the first road and the second road to generate a first road chart and a second road chart, where the generated first road chart and the generated second road chart include shape information, direction information, and attribute information of the first road and the second road respectively; and a step of connecting the generated first road chart and the generated second road chart to generate the first road network.

[0015] In various embodiments, the step of generating the first road network may include: a step of respectively dividing the first road and the second road according to a set criterion to generate one or more independent roads and one or more dependent roads; and a step of connecting the generated one or more independent roads and the generated one or more dependent roads to generate the first road network, and cross-connecting one independent road and one dependent road.

[0016] In various embodiments, the step of generating the second road network may include: a step of respectively charting the plurality of first lane lines and the plurality of second lane lines to generate a first lane line chart representing the respective relative positions of the plurality of first lane lines and a second lane line chart representing the respective relative positions of the plurality of second lane lines, where the generated first lane line chart and the generated second lane line chart include attribute information of the plurality of first lane lines and the plurality of second lane lines respectively; and a step of connecting the generated first lane line chart and the generated second lane line chart to generate the second road network.

[0017] In various embodiments, the steps of generating the above grid road network data may include: the step of generating one or more grid roads using the generated above road network data; the step of generating connection information between the generated one or more grid roads; and the step of generating a grid road network connecting the generated one or more grid roads according to the generated connection information.

[0018] In various embodiments, the step of generating the one or more grid roads may include grouping one or more lanes that meet a set condition among a plurality of lanes located inside the above region based on the generated above road network data to generate one or more grid roads, and the set condition has the same attributes and can be physically and legally moved.

[0019] In various embodiments, the step of generating the one or more grid roads may include: the step of setting a plurality of points in a grid form on the generated one or more grid roads; and the step of storing by matching geometric information and semantic information related to the grid roads where the set plurality of points are respectively located at the set plurality of points.

[0020] In various embodiments, the step of generating the connection information may include determining whether the generated one or more grid roads cross each other, generating connection information representing the connection relationship between the generated one or more grid roads based on the determination of whether they cross, and the form of the generated connection information is determined based on the length of the crossing section between the generated one or more grid roads.

[0021] In various embodiments, the step of generating the above road intersection map may include: the step of determining whether it is possible to move between one or more lanes included in a first grid road and one or more lanes included in a second grid road based on the generated above grid road network data; and the step of generating the above road intersection map connecting one or more lanes included in the above first grid road and one or more lanes included in the above second grid road based on the determination of whether it is possible to move.

[0022] The road network map generation server for the driving plan of an autonomous vehicle according to another embodiment of the present invention for solving the above problems may include: a processor; a network interface; a memory; and a computer program, which is loaded in the above memory and executed by the above processor. The above computer program may include: instructions for generating region-related road network data; instructions for generating grid road network data for the short-term driving plan of the autonomous vehicle using the generated road network data; and instructions for generating a road intersection map for the long-term driving plan of the autonomous vehicle using the generated grid road network data.

[0023] A computer program stored in a computer-readable recording medium according to another embodiment of the present invention for solving the above problems, characterized in that it is combined with a computing device and stored in a computer-readable recording medium to perform the following steps, which may include: a step of generating region-related road network data; a step of generating grid road network data for the short-term driving plan of the autonomous vehicle using the generated road network data; and a step of generating a road intersection map for the long-term driving plan of the autonomous vehicle using the generated grid road network data.

[0024] Other specific matters of the present invention are included in the detailed description and the drawings.

[0025] Effects of the Invention

[0026] According to various embodiments of the present invention, there are advantages of collecting various information related to roads within a region to generate road network data, automatically generating grid road network data and road intersection maps using the same, constructing a road network map, and using the same to generate more accurate short-term and long-term driving plans for autonomous vehicles.

[0027] The effects of the present invention are not limited to the above-mentioned effects, and other effects not mentioned can be clearly understood by those of ordinary skill in the technical field to which the present invention belongs from the following description. Brief Description of the Drawings

[0028] Figure 1 A diagram showing a road network map generation system for the driving plan of an autonomous vehicle according to an embodiment of the present invention.

[0029] Figure 2 A hardware structure diagram of a road network map generation server for the driving plan of an autonomous vehicle according to another embodiment of the present invention.

[0030] Figure 3 A flowchart of a road network map generation method for the driving plan of an autonomous vehicle according to another embodiment of the present invention.

[0031] Figure 4Flowchart of a method for generating road network data in various embodiments.

[0032] Figure 5 Diagram exemplarily showing the form of a road network generated according to the method for generating road network data in various embodiments.

[0033] Figure 6 Diagram exemplarily showing a road chart applicable to various embodiments.

[0034] Figure 7 and Figure 8 Diagram exemplarily showing a lane line chart applicable to various embodiments.

[0035] Figure 9 Diagram exemplarily showing the form of connecting a first road chart and a second road chart and a first lane line chart and a second lane line chart in various embodiments.

[0036] Figure 10 Diagram showing the process of connecting an independent road and a subordinate road in various embodiments.

[0037] Figure 11 Diagram exemplarily showing the form in which a driving plan is set in an external area of a road on a road chart in various embodiments.

[0038] Figure 12 Flowchart of a method for generating grid road network data in various embodiments.

[0039] Figure 13 Diagram exemplarily showing the form of a grid road network generated according to the method for generating grid road network data in various embodiments.

[0040] Figure 14 Diagram showing the process of setting a plurality of points on one or more grid roads in various embodiments.

