Information processing device, information processing method, information processing program and recording medium

Abstract

To provide a data structure of map data capable of determining whether or not a feature at a certain position is deteriorated.SOLUTION: Map data is made into a data structure including position information showing a position of a feature and deterioration information regarding a deterioration state of the feature, the position information and the deterioration information being associated with each other. The map data is used for processing of determining whether or not the feature specified by the position information is deteriorated on the basis of the deterioration information by an information processing device.SELECTED DRAWING: Figure 11

Description

[Technical field]

[0001] The present application relates to a data structure of map data including deterioration information relating to the deterioration state of features. [Background technology]

[0002] In autonomous vehicles, it is necessary to estimate the vehicle's position with high accuracy by matching the positions of features measured by sensors such as LIDAR (Light Detection and Ranging, Laser Imaging Detection and Ranging) with the positions of features described in map data for autonomous driving. The features used include signs, billboards, and white lines painted on roads, and map data for autonomous driving that includes the positions of these features must be maintained and updated in accordance with reality in order to ensure stable autonomous driving. For example, if a white line has partially disappeared due to deterioration over time, etc., it is necessary to reflect the deterioration information in the data representing that white line in the map data.

[0003] For this reason, in the past, it was necessary to run a map maintenance vehicle and conduct a field survey to check for deteriorated features. In the midst of this, with the advancement of laser measurement technology, technology is being developed that utilizes point cloud data obtained by measuring the ground surface for the use and updating of map data. For example, Patent Document 1 discloses a technology for extracting data measuring the road surface from point cloud data that contains a lot of data other than the road surface, such as buildings and roadside trees. This technology can be used as a preprocessing for extracting white lines painted on roads. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2017-9378 A Summary of the Invention [Problem to be solved by the invention]

[0005] By using the technology of Patent Document 1, it was possible to determine the road area from point cloud data obtained by measuring the ground surface, but it was not possible to determine the deterioration state of features. However, in autonomous driving technology, the importance of processing using information on features in vehicle position estimation, lane keeping, recognition of drivable areas, etc. is very high, and the deterioration state of features has a large impact on these processing. Therefore, it is important to understand the actual deterioration state of features and reflect deteriorated features in map data.

[0006] In view of the above circumstances, an object of the present invention is to provide a data structure for map data that makes it possible to determine whether a feature at a certain position has deteriorated. [Means for solving the problem]

[0007] One aspect of the present invention is characterized in that it comprises an acquisition unit that acquires reflected light information including information regarding reflected light of light irradiated onto a feature located at a position predicted by a feature position prediction means that predicts the position of the feature, and position information of the feature, a processing unit that performs statistical processing based on the multiple pieces of reflected light information acquired by the acquisition unit, and a determination unit that determines the deterioration state of the feature by comparing the post-statistical processing information processed by the processing unit with a threshold value.

[0008] Another aspect of the present invention is an information processing method by an information processing device, comprising: an acquisition step of acquiring reflected light information including information regarding reflected light of light irradiated onto a feature located at a position predicted by a feature position prediction step of predicting the position of the feature, and position information of the feature; a processing step of performing statistical processing based on the multiple pieces of reflected light information acquired in the acquisition step; and a determination step of determining a deterioration state of the feature by comparing the statistically processed information obtained in the processing step with a threshold value.

[0009] Another aspect of the present invention is characterized in that a computer included in an information processing device functions as an acquisition unit that acquires reflected light information including information about reflected light of light irradiated onto a feature located at a position predicted by a feature position prediction means that predicts the position of the feature and position information of the feature, a processing unit that performs statistical processing based on the multiple pieces of reflected light information acquired by the acquisition unit, and a determination unit that determines the deterioration state of the feature by comparing the statistically processed information performed by the processing unit with a threshold value.

[0010] Another aspect of the present invention is a computer-readable recording medium having recorded thereon an information processing program for causing a computer included in an information processing device to function as an acquisition unit that acquires reflected light information including information regarding reflected light of light irradiated onto a feature located at a position predicted by a feature position prediction means that predicts the position of the feature, and position information of the feature, a processing unit that performs statistical processing based on the multiple pieces of reflected light information acquired by the acquisition unit, and a judgment unit that judges the deterioration state of the feature by comparing the statistically processed information performed by the processing unit with a threshold value. [Brief description of the drawings]

[0011] [Figure 1] 1 is a block diagram showing a configuration of a deteriorated feature identification system according to an embodiment. [Diagram 2] 1 is a block diagram showing a schematic configuration of a map data management system according to an embodiment; [Diagram 3] FIG. 1A is a diagram showing how a Lidar according to an embodiment measures the reflection intensity of light from a white line (without degradation), and FIG. 1B is a diagram showing an example of a graph obtained by statistically processing the reflection intensity. [Figure 4] FIG. 1A is a diagram showing how a Lidar according to an embodiment measures the reflection intensity of light at a white line (with deterioration), and FIG. 1B is a diagram showing an example of a graph obtained by statistically processing the reflection intensity. [Diagram 5] 5 is a diagram for explaining a method of calculating a predicted white line range according to an embodiment; FIG. [Figure 6]FIG. 4 is a diagram illustrating an example of a data structure of transmission data according to an embodiment. [Figure 7] 5 is a flowchart showing an example of an operation of processing reflection intensity data by the map data management system according to the embodiment. [Figure 8] 10 is a flowchart illustrating an example of an operation of a deterioration determination process performed by a server device according to an embodiment. [Figure 9] FIG. 13(A) is a side view showing how a Lidar according to a third modified example emits multiple beams of light in the vertical direction, and FIG. 13(B) is a diagram showing how the Lidar measures the reflection intensity of light from a white line. [Figure 10] FIG. 13(A) is a diagram showing an example of the reflection intensity measured for a dashed white line along the vehicle travel direction in the third modified example, and FIG. 13(B) is an example diagram showing effective and invalid areas for separating the reflection intensity used for deterioration determination based on the distribution of the reflection intensity. [Figure 11] FIG. 13 is a diagram showing an example of a data structure of map data according to a fifth modified example. [Figure 12] FIG. 23 is a diagram showing an example of a data structure of transmission data according to a sixth modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] An embodiment of the present invention will be described with reference to Fig. 1. Fig. 1 is a block diagram showing a schematic configuration of the data structure of map data according to this embodiment.

