WO2023032444A1 - Système, dispositif et programme de détection de l'état de la surface de la route - Google Patents

Système, dispositif et programme de détection de l'état de la surface de la route Download PDF

Info

Publication number
WO2023032444A1
WO2023032444A1 PCT/JP2022/025654 JP2022025654W WO2023032444A1 WO 2023032444 A1 WO2023032444 A1 WO 2023032444A1 JP 2022025654 W JP2022025654 W JP 2022025654W WO 2023032444 A1 WO2023032444 A1 WO 2023032444A1
Authority
WO
WIPO (PCT)
Prior art keywords
road surface
vehicle
data
surface condition
point
Prior art date
Application number
PCT/JP2022/025654
Other languages
English (en)
Japanese (ja)
Inventor
幸治 石井
顕介 大沼
Original Assignee
あいおいニッセイ同和損害保険株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by あいおいニッセイ同和損害保険株式会社 filed Critical あいおいニッセイ同和損害保険株式会社
Publication of WO2023032444A1 publication Critical patent/WO2023032444A1/fr

Links

Images

Classifications

    • E—FIXED CONSTRUCTIONS
    • E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
    • E01C—CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE; MACHINES OR AUXILIARY TOOLS FOR CONSTRUCTION OR REPAIR
    • E01C23/00—Auxiliary devices or arrangements for constructing, repairing, reconditioning, or taking-up road or like surfaces
    • E01C23/01—Devices or auxiliary means for setting-out or checking the configuration of new surfacing, e.g. templates, screed or reference line supports; Applications of apparatus for measuring, indicating, or recording the surface configuration of existing surfacing, e.g. profilographs
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles

Definitions

  • the present disclosure relates to a road surface condition detection system, a road surface condition detection device, and a road surface condition detection program.
  • a speed sensor, an acceleration sensor, and an angular velocity sensor are attached to the vehicle.
  • This device obtains the travel distance and vertical displacement of the vehicle based on the speed, acceleration, and angular velocity of the vehicle detected by those sensors, and correlates the vertical displacement based on the travel distance and acceleration. , to detect road surface conditions such as unevenness.
  • the road surface condition detection device it is preferable for the road surface condition detection device to avoid detecting irregularities such as humps and railroad crossings as abnormalities in the road surface as much as possible.
  • the road surface condition detection device when the road surface condition is detected simply based on the vertical displacement of the vehicle, as in the road surface condition detection device described in Patent Document 1, there is a high possibility that an abnormality in the road surface such as a hump or railroad crossing will be detected. . If road surface anomalies are detected at many humps, railroad crossings, etc., they may become disturbances, making it impossible to efficiently detect cracks in the road surface, which should be analyzed.
  • An object of the present disclosure is to provide a road surface condition detection system, a road surface condition detection device, and a road surface condition detection program capable of more efficiently detecting the road surface condition to be analyzed.
  • a road surface condition detection system includes a data acquisition unit that acquires running data including acceleration data in the vertical direction of a vehicle and position data of the vehicle; A road surface condition estimating unit for estimating a road surface condition along a travel route, and a point determination unit for determining whether or not an out-of-target point exists on the travel route of the vehicle.
  • the road surface state estimating unit excludes the non-target points from road surface state estimation targets.
  • a road surface condition detection device includes a data acquisition unit that acquires running data including vertical acceleration data of a vehicle and position data of the vehicle, and based on the acceleration data and the position data of the vehicle: and a road surface condition estimating unit for estimating the road condition along the vehicle's travel route, and a point determination unit for determining whether or not there is an out-of-target point on the vehicle's travel route.
  • the road surface state estimating unit excludes the non-target points from road surface state estimation targets.
  • a road surface condition detection program includes, in a computer, a first step of acquiring travel data including vertical acceleration data of a vehicle and position data of the vehicle; Based on the data, a second step of estimating the road surface condition along the travel route of the vehicle and a third step of determining whether or not there is an out-of-target point on the travel route of the vehicle are executed. In the second step, the non-target points are excluded from road surface state estimation targets.
  • road surface condition detection system road surface condition detection device, and road surface condition detection program of the present disclosure, it is possible to more efficiently detect the road surface condition to be analyzed.
  • FIG. 1 is a block diagram showing a schematic configuration of the road surface condition detection system of the first embodiment.
  • FIG. 2 is a block diagram showing a schematic hardware configuration of the vehicle of the first embodiment.
  • FIG. 3 is a block diagram showing a schematic hardware configuration of the server device of the first embodiment.
  • FIG. 4 is a block diagram showing a schematic functional configuration of the server device according to the first embodiment.
  • FIG. 5 is a flow chart showing the procedure of processing executed by the server device of the first embodiment.
  • FIG. 6 is a flow chart showing the procedure of processing executed by the server device of the modification of the first embodiment.
  • FIG. 7 is a flow chart showing the procedure of processing executed by the server device of the second embodiment.
  • FIG. 8 is a diagram schematically showing an example of a learning mode by a learning unit according to the third embodiment;
  • FIG. 9 is a diagram schematically showing an example of a learning mode by a learning unit according to the third embodiment;
  • a road surface condition detection system 1 of this embodiment includes a plurality of vehicles 2 and a server device 3 .
  • Server device 3 can communicate with a plurality of vehicles 2 via network line 4 .
  • the server device 3 acquires data such as acceleration and position from a plurality of vehicles 2 via the network line 4, and estimates road surface conditions based on the acquired data such as acceleration and position.
  • Road surface conditions to be estimated include cracks, ruts, flatness, and the like.
  • the vehicle 2 has a hardware configuration as shown in FIG. 2, for example.
  • the vehicle 2 includes an acceleration sensor 20, a vehicle speed sensor 21, a position sensor 22, a communication IF (Interface) 23, a control device 24, and the like.
  • the acceleration sensor 20 is a so-called six-axis acceleration sensor capable of detecting acceleration in the longitudinal direction, the lateral direction, and the vertical direction of the vehicle 2, as well as the acceleration in the pitch direction, the low direction, and the yaw direction. is.
  • the vertical acceleration of the vehicle 2 is acceleration in a direction perpendicular to the road surface on which the vehicle 2 is grounded.
  • the vehicle speed sensor 21 detects vehicle speed, which is the running speed of the vehicle 2 .
  • the position sensor 22 detects the current position of the vehicle 2 using GPS (Global Positioning System) or the like.
  • the communication IF 23 is a device for performing wireless communication with the server device 3 via the network line 4 .
  • the control device 24 is mainly composed of a microcomputer having a processor, a storage device, and the like.
  • the controller 24 receives output signals from the acceleration sensor 20 , the vehicle speed sensor 21 and the position sensor 22 .
  • the control device 24 acquires data such as the acceleration and vehicle speed of the vehicle 2 and the position of the vehicle 2 at the time when they are detected based on the output signals of the sensors 20 to 22 at a predetermined cycle, and also acquires the acquired data. are sequentially transmitted to the server device 3 through the network line 4 together with the information of the detection time.
  • the server device 3 has a hardware configuration as shown in FIG. 3, for example.
  • the server device 3 includes a processor 30, a storage device 31, a communication IF 32, an input device 33, an output device 34, and the like.
  • the processor 30 is a CPU (Central Processing Unit), a GPU (Graphical Processing Unit), or the like.
  • the storage device 31 is a memory, HDD (Hard Disk Drive) and/or SSD (Solid State Drive).
  • the communication IF 32 is a device that performs wired communication or wireless communication.
