Information processing apparatus, information processing method, and storage medium

Abstract

The invention relates to an information processing apparatus, an information processing method, and a storage medium. The present disclosure assigns information indicating lanes of a road to a road map based on data acquired from a plurality of vehicles. This information processing device is provided with a control unit (110) that: acquires, from a first vehicle, lane topology information indicating a lane topology of a road on which the first vehicle travels, said lane topology information being estimated on the basis of data acquired via an on-board sensor of the first vehicle, and first information including position information corresponding to the lane topology information; associating one or more pieces of lane topology information acquired from the plurality of first vehicles with each of a plurality of road segments included in a road map based on the first information; and determining a lane topology based on the corresponding one or more pieces of lane topology information for each of a plurality of road segments included in the road map.

Description

Technical Field

[0001] This disclosure relates to map generation. Background Technology

[0002] There are technologies for automatically generating maps. For example, Patent Document 1 discloses a map generation device that establishes a correspondence between the lanes to be entered and the lanes to be passed based on the vehicle's driving trajectory, and also establishes a correspondence between the lanes to be entered and the lanes to be passed based on external conditions detected by a camera.

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2023-149356

[0006] Patent Document 2: Japanese Patent No. 6958535

[0007] Patent Document 3: Japanese Patent No. 7151894 Summary of the Invention

[0008] The purpose of this disclosure is to assign lane information representing roads to road maps based on data obtained from multiple vehicles.

[0009] One aspect of this disclosure is an information processing apparatus comprising a control unit that performs the following actions: acquiring lane topology information, which is inferred from data acquired via onboard sensors of the first vehicle and represents the lane topology of a road traversed by the first vehicle, and first information including location information corresponding to the lane topology information; establishing a correspondence between one or more lane topology information acquired from multiple first vehicles and each of multiple road segments included in a road map, based on the first information; and determining a lane topology for each of the multiple road segments included in the road map based on the corresponding one or more lane topology information.

[0010] Furthermore, another aspect of this disclosure is an information processing method comprising the following steps: acquiring lane topology information, which is inferred from data acquired via onboard sensors of the first vehicle, representing the lane topology of the road traveled by the first vehicle, and first information including location information corresponding to the lane topology information; establishing a correspondence between one or more lane topology information acquired from multiple first vehicles and each of multiple road segments included in a road map based on the first information; and determining a lane topology for each of the multiple road segments included in the road map based on the corresponding one or more lane topology information.

[0011] In addition, as another option, a program for causing a computer to perform the above-described information processing method or a computer-readable storage medium for non-temporarily storing the program is provided.

[0012] Invention Effects

[0013] According to this disclosure, road maps can be assigned lane information representing roads based on data obtained from multiple vehicles. Attached Figure Description

[0014] Figure 1 It is a diagram that shows a summary of the processes performed by the server device.

[0015] Figure 2 This diagram illustrates the constituent elements of the server device according to the first embodiment.

[0016] Figure 3 This is a flowchart of the processing performed by the control unit of the server device in the first embodiment.

[0017] Figure 4 This is a diagram illustrating an example of configuring nodes and edges.

[0018] Figure 5 This is a diagram illustrating information about the vehicle's posture.

[0019] Figure 6 This is a flowchart of the lane topology processing performed by the control unit of the server device in the second embodiment.

[0020] Explanation of reference numerals in the attached figures:

[0021] 100: Server device;

[0022] 110: Control Department;

[0023] 111: Acquisition Department;

[0024] 112: Distribution Department;

[0025] 113: Decision-Making Department;

[0026] 120: Storage Department;

[0027] 130: Ministry of Communications. Detailed Implementation

[0028] (summary)

[0029] In autonomous vehicles, driving control is achieved using a map of the surrounding area where the vehicle is traveling.

[0030] For example, in autonomous vehicles, high-resolution maps downloaded from external devices are used for autonomous driving control. In this case, if the high-resolution maps are not updated appropriately to match the current situation, it will create obstacles in the vehicle's autonomous driving control.