[0013] As shown in FIG. 1, a data structure 1 of map data according to this embodiment includes location information 1A indicating the location of a feature, and deterioration information 1B regarding the deterioration state of the feature, in association with each other.

[0014] The transmitted data is used by the information processing device in a process of determining whether the feature specified by the position information is deteriorated based on the deterioration information.

[0015] According to the data structure of the transmission data in this embodiment, the information processing device can determine whether a feature at a certain location is deteriorated based on deterioration information associated with location information indicating the location. EXAMPLES

[0016] The following embodiment will be described with reference to Figures 2 to 8. Note that the following embodiment is an embodiment in which the present invention is applied to a map data management system S.

[0017] [1. Configuration and Overview of Map Data Management System S] As shown in Fig. 2, the map data management system S of this embodiment includes a server device 100 that manages map data, and an in-vehicle terminal 200 that is mounted on each of a plurality of vehicles, and the server device 100 and each in-vehicle terminal 200 are connected via a network NW. Although one in-vehicle terminal 200 is shown in Fig. 2, the map data management system S may be configured to include a plurality of in-vehicle terminals 200. The server device 100 may also be configured with a plurality of devices.

[0018] As shown in Fig. 3(A) and Fig. 4(A), the vehicle-mounted terminal 200 transmits reflection intensity data D indicating the reflection intensity measured by receiving reflected light of the light L emitted by the Lidar 205 itself from the white lines W1 and W2 (examples of "land features") to the server device 100 in the vehicle V equipped with the Lidar 205 together with the vehicle-mounted terminal 200. Note that the bars shown as the reflection intensity data D in Fig. 3(A) and Fig. 4(A) indicate the magnitude of the reflection intensity at that point depending on their length (the longer the bar, the greater the reflection intensity). The reflection intensity data D is data including the reflection intensity at each point where the light L emitted by the Lidar 205 is irradiated. Fig. 3(A) and Fig. 4(A) show that the reflection intensity is measured at five points for each of the white lines W1 and W2.

[0019] The server device 100 identifies a deteriorated feature based on the multiple reflection intensity data D received from each of the multiple vehicle-mounted terminals 200. Specifically, the deteriorated feature is identified by statistically processing the multiple reflection intensity data D. For example, as shown in FIG. 3(A), for a white line that is not deteriorated, the reflection intensity at each point within the white line is high and uniform, so that the average value μ calculated based on the multiple reflection intensities is high and the standard deviation σ is small, as shown in FIG. 3(B). On the other hand, as shown in FIG. 4(A), for a deteriorated white line, the reflection intensity at each point within the white line is low or non-uniform, so that the average value μ calculated based on the multiple reflection intensities is low or the standard deviation σ is large, as shown in FIG. 4(B). Therefore, the server device 100 compares the average value μ and the standard deviation σ calculated based on the multiple reflection intensities with a threshold value to determine whether the feature is deteriorated and identify the deteriorated feature. Then, the server device 100 updates the map data corresponding to the deteriorated feature. The map data may be updated by a device that receives an instruction from the server device 100.

[0020] 2. Configuration of the vehicle-mounted terminal 200 Next, a description will be given of the configuration of the in-vehicle terminal 200 according to this embodiment. As shown in Fig. 2, the in-vehicle terminal 200 is mainly composed of a control unit 201, a storage unit 202, a communication unit 203, and an interface unit 204.

[0021] The storage unit 202 is composed of, for example, a hard disk drive (HDD) or a solid state drive (SSD), and stores an operating system (OS), a reflection intensity data processing program, map data, reflection intensity data D, and various data. The map data describes location information indicating the location of a feature (in this embodiment, a white line) to be subjected to deterioration judgment, and a feature ID for identifying the feature from other features (since the location information and the feature ID are information associated with one feature, the feature ID can be said to be one piece of location information indicating the location of the one feature). In the example of FIG. 3(A), the white lines W1 and W2 are assigned different feature IDs. Note that, when a white line is long, such as several hundred meters, and is inappropriate to be treated as a single feature, the white lines are divided at a certain length (for example, 5 m) and each is treated as a separate feature with a feature ID. Moreover, map data similar to the map data stored in the storage unit 202 (map data in which position information and a feature ID are described for each feature) is also stored in the storage unit 102 of the server device 100, and the same feature can be identified by the feature ID in each of the in-vehicle device 200 and the server device 100. Furthermore, the map data stored in the storage unit 202 may be, for example, map data for the entire country, or map data corresponding to a certain area including the current position of the vehicle may be received in advance from the server device 100 or the like and stored.

[0022] The communication unit 203 controls the state of communication between the on-board terminal 200 and the server device 100 .

[0023] The interface unit 204 realizes an interface function for exchanging data between the vehicle-mounted terminal 200 and external devices such as a Lidar 205 and an internal sensor 206 .

[0024] Lidar205 is a device that is attached to the roof of the vehicle or the like, and detects features by emitting infrared laser light (emitting it downward from the roof at a fixed angle) and receiving the light reflected at points on the surface of features around the vehicle, repeating the process of drawing a circle around the vehicle and generating reflection intensity data D indicating the reflection intensity at each point. Since the reflection intensity data D is data indicating the intensity of laser light reflected by the ground and features when it is emitted horizontally, it includes areas with low reflection intensity (ground areas where no features exist) and areas with high reflection intensity (areas where features exist). In addition, multiple Lidar205s may be attached to the front or rear of the vehicle, and the reflection intensity data of the field of view acquired by each of them may be combined to generate the reflection intensity data D around the vehicle.

[0025] When the Lidar 205 measures the reflection intensity, it immediately transmits the reflection intensity data D (including a portion with low reflection intensity and a portion with high reflection intensity) to the in-vehicle terminal 200 via the interface unit 204. When the control unit 201 receives the reflection intensity data D from the Lidar 205, the control unit 201 stores the received reflection intensity data D in the storage unit 202 in association with irradiation intensity data indicating the intensity of the infrared laser light irradiated to measure the reflection intensity data D, measurement position information indicating the position of the vehicle (Lidar 205) at the time of receiving the reflection intensity data D, and measurement date and time information indicating the date and time at which the reflection intensity data D was received. The control unit 201 may delete from the storage unit 202 the reflection intensity data D, irradiation intensity data, measurement position information, and measurement date and time information stored in the storage unit 202 that have passed a predetermined time since measurement or that have been transmitted to the server device 100.

[0026] The internal sensor 206 is a general term for a satellite positioning sensor (GNSS (Global Navigation Satellite System)), a gyro sensor, a vehicle speed sensor, and the like that are mounted on the vehicle.

[0027] The camera 207 is mounted on the vehicle and captures images of the surroundings of the vehicle and transmits the captured images to the vehicle-mounted terminal 200 via the interface unit 204 .

[0028] The control unit 201 is composed of a CPU (Central Processing Unit) that controls the entire control unit 201, a ROM (Read Only Memory) in which a control program for controlling the control unit 201 and the like are stored in advance, and a RAM (Random Access Memory) that temporarily stores various data. The CPU reads out and executes various programs stored in the ROM and the storage unit 202 to realize various functions.

[0029] The control unit 201 acquires estimated vehicle position information. The estimated vehicle position information may be generated by a device outside the in-vehicle terminal 200, or may be generated by the control unit 201. The estimated vehicle position information can be generated, for example, by matching a feature position measured by the Lidar 205 with a feature position in map data for autonomous driving, or can be generated based on information detected by the internal sensor 206 and map data, or a combination of these.

[0030] The control unit 201 also predicts the actual position of the white line as seen from the vehicle (Lidar 205) based on the estimated vehicle position information and the position information of the white line shown in the map data. At this time, the control unit 201 calculates and sets a predicted white line range that includes the white line with a certain degree of margin.

[0031] Here, a method for setting the predicted white line area will be specifically described with reference to Fig. 5. The coordinate system in Fig. 5 is as follows. Map coordinate system: Xm, Ym Vehicle coordinate system: XV, YV White line map position in map coordinate system: mxm, mym Predicted white line position in vehicle coordinate system: lxv, lyv Estimated vehicle position in map coordinate system: xm, ym Estimated vehicle azimuth in map coordinate system: Ψm The vehicle coordinate system is a coordinate system that uses the position of the vehicle as the reference (origin).

[0032] The control unit 201 calculates a predicted white line range from the white line map position indicated by the position information of a white line in the traveling direction of the vehicle (for example, 10 m ahead) based on the estimated vehicle position indicated by the estimated vehicle position information. At this time, if the lane in which the vehicle V is traveling is divided by a white line 1 on the left side and a white line 2 on the right side as shown in Fig. 5, the control unit 201 calculates the predicted white line ranges for each of the white lines 1 and 2.

[0033] The calculation method of the predicted white line range is the same for white line 1 and white line 2, so here, a case where the predicted white line range is calculated for white line 1 will be described. First, the control unit 201 calculates a predicted white line 1 position 301 (predicted white line position for white line 1) based on the map position of the white line 1 and the estimated vehicle position. The predicted white line position is obtained by the following equation (1).

number

[0034] Next, the control unit 201 sets a white line 1 predicted range 311 based on the white line 1 predicted position 301. Specifically, a certain range including the white line 1 predicted position 301 is set as the white line 1 predicted range 311. Then, the control unit 201 extracts white line 1 reflection intensity data 321 indicating the reflection intensity within the white line 1 predicted range 311 from the reflection intensity data D including the reflection intensities at a plurality of points.

[0035] The control unit 201 transmits the thus extracted reflection intensity data 321, 322 to the server device 100 in association with feature IDs corresponding to the map positions of the white line 1 and the white line 2, respectively, irradiation intensity data corresponding to the reflection intensity data D from which the reflection intensity data 321, 322 were extracted, and measurement date and time information. Note that, hereinafter, the reflection intensity data D (which may be raw data measured by the Lidar 205 or data obtained by processing the raw data) measured by the Lidar 205 and stored in the storage unit 202 by the in-vehicle terminal 200 is referred to as pre-extraction reflection intensity data D, and the reflection intensity data D indicating the reflection intensity extracted within the white line prediction range may be referred to as post-extraction reflection intensity data D.

[0036] Here, the data structure of the transmission data 500 when the in-vehicle terminal 200 transmits the reflection intensity data D to the server device 100 will be described with reference to Fig. 6. As shown in Fig. 6, the transmission data 500 includes a basic information section 510, a recognition object information section 520, and a unique information section 530.

[0037] The basic information section 510 includes a header 511, vehicle metadata 512, and vehicle position 513. The header 511 stores the version (Ver) of the data format of the transmission data and a timestamp (the transmission time of the transmission data 500). The vehicle metadata 512 stores a vehicle ID for identifying the vehicle in which the on-board terminal 200 is mounted, information indicating the vehicle size, and information indicating the type of sensor mounted on the vehicle (Lidar 205 or camera 207). The vehicle position 513 stores information indicating the vehicle position when the on-board terminal 200 recognized the feature.

[0038] The recognition object information unit 520 includes a feature ID 521. The feature ID 521 stores an ID for identifying a feature that is the subject of the degradation information (for example, a feature ID corresponding to each of the map positions of white line 1 and white line 2). The server device 100 and the in-vehicle terminal 200 identify the feature based on the feature ID.

[0039] The unique information section 530 includes an acquisition date and time 531, deterioration information 532, weather information 533, and a sensor type 534. The deterioration information 532 stores the extracted reflection intensity data D and irradiation intensity data. The acquisition date and time 531 stores measurement date and time information indicating the date and time when the control unit 201 received the reflection intensity data D from the Lidar 205. The weather information 533 stores information indicating the weather (sunny, rainy, snowy, foggy, etc.) when the control unit 201 received the reflection intensity data D from the Lidar 205. The weather information may be generated by the control unit 201 based on an image captured by the camera 207, or may be received from a weather information providing server. The unique information section 530 may include road surface information indicating the state of the road surface (wet, snowy, etc.) instead of or in addition to the weather information 533. The sensor type used 534 stores information indicating the type of sensor that measured the data to be stored in the deterioration information 532. In this embodiment, since the post-extraction reflection intensity data D and the irradiation intensity data are stored in the degradation information 532, information indicating the Lidar 205 is stored in the used sensor type 534.

[0040] 3. Configuration of Server Device 100 Next, a description will be given of the configuration of the server device 100. As shown in Fig. 2, the server device 100 is broadly composed of a control unit 101, a storage unit 102, a communication unit 103, a display unit 104, and an operation unit 105.

[0041] The storage unit 102 is configured with, for example, an HDD or SSD, and stores an OS, a white line deterioration determination program, map data, transmission data 500 received from the in-vehicle terminal 200, and various other data.

[0042] The communication unit 103 controls the state of communication with the vehicle-mounted terminal 200 .

[0043] The display unit 104 is configured, for example, with a liquid crystal display or the like, and displays information such as characters and images.

[0044] The operation unit 105 is constituted by, for example, a keyboard, a mouse, etc., and receives operation instructions from an operator and outputs the contents of the instructions to the control unit 101 as instruction signals.

[0045] The control unit 101 is composed of a CPU that controls the entire control unit 101, a ROM in which a control program for controlling the control unit 101 and the like are stored in advance, and a RAM that temporarily stores various data. The CPU reads out and executes various programs stored in the ROM and the storage unit 102 to realize various functions.

[0046] The control unit 101 determines the deterioration state of the white lines based on the multiple reflection intensity data D received from one or multiple in-vehicle terminals 200. Then, the control unit 101 updates the map data corresponding to the deteriorated feature so that the deteriorated feature can be identified as being deteriorated.

[0047] [4. Example of operation of map data management system S] [4.1. Example of operation when processing reflection intensity data] Next, an example of the operation of reflection intensity data processing by the map data management system S will be described with reference to the flowchart of Fig. 7. Note that, although the flowchart of Fig. 7 describes a flow in which one vehicle-mounted terminal 200 measures reflection intensity data D and transmits it to the server device 100, similar processing is performed for each vehicle-mounted terminal 200 included in the map data management system S. Also, the processing of steps S101 to S105 of the vehicle-mounted terminal 200 in Fig. 7 is performed periodically (for example, at predetermined time intervals and / or each time the vehicle on which the vehicle-mounted terminal 200 is mounted moves a predetermined distance), and upon receiving the processing of step S105 by the vehicle-mounted terminal 200, the server device 100 performs the processing of steps S201 to S202.

[0048] First, the control unit 201 of the in-vehicle terminal 200 acquires estimated vehicle position information (step S101).

[0049] Next, the control unit 201 acquires position information of a white line from the map data corresponding to the estimated vehicle position indicated by the estimated vehicle position information acquired in the process of step S101 (step S102). At this time, the control unit 201 acquires the position information of the white line in the traveling direction of the vehicle and the feature ID, as described above.

[0050] Next, the control unit 201 calculates and sets a predicted white line range from the estimated vehicle position indicated by the estimated vehicle position information and the white line map position indicated by the white line position information (step S103).

[0051] Next, the control unit 201 extracts pre-extraction reflection intensity data D measured by the Lidar 205 within the white line prediction range to obtain post-extraction reflection intensity data D (step S104). Specifically, the control unit 201 first identifies pre-extraction reflection intensity data D measured by irradiating a range including the white line prediction range with laser light based on the measurement position of the measurement position information stored in association with the pre-extraction reflection intensity data D and the irradiation angle (a certain downward angle) when the Lidar 205 irradiates the laser light. Next, the control unit 101 extracts a portion within the white line prediction range from the identified pre-extraction reflection intensity data D to obtain post-extraction reflection intensity data D2. For example, the control unit 101 extracts a portion corresponding to the azimuth angles (θ1, θ2 (see FIG. 5)) of the white line prediction range based on the vehicle direction.

[0052] Next, the control unit 201 generates the transmission data 500 (step S105). At this time, the degradation information 532 stores the extracted reflection intensity data D extracted in the process of step S104.

[0053] Next, the control unit 201 transmits the transmission data 500 generated in the process of step S105 to the server device 100 (step S106), and ends the reflection intensity data transmission process.

[0054] In response to this, when the control unit 101 of the server device 100 receives the transmission data 500 from the in-vehicle terminal 200 (step S201), it stores the data in the memory unit 102 (step S202) and ends the reflection intensity data transmission process. As a result, the memory unit 102 of the server device 100 accumulates a plurality of pieces of extracted reflection intensity data D transmitted from the plurality of in-vehicle terminals 200, respectively.

[0055] [4.2. Example of operation during deterioration judgment process] Next, an example of the operation of the deterioration determination process by the server device 100 will be described with reference to the flowchart in Fig. 8. The deterioration determination process is executed, for example, when an operator or the like issues an instruction to determine deterioration of a white line and specifies the feature ID of the white line to be determined for deterioration.

[0056] First, the control unit 101 of the server device 100 acquires the specified feature ID (step S211). Next, the control unit 101 acquires the deterioration information (extracted reflection intensity data D) of the transmission data 500 that includes the specified feature ID and whose measurement date and time is within a predetermined period (e.g., the last three months) from the storage unit 102 (step S212). The reason for limiting the object of acquisition to reflection intensity data D whose measurement date and time is within the predetermined period is that reflection intensity data D that is too old is not appropriate for determining the current deterioration state.

[0057] Next, the control unit 101 corrects the post-extraction reflection intensity data D extracted in the process of step S212 (step S213). Specifically, the reflection intensity data D is corrected using at least one of the measurement date and time information and weather information (road surface information). The reflection intensity measured by the Lidar 205 is affected by the influence of sunlight and the state of the road surface, and therefore varies depending on the measurement date and time and the weather (road surface condition) at the time of measurement. For example, even for the reflection intensity of the same white line, the reflection intensity at dawn or dusk differs from the reflection intensity during the day. In addition, the reflection intensity on a sunny day differs from the reflection intensity on a cloudy day, rainy day, snowy day, etc. This makes it possible to cancel out the difference between the reflection intensity data due to the time and weather (road surface condition) at the time of measurement and to appropriately determine deterioration.

[0058] Next, the control unit 101 calculates the average of the extracted reflection intensity data D corrected in the process of step S213 (step S214), and then calculates the standard deviation (step S215). When calculating the average and standard deviation, the control unit 101 processes the extracted reflection intensity data D for each feature ID (for each of the white lines W1 and W2 in the examples of Figs. 3(A) and 4(A)). In the examples of Figs. 3(A) and 4(A), the reflection intensity is measured at five points for the white line W1, so the control unit 101 calculates the average and standard deviation of the reflection intensity at each point.

[0059] Next, the control unit 101 judges whether or not the average calculated in the process of step S214 is equal to or less than the first threshold (step S216). At this time, when the control unit 101 judges that the average is equal to or less than the first threshold (step S216: YES), it judges the designated white line as "deteriorated" (step S218), updates the map data corresponding to the designated white line by adding information indicating that the designated white line is "deteriorated" (step S219), and ends the deterioration judgment process. Note that the control unit 101's judgment of the designated white line as "deteriorated" in the process of step S218 is an example of identifying a deteriorated white line. On the other hand, when the control unit 101 judges that the average is not equal to or less than the first threshold (step S216: NO), it then judges whether or not the standard deviation calculated in the process of step S215 is equal to or more than the second threshold (step S217).

[0060] At this time, if the control unit 101 determines that the standard deviation is equal to or greater than the second threshold (step S217: YES), it determines that the specified white line is "deteriorated" (step S218), updates the map data corresponding to the white line by adding information indicating that the white line is "deteriorated" (step S219), and ends the deterioration determination process. On the other hand, if the control unit 101 determines that the standard deviation is not equal to or greater than the second threshold (step S217: NO), it determines that the specified white line is "not deteriorated" (step S220), and ends the deterioration determination process.

[0061] As described above, in the map data management system S of this embodiment, the control unit 101 of the server device 100 acquires reflection intensity data D measured by receiving light reflected by a white line (an example of an “feature”) from light emitted by a Lidar 205 equipped on a vehicle (an example of a “moving body”), and identifies deteriorated white lines based on the acquired reflection intensity data D.

[0062] Therefore, according to the map data management system S of this embodiment, it is possible to identify deteriorated white lines by using the reflection intensity data D acquired from the vehicle. Note that while it is conceivable to judge the deterioration of white lines based on images captured by a camera mounted on the vehicle, it is difficult to appropriately judge the deterioration due to restrictions such as changes in brightness at night or backlighting, and camera resolution, and therefore the deterioration judgment using the reflection intensity data D as in this embodiment is advantageous.

[0063] Moreover, the control unit 101 further acquires measurement date and time information indicating the date and time when the reflection intensity data D was measured, selects the reflection intensity data D measured during a predetermined period based on the measurement date and time information, and identifies the deteriorated white lines based on the selected reflection intensity data D. Therefore, by appropriately setting the predetermined period (for example, the most recent few months), it is possible to appropriately identify the deteriorated white lines based on the reflection intensity data excluding the reflection intensity data D that is inappropriate for determining deterioration of the white lines.

[0064] Furthermore, the control unit 101 further acquires a feature ID for identifying the position of the white line that reflects the light, and identifies the deteriorated white line based on the reflection intensity data D and the feature ID. This makes it possible to identify the position of the deteriorated white line.

[0065] Furthermore, the control unit 101 identifies deteriorated white lines based on the extracted reflection intensity data D measured within the set white line prediction range based on the position information. This makes it possible to perform deterioration judgment by excluding reflection intensity data D that indicates light reflected by things other than white lines, and therefore makes it possible to perform deterioration judgment on white lines with higher accuracy.

[0066] Furthermore, the control unit 101 updates the map data corresponding to the white line determined to be "deteriorated" in the process of step S218 in Fig. 8 (performs an update to add information indicating that the white line is "deteriorated"). This allows the deterioration information to be reflected in the map data representing the deteriorated white line.

[0067] Furthermore, the control unit 101 receives light reflected by a white line that is emitted by a Lidar equipped in one or more vehicles, acquires reflection intensity data D measured in each of the one or more vehicles, and identifies a deteriorated white line based on the acquired multiple reflection intensity data D. Therefore, according to the map data management system S of this embodiment, it is possible to identify a deteriorated white line with high accuracy using the reflection intensity data D acquired from one or more vehicles.

[0068] In this embodiment, the feature to be subjected to deterioration determination has been described as a white line, but any feature for which deterioration determination can be performed based on reflection intensity can be subjected to deterioration determination.

[0069] [5. Modifications] Next, modified examples of this embodiment will be described. Note that the modified examples described below can be combined as appropriate.

[0070] [5.1. First modified example] In the above embodiment, the case where the white line to be subjected to the deterioration judgment is a solid line has been described, but the white line may also be a broken line. Furthermore, white lines are not only used to separate lanes, but are also used for guidance strips, letters, pedestrian crossings, etc. Furthermore, the object of the deterioration judgment may not only be the white line, but may also include features such as signs and billboards. In other words, the features to be subjected to the deterioration judgment may be classified into various types. Therefore, feature type information indicating the type of feature may be further linked to a feature ID, and the threshold value when the deterioration judgment is performed using the reflection intensity data may be changed depending on the type of feature.

[0071] Furthermore, if the white line is a broken line, a feature ID may be set for each portion where the white line is painted, and a feature ID may not be set for portions where the white line is not painted, and these portions may be excluded from the deterioration determination. Note that, since the orientation of white lines for guidance strips, letters, pedestrian crossings, etc. may not be parallel to the traveling direction of the vehicle, a method for setting the predicted white line range may be determined for each type of white line (for example, position information of the four corner points of the predicted white line range may be described in the map data, and the control unit 201 of the in-vehicle device 200 may set the predicted white line range based on that), and the predicted white line range may be set according to the type of white line to be subjected to the deterioration determination.

[0072] [5.2. Second Modification] In the above embodiment, the control unit 201 of the in-vehicle terminal 200 periodically transmits the reflection intensity data D to the server device 100. In addition, the control unit 201 may add a condition that the in-vehicle terminal 200 (own vehicle) transmits only the reflection intensity data D measured within a predetermined area (e.g., a measurement area specified by the server device 100). As a result, for example, the server device 100 can specify an area where deterioration judgment of the white line needs to be performed as the measurement area, thereby avoiding receiving reflection intensity data D measured in an area where deterioration judgment of the white line does not need to be performed. This makes it possible to reduce the amount of communication data between the in-vehicle terminal 200 and the server device 100, save the storage capacity of the storage unit 102 of the server device 100 that stores the reflection intensity data D, and reduce the processing load related to the deterioration judgment.

[0073] Furthermore, the control unit 101 of the server device 100 may refer to the position information stored in the memory unit 102 together with the reflection intensity data D, and identify deteriorated white lines based on the reflection intensity data measured in a specified area (for example, an area specified by an operator or the like where deterioration judgment of white lines needs to be performed). In this way, by specifying the area where deterioration judgment needs to be performed, deterioration judgment can be performed only on white lines in that area, and the processing load can be reduced compared to the case where deterioration judgment is performed on areas where deterioration judgment is not required.

[0074] [5.3.Third Modification] In the above embodiment, the Lidar 205 is attached to the roof of the vehicle, etc., and irradiates one infrared laser light L at a certain angle downward to draw a circle around the vehicle. However, for example, as shown in FIG. 9(A), the Lidar 205 may irradiate a plurality of infrared laser lights L (five in FIG. 9(A)) at different downward irradiation angles so as to draw a circle around the vehicle. This allows the reflection intensity data D to be measured along the traveling direction of the vehicle at one time, as shown in FIG. 9(B). Also, as in the above embodiment, the reflection intensity data D can be obtained along the traveling direction of the vehicle by irradiating one infrared laser light L and measuring the reflection intensity data D every time the vehicle V moves a predetermined distance, and combining them.

[0075] As described in the first modified example, as shown in FIG. 10(A), when the white line is a broken line, it is preferable to exclude the portion where the white line is not painted from the deterioration judgment because the deterioration of the white line does not occur in the first place. Therefore, the control unit 101 of the server device 100 may divide the portion where the white line is painted (painted area) into a valid area and the portion where the white line is not painted (non-painted area) into an invalid area based on the reflection intensity data D measured along the traveling direction of the vehicle V as described above, and perform the deterioration judgment based only on the reflection intensity corresponding to the valid area. Specifically, as shown in FIG. 10(A) and (B), the reflection intensity indicated by the reflection intensity data D measured along the traveling direction of the vehicle V for the broken white line is roughly classified as a high value in the painted area and a low value in the non-painted area, so that a threshold value is set, and if the reflection intensity is equal to or higher than the threshold, the area is divided into a valid area and the other areas are divided into an invalid area. As a result, as explained in the first modified example, feature IDs can be set for each predetermined distance in the same way as for solid white lines, without setting feature IDs for each painted area of ​​dashed white lines, and deterioration determination can be avoided for non-painted areas. Note that this method of separating painted areas (valid areas) from non-painted areas (invalid areas) may be used to determine deterioration of guidance strips, characters, pedestrian crossings, and the like, which are composed of painted areas and non-painted areas, in addition to dashed white lines.

[0076] [5.4. Fourth Modification] In the above embodiment, the white line predicted range is calculated in advance, and the reflection intensity data D included therein is processed as being due to light reflected by the white line. That is, the post-extraction reflection intensity data D transmitted by the in-vehicle terminal 200 to the server device 100 is guaranteed to be data indicating the reflection intensity at the white line. In the fourth modified example, the in-vehicle terminal 200 transmits the pre-extraction reflection intensity data D received from the Lidar 205 to the server device 100 in association with the measurement position information and the measurement date and time information. Then, the control unit 101 of the server device 100 specifies the reflection intensity based on the reflection by the white line from the distribution of the reflection intensity indicated by the pre-extraction reflection intensity data D and the positional relationship of the white line separating the lanes on which the vehicle is traveling, and performs the deterioration judgment based on the specified reflection intensity. Then, when it is judged that the feature is deteriorated by the deterioration judgment, the position of the deteriorated white line may be specified by combining the measurement position information corresponding to the reflection intensity data D and the information indicating the irradiation angle at which the Lidar 205 irradiates the laser light L. This makes it possible to reduce the processing load on the in-vehicle terminal 200 required for the process of extracting the portion used for determining deterioration of the white lines from the pre-extraction reflection intensity data D measured by the Lidar 205 and the process of acquiring the map positions of the white lines. Also, in the fourth modification, it becomes possible for the server device 100 to determine deterioration of the white lines even if the map data stored in the memory unit 202 does not have position information of the white lines.