[0041] Figure 15 Diagram showing the process of generating a road intersection map using grid road network data in various embodiments.

[0042] Figure 16 Diagram showing the process of generating a driving plan for an autonomous vehicle using grid road network data and a road intersection map in various embodiments. Detailed Description

[0043] With the attached Figure 1With reference to the embodiments described in detail hereinafter, the advantages and features of the present invention and the methods for achieving these will be clarified. However, the present invention can be implemented in various different forms and is not limited to the embodiments disclosed below. Only, these embodiments make the disclosure of the present invention complete and are used to fully inform those of ordinary skill in the technical field to which the present invention pertains of the scope of the present invention. The present invention is only defined by the scope of the claims.

[0044] The terms used in this specification are for describing the embodiments and do not limit the present invention. In this specification, unless otherwise specifically mentioned in a sentence, the singular form also includes the plural form. The "comprises" and / or "comprising" used in the specification do not exclude the existence or addition of one or more other structural elements in addition to the mentioned structural elements. Throughout the specification, the same reference numerals refer to the same structural elements, and "and / or" includes each of the mentioned structural elements and all combinations of one or more of them. Although "first", "second", etc. are used to describe various structural elements, these structural elements are not limited to these terms. These terms are only used to distinguish one structural element from another. Therefore, the first structural element mentioned below can also be the second structural element within the technical idea of the present invention.

[0045] Unless otherwise defined, all terms (including technical and scientific terms) used in this specification can be used with the meanings commonly understood by those of ordinary skill in the technical field to which the present invention pertains. And, unless specifically defined otherwise, the terms defined in a commonly used dictionary are not ideally or overly interpreted.

[0046] The terms "unit" or "module" used in the specification refer to hardware components such as software, FPGA, or ASIC, and the "unit" or "module" performs a certain function. However, the "unit" or "module" is not limited to the meaning of software or hardware. The "unit" or "module" can be configured to be located in an addressable storage medium and can be configured to be executed on one or more processors. Therefore, as an example, the "unit" or "module" includes components such as software components, object-oriented software components, class components, and task components, processes, functions, attributes, programs, subroutines, program code segments, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within a component and the "unit" or "module" can be combined into smaller components and the "unit" or "module", or further separated into additional components and the "unit" or "module".

[0047] As shown in the figure, spatially relative terms such as "below", "beneath", "lower", "above", "upper", etc. can be used to easily describe the relative relationship between one structural element and another. Spatially relative terms should be understood to include terms in different directions of the structural element during use or operation, in addition to the directions shown in the figure. For example, when the structural element shown in the figure is flipped, the structural element described as "below" or "beneath" another structural element can be placed "above" the other structural element. Therefore, the exemplary term "lower" can include both the up and down directions. The structural element can also be oriented in other directions, and thus the spatially relative terms can be interpreted according to the orientation.

[0048] In this specification, a computer refers to all types of hardware devices including at least one processor, and according to an embodiment, it can be understood to also include the meaning of software structures operating in the hardware device. For example, a computer can be understood to include all of smartphones, tablets, desktop computers, laptop computers, and user clients and applications driven in each device, and is not limited thereto.

[0049] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0050] Each step described in this specification is executed by a computer, but the subject of each step is not limited thereto. According to an embodiment, at least a part of each step can be executed in different devices.

[0051] Among them, in this specification, a method for generating a road network map by pre-data for designing short-term and long-term driving plans for an autonomous vehicle is described as an object, but it is not limited thereto, and a semi-autonomous vehicle or an ordinary vehicle that does not use an autonomous driving function can be applied as an object.

[0052] Figure 1 A diagram showing a road network map generation system for a driving plan of an autonomous vehicle according to an embodiment of the present invention.

[0053] Refer to Figure 1 , a road network map generation system for a driving plan of an autonomous vehicle according to an embodiment of the present invention may include a road network map generation server 100, a user terminal 200, and an external server 300.

[0054] Among them, Figure 1 The road network map generation system for a driving plan of an autonomous vehicle shown is according to an embodiment, and its structural elements are not limited to Figure 1 the embodiment shown, and can be added, changed, or deleted as needed.

[0055] In one embodiment, the road network map generation server 100 may generate a road network map for the driving plan of the autonomous vehicle 10. For example, the road network map generation server 100 may collect all road-related information in the area (such as information related to road structure, etc.) to generate road network data, may use the generated road network data to generate grid road network data for the short-term driving plan of the autonomous vehicle 10, and may use the generated grid road network data to generate a road intersection map for the long-term driving plan of the autonomous vehicle 10.

[0056] In various embodiments, the road network map generation server 100 may be connected to the user terminal 200 or a vehicle passing through the area (such as the autonomous vehicle 10) via the network 400, may collect area-related sensor data from the user terminal 200 or the vehicle, and may use the collected sensor data to generate area-related road network data.

[0057] Moreover, the road network map generation server 100 may be connected to an external server 300 (such as the server of the Ministry of Land, Infrastructure and Transport) via the network 400, and may collect various road-related information in the area through the external server 300 to generate road network data.

[0058] Furthermore, the road network map generation server 100 may automatically generate grid road network data in response to the generation of area-related road network data, and may re-automatically generate a road intersection map in response to the generation of grid road network data. However, it is not limited thereto.