  • the input device 33 is a device that receives input operations, such as a keyboard, touch panel, mouse and/or microphone.
  • the output device 34 is a device that outputs information, such as a display, a touch panel, and/or a speaker.
  • the server device 3 corresponds to a computer.
  • the server device 3 includes, for example, a storage unit 40, an input unit 41, a display unit 42, a communication unit 43, a data acquisition unit 44, a road surface condition estimation unit 45, and the like, as shown in FIG. I have.
  • Various data such as a map database 400 and a vehicle database 401 are stored in the storage unit 40 .
  • the map database 400 information such as the positions of roads and various facilities and the shape of roads is stored as a database.
  • Information on the positions of roads and various facilities is stored in the storage unit 40 as, for example, latitude and longitude information at which they are located.
  • the vehicle database 401 stores data such as acceleration, vehicle speed, position, and time transmitted from each vehicle 2 in association with vehicle type information of each vehicle 2 .
  • the vehicle type information is a number or the like set in advance for each vehicle type, and is information with which the vehicle type of the vehicle 2 can be identified.
  • the storage unit 40 can be implemented by the storage device 31 included in the server device 3 .
  • the input section 41 is a section through which the user can input various information to the server device 3 .
  • the input unit 41 can be realized, for example, by the processor 30 executing a program stored in the storage device 31 and controlling the input device 33 .
  • the display unit 42 is a part that displays various information.
  • the display unit 42 displays, for example, map information registered in the map database 400 .
  • the display unit 42 can be realized, for example, by the processor 30 executing a program stored in the storage device 31 and controlling the output device 34 .
  • the communication unit 43 is a part that communicates with each vehicle 2 via the network line 4 .
  • the communication unit 43 can be realized, for example, by the processor 30 executing a program stored in the storage device 31 and controlling the communication IF 32 .
  • the data acquisition unit 44 acquires travel data transmitted from the vehicle 2 via the communication unit 43 and stores the acquired travel data in the vehicle database 401 .
  • the data acquisition unit 44 can be implemented by the processor 30 executing a program stored in the storage device 31, for example.
  • the road surface state estimation unit 45 estimates the road surface state along the travel route of the vehicle 2 based on the acceleration data, position data, etc. of each vehicle 2 stored in the vehicle database 401 . For example, the road surface state estimation unit 45 acquires vertical acceleration data of the vehicle 2 and position data of the vehicle 2 associated with the acceleration from the vehicle database 401 . The road surface state estimating unit 45 compares the absolute value of the acceleration in the vertical direction of the vehicle 2 with a preset threshold, and if the absolute value of the acceleration is greater than the threshold, determines the position where the acceleration was detected. It is determined that unevenness is formed on the road surface. At this time, the road surface condition estimating unit 45 can use a plurality of thresholds having different sizes to determine stepwise the size of the unevenness formed on the road surface. The road surface state estimating unit 45 registers in the map database 400 the position determined to have unevenness on the road surface as an abnormality detection point.
  • the road surface state estimator 45 can be implemented by the processor 30 executing a program stored in the storage device 31, for example
  • the acceleration data of the vehicle 2 stored in the vehicle database 401 that is, the acceleration data detected by the acceleration sensor 20 of the vehicle 2 includes not only the actual vertical acceleration of the vehicle 2 but also the gravitational acceleration. include. Therefore, in order to estimate the road surface condition with higher accuracy, the road surface condition estimating unit 45 performs arithmetic processing to exclude the gravitational acceleration from the vertical acceleration data of the vehicle 2, and calculates the resulting vertical acceleration of the vehicle 2. It is preferable to estimate the road surface condition based on the actual acceleration data in the direction.
  • the road surface state estimation unit 45 may change the threshold value set for the acceleration for detecting road surface unevenness based on the vehicle speed data stored in the vehicle database 401 .
  • the road surface state estimating unit 45 determines that the vehicle speed V satisfies "V ⁇ 20 [km/h]” and the vehicle speed V is "20 [km/h] ⁇ V ⁇ 80 [km/h]".
  • a different threshold value is used for each of the second speed region and the third region where the vehicle speed V satisfies "80 [km/h] ⁇ V". This is because the faster the running speed of the vehicle 2 is, the greater the vibration generated in the vehicle 2 when the vehicle 2 runs over the uneven road surface. is larger.
  • the road surface state estimating unit 45 may change the threshold value set for the acceleration for detecting the unevenness of the road surface according to the vehicle type information stored in the vehicle database 401 .
  • the road surface condition estimating unit 45 may improve the estimation accuracy of the road surface condition by using a plurality of travel data detected by each of the plurality of vehicles 2 as big data. For example, the road surface condition estimating unit 45 estimates the road surface condition using a plurality of pieces of travel data, and based on the number of times that the road surface is determined to be uneven at a predetermined point is greater than or equal to a predetermined number of times. , the predetermined point is determined as the abnormality detection point. Considering that the position data of the vehicle 2 detected by the position sensor 22 such as GPS has a predetermined error, the predetermined point is not a point but an area having a certain size, for example You may set as an area which has a predetermined radius.
  • the road surface condition estimating unit 45 estimates the road surface condition using a plurality of pieces of travel data, based on the number of times it is determined that unevenness is formed on the road surface within a predetermined area is equal to or greater than a predetermined number of times. Then, it may be determined that the abnormality detection point exists within the predetermined area.
  • the abnormality detection points registered in the map database 400 by the road surface condition estimation unit 45 are also displayed when the map information is displayed on the display unit 42 . Therefore, the user can check the point where the unevenness is formed on the road surface by viewing the abnormality detection point through the display unit 42, and can take appropriate measures such as repairing the point. becomes.
  • the road surface state detection system 1 of the present embodiment does not estimate the road surface state at the out-of-target point.
  • the storage unit 40 further stores an out-of-target point database 402 .