[0031] However, updating high-resolution maps requires the use of specialized surveying vehicles, and frequent updates are costly.

[0032] Suppose that even without using high-resolution maps that are difficult to update frequently, the current alternative road maps do not contain the lane information required for autonomous driving control. Without lane information or information on the connectivity between lanes, the vehicle's autonomous driving control may struggle to determine the correct lane, thus hindering proper autonomous driving control.

[0033] Therefore, it is preferable not to collect data measured by a dedicated survey vehicle used to generate high-resolution maps, but to collect data measured by multiple vehicles such as connected cars, and to assign lane information representing roads to existing road maps based on this data.

[0034] This is because by effectively utilizing the data measured by existing vehicles, there is no need to drive dedicated measurement vehicles to obtain the data required for updating high-resolution maps. Furthermore, this is because by incorporating information about missing lanes in road maps used for autonomous driving control based on the data measured by vehicles, smooth autonomous driving control can be achieved.

[0035] An information processing apparatus according to one embodiment of the present disclosure includes a control unit that performs the following operations: acquiring lane topology information, which is inferred from data acquired via onboard sensors of the first vehicle and represents the lane topology of the road traveled by the first vehicle, and first information including location information corresponding to the lane topology information; establishing a correspondence between one or more lane topology information acquired from multiple first vehicles and each of multiple road segments included in a road map based on the first information; and determining a lane topology for each of the multiple road segments included in the road map based on the corresponding one or more lane topology information.

[0036] Lane topology is information representing the topology of lanes relative to each other, or the topology of objects on or near the road and lanes. Here, an object can be any of several types of objects that represent a specific meaning in a road map. Topology is a mathematical structure representing the spatial relationships between objects. That is, topological information represents how the lanes that make up a road are connected to each other, and how objects on or near the road are connected to lanes.

[0037] The first information includes location information corresponding to the lane topology information. Specifically, the first information includes location information indicating which location on the road a given lane topology information represents. Additionally, the first information may also include the latitude and longitude information of the first vehicle and information indicating the orientation of the first vehicle.

[0038] A road segment is a section of a road shown on a road map that represents a part of a road route divided into multiple zones. For example, a road segment can be a section on a road map corresponding to a road from one intersection to the next.

[0039] One aspect of this disclosure involves an information processing device that acquires lane topology information and first information, and establishes a correspondence between one or more lane topology information and a road segment based on the first information. Then, the information processing device determines the lane topology for the established road segment.

[0040] The accuracy of lane topology assigned to road maps can be improved by acquiring lane topology information and primary information from multiple vehicles and establishing correspondences between them and road segments. Furthermore, by determining the lane topology of a specific area based on lane topology information corresponding to that area in the road map, the lane topology of that area can be accurately determined without confusion with lane topology information from other areas.

[0041] Based on the above configuration, an information processing device of this disclosure can assign lanes to each area on a road map or indicate the connection relationship between lanes.

[0042] Alternatively, the lane topology can be a network topology representing the road network topology in units of carriageways, and the lane topology information can be information about the network topology of the represented portion inferred from the data.

[0043] Alternatively, when determining the lane topology for each of the plurality of road segments, the control unit may configure the edges representing the vehicle's travel route and the nodes connecting the edges to each other on the road segment of the object.

[0044] Therefore, the information processing apparatus of one embodiment of this disclosure can represent lane topology through a combination of nodes that are endpoints of the edges. Thus, the information processing apparatus of one embodiment of this disclosure represents lane topology through edges and nodes representing the vehicle's travel path, thereby determining the appropriate vehicle travel path (trajectory).

[0045] Alternatively, the first information may also include the latitude and longitude information of the first vehicle and information indicating the posture of the first vehicle.

[0046] Alternatively, the information representing the posture of the first vehicle can be represented by the rotation angle of an axis parallel to the vehicle's direction of travel relative to the axis of the geographic coordinate system.