[0059] Among them, the user terminal 200 is a wireless communication device that ensures portability and mobility, and may include navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), personal handyphone system (PHS), personal digital assistant (PDA), international mobile telecommunication (IMT)-2000, code division multiple access (CDMA)-2000, W-code division multiple access (W-CDMA), wireless broadband internet (Wibro) terminal, smartphone, smartpad, tablet PC, and all kinds of handheld wireless communication devices such as these, but is not limited thereto.

[0060] Moreover, among them, the network 400 may refer to a connection structure in which each node such as multiple terminals and servers can exchange information with each other. For example, the network 400 includes local area network (LAN), wide area network (WAN), world wide web (WWW), wired and wireless data communication network, telephone network, wired and wireless television communication network, etc.

[0061] And, among them, the wireless data communication network includes 3G, 4G, 5G, the 3rd Generation Partnership Project (3GPP), the 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi, Internet, Local Area Network (LAN), Wireless Local Area Network (Wireless LAN), Wide Area Network (WAN), Personal Area Network (PAN), Radio Frequency (RF), Bluetooth network, Near-Field Communication (NFC) network, satellite broadcast network, analog broadcast network, Digital Multimedia Broadcasting (DMB) network, etc., but is not limited thereto.

[0062] In various embodiments, the road network map generation server 100 may utilize grid road network data and road intersection maps to generate a driving plan for controlling the autonomous driving vehicle 10. Among them, in addition to generating a driving path from the current position of the autonomous driving vehicle 10 to the destination and thus controlling the autonomous driving vehicle 10 to move, the driving plan may also refer to a plan for various controls such as the lane to be driven, lane change position, speed or acceleration control, steering angle control, etc.

[0063] In one embodiment, the external server 300 may be connected to the road network map generation server 100 through the network 400. The road network map generation server 100 may provide various information (such as road network map generation rules) required to execute the road network map generation process for the driving plan of the autonomous driving vehicle 10, or receive the data (such as road network data, grid road network data, and road intersection maps, etc.) generated by executing the road network map generation process for the driving plan of the autonomous driving vehicle 10, and store them. For example, the external server 300 may be a storage server separately set outside the road network map generation server 100, but is not limited thereto. Hereinafter, refer to Figure 2 Describe the hardware structure of the road network map generation server 100 that executes the road network map generation process for the driving plan of the autonomous driving vehicle.

[0064] Figure 2 Hardware structure diagram of a road network map generation server for a driving plan of an autonomous vehicle according to another embodiment of the present invention.

[0065] Referring to Figure 2 , the road network map generation server 100 (hereinafter, "server 100") according to another embodiment of the present invention may include one or more processors 110, a memory 120 that loads a computer program 151 executed by the processor 110, a bus 130, a communication interface 140, and a memory 150 that stores the computer program 151. Among them, Figure 2 only shows the structural elements related to the embodiments of the present invention. Therefore, as long as it is a person of ordinary skill in the technical field to which the present invention pertains, it can be known that in addition to Figure 2 the structural elements shown, other general structural elements may also be included.

[0066] The processor 110 controls the overall operation of each structure of the server 100. The processor 110 may include a central processing unit (CPU, Central Processing Unit), a microprocessor (MPU, Micro Processor Unit), a microcontroller unit (MCU, Micro Controller Unit), a graphics processing unit (GPU, Graphic Processing Unit), or any form of processor well-known in the technical field of the present invention.

[0067] Moreover, the processor 110 may execute the operation of at least one application or program for executing the method of the embodiments of the present invention, and the server 100 may have one or more processors.

[0068] In various embodiments, the processor 110 may further include a random access memory (RAM, RandomAccess Memory, not shown) and a read-only memory (ROM, Read-Only Memory, not shown) that temporarily and / or permanently store signals (or data) processed inside the processor 110. Moreover, the processor 110 can be implemented in the form of a system on chip (SoC, system on chip) including at least one of a graphics processing unit, a random access memory, and a read-only memory.

[0069] Memory 120 stores various data, commands, and / or information. Memory 120 can load computer program 151 from storage 150 to execute the methods / actions of various embodiments of the present invention. When computer program 151 is loaded in memory 120, processor 110 can execute one or more instructions constituting computer program 151 to perform the above-mentioned methods / actions. Memory 120 can be implemented by a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

[0070] Bus 130 provides a communication function between the structural elements of server 100. Bus 130 can be implemented by various types of buses such as an address bus, a data bus, and a control bus.

[0071] Communication interface 140 supports wired and wireless Internet communication of server 100. In addition, communication interface 140 can also support various communication methods other than Internet communication. To this end, communication interface 140 can include a communication module well-known in the technical field of the present invention. In several embodiments, communication interface 140 can be omitted.

[0072] Storage 150 can non-temporarily store computer program 151. When a road network map generation process for a driving plan of an autonomous vehicle is executed through server 100, storage 150 can store various information required for the road network map generation process for providing a driving plan for the autonomous vehicle.

[0073] Storage 150 can include non-volatile memories such as read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well-known in the technical field to which the present invention pertains.

[0074] Computer program 151 can include one or more instructions that, when loaded in memory 120, cause processor 110 to perform the methods / actions of various embodiments of the present invention. That is, when processor 110 executes the above-mentioned one or more instructions, the above-mentioned methods / actions of various embodiments of the present invention can be performed.