  • the non-target point database 402 is a database of position data of non-target points.
  • the out-of-target points include points with low urgency regarding road repair, points outside the jurisdiction, and points where unevenness is inevitably formed on the road surface. Locations outside the jurisdiction include private land, parking lots, and the like.
  • Points where unevenness is inevitably formed on the road surface include points where humps are formed, points where railroad crossings are formed, points where manholes are provided, points where tram lines are provided, and gravel roads. are formed, points of unpaved roads, and so on. At least one of these is used for the non-target point.
  • the position data of the non-target points is registered in the non-target point database 402 as, for example, the latitude and longitude position data of the non-target points.
  • the user can, for example, correct the position data of a point already registered in the non-target point database 402, register a new point in the non-target point database 402, or A point already registered in the out-of-sight database 402 can be deleted.
  • the server device 3 further includes a location determining section 46 .
  • the point determination unit 46 acquires position data of non-target points from the non-target point database 402 and acquires acceleration data and position data of the vehicle 2 from the vehicle database 401 .
  • the point determination unit 46 determines whether or not the position data associated with the acceleration data of the vehicle 2 matches the position data of the non-target point. is determined to be an out-of-target point.
  • the point determination unit 46 can be implemented by the processor 30 executing a program stored in the storage device 31, for example.
  • the road surface state estimating unit 45 estimates the road surface state based on the acceleration data of the vehicle 2 stored in the vehicle database 401 excluding the acceleration data obtained at the non-target points. As a result, the out-of-target points are excluded from road surface state estimation targets.
  • FIG. 5 a specific procedure of road surface state estimation processing executed by the server device 3 will be described. Note that the server device 3 repeatedly executes the processing shown in FIG. 5 at a predetermined cycle.
  • the data acquisition unit 44 first selects a vehicle to be analyzed from among the plurality of vehicles 2 (step S10). Specifically, the data acquisition unit 44 selects one of the multiple vehicles 2 registered in the vehicle database 401 . Subsequently, the data acquisition unit 44 acquires data of a predetermined analysis section from the time-series travel data of the selected vehicle 2 to be analyzed from the vehicle database 401 (step S11).
  • the predetermined analysis section defines the range of road surface condition estimation targets, and is set based on the travel distance of the vehicle and the like.
  • the vehicle database 401 stores time-series travel data of the vehicle 2 along a travel route from a predetermined travel start point to a predetermined travel end point. and In this case, the section from the predetermined travel start point to the first point where the vehicle 2 has traveled a predetermined distance is set as the first analysis section. Then, after the road surface condition estimation is completed for the first analysis section, the section from the first point to the second point where the vehicle 2 has traveled a predetermined distance is set as the next analysis section.
  • the point determination unit 46 determines whether or not there is an out-of-target point in the predetermined analysis section (step S12). Specifically, the point determination unit 46 compares the time-series data of the position of the vehicle 2 corresponding to the predetermined analysis section with the position data of the non-target points stored in the non-target point database 402. . Then, if all the time-series data of the position of the vehicle 2 do not match the position data of the non-target point, the point determination unit 46 determines that the non-target point does not exist in the predetermined analysis section (step S12: NO).
  • the road surface condition estimating unit 45 estimates the road surface condition based on the time-series data of the vertical acceleration of the vehicle 2 corresponding to the predetermined analysis section (step S13). After registering in the database 400 (step S14), the process proceeds to step S17.
  • step S12 the point determination unit 46 determines that part or all of the time-series data of the position of the vehicle 2 corresponding to the predetermined analysis section matches the position data of the non-target point. determines that an out-of-target point exists in a predetermined analysis section (step S12: YES).
  • the road surface condition estimating unit 45 estimates the road surface condition based on the acceleration data excluding the acceleration data detected at the non-target point among the time-series data of the acceleration corresponding to the predetermined analysis section (Ste S15), after registering the analysis result of the road surface condition in the map database 400 (step S16), the process proceeds to step S17.
  • the road surface state estimation unit 45 determines whether or not the analysis end condition is satisfied as the process of step S17. For example, when the time-series data of the vehicle 2 from a predetermined travel start point to a predetermined travel end point is subject to analysis, the road surface condition estimation unit 45, except for the non-target points, If the estimation of the road surface condition up to the predetermined travel end point has not been completed, it is determined that the analysis end condition is not satisfied (step S17: NO). In this case, the road surface state estimation unit 45 updates the analysis section to the next section (step S18), and returns to the process of step S11. As a result, the road surface condition is sequentially estimated based on the time-series travel data of the vehicle 2 during the period until the estimation of the road surface condition from the predetermined travel start point to the predetermined travel end point is completed.
  • step S18 the road surface condition estimating unit 45 determines that the analysis end condition is satisfied when the estimation of the road surface condition from the predetermined travel start point to the predetermined travel end point is completed except for the non-target points. It is judged that it did (step S18: YES). In this case, the road surface state estimation unit 45 terminates the series of processes shown in FIG.
  • the data acquisition unit 44 acquires travel data including vertical acceleration data and position data of the vehicle 2 .
  • the road surface condition estimator 45 estimates the road surface condition along the travel route of the vehicle 2 based on the acceleration data and position data of the vehicle 2 .
  • the point determination unit 46 determines whether or not an out-of-target point exists on the travel route of the vehicle 2 .
  • the road surface state estimating unit 45 excludes the non-target points from road surface state estimation targets.
  • the estimated road surface state information includes disturbances such as the road surface state of a hump and the road surface state of a railroad crossing. is less likely to be included. Therefore, it is possible to more efficiently detect road surface conditions, which are the original targets of analysis, such as cracks, ruts, flatness, and the like.
