Map generation device, map generation method, map generation program

Abstract

We provide map generation equipment and other devices that can generate highly accurate map data quickly. [Solution] The map generation device has a processor and generates a probe map from probe data collected by a vehicle. The processor is configured to perform the task of acquiring probe data collected when a vehicle travels along a road. The processor is configured to perform the task of generating a probe map by compositing the probe data onto a base map which includes at least base shape information, which is information about the shape of the road. The processor is configured to perform the task of correcting the probe data based on the difference in shape between the probe shape information, which is information about the shape of the road estimated from probe behavior data regarding the behavior of the vehicle in the probe data, and the base shape information. Generating a probe map includes compositing the corrected probe data onto a base map.

Description

Technical Field

[0001] The present disclosure relates to a map generation technology for generating a probe map from probe data collected by a vehicle.

Background Art

[0002] Patent Document 1 discloses a map data generation device that generates map data based on probe data collected from a plurality of vehicles. This map data generation device acquires difference data between the probe data and the basic map data. The map data generation device uses the difference data accumulated for a predetermined number or a predetermined period to exclude transient difference data from the difference data. The map data generation device generates map data based on the remaining difference data.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The map generation device of Patent Document 1 requires accumulation of difference data for a predetermined number or a predetermined period for discrimination of transient difference data. Therefore, there is a possibility that it takes time to generate highly accurate map data.

[0005] An object of the present disclosure is to provide a map generation device capable of generating highly accurate map data at an early stage. Another object of the present disclosure is to provide a map generation program capable of improving the accuracy of map data and shortening the time until generation.

Means for Solving the Problems

[0006] The following describes the technical means of solving the problem described in this disclosure. Note that the claims and the reference numerals in parentheses in this section indicate the correspondence with the specific means described in the embodiments detailed later, and do not limit the technical scope of this disclosure.

[0007] A first aspect of the present disclosure is a map generation device having a processor (102) that generates a probe map (Mp) from probe data collected by a vehicle (1), The processor is This involves acquiring probe data collected as the vehicle travels along the road, The probe data is combined with a base map (Mb) that contains at least base shape information, which is information about the shape of the road, to generate a probe map. It is configured to perform, The processor is The system is configured to further correct the probe data based on the difference in shape between the probe shape information, which is information about the shape of the road estimated from the probe behavior data regarding the vehicle's behavior in the probe data, and the base shape information. Generating a probe map is This includes compositing the corrected probe data onto a base map.

[0008] A second aspect of the present disclosure is a map generation method performed by a processor (102) to generate a probe map (Mp) from probe data collected by a vehicle (1), This involves acquiring probe data collected as the vehicle travels along the road, The probe data is combined with a base map (Mb) that contains at least base shape information, which is information about the shape of the road, to generate a probe map. Includes, moreover, This includes correcting the probe data based on the difference in shape between the probe shape information, which is information about the shape of the road estimated from probe behavior data regarding the behavior of the vehicle in the probe data, and the base shape information. Generating a probe map is This includes compositing the corrected probe data onto a base map.

[0009] A third aspect of this disclosure is a map generation program which includes instructions to be executed by a processor (102) and stored in a storage medium (101) for generating a probe map (Mp) from probe data collected by a vehicle (1), This involves acquiring probe data collected as the vehicle travels along the road, The probe data is combined with a base map (Mb) that contains at least base shape information, which is information about the shape of the road, to generate a probe map. Includes instructions to execute, moreover, The command includes instructions to correct the probe data based on the difference in shape between the probe shape information, which is information about the shape of the road estimated from the probe behavior data regarding the behavior of the vehicle in the probe data, and the base shape information. Generating a probe map is This includes compositing the corrected probe data onto a base map.