[0047] Therefore, the information processing apparatus of one embodiment of this disclosure can accurately determine the position corresponding to the lane topology information by taking into account the vehicle's posture when the lane topology information is acquired. Thus, the information processing apparatus of one embodiment of this disclosure can assign accurate lane topology to a road map.

[0048] Alternatively, the location information corresponding to the lane topology information can be represented by a coordinate system based on the first vehicle. The control unit uses the latitude and longitude information of the first vehicle and information representing the posture of the first vehicle to correct the coordinate system of the location information to a geographic coordinate system.

[0049] Therefore, the information processing device of one embodiment of this disclosure can use the geographic coordinate system used in the road map to represent the location information corresponding to the lane topology information.

[0050] When the location information corresponding to the lane topology information is represented using a coordinate system based on the first vehicle, the control unit cannot assign lane topology information to the road segments included in the road map. Therefore, the control unit can also convert the coordinate system of the location information corresponding to the lane topology information into a geographic coordinate system used for the road map. This allows the control unit to assign lane topology information to the road map.

[0051] Alternatively, the control unit may determine which lane topology information to establish based on the number of carriageways in each lane topology information when there are multiple candidate lane topology information for each of the plurality of road segments.

[0052] For example, when multiple candidate lane topology information entries exist, a majority vote can be used to determine which lane topology information entry will be associated with the road segment. This is because if the lane number represented by the lane topology information differs from others, it may be due to a misidentification of the lane number. In this way, the control unit can exclude lane topology information with low accuracy.

[0053] Alternatively, the control unit may determine the lane topology corresponding to the road segment by using the lane topology represented by a randomly selected lane topology information from the plurality of lane topology information, provided that a correspondence has been established between the plurality of lane topology information and each of the plurality of road segments.

[0054] Alternatively, when the control unit has established a correspondence between the multiple lane topology information and each of the multiple road segments, it may use the result obtained by integrating the multiple lane topology information to determine the lane topology corresponding to the road segment.

[0055] Lane topology information integration can be achieved, for example, by excluding information deemed to contain errors from multiple lane topology data sets and selecting appropriate lane topology data. Alternatively, lane topology information integration can be achieved by clustering multiple lane topology data sets based on their similarity and using the lane topology information corresponding to the cluster with the most members.

[0056] Hereinafter, specific embodiments of the present disclosure will be described based on the accompanying drawings. Unless otherwise specified, the hardware configuration, module configuration, functional configuration, etc., described in each embodiment are not intended to limit the scope of the disclosed technology.

[0057] (First Implementation)

[0058] [Summary of the processing performed by the server device]

[0059] Reference Figure 1An overview of the information processing apparatus of the first embodiment will be described. Figure 1 This is a diagram illustrating the outline of the processing performed by the server device. In this embodiment, the information processing apparatus is implemented, for example, as server device 100. Server device 100 communicates with vehicle 10 and obtains various data from vehicle 10 to update the road map. Typically, vehicle 10 is an autonomous vehicle capable of communicating with external devices via a wireless communication network (e.g., a cellular communication network). It should be noted that vehicle 10 is a specific example of a "first vehicle".

[0060] Vehicle 10 generates a road map in real time based on the data sensed by the vehicle, and drives autonomously using the road map.

[0061] The onboard device of vehicle 10 generates a road map showing the lanes, objects on the road, and their connections for the area surrounding the vehicle. Vehicle 10 drives using autonomous driving control based on this road map. For smooth autonomous driving control, it is preferable that vehicle 10 acquires the road map from an external source for areas outside its own perimeter that it does not sense. Furthermore, it is preferable that this road map is infused with information related to the road lanes.

[0062] Therefore, the server device 100, which serves as the central device for communicating with the vehicles 10, generates a wide-area road map with lane information assigned to the road based on various data acquired from the multiple vehicles 10. The multiple vehicles 10 download the generated road map from the server device 100 in a timely manner. Thus, the vehicle 10 that receives the road map can obtain a road map with lane information assigned to the road for areas outside the range that the vehicle can sense.