[0075] In one embodiment, the computer program 151 may include more than one instruction for executing a road network map generation method for a driving plan of an autonomous vehicle. The road network map generation method for the driving plan of the autonomous vehicle includes: a step of generating region-related road network data; a step of generating grid road network data for a short-term driving plan of the autonomous vehicle by using the generated road network data; and a step of generating a road intersection map for a long-term driving plan of the autonomous vehicle by using the generated grid road network data.

[0076] The steps of the methods or algorithms described in connection with the embodiments of the present invention may be directly implemented by hardware, or implemented by software modules executed by the hardware, or implemented by a combination thereof. The software modules may reside in a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a hard disk, a removable disk, a compact disc read-only memory (CD-ROM), or any form of computer-readable recording medium well-known in the technical field to which the present invention pertains.

[0077] The structural elements of the present invention may be implemented by a program (or application) and stored in a medium to be executed in combination with a computer as hardware. The structural elements of the present invention may be executed by software programming or software components. Similarly, the embodiments may include various algorithms implemented by a combination of data structures, procedures, routines, or other programming structures, and are implemented by programming or scripting languages such as C, C++, Java, an assembler, etc. The functional aspects may be implemented by algorithms executed in one or more processors. Hereinafter, with reference to Figures 3 to 16 , a road network map generation method for a driving plan of an autonomous vehicle executed by the server 100 will be described.

[0078] Figure 3 It is a flowchart of a road network map generation method for a driving plan of an autonomous vehicle according to another embodiment of the present invention.

[0079] With reference to Figure 3 , in step S110, the server 100 may generate region-related road network data. For example, the server 100 may be connected to the user terminal 200 or a vehicle passing through the region (such as the autonomous vehicle 10) through the network 400, may collect region-related sensor data from the user terminal 200 or the vehicle, and may generate region-related road network data by using the collected sensor data.

[0080] Among them, the sensor data may refer to all information related to the structure of the roads in the area, and may include image data generated by photographing the area through a camera sensor, lidar sensor data collected by a lidar sensor, radar sensor data collected by a radar sensor, and position data collected by a Global Positioning System (GPS) sensor.

[0081] Moreover, the road network map generation server 100 may be connected to an external server 300 (such as a server of the Ministry of Land, Infrastructure and Transport) through the network 400, and may collect various information related to the roads in the area through the external server 300 to generate road network data.

[0082] Among them, the road network data is data for generating a driving plan for an autonomous vehicle, and may refer to data including necessary information related to the road structure.

[0083] In various embodiments, the road network data may include information (such as road structure, shape, direction, Geometric Information, and Semantic Information, etc.) for automatically generating a grid road network data and a road intersection map through the subsequent steps S120 and S130, and can be stored in a structure in a form that is easy for users to directly edit.

[0084] In various embodiments, the server 100 may generate a road network (such as Figure 5 ) representing the connection relationship between a first road in the area and a second road connected to the first road, including the connection relationship between the lane lines of the first road and the second road. Hereinafter, refer to Figures 4 to 11 for description.

[0085] Figure 4 It is a flowchart of a method for generating road network data in various embodiments.

[0086] Refer to Figure 4 , in step S210, the server 100 may generate a first road network representing the connection relationship between a first road in the area and a second road connected to the first road.

[0087] First, the server 100 may respectively graph the first road and the second road above to generate a first road graph and a second road graph. For example, as Figure 6 shown, the server 100 uses the first graph generation model to graph the first road and the second road respectively, and may generate a first road graph and a second road graph.

[0088] Among them, the first chart generation model can be a spline curvature path (SCP) model that uses partial polynomials to estimate the Nth-degree polynomial function related to the road and charts it into a chart in the S-D domain. For example, the server 100 estimates the Nth-degree polynomial functions related to the first road and the second road based on the shape information of the first road and the second road to be charted, substitutes various data values (such as the coordinate values (X, Y) related to the starting and ending points of the first road and the second road, the boundary condition, and the continuity condition related to the curvature of the first road and the second road) into the estimated Nth-degree polynomial functions to determine the Nth-degree polynomial functions, and can generate the first road chart and the second road chart of the first road and the second road respectively. However, it is not limited to this, and various methods for charting the first road and the second road can be applied.

[0089] Among them, the first road chart and the second road chart can respectively include geometric information related to the first road and the second road. For example, the first road chart and the second road chart can respectively include the shape information of the first road and the second road. As an example, the first road chart and the second road chart estimate the polynomial function representing the shape information of the road through the SCP model, and use the estimated polynomial function for charting, and the shape information of the road can be represented by a representative line. And the first road chart and the second road chart can respectively include the directional information of the first road and the second road.

[0090] And the first road chart and the second road chart can respectively include attribute information related to the first road and the second road. For example, the first road chart and the second road chart can respectively include the explicitness of the first road and the second road (such as explicit road: a road with pavement markings explicitly represented, implicit road: like a U-turn section or an intersection, etc., where the pavement markings are not explicitly represented), and information related to the protection area (such as the disabled protection area, the children protection area, and the elderly and weak protection area, etc.).

[0091] After that, the server 100 connects the first road chart and the second road chart to generate the first road network. Among them, the first road network can be represented in a form that directly connects the first road chart and the second road chart, but it is not limited to this. As Figure 5 shown, it is represented in a form that connects the indicator indicating the first road and the indicator indicating the second road, and can be implemented in a form that is easy for users to directly modify and edit the road network.

[0092] In various embodiments, the server 100 may divide the first road and the second road respectively according to a set benchmark to generate one or more independent roads and one or more dependent roads, connect the one or more independent roads and the one or more dependent roads to generate a first road network, and cross-connect an independent road and a dependent road.