[0010] According to these embodiments, the probe shape information of the probe data synthesized on the base map is corrected based on the base shape information of the base map. Since the base map is data that includes base shape information, the need to accumulate data for correcting the probe shape information is avoided. Therefore, the accuracy of the map data is increased, and the time to generate it can be shortened. [Brief explanation of the drawing]

[0011] [Figure 1] This is a block diagram showing the overall configuration of the first embodiment. [Figure 2] It is a schematic diagram showing the driving environment of the vehicle to which the first embodiment is applied. [Figure 3] It is a schematic diagram for explaining the base map according to the first embodiment. [Figure 4] It is a schematic diagram for explaining the probe map according to the first embodiment. [Figure 5] It is a schematic diagram for explaining the probe map according to the first embodiment. [Figure 6] It is a block diagram showing the functional configuration of the map generation device according to the first embodiment. [Figure 7] It is a flowchart showing the map generation flow according to the first embodiment. [Figure 8] It is a schematic diagram showing an example of a point cloud as probe data in the first embodiment. [Figure 9] It is a graph showing an example of data used in the correction process in the first embodiment. [Figure 10] It is a graph showing an example of data used in the correction process in other embodiments.

Embodiments for Carrying Out the Invention

[0012] Hereinafter, an embodiment of the present disclosure will be described based on the drawings.

[0013] (First Embodiment) The map generation device 100 according to the first embodiment shown in FIG. 1 generates a probe map Mp from the probe data collected by the vehicle 1 shown in FIG. 2. From the viewpoint centered on the vehicle 1, the vehicle 1 can also be said to be an ego-vehicle. The vehicle 1 is a moving body such as an automobile that can travel on a road in the state where a passenger is on board.

[0014] Vehicle 1 is provided with an automated driving mode, which is divided into levels according to the degree of manual intervention by the occupant in dynamic driving tasks. The automated driving mode may be implemented by autonomous driving control, in which case the system performs all dynamic driving tasks. Autonomous driving control can be implemented, for example, by conditional driving automation, advanced driving automation, or full driving automation. The automated driving mode may also be implemented by advanced driving assistance control, in which the occupant performs some dynamic driving tasks, such as driving assistance or partial driving automation. The automated driving mode may be implemented by either one of these autonomous driving controls or advanced driving assistance controls, or by a combination of them, or by switching between them.

[0015] Vehicle 1 is equipped with the sensor system 10, communication system 20, and map database Dm shown in Figure 1. The sensor system 10 acquires usable sensor information for the external and internal environments of Vehicle 1 using the map generation device 100. For this purpose, the sensor system 10 is composed of an external sensor 11 and an internal sensor 12.

[0016] The external sensor 11 acquires external information as sensor information from the external environment surrounding the vehicle 1. The external sensor 11 may be a target detection sensor that detects targets present in the external environment of the vehicle 1. The external sensor 11 as a target detection sensor is at least one of the following: a camera, LiDAR (Light Detection and Ranging / Laser Imaging Detection and Ranging), radar, and sonar. The external sensor 11 may also be a positioning sensor that receives positioning signals from GNSS (Global Navigation Satellite System) satellites present in the external environment of the vehicle 1. The external sensor 11 as a positioning sensor is, for example, a GNSS receiver.

[0017] The interior sensor 12 acquires interior information as sensor information from the interior environment of the vehicle 1. The interior sensor 12 may be a physical quantity detection sensor that detects specific kinetic physical quantities in the interior environment of the vehicle 1. The interior sensor 12 as a physical quantity detection sensor is at least one of the following: for example, a driving speed sensor, an acceleration sensor, and a gyro sensor. The interior sensor 12 may be an occupant detection sensor that detects a specific state of an occupant in the interior environment of the vehicle 1. The interior sensor 12 as an occupant detection sensor is at least one of the following: for example, a driver status monitor (registered trademark), a biosensor, a seating sensor, an actuator sensor, and an in-vehicle equipment sensor.

[0018] The communication system 20 acquires usable communication information from the map generation device 100 via wireless communication. The communication system 20 may be a V2X type that transmits and receives communication signals with a V2X system located outside the vehicle 1. A V2X type communication system 20 is at least one of the following: a DSRC (Dedicated Short Range Communications) communication device, a cellular V2X (C-V2X) communication device, etc. The communication system 20 may also be a terminal communication type that transmits and receives communication signals with a terminal located inside the vehicle 1. A terminal communication type communication system 20 is, for example, a communication device that conforms to a predetermined short-range wireless communication standard.