[0063] It should be noted that, even without the current road map, the server device 100 can also generate a new road map of the area outside the area surrounding the vehicle 10 based on various data obtained from multiple other vehicles 10.

[0064] First, the server device 100 obtains lane topology information and corresponding location information for each of the multiple vehicles 10 acquired during their travel. Here, the lane topology information represents the network topology of a portion of the road's lanes traversed by the multiple vehicles 10. That is, the lane topology information represents the connection scheme between the road lanes. Furthermore, the location information corresponding to the lane topology information indicates the location on the road corresponding to the lane topology represented by the lane topology information.

[0065] Next, the server device 100 establishes a correspondence between a lane topology information and one of multiple road segments. The server device 100 also establishes a correspondence between the lane topology information and the road segment located on the road map corresponding to the position information of a given lane topology information. That is, the server device 100 calculates the position on the road corresponding to the lane topology represented by the lane topology information based on the position information, and then establishes a correspondence between the lane topology information and the road segment corresponding to that position. In the case of multiple lane topology information entries corresponding to a single road segment, a prescribed method is used to determine which lane topology information to establish.

[0066] Next, the server device 100 determines the lane topology for the edges included in the road segment. An edge is a line segment with two nodes as endpoints, used to represent the lane topology. The lane topology is represented by a combination of edges and nodes. The server device 100 determines the lane topology at the edge corresponding to the location of a road segment. For example, the lane topology at edge 220b indicates that the endpoints of edge 220b are nodes 210a and 210b. Moreover, this lane topology indicates that node 210a, as an endpoint of edge 220b, is connected to other nodes 210c via edge 220c, and further connected to node 210d via edge 220d. In addition, there may be multiple edges in a road segment, each corresponding to multiple lanes. For example, if the road on which vehicle 10 travels consists of multiple lanes, and lane topology information about these multiple lanes is obtained, sometimes a lane topology consisting of multiple parallel edges is determined for a road segment.

[0067] The server device 100 determines the lane topology at each edge and generates a road map that assigns lane topology information to each road segment.

[0068] Thus, the server device 100 can assign appropriate lane topology information to road maps that do not have lane topology information, based on data measured by multiple vehicles 10.

[0069] As described above, the server device 100 can assign network topology information representing the lanes of a road to a road map based on data acquired from multiple vehicles. Furthermore, by acquiring such a road map through the vehicle 10, the vehicle 10 can also obtain lane-related information about the road in areas beyond its sensing range, thereby enabling smooth autonomous driving control.

[0070] [Server Device Configuration]

[0071] Next, the hardware and software configurations of each device constituting the server device 100 will be described. Figure 2This diagram illustrates the constituent elements of the server device 100 according to the first embodiment.

[0072] Server device 100 can be configured as a computer having a processor (CPU, GPU, etc.), main storage (RAM, ROM, etc.), and auxiliary storage (EPROM, hard disk drive, removable media, etc.). The auxiliary storage stores an operating system (OS), various programs, various tables, etc., and can execute the programs stored therein to achieve the various functions (software modules) that meet the specified purposes as described below. However, some or all of the functions can also be implemented as hardware modules using hardware circuits such as ASICs (Application Specific Integrated Circuits) and FPGAs (Field-Programmable Gate Arrays).

[0073] The server device 100 is configured to include a control unit 110, a storage unit 120, and a communication unit 130.

[0074] The control unit 110 is implemented using a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit) and memory. The control unit 110 includes an acquisition unit 111, an allocation unit 112, and a decision unit 113 as functional modules. These functional modules can also be implemented by the control unit 110 executing programs.

[0075] The acquisition unit 111 communicates with multiple vehicles 10 via the communication unit 130 to acquire lane topology information and first information. Here, lane topology information is information representing the connection methods between lanes of a road or between lanes of a road and objects on or near the road; it is information that uses a mathematical structure to represent the spatial relationship between lanes or between objects and lanes. Furthermore, the first information refers to information including location information corresponding to the lane topology information. Specifically, the first information may include location information corresponding to the lane topology information, the latitude and longitude information of the first vehicle, and information representing the orientation of the first vehicle.