[0093] For example, as Figure 10 shown, the server 100 divides the first road and the second road respectively according to a set benchmark (such as whether it can move to other roads), can generate multiple unit roads, and can classify them as independent roads or dependent roads according to the respective attributes of the multiple unit roads.

[0094] Among them, an independent road may refer to a unit road selected from two or more unit roads in different directions for connection, or a unit road that can select two or more unit roads in different directions for connection, and a dependent road may refer to a unit road selected from one unit road for connection, or a unit road that can only select one unit road for connection.

[0095] At this time, the server 100 divides the first road and the second road respectively to generate multiple unit roads, classifies them as independent roads or dependent roads according to the respective attributes of the multiple unit roads. When two or more consecutive unit roads are classified as independent roads, or two or more consecutive unit roads are classified as dependent roads, the two or more consecutive unit roads can be merged into one unit road so that an independent road and a dependent road can be cross-arranged.

[0096] After that, the server 100 connects the multiple independent roads and the multiple dependent roads generated according to the above method respectively, and an independent road and a dependent road can be connected alternately. For example, after the server 100 first configures the unit roads classified as independent roads among the multiple unit roads, it configures the dependent roads between each configured independent road, and can connect the independent road and the dependent road automatically while configuring the dependent road, so that an independent road and a dependent road can be connected alternately.

[0097] As an example, the server 100 can provide a user interface (UI, User interface) (such as a GUI) for generating road network data to the user terminal 200, and can first configure the independent roads according to the first user input obtained from the user through the UI. After that, the server 100 configures the dependent roads between each independent road according to the second user input obtained from the user through the UI, and automatically connects the independent road and the dependent road while configuring the dependent road, so that an independent road and a dependent road can be connected alternately.

[0098] After that, when the server 100 receives user input for editing a specific independent road through the UI, the server 100 can edit the specific independent road according to the user input. By editing the specific independent road, the subordinate roads connected to the specific independent road can be automatically edited as well (automatically edited according to the positions of the independent roads connected to both sides of the subordinate road).

[0099] As described above, when the road is not divided and connected into multiple unit roads, during the process of the user directly editing the road network, every time the connection relationship between roads is modified, propagation occurs, resulting in continuous changes to the entire road network. Therefore, there is a problem in that it is difficult to manage and maintain the road network.

[0100] Considering this situation, in the road network map generation method for the driving plan of an autonomous vehicle according to various embodiments of the present invention, instead of simply connecting the entire first road and the second road, by subdividing the first road and the second road and then connecting them, it is possible to easily maintain, manage, and edit the road network.

[0101] In step S220, the server 100 can generate a second road network representing the connection relationship between the multiple first lane lines included in the first road and the multiple second lane lines included in the second road by using the first road network.

[0102] First, the server 100 can respectively tabulate the multiple first lane lines and the multiple second lane lines to generate a first lane line chart representing the respective relative positions of the multiple first lane lines and a second lane line chart representing the respective relative positions of the multiple second lane lines. For example, as Figure 7 shown, the server 100 can use a second chart generation model to generate the respective first lane line charts and second lane line charts of the multiple first lane lines and the multiple second lane lines.

[0103] Among them, the second chart generation model can be a spline path (SP) model charted in the S-L domain that uses the first road chart and the second road chart charted in the S-D domain to represent the respective relative positions of the multiple first lane lines and the multiple second lane lines. For example, the server 100 can select a reference first lane line among the multiple first lane lines and generate a connection from the starting point (S START ) to the end point (S FINISH) linear graph (L = +0.5). After that, the server 100 generates a linear graph related to the remaining first lane lines based on the reference first lane line, and can generate a linear graph considering the relative position with respect to the reference first lane line (for example, the first lane line located on the reference first lane line is L = +1.5, and the first lane line directly below the reference first lane line is L = -0.5). Thus, the first lane line graph and the second lane line graph can respectively include geometric information related to the relative positions of multiple first lane lines and multiple second lane lines.

[0104] Moreover, the first lane line graph and the second lane line graph can respectively include attribute information related to multiple first lane lines and multiple second lane lines. For example, the first lane line graph and the second lane line graph can respectively include information related to the type (e.g., solid line, dashed line, double line (double solid line, solid line and dashed line or dashed line and solid line)) and color (e.g., white, yellow, blue) of multiple first lane lines and multiple second lane lines.

[0105] After that, the server 100 connects the first lane line graph and the second lane line graph, and can generate a second road network. For example, the server 100 not only connects the feature points (such as the center points) of the first lane line graph and the second lane line graph, but also can connect all the locations at the intersections of multiple first lane lines and multiple second lane lines in a smooth curve form.

[0106] For example, as Figure 9 shown, when the first road 20 including multiple first lane lines and the second road 30 including multiple second lane lines are connected (such as Figure 9 (A)), all the locations at the intersections of multiple first lane lines and multiple second lane lines can be connected in a smooth curve (such as a straight line). That is, even if the positions of the multiple first lane lines and the multiple second lane lines respectively connected to the multiple first lane lines are different, when the relative positions are the same, they are arranged at the same position on the S-L coordinate. As Figure 9 shown, the first lane line graph and the second lane line graph are connected by a straight line, and a linear graph of one S-L domain can be generated (such as Figure 9 (B)).