[0019] The map generation device 100 is connected to the sensor system 10 and the communication system 20 in a communication manner. The map generation device 100 is connected to the above-described in-vehicle configuration via at least one of the following: a LAN (Local Area Network) line, a wire harness, an internal bus, and a wireless communication line. The map generation device 100 is configured to include at least one dedicated computer.

[0020] The dedicated computer constituting the map generation device 100 may be an integrated ECU (Electronic Control Unit) that integrates the driving control of the vehicle 1. The dedicated computer constituting the map generation device 100 may be a decision ECU that determines driving tasks in the driving control of the vehicle 1. The dedicated computer constituting the map generation device 100 may be a monitoring ECU that monitors the driving control of the vehicle 1. The dedicated computer constituting the map generation device 100 may be an evaluation ECU that evaluates the driving control of the vehicle 1.

[0021] The dedicated computer constituting the map generation device 100 may be a navigation ECU that navigates the driving route of vehicle 1. The dedicated computer constituting the map generation device 100 may be a locator ECU that estimates the self-state quantities of vehicle 1. The dedicated computer constituting the map generation device 100 may be an actuator ECU that controls the driving actuators of vehicle 1. The dedicated computer constituting the map generation device 100 may be an HCU (HMI (Human Machine Interface) Control Unit) that controls the presentation of information in vehicle 1. The dedicated computer constituting the map generation device 100 may be a computer other than vehicle 1. A computer other than vehicle 1 is, for example, a computer that constructs an external center or mobile terminal that can communicate with vehicle 1.

[0022] The dedicated computer constituting the map generation device 100 has at least one memory 101 and one processor 102. The memory 101 is a non-transitory tangible storage medium that non-temporarily stores programs and data that can be read by the computer. For example, the memory 101 is at least one of the following: semiconductor memory, magnetic medium, and optical medium. The memory 101 stores a map generation program for generating a probe map Mp from probe data collected by the vehicle 1.

[0023] In addition, memory 101 stores a map database Dm in a portion of its storage area. The map database Dm contains map information that can be used in the map generation method described later. The memory 101 that stores the map database Dm may also be a storage medium for a locator that estimates self-state quantities, including the self-position of vehicle 1. The memory 101 that stores the map database Dm may also be a storage medium for a navigation unit that navigates the driving route of vehicle 1. The memory 101 that stores the map database Dm may be composed of a combination of multiple types of these storage media.

[0024] The map database Dm includes, at a minimum, the base map Mb, which serves as the basis for the probe map Mp described later, as map information. The base map Mb is digital data containing two-dimensional or three-dimensional topological information about the vehicle's travel path. Here, topological information refers to data that shows the relative connection relationships between the components of the travel path.

[0025] Specifically, as shown in Figure 3, the base map Mb defines a road by nodes N and links L connecting the nodes N. Node N defines, for example, a point where multiple roads connect. Node N is at least one type, such as an intersection, merging point, or branching point. Node N may also include those that define the start and end points of curved sections in the road. Furthermore, Node N may include those that define one or more points between the start and end points of a curved section. The base map Mb includes, for example, location information and type information for each node N.

[0026] Link L defines a road between nodes N. Link L may define the left and right boundaries of the road, or the road may be defined as a single line segment. The base map Mb includes, for example, identification information of the node N to which each link L is connected. The base map Mb includes curvature information for links L corresponding to curved sections. Alternatively, the base map Mb may define a curved section by multiple nodes N set within the curved section and straight link L connecting those nodes N. The base map Mb may also include information such as the width and number of lanes of each link L.

[0027] Based on the aforementioned node N and link L, the base map Mb abstracts and defines the route as a graph structure. The information regarding node N and link L is an example of "base shape information". The base map Mb is described in at least one of the following formats: text map format, graphical map format, etc. The base map Mb may be stored in memory 101, for example, at the factory shipment stage. Alternatively, the base map Mb may be acquired after factory shipment by distribution, etc., and stored in memory 101. The base map Mb is a map used, for example, for route guidance in a navigation function.

[0028] In the map database Dm, probe data collected by vehicle 1 is merged with the base map Mb described above to generate the probe map Mp. The probe map Mp is a hierarchical data structure that includes a base layer based on the base map Mb and a probe layer onto which the probe data is mapped.