  • the spot determination unit 46 uses spots with low urgency for road repair as non-target spots. According to this configuration, it is possible to avoid detection of the road surface condition at a point where the urgency regarding road repair is low, so it is possible to more efficiently detect the road surface condition to be analyzed.
  • the point determination unit 46 uses at least one of a private property and a parking lot as the non-target point. According to this configuration, it is possible to avoid detecting the road surface condition of a point outside the jurisdiction, such as a private property or a parking lot, so that it is possible to more efficiently detect the road surface condition to be analyzed.
  • the point determination unit 46 selects points where unevenness is inevitably formed on the road surface, specifically, points where humps are formed, points where railroad crossings are formed, and points where manholes are provided. Use at least one of the following: a point with a tram line, a point with a gravel road, and a point with a dirt road. According to this configuration, it is possible to avoid detection of the road surface condition at a point such as a hump where unevenness is inevitably formed on the road surface. .
  • the storage unit 40 stores position data of non-target points.
  • the point determination unit 46 compares the position data associated with the acceleration data acquired by the data acquisition unit 44 with the position data of the non-target points stored in the storage unit 40, thereby determining the traveling route of the vehicle 2. determines whether or not there is an out-of-target point. According to this configuration, it is possible to easily determine whether or not there is an out-of-target point on the travel route of the vehicle 2 .
  • the server device 3 executes the process shown in FIG. 6 instead of the process shown in FIG.
  • the road surface condition estimating unit 45 performs the analysis of the predetermined analysis section based on the time-series data of the vertical acceleration of the vehicle 2 corresponding to the predetermined analysis section.
  • the information of the road surface condition estimated at the point corresponding to the non-target point is excluded from the estimated road surface condition of the entire area (step S19).
  • the road surface condition estimation unit 45 registers the estimation result of the road surface condition in the map database 400 (step S14), and then executes the processes from step S17 onward. Even with such a configuration, it is possible to obtain the same or similar actions and effects as those of the above embodiment.
  • the flowchart shown in FIG. 6 and the flowchart shown in FIG. 5 are compared. , it is possible to simplify the overall process.
  • the processing procedure is such that the road surface state estimation processing is performed after the non-target point determination processing is performed, the amount of data used in estimating the road surface state can be reduced in advance. It is possible. Therefore, when processing big data at high speed, for example, it is effective to use the processing procedure as shown in FIG.
  • the road surface condition detection system 1 of the present embodiment compares a reference change pattern of acceleration corresponding to an out-of-target point with a change pattern of acceleration detected in the vehicle 2, and determines whether the acceleration detection position is at the out-of-target point. Determine whether or not there is
  • the acceleration reference change pattern corresponding to the non-target point corresponds to the acceleration reference data
  • the acceleration change pattern detected in the vehicle 2 corresponds to the acceleration data.
  • the non-target acceleration database 403 is stored in the storage unit 40 of the server device 3 .
  • the non-target acceleration database 403 reference change patterns of the vertical acceleration of the vehicle 2 when traveling at non-target points are registered for each type of non-target point. For example, a change pattern of vertical acceleration when the vehicle 2 runs on a hump is obtained in advance by experiments or the like, and is registered in the non-target acceleration database 403 as a reference change pattern of acceleration when running on a hump.
  • points with railroad crossings, manholes, streetcar tracks, gravel roads, unpaved roads, etc. are registered in the non-target acceleration database 403 .
  • the non-target acceleration database 403 may register a plurality of reference acceleration change patterns that differ according to vehicle speed.
  • the non-target acceleration database 403 includes a first speed region where the vehicle speed V satisfies “V ⁇ 20 [km/h]” and a vehicle speed V where “20 [km/h] ⁇ V ⁇ 80 [km/h]”.
  • Different reference change patterns of acceleration may be registered for each of the second speed region that satisfies the following and the third region where the vehicle speed V satisfies "80 [km/h] ⁇ V".
  • the server apparatus 3 of this embodiment executes the process shown in FIG. 7 instead of the process shown in FIG.
  • the same processing as the processing shown in FIG. 5 is denoted by the same reference numeral, thereby omitting redundant description as much as possible.
  • the point determination unit 46 of the present embodiment determines whether or not an out-of-target point exists in a predetermined analysis section in the process of step S12. The change pattern of the acceleration of the vehicle 2 to be measured is compared with the reference change pattern of the acceleration of various non-target points stored in the non-target acceleration database 403 .
  • the point determination unit 46 selects one of the plurality of acceleration reference change patterns based on the vehicle speed data. A variation pattern may be selected. If part or all of the change pattern of the acceleration of the vehicle 2 corresponding to the predetermined analysis target section does not show high similarity to the reference change pattern of the acceleration of all the non-target points , it is determined that there is no non-target point in the predetermined analysis section (step S12: NO).
  • the point determination unit 46 indicates that part or all of the change pattern of acceleration of the vehicle 2 is highly similar to the reference change pattern of acceleration of any non-target point. In this case, it is determined that an out-of-target point exists in the predetermined analysis section (step S12: YES). For example, if part or all of the change pattern of the acceleration of the vehicle 2 shows high similarity to the reference change pattern of the acceleration during hump driving, the point determination unit 46 determines that the hump is in a predetermined analysis section. is determined to exist.
  • the road surface condition estimating unit 45 uses the acceleration data detected at positions other than the position where the highly similar acceleration change pattern is detected in the time-series data of the acceleration corresponding to the predetermined analysis section. Based on this, the road surface condition is estimated (step S15), and the analysis result of the road surface condition is registered in the map database 400 (step S16).