[0107] At this time, as Figure 9 (A) shown, for the first road 20, a driving path for continuing to drive on the first road 20 in the case of moving to the undirected other road (the second road 30) and a driving path for moving from the first road 20 to the second road 30 can be generated. That is, two driving paths. The first road 20 can be divided into two unit roads 20-1 and 20-2 based on the intersection of the first road 20 and the second road 30. As Figure 9 (B) shown, two second road networks can be generated considering each driving path.

[0108] Among them, as Figure 8 shown, one or more lanes included in the first road and the second road can be represented by interpolation of two adjacent lane line charts. That is, the server 100 does not separately generate a road network connecting the lanes included in the first road and the second road, and can represent the connection state between one or more lanes included in the first road and the second road on the second road network generated by connecting the first lane line chart and the second lane line chart.

[0109] Among them, one or more lanes are represented by interpolation of two adjacent lane line charts, and the interval between two adjacent lane lines is set according to the relative position regardless of the actual distance (as shown in 1), and does not include information related to the width of the actual lane.

[0110] Among them, the lanes of the first road and the second road included in the second road network can include lane-related attribute information. For example, the lanes located on the first road and the second road can include direction indication information (such as straight, none, left turn, right turn, straight and right turn, straight and left turn, no straight, U-turn, etc.), type information (such as general lane, bus-only lane (all-day, peak-hour), etc.) and speed information (such as specified speed, minimum specified speed, maximum specified speed, standard driving path, etc.). At this time, the lanes included in the first road and the second road can each include two or more attribute information.

[0111] On the other hand, during the process of generating the driving plan of the autonomous vehicle 10, when an emergency occurs, it may be necessary to drive into an area outside the designated lane (such as when the vehicle in front of the autonomous vehicle 10 driving according to the driving plan suddenly stops, in order to avoid sudden stop, drive onto the shoulder, or when the autonomous vehicle 10 in a two-way lane section has to drive in the opposite lane in reverse due to an obstacle in the driving lane, etc.).

[0112] Taking this into account, the server 100 generates the second road network according to the above method, as Figure 11 shown, in the first lane line chart and the second lane line chart, the area above the uppermost lane line (considering reverse driving into the opposite lane line) and the area below the lowermost lane line (considering shoulder driving) are expanded to generate. As described above, variables occur in driving, and a driving plan for leaving the designated lane can be realized.

[0113] Refer back to Figure 3, in step S120, the server 100 can generate grid road network data by using the road network data generated in step S110. Among them, the grid road network data can refer to the data for the short-term driving plan of the autonomous vehicle 10.

[0114] In various embodiments, the server 100 can use the road network data to set one or more grid roads related to the area, define the connection relationship between the set one or more grid roads, and thus generate a grid road network. Hereinafter, refer to Figures 12 to 14 Description.

[0115] Figure 12 It is a flowchart of a method for generating grid road network data in various embodiments.

[0116] Refer to Figure 12 , in step S310, the server 100 can use the road network data to generate one or more grid roads (such as lattice roads (LR, Lattice Road), Figure 13 (A)'s LR_A, LR_B, LR_C, LR_D, LR_E, LR_F). For example, the server 100 can group one or more lanes among the multiple lanes located in the area that meet the set conditions (such as having the same attributes, physically or legally movable) based on the road network data to generate one or more grid roads.

[0117] In various embodiments, the server 100 can set multiple points in the form of a grid on one or more grid roads, and can match and store the geometric information and attribute information related to the grid roads where the multiple points are located respectively at the set multiple points. For example, as Figure 14 shown, the server 100 can set the multiple points in a grid form with a first distance (such as 1m) unit along the S axis and a second distance (such as 0.25m) unit along the L axis on each graph (S-L graph) of one or more grid roads. Each of the set multiple points can match the geometric information (such as direction information, shape information, etc.) and attribute information (such as dominance, whether it is a protected area, etc.) related to the road where each point is located and store them. Among them, the first distance along the S axis and the second distance along the L axis for setting the multiple points are only one example and are not limited thereto, and can be adjusted within a specified range.

[0118] Moreover, for one or more points among the multiple points located on the lane lines of one or more grid roads, it can also include lane line-related geometric information (such as relative position information, etc.) and attribute information (such as type, color-related information).

[0119] Also, for one or more points among multiple points that are located on lanes respectively included in one or more grid roads, geometric information and attribute information related to each lane (such as direction indication information, type, speed information, etc.) can be matched and stored.

[0120] In step S320, the server 100 can generate connection information between one or more grid roads (lattice road edges (LREs) of a square-shaped road, Figure 13 (B) and Figure 13 (C)'s LRE1, LRE2, LRE3, LRE4, LRE5, and LRE6). For example, the server 100 can determine whether the one or more grid roads cross each other, and generate connection information representing the connection relationship between the generated one or more grid roads based on the determination of whether they cross.

[0121] At this time, the server 100 can determine the form of the connection information based on the length of the intersection interval between the one or more grid roads. For example, as Figure 13 shown, when the first grid road LR_A and the second grid road LR_B cross and the length of the intersection interval is 0, the server 100 can generate connection information in the form of points (such as XPoint3, XPoint4, XPoint5, XPoint6).

[0122] On the other hand, as Figure 13 shown, when the first grid road LR_A and the third grid road LR_C cross and include an intersection interval with a specified length, that is, when the length of the intersection interval is not 0, the server 100 can generate linear connection information with a specified length (such as XSeg1, XSeg2).