[0029] Such probe maps Mp may include road information that represents at least one type of information, such as the location, shape, and surface condition of the road itself. Probe maps Mp may also include marking information that represents at least one type of information, such as the location and shape of road signs and lane markings. Map information may also include structural information that represents at least one type of information, such as the location and shape of buildings and traffic lights facing the road.

[0030] The probe map Mp is updated each time a drive is made, that is, each time new probe data is collected. Figures 4 and 5 show an example of a probe map Mp for the same area as the base map Mb in Figure 3. Figure 5 shows the probe map Mp from Figure 4 after it has been updated. As shown in Figures 4 and 5, the amount of information in the probe map Mp can increase through updates.

[0031] The processor 102 includes at least one core from among, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a RISC (Reduced Instruction Set Computer)-CPU, a CISC (Complex Instruction Set Computer)-CPU, a DFP (Data Flow Processor), and a GSP (Graph Streaming Processor).

[0032] In the map generation device 100, the processor 102 executes multiple instructions included in the map generation program stored in the memory 101. This causes the map generation device 100 to construct multiple functional blocks for generating probe maps. These functional blocks, as shown in Figure 6, include an acquisition block 110, a correction block 120, and a generation block 130.

[0033] The acquisition block 110 acquires probe data collected by the sensor system 10 of vehicle 1. The acquisition block 110 acquires probe data collected by driving a specific driving section. The driving section is, for example, the section from the starting point to the destination point of vehicle 1. The probe data includes probe target data related to objects in the outside world of vehicle 1, acquired by external sensors 11, etc. Objects include, for example, road markings such as lane markings, stop lines, and pedestrian crossings. Objects also include, for example, road fixtures such as traffic lights, road signs, and curbs, and buildings facing the road. The acquisition block 110 acquires the probe target data as a point cloud Pc that includes, for example, relative position information with respect to vehicle 1. In addition to the static objects described above, the acquisition block 110 may also acquire data related to dynamic objects such as other vehicles and pedestrians as probe target data.

[0034] Furthermore, the probe data includes probe behavior data relating to the behavior of the vehicle 1, acquired by the internal sensor 12, etc. The behavior is at least one type, such as yaw rate, velocity, acceleration, jerk, attitude angle, steering angle, and self-position. The acquisition block 110 acquires the probe behavior data, for example, as time-series data associated with driving. In this embodiment, the probe data is data collected from a single vehicle 1.

[0035] Correction block 120 corrects the probe data using the base map Mb. Specifically, correction block 120 compares probe shape information, which is the shape information of the travel path estimated from the probe behavior data among the probe data, with base shape information, which is the shape information of the travel path based on the base map Mb. Then, correction block 120 calculates the shape error of the probe shape information with respect to the base shape information. Correction block 120 corrects the probe behavior data by correcting the shape error that falls outside the set range. Furthermore, correction block 120 corrects the position information of the probe target data mapped based on the probe behavior data based on the corrected probe behavior data. The shape information of the travel path used for correction is, for example, the curvature information of the travel path.

[0036] The generation block 130 generates a probe map Mp from probe data and base map Mb. Specifically, the generation block 130 first maps the collected probe data. The generation block 130 then combines (merges) the mapped probe data (either uncorrected or corrected) with the base map Mb as a separate layer. In this way, the generation block 130 generates a probe map Mp with a hierarchical structure.

[0037] The generation block 130 integrates probe data acquired during the second and subsequent runs of the same driving section with previous probe data and combines it into the base map Mb. This allows the generation block 130 to update the probe map Mp each time a run is performed. The generation block 130 stores the generated and updated probe map Mp in a storage medium such as memory 101. The stored probe map Mp is used, for example, for trajectory generation in automated driving. Alternatively, the generation block 130 may transmit the generated probe map Mp to an external source such as a center or another vehicle.

[0038] Based on the combined efforts of blocks 110, 120, and 130 described above, the map generation method by which the map generation device 100 generates the probe map Mp is executed according to the map generation flow shown in Figure 7. This map generation flow is executed repeatedly while the vehicle 1 is running. In this map generation flow, each "S" represents multiple steps executed by multiple instructions included in the map generation program.