  • the point determination unit 46 determines that the position where the acceleration change pattern showing high similarity to the acceleration change pattern of the non-target point is detected is already stored in the map database 400 as the non-target point. It is determined whether or not it is stored (step S20). If the position is not stored in the map database 400 (step S20: NO), the point determination unit 46 automatically registers the position in the map database 400 as a new non-target point (step S21). Note that the process of registering the non-target points in the map database 400 may not be an automatic process, but may be manually registered after confirmation by the user, for example.
  • the storage unit 40 stores reference change patterns of acceleration of the vehicle 2 corresponding to non-target points.
  • the point determination unit 46 compares the change pattern of the acceleration of the vehicle 2 detected at the predetermined point with the reference change pattern of the acceleration of the non-target point stored in the storage unit 40, thereby determining the travel route of the vehicle. Determine whether or not an out-of-target point exists. According to this configuration, it is possible to easily determine whether or not there is an out-of-target point on the travel route of the vehicle 2 .
  • the point determination unit 46 of this modification is based on the difference value of the acceleration of the vehicle 2 corresponding to the predetermined analysis section.
  • the difference value of the acceleration of the vehicle 2 is the difference between the current value and the previous value of the acceleration detected by the acceleration sensor 20 .
  • the differential value of the acceleration of the vehicle 2 has a correlation with the differential value of the acceleration of the vehicle 2 . If there is a spot where the acceleration difference value of the vehicle 2 is greater than or equal to a predetermined value, the spot determination unit 46 determines that there is an out-of-target spot near that spot. The point determination unit 46 determines whether or not an out-of-target point exists within a predetermined area based on the change pattern of the acceleration of the vehicle 2 detected in a predetermined area before and after the point.
  • the road surface condition detection system 1 of the third embodiment learns the acceleration reference change pattern at various non-target points based on the acceleration, position, and speed data detected by the vehicle 2 .
  • the server device 3 further includes a learning unit 47, as indicated by the dashed line in FIG.
  • the learning unit 47 learns the reference change pattern of acceleration at various non-target points by using time-series data of acceleration of each vehicle 2 stored in the vehicle database 401 .
  • the learning unit 47 can be implemented by the processor 30 executing a program stored in the storage device 31 of the server device 3, for example. As a learning method, either method of learning with a teacher or learning without a teacher may be used.
  • the user operates the input unit 41 of the server device 3 to give the time-series data of the acceleration of the vehicle 2 stored in the vehicle database 401 a label of an out-of-target point. do.
  • the user assigns a "hump" label to time-series data 50 of acceleration when traveling on a hump, and labels time-series data 51 of acceleration when traveling on a railroad crossing. Labels are added to time-series data of acceleration for each type of non-target points, such as adding a label of "railway crossing".
  • the learning unit 47 uses the labeled time-series data of acceleration as teacher data, and learns the time-series data of acceleration for each type of non-target point using a predetermined learning model.
  • the learning result is stored in the non-target point database 402 .
  • the learning unit 47 stores the data related to the detection position of the acceleration of the vehicle 2 and the non-target point database 402.
  • the time-series data of the acceleration of the vehicle 2 can automatically be labeled with the non-target points. good.
  • the learning unit 47 as shown in FIG. Time-series data of acceleration is learned for each type of non-target point using a predetermined learning model, and the learning result is stored in the non-target point database 402 .
  • the learning unit 47 acquires time-series data of acceleration of each vehicle 2 stored in the vehicle database 401, in other words, time-series data of acceleration of each vehicle 2 acquired by the data acquisition unit 44. Learn the reference change pattern of the acceleration of the non-target point based on. According to this configuration, it is possible to improve the accuracy of the acceleration reference change pattern corresponding to each non-target point, and as a result, it is possible to more accurately determine whether or not the non-target point exists on the travel route of the vehicle. becomes possible.
  • the point determination unit 46 of the second embodiment uses artificial intelligence or the like from the time-series data of the acceleration of each vehicle 2 stored in the vehicle database 401 without using the reference change pattern of the acceleration of the non-target point. may be used to determine whether or not there is an out-of-target point on the travel route of the vehicle 2 .
  • non-target points registered in the non-target point database 402 of the storage unit 40 may be set to points different from the points exemplified in the above embodiment.
  • non-target points include points where unevenness is formed in advance, points where roads are not paved such as riverbeds, points where there is a step between the road and a convenience store or gas station, and where there is a parking lot.
  • a point where the hump is provided or a point where a hump is formed in the parking lot may be set.
  • the vertical acceleration detected in the vehicle 2 differs depending on whether the vehicle speed is fast or slow, for example. This is a factor that deteriorates the detection accuracy of road surface conditions and non-target points.
  • the vertical acceleration of the vehicle 2 may be corrected based on not only the vehicle speed but also the acceleration of the vehicle 2 in the yaw direction, the weight of the vehicle 2, the spring coefficient and the viscosity coefficient of the suspension of the vehicle 2, and the like.
  • the vehicle 2 may be equipped with a device different from the acceleration sensor 20 as a device for detecting road surface conditions. As such a device, for example, a drive recorder having various sensors and a mobile terminal such as a smart phone can be used.
  • ⁇ It is possible to appropriately change which device functions each functional element provided in the vehicle 2 and the server device 3 .
  • a vehicle may be equipped with a road surface condition detection device having these functional elements.
  • a road surface condition detection program capable of realizing the processing executed by the road surface condition detection system 1 of the above embodiment may be installed in any computer.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Architecture (AREA)
  • Civil Engineering (AREA)
  • Structural Engineering (AREA)
  • Traffic Control Systems (AREA)
  • Road Repair (AREA)
  • Length Measuring Devices With Unspecified Measuring Means (AREA)