[0076] The allocation unit 112 establishes a correspondence between lane topology information and road segments included in the road map based on the first information. When multiple lane topology information is obtained, the allocation unit 112 establishes a correspondence between each lane topology information and any one of the multiple road segments included in the road map. It should be noted that multiple lane topology information can also be corresponded to a single road segment. Here, a road segment refers to an area obtained by capturing a portion of the roads included in the road map. For example, a road segment can also be an area obtained by capturing the road from one intersection to the next intersection.

[0077] The decision unit 113 determines the lane topology for each of the multiple road segments included in the road map, based on one or more corresponding lane topology information. The decision unit 113 determines the lane topology of the lanes included in the road segment based on the lane topology information corresponding to the road segment determined by the allocation unit 112. Here, lane topology refers to the network topology representing the connection schemes between lanes or between lanes and objects on the road.

[0078] Storage unit 120 may be a main storage device such as RAM (Random Access Memory) or ROM (Read Only Memory), an auxiliary storage device such as EPROM (Erasable Programmable Read Only Memory), a hard disk drive, or a removable medium. The auxiliary storage device stores an operating system (OS), various programs, various tables, etc., and can perform various functions that conform to the purposes specified by each part of control unit 110 by executing the programs stored therein. However, some or all of the functions may also be implemented using hardware circuits such as ASICs or FPGAs.

[0079] The storage unit 120 stores data used or generated in the processing performed in the control unit 110. Furthermore, the storage unit 120 may also store first information and lane topology information obtained from the vehicle 10.

[0080] The communication unit 130 is composed of a communication circuit for wireless communication. For example, the communication unit 130 may be a communication circuit for wireless communication using 4G (4th Generation) or 5G (5th Generation) technology. Furthermore, the communication unit 130 may be a communication circuit for wireless communication using LTE (Long Term Evolution) or for communication using LPWA (Low Power Wide Area). Additionally, the communication unit 130 may also be a communication circuit for wireless communication using Wi-Fi (registered trademark).

[0081] [Server device processing]

[0082] Next, the specific details of the processing performed by the server device 100 will be explained. Figure 3 This is a flowchart of the process performed by the control unit 110 of the server device 100 in the first embodiment.

[0083] The server device 100, for example, performs periodic operations. Figure 3 The processing described in the document. Alternatively, server device 100 may also begin processing any request received from a user such as vehicle 10. Figure 3 The processing described herein. Any request could refer to an operation requesting the download of road maps required for the autonomous driving control of vehicle 10.

[0084] First, in step S10, the acquisition unit 111 acquires lane topology information and first information. The acquisition unit 111 communicates with the plurality of vehicles 10 via the communication unit 130, and acquires lane topology information and first information from each of the plurality of vehicles 10. The acquisition unit 111 may also acquire multiple lane topology information corresponding to the same position from each of the plurality of vehicles 10.

[0085] In step S11, the allocation unit 112 obtains the number of lanes of the target road segment based on lane topology information. The allocation unit 112 determines the number of lanes of the target road segment by selecting the number of lanes represented by multiple lane topology information corresponding to the target road segment using a predetermined method. The lane topology information corresponding to the target road segment refers to lane topology information where the location of the road segment is approximately consistent with the location information represented by the corresponding lane topology information.

[0086] The allocation unit 112 may also determine the number of lanes of the road segment of the object by the lane topology information that represents the most lane topology information among multiple lane topology information corresponding to the road segment of the object.

[0087] Next, in step S12, the allocation unit 112 establishes a correspondence between lane topology information and the target road segment based on the number of lanes determined in step S11. The allocation unit 112 establishes a correspondence between a road segment and an appropriate lane topology information suitable for the number of lanes determined in step S11 from among multiple lane topology information corresponding to the location of the road segment. For example, the allocation unit 112 may also establish a correspondence between lane topology information randomly selected from multiple lane topology information corresponding to the location of the road segment and suitable for the number of lanes of the target road segment.