[0039] First, in S10, acquisition block 110 acquires the location information of vehicle 1 while it is in motion. Next, in S20, acquisition block 110 acquires a base map Mb relating to the road around the location of vehicle 1. Acquisition block 110 acquires the base map Mb by reading it from memory 101 for the corresponding area.

[0040] Then, in S30, the acquisition block 110 acquires the probe data collected by the sensor system 10 during the current drive. In the following S40, the generation block 130 maps the probe data. Specifically, the generation block 130 converts the position information of the probe target data from the probe data into position information in a map coordinate system based on the probe behavior data. As a result, the generation block 130 generates mapped probe data in which various targets are represented by a point cloud P that includes position information in a map coordinate system. Figure 8 shows an example of a point cloud P mapped to the driving lane markings LL of the driving path. Due to noise when the sensor system 10 collects probe behavior data, the position of the point cloud P may be shifted from the actual driving lane markings LL. The mapping of probe data may be performed at any time during the drive or after arrival at the destination.

[0041] Next, in S50, the correction block 120 generates probe shape information for the driving section targeted for probe map Mp generation. The probe shape information is probe curvature information, as shown by the dashed line in Figure 9. Since curvature is a value correlated with yaw rate, the correction block 120 generates the time-series curvature calculated from the time-series yaw rate in the probe behavior data as probe curvature information. As shown in Figure 9, the probe shape information tends to contain relatively high-frequency noise. On the other hand, the base shape information for the probe shape information is data that does not contain high-frequency components, as shown by the solid line in Figure 9.

[0042] In the subsequent S60, the correction block 120 determines whether there is a section where the shape error falls outside the set range. Specifically, the correction block 120 calculates the curvature error for each probe curvature information, which is the error relative to the base curvature information. Then, the correction block 120 determines whether there is a section (location) where the curvature error falls outside the set range. In this case, the set range is the range where the curvature error is below or equal to the upper threshold.

[0043] Furthermore, if the base map Mb includes the curvature of link L, the base curvature information will be the curvature of link L in the target section. Also, if the base map Mb describes a curved road with node N and a straight link L, the base curvature information will be the curvature approximately calculated from node N and link L.

[0044] If it is determined that there is a section where the difference falls outside the set range, this flow proceeds to S70. In S70, the correction block 120 corrects the probe data for the section where the curvature difference falls outside the set range. For example, the correction block 120 first corrects the probe curvature information. The correction block 120 may correct the probe curvature information by simply subtracting the curvature error from the probe curvature information. Alternatively, the correction block 120 may correct the probe curvature information using filtering by a Kalman filter or the like. Then, the correction block 120 corrects the probe behavior data based on the corrected probe curvature information. In particular, in this embodiment, the correction block 120 corrects the yaw rate. Furthermore, the correction block 120 corrects the position information of the mapped probe target data based on the corrected probe behavior data.

[0045] Furthermore, correction block 120 will stop correcting probe data at points where the curvature difference falls outside the tolerance range, which is greater than the upper limit of the set range. The tolerance range is the range in which the curvature difference is less than or equal to the upper limit threshold, which is greater than the upper limit threshold of the set range.

[0046] In S90, generation block 130 generates probe map Mp by merging probe data into base map Mb. Specifically, generation block 130 associates mapped probe data, whether correction-free or corrected, with the base layer as a separate layer from the base layer. As a result, generation block 130 generates probe map Mp, which consists of a hierarchical structure of base map Mb and probe data.

[0047] Furthermore, if it is the second or subsequent run in the probe data collection section, the generation block 130 generates integrated probe data by combining the probe data from multiple runs. For example, integrated probe data is data obtained by averaging the location information of features for each run. The generation block 130 merges the integrated probe data with the probe map Mp. In other words, the generation block 130 updates the probe map Mp each time it runs through the same collection section.