[0123] In step S330, the server 100 can generate a grid road network that connects the one or more grid roads generated in step S310 according to the connection information generated in step S320 (such as Figure 13 (B) and Figure 13 (C)).

[0124] That is, the server 100 generates grid road network data according to the above method, which can be used to generate a short-term driving plan for the autonomous vehicle 10 (such as a driving path from the first grid included in one grid road to the second grid).

[0125] Referring back to Figure 3 , in step S130, the server 100 can generate a road intersection map using the grid road network data generated in step S120.

[0126] Among them, the road intersection map can refer to data for the long-term driving plan of the autonomous vehicle 10.

[0127] In various embodiments, the server 100 may generate a road intersection map connecting more than one grid road by using grid road network data.

[0128] First, the server 100 may determine whether it is possible to move between one or more lanes included in the first grid road and one or more lanes included in the second grid road based on the grid road network data.

[0129] For example, as Figure 15 shown, when there is a dashed-line shaped lane changeable section set in the direction from the second grid road LR_B to the fourth grid road LR_D, it is possible to change lanes from the second grid road LR_B to the fourth grid road LR_D. However, the distance from the first lane of the second grid road LR_B to the fourth grid road LR_D is long. Considering that when changing lanes according to the Road Traffic Law, it is necessary to change lanes one by one for each lane, in reality, it may not be possible to move from the first lane of the second grid road LR_B to the fourth grid road LR_D.

[0130] If this is not considered, when connecting the first lane of the second grid road LR_B and the fourth grid road LR_D with a movable path, the autonomous driving vehicle 10 changing lanes from the first lane of the second grid road LR_B to the fourth grid road LR_D based on the driving plan generated according to this data may put other surrounding vehicles in a dangerous situation or may cause inconvenience, and may be fined or have points deducted according to Article 19 (Ensuring Safety Distance, etc.), Paragraph 3 of the Road Traffic Law ("When the driver of any vehicle changes the path of the vehicle, if there is a concern that it may obstruct the normal passage of other vehicles coming in the direction to which it is to change, the driver shall not change the path").

[0131] Considering this, the server 100 may determine whether it is possible to move between the lanes included in the first grid road and the second grid road respectively for the connected first grid road and second grid road, and generate a road intersection map connecting one or more lanes included in the first grid road and one or more lanes included in the second grid road based on the determined movability.

[0132] Among them, the method for determining whether it is possible to move between one or more lanes included in the first grid road and one or more lanes included in the second grid road may be determined based on the distance between one or more lanes included in the first grid road and one or more lanes included in the second grid road, the length of the crossable section set between the first grid road and the second grid road, and the lane change cycle according to the attributes of the road (such as 30m for ordinary roads and 100m for expressways), but is not limited thereto.

[0133] In various embodiments, the server 100 may generate a driving plan (short-term driving plan and long-term driving plan) for the autonomous vehicle 10 by using the grid road network data and road intersection map generated according to the above method.

[0134] For example, as Figure 16 shown, when destination-related information is input from the user, the server 100 may formulate a long-term driving plan from the user's current location to the destination by using the user's location information (or the location information of the autonomous vehicle 10 in which the user is riding), the destination-related location information input from the user, and the road intersection map. For example, the server 100 may select one or more roads for driving from the user's current location to the destination by using the road intersection map, and may generate a long-term driving plan that connects the selected one or more roads.

[0135] After that, the server 100 may formulate a short-term driving plan from the user's current location to the destination by using the grid road network data. For example, the server 100 may connect a plurality of grids respectively set for one or more roads selected by using the road intersection map, and may generate a short-term driving plan on the one or more roads selected by using the road intersection map.

[0136] The above method for generating a road network map for a driving plan of an autonomous vehicle will be described with reference to the flowchart shown in the figure. For the sake of brief description, the method for generating a road network map for a driving plan of an autonomous vehicle is described in a manner represented by a series of blocks, but the present invention is not limited to the order of the above blocks. Several blocks may be shown in this specification and executed in an order different from the described order or simultaneously, and can be executed by adding new blocks not described in this specification and the figure, or deleting or changing part of the blocks.

[0137] As described above, embodiments of the present invention have been described with reference to the drawings, but those of ordinary skill in the technical field to which the present invention pertains can understand that the present invention can be implemented in other specific forms without changing its technical idea or essential features. Therefore, it should be understood that the above-described embodiments are illustrative in all respects and not restrictive.

Claims

1. A method for generating a road network map of a driving plan for an autonomous vehicle, which is executed by a computing device, characterized in that, Including: Steps of generating regional relevant road network data; Steps of generating grid road network data for short-term driving plans of autonomous vehicles by using the generated above-mentioned road network data; And Steps of generating road intersection diagrams for long-term driving plans of the above-mentioned autonomous vehicles by using the generated above-mentioned grid road network data, wherein, the steps of generating the above-mentioned grid road network data include: Steps of generating one or more grid roads by using the generated above-mentioned road network data; Steps of generating connection information between the generated above-mentioned one or more grid roads; and Steps of generating a grid road network connecting the generated above-mentioned one or more grid roads according to the generated above-mentioned connection information, The steps of generating the above-mentioned road intersection diagrams include: Steps of judging whether it is possible to move between one or more lanes included in a first grid road and one or more lanes included in a second grid road based on the generated above-mentioned grid road network data; and Steps of generating the above-mentioned road intersection diagrams connecting one or more lanes included in the above-mentioned first grid road and one or more lanes included in the above-mentioned second grid road based on the above-mentioned judgment of whether it is possible to move.