[0088] Next, in step S13, the decision unit 113 determines the lane topology corresponding to each road segment based on the lane topology information established with each road segment. Specifically, when determining the lane topology for each of the multiple road segments, the decision unit 113 configures the edges representing the vehicle's travel route and the nodes connecting the edges to each other on the target road segment.

[0089] Figure 4 This is a diagram illustrating examples of configuring nodes and edges. For example... Figure 4 As shown, the decision unit 113 configures one or more nodes 210 for the road segment 200. When the road segment 200 includes multiple lanes, the decision unit 113 configures a node 210 for each lane. Then, the decision unit 113 configures an edge 220 between two nodes 210. One edge corresponds to one lane. For example, in a road segment 200 with two lanes, two edges 220 and four nodes 210 as their ends are configured.

[0090] As described above, the decision unit 113 can determine the network topology of each road segment, indicating which node a certain node is connected to.

[0091] In the first embodiment, the acquisition unit 111 acquires lane topology information corresponding to each road segment and first information such as the location corresponding to the lane topology information from multiple vehicles 10. Then, the determination unit 113 determines the appropriate lane topology in each road segment based on the multiple lane topology information. As a result, the server device 100 can assign lane information representing roads to the road map based on the data acquired from the multiple vehicles.

[0092] (A variation of the first embodiment)

[0093] In the first embodiment, the server device 100 establishes a correspondence between lane topology information and road segments using location information corresponding to the lane topology information included in the first information. However, the location information corresponding to the lane topology information is not always limited to the form that can be used in the server device 100. For example, the location information corresponding to the lane topology information obtained from the vehicle 10 is sometimes represented using a coordinate system centered on the vehicle. On the other hand, the generation (or updating) of road maps sometimes requires location information represented in a geographic coordinate system. Therefore, in a variation of the first embodiment, the server device 100 uses the information representing the vehicle's posture included in the first information to correct the coordinate system of the location information corresponding to the lane topology information to a geographic coordinate system for use.

[0094] Figure 5 This is a diagram illustrating information representing the orientation of vehicle 10. The information representing the orientation of vehicle 10 is included in the first information. The information representing the orientation of vehicle 10 is information indicating the angle of inclination of the axis showing the direction of travel of vehicle 10 relative to the X-axis of the geographic coordinate system. Alternatively, the information representing the orientation of vehicle 10 may also be information indicating the angle of inclination of the axis showing the direction of travel of vehicle 10 relative to the Y-axis of the geographic coordinate system.

[0095] The allocation unit 112 uses the latitude and longitude information of the vehicle 10 and the information representing the attitude of the vehicle 10 acquired by the acquisition unit 111 to correct the coordinate system of the position information corresponding to the lane topology information from a coordinate system centered on the vehicle 10 to a geographic coordinate system. Specifically, the coordinates of the position information corresponding to the lane topology information represented by the coordinate system centered on the vehicle 10 can be rotated by the angle represented by the information representing the attitude of the vehicle 10, thereby correcting them to coordinates in the geographic coordinate system.

[0096] In this way, the server device 100 can convert the location information corresponding to the lane topology information obtained from the vehicle into a geographic coordinate system for processing.

[0097] (Second Implementation)

[0098] [Summary of the processing performed by the server device]

[0099] In the first embodiment, the server device 100 determines the lane topology of a road segment by establishing a correspondence between the most appropriate lane topology information from multiple lane topology information corresponding to the location of the target road segment and the road segment. However, when multiple lane topology information corresponding to the location of the road segment exist, it is sometimes preferable to consider all of these lane topology information to determine the lane topology corresponding to the location of the road segment. Therefore, in the second embodiment, the server device 100 integrates the multiple lane topology information corresponding to the location of the target road segment to select the appropriate lane topology information and assigns the selected lane topology information to the road segment.

[0100] Figure 6 This is a flowchart of the process for determining the lane topology executed by the control unit 110 of the server device 100 in the second embodiment. Figure 6 The processing described in the document is as follows Figure 3 Step S12 is executed after the processing of step S13.

[0101] First, in step S20, the decision unit 113 determines whether the multiple lane topology information corresponding to the allocation unit 112 has been established with the road segment of the target. If multiple lane topology information suitable for... Figure 3 In step S11, given the lane topology information for the number of lanes determined, it can be said that multiple lane topology information pieces have established a correspondence with the target road segment. This step becomes a positive determination when the determination unit 113 determines that multiple lane topology information pieces have established a correspondence with the target road segment.

[0102] If the decision is positive in this step, the process proceeds to step S21.

[0103] If the decision is negative in this step, the processing is transferred to... Figure 3 S13 as described in the text.

[0104] When the process is transferred to step S21, the decision unit 113 determines the lane topology of the target road segment by integrating multiple lane topology information corresponding to the target road segment.

[0105] As a process for integrating multiple lane topology information, for example, it can be illustrated by classifying (e.g., clustering) the multiple lane topology information according to each lane topology and using the lane topology with the most data.

[0106] For example, the decision unit 113 selects the lane topology information corresponding to the content represented by the most lane topology information among multiple lane topology information as the lane topology information of the target road segment. For example, let's explain the case where three lane topology information corresponds to a certain road segment. If two of the three lane topology information indicate that node 3 is connected to node 1, and one lane topology information indicates that node 2 is connected to node 1, the decision unit 113 can use the lane topology information indicating that node 3 and node 1 are connected. That is, the decision unit 113 can use the lane topology information represented by the most frequent lane topology information among all lane topology information for each road segment.

[0107] It should be noted that any method that can integrate multiple lane topologies is acceptable, but other methods can also be used.

[0108] Next, in step S22, the decision unit 113 determines the lane topology corresponding to the road segment of the target based on the lane topology information used.

[0109] In the second embodiment, the server device 100 can integrate multiple lane topology information and determine an appropriate lane topology for the target road segment. Therefore, the server device 100 can appropriately assign lane information representing the road to the road map based on data obtained from multiple vehicles.

[0110] (Other variations)

[0111] The above-described embodiments are merely examples, and this disclosure can be implemented with appropriate modifications without departing from its spirit. For example, the processes and methods described in this disclosure can be freely combined and implemented as long as no technical contradictions arise.

[0112] This disclosure includes an information processing method that performs the processing described in the above embodiments, and a program for causing a computer to execute the information processing method.

[0113] This disclosure can also be implemented by supplying a computer program that implements the functions described in the above embodiments to a computer, and having one or more processors of the computer read and execute the program. Such a computer program can be provided to the computer by a non-transitory computer-readable storage medium that can be connected to the computer's system bus, or it can be provided to the computer via a network. Non-transitory computer-readable storage media include, for example, any type of disk such as a hard disk (floppy disk, hard disk drive, etc.), an optical disk (CD-ROM, DVD, Blu-ray disc, etc.), a read-only memory (ROM), a random access memory (RAM), an EPROM, an EEPROM (Electrically Erasable Programmable Read Only Memory), a magnetic card, flash memory, an optical card, or any type of medium suitable for storing electronic instructions.

Claims

1. An information processing device comprising a control unit, The control unit performs the following actions: From the first vehicle, obtain lane topology information that represents the lane topology of the road traveled by the first vehicle, based on data obtained via the vehicle's onboard sensors, and first information including location information corresponding to the lane topology information; Based on the first information, a correspondence is established between one or more lane topology information obtained from multiple first vehicles and each of the multiple road segments included in the road map; and For each of the multiple road segments included in the road map, the lane topology is determined based on the corresponding one or more lane topology information.

2. The information processing apparatus according to claim 1, wherein, The lane topology is a network topology that represents roads in units of carriageways. The lane topology information is information representing a portion of the network topology, inferred based on the data.

3. The information processing apparatus according to claim 2, wherein, When determining the lane topology for each of the plurality of road segments, the control unit configures the edges representing the travel route of the first vehicle and the nodes connecting the edges to each other on the road segment of the object.

4. The information processing apparatus according to claim 1, wherein, The first information also includes the latitude and longitude information of the first vehicle and information indicating the posture of the first vehicle.

5. The information processing apparatus according to claim 4, wherein, Information indicating the posture of the first vehicle is represented by the rotation angle of an axis parallel to the vehicle's direction of travel relative to the axis of the geographic coordinate system.

6. The information processing apparatus according to claim 4, wherein, The location information corresponding to the lane topology information is represented by a coordinate system with the first vehicle as the reference. The control unit uses the latitude and longitude information of the first vehicle and the information representing the posture of the first vehicle to correct the coordinate system of the position information to a geographic coordinate system.

7. The information processing apparatus according to claim 1 or 2, wherein, When there are multiple candidate lane topology information for each of the multiple road segments, the control unit determines which lane topology information to establish based on the number of carriageways in each lane topology information.

8. The information processing apparatus according to claim 1 or 2, wherein, When the control unit establishes a correspondence between the multiple lane topology information and each of the multiple road segments, it determines the lane topology corresponding to the road segment by using the lane topology represented by the randomly selected lane topology information from the multiple lane topology information.

9. The information processing apparatus according to claim 1 or 2, wherein, When the control unit establishes a correspondence between the multiple lane topology information and each of the multiple road segments, it uses the result obtained by integrating the multiple lane topology information to determine the lane topology corresponding to the road segment.

10. An information processing method, comprising the following steps: From the first vehicle, obtain lane topology information that represents the lane topology of the road traveled by the first vehicle, based on data obtained via the vehicle's onboard sensors, and first information including location information corresponding to the lane topology information; Based on the first information, a correspondence is established between one or more lane topology information obtained from multiple first vehicles and each of the multiple road segments included in the road map; and For each of the multiple road segments included in the road map, the lane topology is determined based on the corresponding one or more lane topology information.

11. The information processing method according to claim 10, wherein, The lane topology is a network topology that represents roads in units of carriageways. The lane topology information is information representing a portion of the network topology, inferred based on the data.

12. The information processing method according to claim 11, wherein, In the step of determining the lane topology The edges representing the travel route of the first vehicle and the nodes connecting the edges to each other are configured in the road segments of the object.

13. The information processing method according to claim 10, wherein, The first information also includes the latitude and longitude information of the first vehicle and information indicating the posture of the first vehicle.

14. The information processing method according to claim 13, wherein, Information indicating the posture of the first vehicle is represented by the rotation angle of an axis parallel to the vehicle's direction of travel relative to the axis of the geographic coordinate system.

15. The information processing method according to claim 13, wherein, The location information corresponding to the lane topology information is represented by a coordinate system with the first vehicle as the reference. The information processing method further includes the step of using the latitude and longitude information of the first vehicle and information representing the posture of the first vehicle to correct the coordinate system of the location information to a geographic coordinate system.

16. The information processing method according to claim 10, wherein, In the step of establishing a correspondence between the lane topology information and each of the multiple road segments included in the road map, In the case where there are multiple candidate lane topology information for each of the multiple road segments, the lane topology information to be established is determined based on the number of carriageways of each lane topology information.

17. The information processing method according to claim 10, wherein, In the step of determining the lane topology When a correspondence is established between multiple lane topology information and each of the multiple road segments, the lane topology corresponding to the road segment is determined by the lane topology represented by a randomly selected lane topology information from the multiple lane topology information.

18. The information processing method according to claim 10, wherein, In the step of determining the lane topology When a correspondence is established between multiple lane topology information and each of the multiple road segments, the lane topology corresponding to the road segment is determined using the result obtained by integrating the multiple lane topology information.

19. A storage medium storing a program for causing a computer to perform the information processing method as described in any one of claims 10 to 18.

Images