[0048] Furthermore, in the merging process, the generation block 130 reduces the contribution of probe data whose curvature difference falls outside the acceptable range to the probe map Mp compared to probe data whose curvature difference falls within the acceptable range. Specifically, the generation block 130 may, for example, exclude probe data that falls outside the acceptable range during merging, thereby setting the contribution of such data to zero. Alternatively, the generation block 130 may assign a weight to probe data that falls outside the set range as a contribution when generating integrated probe data. In this case, the weight of probe data that falls outside the acceptable range is set lower than the weight of probe data that falls within the acceptable range. Note that a weight corresponding to the shape difference may also be set for probe data that falls within the set range.

[0049] Furthermore, the generation block 130 may suspend the generation of probe map Mp for the same collection section until probe data for a set number of runs has been acquired for that collection section. The set number of runs is, for example, the number of runs in which it can be determined that the collected probe data is usable for purposes such as autonomous driving.

[0050] Next, in S100, the generation block 130 stores the generated probe map Mp into memory 101. The stored probe map Mp is used in autonomous driving and other applications.

[0051] According to the first embodiment described above, when synthesizing probe data with the base map Mb, differences are corrected using information about the shape of the road. Therefore, the accuracy of the probe map Mp is improved based on the already existing base map Mb. Consequently, highly accurate map data is improved at an early stage. In particular, by using a global map such as a map used in navigation functions as the base map Mb, it becomes easier to remove high-frequency noise in the probe data.

[0052] Furthermore, according to the first embodiment, curvature information is used as probe shape information and base shape information. Therefore, it becomes possible to correct the probe data based on the curve shape of the travel path.

[0053] Furthermore, according to the first embodiment, correction is stopped if the degree of discrepancy between the base shape information and the probe shape information falls outside the acceptable range. If the degree of discrepancy is large, there is a possibility that the shape error of the base map Mb relative to the actual road is large. Therefore, by focusing on correction when the degree of discrepancy is large, the probe data is corrected based on the base map Mb with a large shape error, and it is avoided that the error relative to the actual shape will become large.

[0054] In addition, according to the first embodiment, a probe map Mp, which is generated by integrating probe data collected over different periods, can be generated accurately and quickly.

[0055] Furthermore, according to the first embodiment, a highly accurate probe map Mp can be generated early from probe data collected from a single vehicle 1. Therefore, when using a map generation method that may take longer than collecting probe data from multiple vehicles 1, the time required to generate a highly accurate probe map Mp can be shortened.

[0056] (Other embodiments) Although one embodiment has been described above, this disclosure is not to be construed as being limited to the embodiment described herein, and can be applied to various embodiments without departing from the gist of this disclosure.

[0057] In the modified example, the map generation device 100 may use the vehicle's position information as the shape information of the road, as shown in Figure 10. That is, the map generation device 100 may correct the probe data by correcting the error at each point of the probe position information ILp, which is the probe shape information, relative to the base position information ILb, which is the base shape information.

[0058] In a modified example, the map generation device 100 may acquire probe data from other vehicles and integrate it with the probe data of its own vehicle.

[0059] In the modified example, the dedicated computer constituting the map generation device 100 may have at least one of the digital circuit and the analog circuit as a processor. Here, the digital circuit is at least one of the following, for example, ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), SOC (System on a Chip), PGA (Programmable Gate Array), and CPLD (Complex Programmable Logic Device). Furthermore, such a digital circuit may have a memory that stores a program.

[0060] In the modified example, the vehicle 1 to which the map generation device 100 is applied may be, for example, an autonomous robot capable of transporting goods or collecting information by autonomous driving or remote driving. The autonomous robot may also be called an autonomous vehicle.

[0061] (Disclosure of technical ideas) This specification discloses several technical concepts, as listed in the following paragraphs. Some paragraphs are written in a multiple dependent form, where subsequent paragraphs optionally refer to preceding paragraphs. Furthermore, some paragraphs are written in a multiple dependent form, referring to other multiple dependent forms. These paragraphs written in multiple dependent forms define several technical concepts.

[0062] (Technical thought 1) A map generation device having a processor (102) that generates a probe map (Mp) from probe data collected by a vehicle (1), The aforementioned processor, The vehicle travels along the road and collects the probe data, The probe data is combined with a base map (Mb) which includes at least base shape information, which is information about the shape of the road, to generate the probe map. It is configured to perform, The aforementioned processor, The system is configured to further correct the probe data based on the difference in shape between the probe shape information, which is information about the shape of the road estimated from the probe behavior data relating to the behavior of the vehicle in the probe data, and the base shape information. The generation of the aforementioned probe map is A map generation apparatus that includes compositing the corrected probe data onto the base map.

[0063] (Technical thought 2) Correcting the aforementioned probe data is A map generation device according to technical concept 1, which includes correcting the probe data based on the difference between the curvature information of the road estimated from the probe behavior data and the curvature information of the road included in the base map.

[0064] (Technical Thought 3) The generation of the aforementioned probe map is A map generation device according to technical concept 1 or technical concept 2, which includes reducing the contribution of probe data to the probe map with respect to probe data where the difference in shape of the probe shape information from the base shape information is outside the acceptable range.

[0065] (Technical Thought 4) The generation of the aforementioned probe map is A map generation device according to any one of Technical Concepts 1 to 3, which includes integrating the probe data obtained by traveling along the same route at different time periods and combining them with the base map.

[0066] (Technical Thought 5) The generation of the aforementioned probe map is A map generation device according to any one of Technical Concepts 1 to 4, which includes synthesizing the probe data collected by a single vehicle onto the base map.

[0067] Furthermore, the above technical concepts 1 to 5 may be implemented in the form of a map generation method and a map generation program. [Explanation of Symbols]

[0068] 1: Vehicle, 100: Map generation device, 101: Memory (storage medium), 102: Processor, Mb: Base map, Mp: Probe map

Claims

1. A map generation device having a processor (102) that generates a probe map (Mp) from probe data collected by a vehicle (1), The aforementioned processor, The vehicle travels along the road and collects the probe data, The probe data is combined with a base map (Mb) which includes at least base shape information, which is information regarding the shape of the road, to generate the probe map. It is configured to perform, The aforementioned processor, The system is configured to further correct the probe data based on the difference in shape between the probe shape information, which is information about the shape of the road estimated from the probe behavior data relating to the behavior of the vehicle in the probe data, and the base shape information. The generation of the aforementioned probe map is A map generation apparatus that includes compositing the corrected probe data onto the base map.

2. Correcting the aforementioned probe data is The map generation apparatus according to claim 1, further comprising correcting the probe data based on the difference between the curvature information of the road estimated from the probe behavior data and the curvature information of the road included in the base map.

3. The generation of the aforementioned probe map is The map generation apparatus according to claim 1, further comprising reducing the contribution of probe data to the probe map with respect to probe data in which the difference in shape of the probe shape information with respect to the base shape information is outside the acceptable range.

4. The generation of the aforementioned probe map is The map generation apparatus according to claim 1, which includes integrating the probe data obtained by traveling along the same route at different time periods and combining them with the base map.

5. The generation of the aforementioned probe map is The map generation apparatus according to claim 1, comprising synthesizing the probe data collected by a single vehicle onto the base map.

6. A map generation method performed by a processor (102) to generate a probe map (Mp) from probe data collected by a vehicle (1), The vehicle travels along the road and collects the probe data, The probe data is combined with a base map (Mb) which includes at least base shape information, which is information regarding the shape of the road, to generate the probe map. Includes, moreover, This includes correcting the probe data based on the difference in shape between the probe shape information, which is information about the shape of the road estimated from the probe behavior data relating to the behavior of the vehicle in the probe data, and the base shape information. The generation of the aforementioned probe map is A map generation method comprising compositing the corrected probe data onto the base map.

7. A map generation program, which is stored in a storage medium (101) and includes instructions to be executed by a processor (102) in order to generate a probe map (Mp) from probe data collected by a vehicle (1), The vehicle travels along the road and collects the probe data, The probe data is combined with a base map (Mb) which includes at least base shape information, which is information regarding the shape of the road, to generate the probe map. The instruction to cause the execution of the said instruction, moreover, The command includes causing the system to correct the probe data based on the difference in shape between the probe shape information, which is information about the shape of the road estimated from the probe behavior data relating to the behavior of the vehicle in the probe data, and the base shape information. The generation of the aforementioned probe map is A map generation program that includes compositing the corrected probe data onto the base map.

Images