Abstract

Le système de détection de l'état de la surface de la route d'après la présente invention comprend une unité d'acquisition de données (44), une unité d'estimation de l'état de la surface de la route (45) et une unité de détermination de site (46). L'unité d'acquisition de données (44) acquiert des données de déplacement, parmi lesquelles des données d'accélérations verticales relatives à un véhicule et des données de positions relatives au véhicule. L'unité d'estimation de l'état de la surface de la route (45) estime l'état de la surface de la route le long de l'itinéraire de déplacement du véhicule sur la base des données d'accélérations et des données de positions relatives au véhicule. L'unité de détermination de site (46) détermine s'il existe un site exclu sur l'itinéraire de déplacement du véhicule. L'unité d'estimation de l'état de la surface de la route (45) omet le site exclu de l'estimation de l'état de la surface de la route.
PCT/JP2022/025654 2021-08-31 2022-06-28 Système, dispositif et programme de détection de l'état de la surface de la route WO2023032444A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021140742A JP2023034486A (ja) 2021-08-31 2021-08-31 路面状態検出システム、路面状態検出装置、路面状態検出プログラム
JP2021-140742 2021-08-31

Publications (1)

Publication Number Publication Date
WO2023032444A1 true WO2023032444A1 (fr) 2023-03-09

Family

ID=85412055

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/025654 WO2023032444A1 (fr) 2021-08-31 2022-06-28 Système, dispositif et programme de détection de l'état de la surface de la route