[0077] [5.5. Fifth Modification] The deterioration information 532 of the transmission data 500 may store a reflectance (the ratio of the extracted reflection intensity data D to the irradiation intensity data) instead of the extracted reflection intensity data D and the irradiation intensity data. In this case, the acquisition date and time 531 stores the date and time when the extracted reflection intensity data D, which is the basis of the reflectance, was measured. The control unit 101 of the server 100 may determine the deterioration level (e.g., 10 levels) and the deterioration type (e.g., partial peeling of paint, fading of paint, adhesion of dirt) of the feature based on the extracted reflection intensity data D and the irradiation intensity data, or the reflectance (hereinafter, the "extracted reflection intensity data D and the irradiation intensity data, or the reflectance" may be collectively referred to as the "reflection intensity data D, etc.") received from the vehicle-mounted terminal 200. In this case, the control unit 101 may receive a photographed image taken by the camera 207 from the vehicle-mounted terminal 200, and determine the deterioration level and the deterioration type of the feature based on at least one of the photographed image and the reflection intensity data D, etc. For example, the control unit 101 may perform a statistical process on the reflection intensity data D or the like to make a judgment, or may perform a judgment by analyzing the captured image, or may perform a judgment by combining both. When receiving a captured image from the in-vehicle terminal 200, for example, the captured image may be included in the deterioration information 532 of the transmission data 500, or a separate area for the captured image may be provided. In such a case, the acquisition date and time 531 stores the capture date and time of the captured image, and the used sensor type 534 stores information indicating the camera 207. The control unit 101 then reflects the determined deterioration level and deterioration type of the feature in the map data. Next, the data structure of the map data stored in the storage unit 102 (particularly, the data structure of the map data that holds deterioration information on white lines (sometimes called "demarcation lines"), which are features) will be described with reference to FIG. 11.

[0078] As shown in FIG. 11, the map data 600 includes a feature ID (demarcation line ID) 601, a position 602, a line width 603, an associated link 604, a line type 605, a deterioration information acquisition date (time) 606, deterioration information 607, and a deterioration type 608. The map data 600 is used by the server device 100, the vehicle-mounted terminal 200, or another information processing device in a process of determining whether a feature identified by a position 602 is deteriorated based on the deterioration information 607. The feature ID (demarcation line ID) 601 stores an ID for identifying a demarcation line, and is used when the server device 100 or the vehicle-mounted terminal 200 identifies a feature (demarcation line). The position 602 stores latitude and longitude information indicating the position of the demarcation line. Note that latitude and longitude information indicating the position of each of a plurality of points constituting a longitudinal line passing through the center of the demarcation line may be stored. The line width 603 stores information on the short side length of the demarcation line. The line type 605 stores information indicating the type of the demarcation line (broken line, solid line, etc.).

[0079] The degradation information acquisition date (hour) 606 stores the date on which the degradation level stored in the degradation information 607 was acquired (determined). The degradation information 607 stores the degradation level of the lane marking. The degradation type 608 stores information indicating the type of degradation. The degradation information acquisition date (hour) 606 may store the measurement date and time of the reflection intensity data D used to determine the degradation level, or a date or date derived from the measurement date and time (if the degradation level is determined based on the reflection intensity data D measured in a certain period, a date or date representing the certain period) instead of the date on which the degradation level was determined. For example, when a large amount of reflection intensity data D is received in a day, the predetermined period in step S212 may be a day such as the day before the processing date, and in that case, the date (the date of the day before the processing date) is stored. The predetermined period may also be 10:00 a.m. to 11:00 a.m. on a certain year, month, day, or the like, and in that case, 10:00 a.m. (or 11:00 a.m.) on a certain year, month, day may be stored in the degradation information acquisition date (hour) 606. Although the above has been shown as an example of the data structure of the map data 600, when the target is a white line, in addition to the above, further information indicating whether or not a retroreflective material is applied, whether or not the line is likely to become a puddle during rain, etc. may be added.

[0080] Each time the control unit 101 determines the deterioration level and deterioration type of the same feature, the control unit 101 may associate the deterioration information acquisition date (time) 606, which stores information indicating the date and time when the deterioration level and deterioration type were determined, with the feature ID 601 or position 602 that identifies the feature, and may retain the deterioration information acquisition date (time) 606, which stores information on the date and time when the deterioration level and deterioration type were determined, deterioration information 607, which stores the deterioration level, and deterioration type 608, which stores information on the deterioration type, as history information in the map data 600. The history information can be used to predict the progress of deterioration of the feature. In addition, if the deterioration of the feature is restored without repairing the feature, it can also be determined that the deterioration type was dirt adhesion.

[0081] [5.6. Sixth Modification] In the fifth modification, the control unit 101 of the server device 100 determines the degradation level and degradation type of the feature based on the reflection intensity data D and the like received from the vehicle-mounted terminal 200 and the captured image, but the control unit 201 of the vehicle-mounted terminal 200 may determine the degradation level and degradation type of the feature based on the reflection intensity data D and the like, and include the determination result in the transmission data 500 and transmit it to the server device 100. In the transmission data 500 in the sixth modification, the acquisition date and time 531 stores the date and time when the degradation level was determined (or the date or date and time specifying the measurement time of the reflection intensity data D and the like used to determine the degradation level may be stored). In addition, the degradation level determined by the control unit 201 is stored in the degradation information 532 (however, it is preferable to include the reflection intensity data D and the like in the transmission data 500 in this case as well). Furthermore, as shown in FIG. 12, a degradation type 535 is provided in the unique information section 530 of the transmission data 500, and information indicating the degradation type is stored. Furthermore, the weather information 533 may store information specifying the weather or road surface condition when the reflection intensity data D used to determine the deterioration level was measured. Furthermore, when the deterioration level or deterioration type of the feature is determined based on both the reflection intensity data D measured by the Lidar 205 and the image captured by the camera 207, information indicating the Lidar 205 and the camera 207 is stored in the used sensor type 534 of the transmission data 500. Note that, when the in-vehicle terminal 200 determines the deterioration level or deterioration type of the feature based on data measured by another sensor, information indicating the other sensor is stored in the used sensor type 534 of the transmission data 500.

[0082] On the other hand, the control unit 101 of the server device 100 stores the information stored in the acquisition date and time 531 of the transmission data 500 in the degradation information acquisition date (hour) 606 of the map data 600. The control unit 101 also stores the degradation level stored in the degradation information 532 of the transmission data 500 in the degradation information 607 of the map data 600. Furthermore, the control unit 101 stores the information stored in the degradation type 535 of the transmission data 500 in the degradation type 608 of the map data 600. Note that, every time the control unit 101 receives the transmission data 500 including the same feature ID (division line ID), the control unit 101 may store the degradation information acquisition date (hour) 606 storing the information stored in the acquisition date and time 531, the degradation information 607 storing the degradation level stored in the degradation information 532, and the degradation type 608 storing the information stored in the degradation type 535 as history information in the map data 600 in association with the feature ID. The history information can be used to predict the progress of deterioration of the feature. Moreover, if the deterioration of the feature is repaired without repairing the feature, it can be determined that the deterioration type is dirt adhesion.

[0083] [5.7. Seventh Modification] The seventh modification is a modification of the fifth modification. The deterioration information 607 of the map data 600 in the seventh modification may store the reflection intensity data D and the like stored in the deterioration information 532 of the transmission data 500. That is, the control unit 101 of the server device 100 may store the reflection intensity data D and the like stored in the deterioration information 532 in the transmission data 500 received from the vehicle terminal 200 without determining the deterioration level and the deterioration type, and may store the measurement date and time stored in the acquisition date and time 531 of the transmission data 500 in the deterioration information acquisition date (time) 606 of the map data 600. Also in this case, every time transmission data 500 including the same feature ID (latitude line ID) is received, the deterioration information acquisition date (time) 606 storing the information stored in the acquisition date and time 531 and the deterioration information 607 storing the reflection intensity data D and the like stored in the deterioration information 532 may be stored in the map data 600 as history information in association with the feature ID. The history information can be used to predict the progress of deterioration of the feature. Moreover, if the deterioration of the feature is repaired without repairing the feature, it can be determined that the deterioration type is dirt adhesion. [Explanation of symbols]

[0084] 1. Map data 1A Location information 1B Deterioration Information S Map Data Management System 100 Server device 101 Control section 102 Storage section 103 Communications Department 104 Display section 105 Operation section 200 Vehicle-mounted terminal 201 Control section 202 Storage section 203 Communications Department 204 Interface section 205 Lidar 206 Internal Sensor 207 Camera

Claims

1. an acquisition unit that acquires reflected light information including information on reflected light of light irradiated onto a feature located at a position predicted by a feature position prediction means that predicts the position of the feature, and position information of the feature; A processing unit that performs statistical processing based on the plurality of pieces of reflected light information acquired by the acquisition unit; a determination unit that determines a deterioration state of the feature by comparing the statistically processed information obtained by the processing unit with a threshold value; An information processing device comprising:

2. 2. The information processing device according to claim 1, 2. An information processing apparatus according to claim 1, wherein the information regarding the reflected light is information regarding the reflection intensity or the reflectance with respect to the irradiation intensity of the light.

3. 3. The information processing device according to claim 1, The processing unit performs the statistical processing of calculating an average based on the reflected light information, The information processing apparatus is characterized in that the determination unit determines a deterioration state of the feature depending on whether the average calculated by the processing unit is equal to or less than a first threshold value.

4. 4. The information processing device according to claim 1, The processing unit performs the statistical processing of calculating a standard deviation based on the reflected light information, The information processing apparatus is characterized in that the determination unit determines a deterioration state of the feature depending on whether the standard deviation calculated by the processing unit is equal to or greater than a second threshold value.

5. 5. The information processing device according to claim 1, An information processing device characterized in that it further comprises a correction unit that corrects the reflected light information using at least one of measurement date and time information and weather information when the reflected light is measured before the processing unit performs the statistical processing.

6. 6. The information processing device according to claim 1, The information processing device is characterized in that the feature is a white line.

7. 7. The information processing device according to claim 6, 2 is a block diagram showing an information processing apparatus for processing a white line having a dashed line on a surface of a ground surface;

8. An information processing method by an information processing device, an acquisition step of acquiring reflected light information including information on reflected light of light irradiated onto a feature located at a position predicted by a feature position prediction step of predicting the position of the feature, and position information of the feature; a processing step of performing statistical processing based on the plurality of pieces of reflected light information acquired in the acquisition step; a determination step of determining a deterioration state of the feature by comparing the statistically processed information obtained in the processing step with a threshold value; 13. An information processing method comprising:

9. A computer included in the information processing device, an acquisition unit that acquires reflected light information including information on reflected light of light irradiated onto a feature located at a position predicted by a feature position prediction means that predicts the position of the feature, and position information of the feature; a processing unit that performs statistical processing based on the plurality of pieces of reflected light information acquired by the acquisition unit; a determination unit for determining a deterioration state of the feature by comparing the statistically processed information obtained by the processing unit with a threshold value; An information processing program characterized by causing the program to function as follows.

10. A computer included in the information processing device, an acquisition unit that acquires reflected light information including information on reflected light of light irradiated onto a feature located at a position predicted by a feature position prediction means that predicts the position of the feature, and position information of the feature; a processing unit that performs statistical processing based on the plurality of pieces of reflected light information acquired by the acquisition unit; a determination unit for determining a deterioration state of the feature by comparing the statistically processed information obtained by the processing unit with a threshold value; A computer-readable recording medium having recorded thereon an information processing program for causing the device to function as a

Images