2. The method for generating a road network map for a driving plan of an autonomous vehicle according to claim 1, wherein The steps of generating the above-mentioned road network data include: Steps of generating a first road network representing the connection relationship between a first road located in the above-mentioned region and a second road connected to the above-mentioned first road; and Steps of generating a second road network representing the connection relationship between a plurality of first lane lines included in the above-mentioned first road and a plurality of second lane lines included in the above-mentioned second road by using the generated above-mentioned first road network.

3. The method for generating a road network map for a driving plan of an autonomous vehicle according to claim 2, wherein The steps of generating the above-mentioned first road network include: Steps of respectively graphing the above-mentioned first road and the above-mentioned second road to generate a first road graph and a second road graph, and the generated above-mentioned first road graph and the generated above-mentioned second road graph include the shape information, direction information and attribute information of the above-mentioned first road and the above-mentioned second road respectively; and Steps of connecting the generated above-mentioned first road graph and the generated above-mentioned second road graph to generate the above-mentioned first road network.

4. The method for generating a road network map of a driving plan for an autonomous vehicle according to claim 2, wherein, The steps of generating the above-mentioned first road network include: Steps of respectively dividing the above-mentioned first road and the above-mentioned second road according to a set benchmark to generate one or more independent roads and one or more subordinate roads; and Steps of connecting the generated above-mentioned one or more independent roads and the generated above-mentioned one or more subordinate roads to generate the above-mentioned first road network, and cross-connecting an independent road and a subordinate road.

5. The method for generating a road network map for a driving plan of an autonomous vehicle according to claim 2, wherein The steps of generating the above-mentioned second road network include: Steps of respectively graphing the above-mentioned plurality of first lane lines and the above-mentioned plurality of second lane lines to generate a first lane line graph representing the respective relative positions of the above-mentioned plurality of first lane lines and a second lane line graph representing the respective relative positions of the above-mentioned plurality of second lane lines, and the generated above-mentioned first lane line graph and the generated above-mentioned second lane line graph include the respective attribute information of the above-mentioned plurality of first lane lines and the above-mentioned plurality of second lane lines; and Steps of connecting the generated above-mentioned first lane line graph and the generated above-mentioned second lane line graph to generate the above-mentioned second road network.

6. The method for generating a road network map for a driving plan of an autonomous vehicle according to claim 1, wherein, The steps of generating one or more of the above grid roads include grouping one or more lanes that meet the set conditions among multiple lanes located inside the above region based on the generated above road network data to generate one or more grid roads, and the above set conditions have the same attributes and can be physically and legally moved.

7. The method for generating a road network map for a driving plan of an autonomous vehicle according to claim 1, wherein The steps of generating one or more of the above grid roads include: The step of setting multiple points in the form of a grid on the generated one or more of the above grid roads; and The step of storing by matching the geometric information and semantic information related to the grid roads where the above multiple set points are located respectively at the set above multiple points.

8. The method for generating a road network map of a driving plan for an autonomous vehicle according to claim 1, wherein, The steps of generating the above connection information include determining whether the generated one or more of the above grid roads cross, generating connection information representing the connection relationship between the generated one or more of the above grid roads based on the above determination of crossing or not, and the form of the generated above connection information is determined based on the length of the crossing section between the generated one or more of the above grid roads.

9. A road network map generation server for a driving plan of an autonomous vehicle, characterized in that it includes: a processor; a network interface; a memory; and a computer program, loaded into the above memory and executed by the above processor, the above computer program includes: instructions for generating road network data related to a region; instructions for generating grid road network data for a short-term driving plan of an autonomous vehicle using the generated above road network data; and instructions for generating a road intersection map for a long-term driving plan of the above autonomous vehicle using the generated above grid road network data, wherein the instructions for generating the above grid road network data include: instructions for generating one or more grid roads using the generated above road network data; instructions for generating connection information between the generated one or more of the above grid roads; and instructions for generating a grid road network connecting the generated one or more of the above grid roads according to the generated above connection information, the instructions for generating the above road intersection map include: instructions for determining whether it is possible to move between one or more lanes included in a first grid road and one or more lanes included in a second grid road based on the generated above grid road network data; and instructions for generating the above road intersection map connecting one or more lanes included in the above first grid road and one or more lanes included in the above second grid road based on the above determination of whether it is possible to move.

10. A computer program stored in a computer-readable recording medium, characterized in that, Combined with a computing device and stored in a computer-readable recording medium to perform the following steps, which include: The step of generating road network data related to a region; The step of generating grid road network data for a short-term driving plan of an autonomous vehicle using the generated above road network data; and The step of generating a road intersection map for a long-term driving plan of the above autonomous vehicle using the generated above grid road network data, wherein the step of generating the above grid road network data includes: The step of generating one or more grid roads using the generated above road network data; The step of generating connection information between the generated one or more of the above grid roads; and The step of generating a grid road network of one or more grid roads generated according to the above-generated connection information The step of generating the above road intersection map includes: The step of determining whether movement is possible between one or more lanes included in the first grid road and one or more lanes included in the second grid road based on the above-generated grid road network data; and The step of generating the above road intersection map that connects one or more lanes included in the above first grid road and one or more lanes included in the above second grid road based on the above determination of whether movement is possible.

Images