Country Status (2)

Country Link
JP (1) JP2023034486A (fr)
WO (1) WO2023032444A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0921639A (ja) * 1995-07-10 1997-01-21 Nippon Telegr & Teleph Corp <Ntt> 学習型位置検出システム
JP2011070356A (ja) * 2009-09-25 2011-04-07 Toyota Motor Corp 車両の走行支援システム及び方法
JP2012064126A (ja) * 2010-09-17 2012-03-29 Yupiteru Corp ドライブレコーダ
WO2018025341A1 (fr) * 2016-08-03 2018-02-08 三菱電機株式会社 Système de diagnostic de l'état d'une route, dispositif de génération d'informations de diagnostic et procédé de génération d'informations de diagnostic
JP2018120409A (ja) * 2017-01-25 2018-08-02 株式会社ユピテル データ収集装置、道路状態評価支援装置、及びプログラム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0921639A (ja) * 1995-07-10 1997-01-21 Nippon Telegr & Teleph Corp <Ntt> 学習型位置検出システム
JP2011070356A (ja) * 2009-09-25 2011-04-07 Toyota Motor Corp 車両の走行支援システム及び方法
JP2012064126A (ja) * 2010-09-17 2012-03-29 Yupiteru Corp ドライブレコーダ
WO2018025341A1 (fr) * 2016-08-03 2018-02-08 三菱電機株式会社 Système de diagnostic de l'état d'une route, dispositif de génération d'informations de diagnostic et procédé de génération d'informations de diagnostic
JP2018120409A (ja) * 2017-01-25 2018-08-02 株式会社ユピテル データ収集装置、道路状態評価支援装置、及びプログラム

Also Published As

Publication number Publication date
JP2023034486A (ja) 2023-03-13

Similar Documents

Publication Publication Date Title
CN110395258B (zh) 路面状态推断装置以及路面状态推断方法
JP7172619B2 (ja) 路面状態推定装置及び路面状態推定方法
US20200042800A1 (en) Image acquiring system, terminal, image acquiring method, and image acquiring program
JP6807225B2 (ja) 不確実性ベースの交通渋滞指標を生成するための方法、コンピュータ可読ストレージ媒体、およびシステム
US20120203402A1 (en) Intelligent Railway System for Preventing Accidents at Railway Passing Points and Damage to the Rail Track
BR112015019746B1 (pt) Sistema de detecção de defeitos na via férrea, sistema para detecção e relatório dos defeitos na via férrea enquanto um trem se desloca sobre as vias da ferrovia e método de detecção de defeitos na via da ferrovia enquanto um veículo ferroviário está em movimento
EP3705627A1 (fr) Surveillance de nids-de-poule
WO2007105518A1 (fr) Dispositif d&#39;enregistrement de position, dispositif de recherche d&#39;itinéraire, procédé d&#39;enregistrement de position, programme d&#39;enregistrement de position, et support d&#39;enregistrement associé
US11788859B2 (en) Method, apparatus, and computer program product for road noise mapping
JP2009237805A (ja) 橋梁通過車両監視システム、橋梁通過車両監視方法、およびコンピュータプログラム
CN107784381A (zh) 一种判断出租车绕路和计价异常的方法及装置
CN109377758B (zh) 一种行驶时间预估方法及系统
US20230322279A1 (en) Track condition monitoring device, track condition monitoring system and track condition monitoring method
JP6931159B2 (ja) 交通予測プログラム、交通予測装置、及び交通予測方法
WO2023032444A1 (fr) Système, dispositif et programme de détection de l&#39;état de la surface de la route
US11315425B2 (en) History information storage apparatus, route calculation method, and influence range distribution system
KR20180096235A (ko) 차량용 도로 상태 추정 시스템 및 그 방법
JP2014091424A (ja) 鉄道車両における運用を考慮した走行距離補正システム
US11302345B2 (en) Method, apparatus, and computer program product for vehicle localization via frequency audio features
US11449543B2 (en) Method, apparatus, and computer program product for vehicle localization via amplitude audio features
JP7172491B2 (ja) 交通流予測装置、交通流予測方法及びプログラム
JP2017059000A (ja) 商圏予測装置及び商圏予測プログラム
Kortmann et al. Creating value from in-vehicle data: Detecting road surfaces and road hazards
JP7492656B1 (ja) バラスト状態監視システム、バラスト状態監視装置及びバラスト状態監視方法
US11393489B2 (en) Method, apparatus, and computer program product for road noise mapping

Legal Events

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

Ref document number: 22864032

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE