WO2018180104A1 - Dispositif de détermination, procédé de détermination, programme de détermination et structure de données - Google Patents

Dispositif de détermination, procédé de détermination, programme de détermination et structure de données Download PDF

Info

Publication number
WO2018180104A1
WO2018180104A1 PCT/JP2018/007027 JP2018007027W WO2018180104A1 WO 2018180104 A1 WO2018180104 A1 WO 2018180104A1 JP 2018007027 W JP2018007027 W JP 2018007027W WO 2018180104 A1 WO2018180104 A1 WO 2018180104A1
Authority
WO
WIPO (PCT)
Prior art keywords
threshold
ground
determination
information
inclination
Prior art date
Application number
PCT/JP2018/007027
Other languages
English (en)
Japanese (ja)
Inventor
良司 野口
誠 松丸
雄悟 石川
宏 永田
竹村　到
Original Assignee
パイオニア株式会社
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 パイオニア株式会社 filed Critical パイオニア株式会社
Priority to JP2019509010A priority Critical patent/JPWO2018180104A1/ja
Publication of WO2018180104A1 publication Critical patent/WO2018180104A1/fr
Priority to JP2021170759A priority patent/JP7174131B2/ja

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B29/00—Maps; Plans; Charts; Diagrams, e.g. route diagram

Definitions

  • This application belongs to the technical field of determination apparatus, determination method, determination program, and data structure. More specifically, the present invention belongs to a technical field of a determination device and a determination method for performing determination related to a map, a program for the determination, and a data structure.
  • One of the techniques necessary for realizing automatic driving is the detection of obstacles on the ground.
  • One of the techniques that can be used to detect such an obstacle is object detection using a LiDAR (Light Detection Detection and Ranging, Laser Imaging Detection and Ranging) system.
  • the inclination (gradient) of the portion of the ground is detected from data calculated from the reflected light from the ground, and if the inclination is gentle, the reflected light from the ground If the slope is steep, it is determined that the reflected light is from the obstacle.
  • Patent Document 1 As an example of a technique related to the background art, there is a technique described in Patent Document 1 below, for example.
  • a threshold for determining whether or not the obstacle is an obstacle by the above inclination is necessary.
  • the threshold value is too small, for example, even a slope is judged as an obstacle, and if the threshold value is too large, a small obstacle is judged as the ground.
  • the present application has been made in view of the above-described problems, and an example of the problem is a determination device and a determination method capable of accurately determining the inclination (gradient) of the ground, and the determination device. It is to provide a program and a data structure.
  • the invention according to claim 1 is a first acquisition unit that acquires light reception information obtained by receiving reflected light from the ground of light emitted from a moving body to the surroundings; Detection means for detecting the inclination of the reflection point of the light based on the light reception information, and threshold information indicating a threshold for determining the type of the inclination are associated with the map information corresponding to the ground, and the threshold information is obtained. Whether the reflection point is the ground or an object on the ground based on a comparison between the threshold value indicated by the threshold information and the detected inclination based on the second acquisition means for acquiring from the recording medium being recorded. Determining means for determining.
  • the invention according to claim 14 is a determination method executed in a determination apparatus including a first acquisition unit, a detection unit, a second acquisition unit, and a determination unit.
  • the second acquisition step acquired by the means and a comparison between the threshold value indicated by the threshold value information and the detected inclination it is determined whether the reflection point is the ground or an object on the ground.
  • Ri determines comprising a determining step.
  • the invention according to claim 15 is directed to a computer included in the determination device, wherein the light reception information obtained by receiving the reflected light from the ground of the light emitted from the moving body to the surroundings is received.
  • Second acquisition means for acquiring the threshold information in association with the recording medium, and comparing the threshold indicated by the threshold information with the detected inclination, whether the reflection point is the ground , And functioning as a determination means for determining whether the object is on the ground.
  • the invention according to claim 16 is characterized in that the threshold information acquired by the second acquisition means of the determination device according to any one of claims 1 to 13 is the threshold value information.
  • a data structure of a recording medium recorded in association with map information, wherein the threshold value information and the threshold value indicated by the threshold value information indicate a position on the map of the ground used for the type determination of the inclination Position information that is paired with the threshold information and the map information corresponding to the map that includes the position indicated by the position information, and the threshold information and the position information that form the pair are The map information corresponding to the map including the position indicated by the read position information is read together with the threshold information by being read by the second acquisition unit. Configured to be read to.
  • the invention according to claim 17 is the light reception obtained by receiving the reflected light from the ground or the object on the ground of the light emitted from the emitting means to the predetermined area.
  • Second acquisition for acquiring threshold information indicating a first threshold value for determining whether the object is on the ground based on the inclination state and a second threshold value for determining based on the reflectance
  • the irradiation target is on the ground on the basis of means, a comparison between the first threshold value indicated by the threshold value information and the detected inclination state, and a comparison between the second threshold value and the detected reflectance.
  • an object on the ground Comprising a determining means.
  • (a) is a flowchart which shows the said map data recording process
  • (b) is a flowchart which shows the whole ground determination process which concerns on 1st Example.
  • (C) is a flowchart showing details of the ground determination process. It is a flowchart which shows the ground determination process which concerns on 2nd Example. It is a flowchart which shows the map data recording process etc. which concern on 3rd Example
  • (a) is a flowchart which shows the said map data recording process
  • (b) is a flowchart which shows the ground determination process which concerns on 3rd Example. .
  • FIG. 1 is a block diagram illustrating a schematic configuration of the determination apparatus according to the embodiment.
  • the determination device S includes a first acquisition unit 1, a detection unit 2, a determination unit 3, and a second acquisition unit 4.
  • the first acquisition means 1 acquires the light reception information obtained by receiving the reflected light from the ground of the light emitted from the moving body to the surroundings.
  • the detection means 2 detects the inclination of the reflection point of light based on the light reception information acquired by the 1st acquisition means.
  • the second acquisition means 4 acquires threshold information indicating a threshold for determining the type of inclination from a recording medium in which the threshold information is recorded in association with map information corresponding to the ground.
  • the determination unit 3 determines whether the light reflection point is the ground or an object on the ground based on the comparison between the threshold indicated by the threshold information and the inclination detected by the detection unit 2.
  • the inclination of the reflection point is detected based on the light reception information obtained by receiving the reflected light from the ground, and the inclination corresponds to the ground. Whether the reflection point is the ground or an object is determined based on the comparison with the threshold value indicated by the threshold value information recorded in association with the map information. Therefore, since it is determined whether the reflection point is the ground or an object by comparison with the threshold value recorded for determining the type of inclination, the determination can be accurately performed without requiring complicated processing.
  • each Example demonstrated below is an Example at the time of applying to the threshold value used for the obstacle detection using the LiDAR system mounted in the vehicle.
  • FIG. 2 is a block diagram showing a schematic configuration of the map data system according to the first embodiment
  • FIG. 3 is a diagram showing a structure of map data according to the first embodiment
  • FIG. 4 is a diagram showing the first embodiment.
  • FIG. 5 is a flowchart showing a ground determination process according to the second embodiment
  • FIG. 6 is a flowchart showing a map data recording process according to the third embodiment. .
  • the map data system SS includes a map server device SV that can exchange data via a network NW such as the Internet, and a ground determination device C that is mounted on a vehicle. , Is configured.
  • the map server device SV includes a processing area determining unit 11, a map database 12, a graph / gradient calculating unit 13, an object recognizing unit 14, a discriminator 15, and an in-processing area gradient threshold determining unit 16.
  • the processing area gradient threshold value determination unit 16 is connected to the map database 17.
  • the map database 17 may be provided separately from the map server device SV, or may be provided in the map server device SV.
  • the processing area determining unit 11, the graph / gradient calculating unit 13, the object recognizing unit 14, and the in-processing area gradient threshold determining unit 16 are implemented by a hardware logic circuit including a CPU (not shown) provided in the map server device SV. It may be realized, or may be realized in software by the CPU or the like reading and executing a program corresponding to map data recording processing according to a first embodiment described later.
  • the ground determination device C includes a graph / gradient calculation unit 21 connected to the network NW and the LiDAR sensor 20, a processing area determination unit 22, a map database 23, and an in-processing area gradient threshold comparison unit 24.
  • the graph / gradient calculation unit 21, the processing area determination unit 22, and the in-processing area gradient threshold comparison unit 24 may be realized by a hardware logic circuit including a CPU (not shown) provided in the ground determination device C.
  • the program may be realized in software by causing the CPU or the like to read and execute a program corresponding to a ground determination process according to a first embodiment described later.
  • the processing area gradient threshold value comparison unit 24 corresponds to an example of the “first acquisition unit 1”, an example of the “second acquisition unit”, and an example of the “determination unit 3” according to the embodiment.
  • the graph / gradient calculation unit 21 corresponds to an example of the “detection unit 2” according to the embodiment.
  • the map database 17 corresponds to an example of a “recording medium” according to the present application.
  • the map database 12 of the map server device SV records map data for matching with data from the LiDAR sensor 10. Then, the processing area determination unit 11 of the map server device SV reads out the map data for matching from the map database 12 and sets a predetermined area on the map on which the gradient data according to the embodiment is generated. Determined by This area determination may be made manually.
  • the graph / gradient calculation unit 13 has four neighboring points of interest (for example, four directions centered on the point of interest (for example, up, down, left, and right directions))
  • the graphs connecting the neighborhoods of the graphs are created, and the gradients of the edges of the respective graphs are executed at all the points of interest. Details of the calculation method in the graph / gradient calculation unit 13 are described in, for example, the paper “On ⁇ the Segmentation of 3D LIDAR Point Clouds” ICRA, 2011, The University of Sydney, B. Douillard et al. SEGMENTATION ALGORITHMS, C Segmentation for Sparse Data, and 2) Mesh Based on Segmentation.
  • the above-described gradient calculation method is simply referred to as “gradient calculation method according to the embodiment”.
  • the object recognition unit 14 detects whether the target from which the data is obtained is the ground or an obstacle using the classifier 15 or manually.
  • the in-processing area gradient threshold value determination unit 16 determines a threshold value for determining the slope type of the ground in the area determined by the processing area determination unit 11 (that is, a threshold value for determining the inclination type in the area).
  • the determined threshold value is recorded in the map database 17 in association with the map data corresponding to the area.
  • the graph / gradient calculation unit 21 of the ground determination device C calculates the gradient at each point of interest based on the data from the LiDAR sensor 20, for example, by the gradient calculation method according to the above embodiment.
  • the map database 23 records map data for matching with data from the LiDAR sensor 20.
  • the processing area determination unit 22 reads the map data for matching from the map database 23, and determines an area on the map that is a target for detecting the inclination (gradient) according to the embodiment by a preset method. .
  • the processing area gradient threshold value comparison unit 24 acquires the threshold value recorded in the map database 17 of the map server device SV via the network NW as necessary, and the threshold value and the data from the LiDAR sensor 20. To detect the inclination (gradient) of the area to be processed.
  • the threshold for determining the type of inclination is recorded for each area as a map. That is, for example, as illustrated in FIG. 3A, for each of the areas A1 to A3 obtained by equally dividing the road on which the vehicle CC travels in the traveling direction, the threshold value is recorded in association with each of the areas A1 to A3. Has been. At this time, for example, the threshold value may be recorded for each of the areas B1 to B4 having different lengths in the traveling direction as shown in FIG. 3B, or along the curve as shown in FIG.
  • the threshold value may be recorded for each of the divided areas C1 to C3, or for each of the areas D1 to D8 divided corresponding to the intersection CR indicated by a broken line in FIG. It may be recorded. Furthermore, as illustrated in FIG. 3E, the threshold value may be recorded for each of the areas E1 to E6 that are freely divided with respect to the road R.
  • map data recording processing according to the first embodiment will be described with reference to FIG.
  • the map data recording process according to the first embodiment is started, for example, at the timing when the power switch of the map server device SV is turned on.
  • the processing area determination unit 11 selects, for example, any one of the areas A1 illustrated in FIG. 3 (step S2).
  • step S1 when the area to be processed is determined (step S1: YES or step S2), the graph / gradient calculation unit 13 uses the gradient calculation method according to the above embodiment based on the data from the LiDAR sensor 10. Then, the slope (the slope) based on the data for the determined area is calculated for each data (step S3).
  • the object recognizing unit 14 detects whether the target from which the data is obtained is the ground or an obstacle by a method using the discriminator 15 or visual observation (step S4).
  • the processing area gradient threshold value determination unit 16 determines the type of gradient in the determined area based on the gradient calculated from the data about the object in which whether the ground or the obstacle is detected in step S4.
  • the above threshold A of It is determined so that the maximum value of the gradient of the object that is the ground ⁇ the threshold A ⁇ the minimum value of the gradient of the object that is the obstacle.
  • the threshold A after this determination is recorded in the map database 17 in association with the area.
  • step S6 determines whether or not to determine the threshold value for the next area.
  • step S6 determines whether or not to determine the threshold value for the next area.
  • the ground determination process according to the first embodiment is started, for example, when the power switch of the ground determination device C is turned on.
  • the threshold value data is not acquired in the determination in step S10 (step S10: NO)
  • the map server 17 of the map server device SV is accessed to acquire the necessary threshold value data (step S11).
  • necessary threshold data is acquired (step S10: YES or step S11)
  • the ground determination process according to the first embodiment is then executed (step S12).
  • step S13 whether or not to end the ground determination processing according to the first embodiment is determined, for example, by determining whether or not the vehicle on which the ground determination device C is mounted has reached the destination (step) S13).
  • step S13: YES the ground determination process is terminated as it is. It is.
  • the in-process area gradient threshold value comparison unit 24 associates the threshold value with respect to one of the attention points (attention points on the ground) (i). It is determined whether or not (step S120). When the threshold value is not associated with the current attention point (i) in the determination in step S120 (step S120: NO), the in-processing area gradient threshold value comparison unit 24 performs the ground determination process for the next attention point (i + 1). It is determined whether or not to perform (step S121).
  • step S121 When the ground determination process is performed for the next attention point (i + 1) in the determination of step S121 (step S121: YES), the in-process area gradient threshold value comparison unit 24 returns to step S120 to determine the next attention point (i + 1). Repeat the ground determination process. On the other hand, when there is no point of interest to be subjected to the ground determination process next in the determination in step S120 (step S121: NO), the in-process area gradient threshold value comparison unit 24 returns to step S13. On the other hand, when the threshold value is associated with the current attention point (i) in the determination in step S120 (step S120: YES), the in-processing area gradient threshold value comparison unit 24 determines that the inclination of the attention point (i) is greater than the threshold value.
  • step S122 It is determined whether or not the inclination is smaller (step S122), and when the inclination of the attention point (i) is smaller than the threshold value (step S122: YES), the in-processing area gradient threshold value comparison unit 24 determines that the attention point (i) is the ground surface. It is determined that there is (step S123), and the process proceeds to step S121.
  • step S122: NO when the inclination of the point of interest (i) is equal to or greater than the threshold value in the determination in step S122 (step S122: NO), the in-processing area gradient threshold value comparison unit 24 determines that there is an obstacle at the point of interest (i). (Step S124), the process proceeds to Step S121.
  • the inclination of the reflection point is detected based on the data obtained by receiving the reflected light from the ground, and the inclination and the ground are detected. Based on the comparison with the threshold value recorded in association with the corresponding map data, it is determined whether the reflection point is the ground or an object. Therefore, since it is determined whether the reflection point is the ground or an object by comparison with the threshold value recorded for determining the type of inclination, the determination can be accurately performed without requiring complicated processing.
  • the threshold value is a threshold value for each ground corresponding to an area divided in advance, it is possible to accurately determine whether or not the surface is a ground by using a fine threshold value for each area.
  • the threshold value is determined / recorded finely at regular intervals in the moving direction. Can do.
  • the area for which the threshold is determined is an area divided at intervals corresponding to the change in the ground inclination in the moving direction of the vehicle, it corresponds to the change in the inclination of the ground in the moving direction (that is, the undulation of the ground).
  • the threshold value can be determined / recorded in detail.
  • the map server device SV executes the discrimination of the object on the ground based on the reflected light from the ground within the predetermined angle range by the LiDAR sensor 10, the gradient of the ground within the predetermined angle range is set.
  • a threshold for accurate detection can be recorded in association with the map data.
  • a plurality of threshold values for the ground are determined according to changes in the inclination of the ground, it is possible to more appropriately determine whether or not the ground is concerned.
  • a plurality of threshold values are determined according to the change in the inclination of the ground, for example, in an area where there is no change in the inclination of the ground, a single threshold value is determined for the area.
  • a plurality of threshold values are determined for the area in accordance with the change in inclination in the area.
  • a threshold corresponding to the speed limit of the vehicle in the same area is determined.
  • the threshold value is determined to be 0.7 when the speed limit is 80 km / h, and the threshold value is determined to be 1.0 when the speed limit is 20 km / h. It is mentioned that.
  • the moving speed of the management vehicle itself when the map management vehicle on which the LiDAR sensor 10 is mounted moves or the movement speed is set. Even when one or more threshold values for the ground are determined with reference, it is possible to more appropriately determine whether the ground is the ground.
  • one or a plurality of threshold values are determined according to the moving speed or with reference to the moving speed
  • a plurality of threshold values are determined according to the speed limit
  • the management vehicle is moved a plurality of times for one point, and a threshold value is determined for each movement.
  • the management vehicle is moved once for one point, one threshold is determined according to the moving speed of the one movement, and the other threshold for the one point is determined according to the moving speed.
  • the other threshold is determined manually or by a preset calculation method based on the determined one threshold. It is preferable that the relationship between the moving speed and the plurality of threshold values is tabulated, which is acquired by the ground determination device C according to the first embodiment and used for the type determination of the inclination.
  • the threshold is determined to be 0.7 when the moving speed of the management vehicle is 80 km / h, and the moving speed is In the case of 20 kilometers per hour, the threshold is determined to be 1.0.
  • the threshold value may be determined according to the moving speed of or referring to the moving speed.
  • the type of inclination is determined using the threshold value A as the value of the ground gradient.
  • the threshold value A is also used.
  • the type of inclination may be determined by further using a threshold value as a reflectance value from the ground (having a gradient) of the emitted light.
  • the threshold value as the reflectance value is referred to as “threshold value B”.
  • the threshold value B is set based on the data from the LiDAR sensor 10.
  • the maximum reflectance of the object that is the ground ⁇ the threshold B ⁇ the minimum value of the reflectance of the object that is the obstacle is determined, and this is recorded in the map database 17 in association with the area.
  • the reflectance as the threshold value B varies depending on the wavelength of the emitted light from the LiDAR sensor 10. Therefore, the threshold value B is recorded in the map database 17 in association with the wavelength of the emitted light from the used LiDAR sensor 10.
  • the LiDAR sensor 10 and the LiDAR sensor 20 originally use emitted light of various wavelengths, it is necessary to determine and record a threshold value B as a reflectance for each of a plurality of types of wavelengths. For this reason, for example, the reflectance data is collected and recorded by changing the wavelength of the light emitted from the LiDAR sensor 10, or the reflectance data is collected by a plurality of LiDAR sensors 10 having different original specifications (wavelengths). Is preferably configured to collect. Furthermore, at the time of the collection, it is preferable to record the emission angle of the emitted light from the LiDAR 10 in association with the distance to the target. This is because the emission angle and distance affect the threshold value B, which is a reflectance value.
  • the relationship with the threshold B as the reflectance value is also taken into consideration. Determine whether the area is the ground or there are obstacles. More specifically, “YES” is determined in step S122 of FIG. 4C, and the reflectance of the point of interest (i) when using emitted light having a predetermined angle, distance, and wavelength is the threshold value B. If it is less than the threshold value, the in-processing-area gradient threshold value comparing unit 24 determines that the attention point (i) is the ground (see step S123 in FIG. 4C). On the other hand, the determination in step S122 of FIG.
  • the processing area gradient threshold value comparison unit 24 determines that there is an obstacle at the attention point (i) (see step S124 in FIG. 4C).
  • the threshold value B as the reflectance value is used in a superimposed manner in addition to the threshold value A as the gradient value, the inclination type is determined.
  • the possibility that the type determination is erroneously determined can be reduced.
  • FIG. 5 is a flowchart showing the ground determination process according to the second embodiment.
  • a ground determination process corresponding to the speed of the vehicle is performed as the ground determination process.
  • the other configuration and processing (including map data recording processing) according to the second embodiment are the same as the configuration and processing according to the first embodiment, and thus detailed description thereof is omitted.
  • step S120 determines whether or not to perform the ground determination process according to the speed of the vehicle (step S130). And when not performing the ground determination process according to the speed of a vehicle (step S130: NO), the process area gradient threshold value comparison part 24 performs the process after step S122 similar to the ground determination process which concerns on 1st Example. .
  • step S130 determines that the inclination of the point of interest (i) corresponds to the threshold value according to the speed. It is determined whether or not the value is smaller than the value obtained by multiplying the correction value ⁇ (step S131). If the inclination of the attention point (i) is smaller than the result of the multiplication (step S131: YES), the process proceeds to step S123, and attention is paid. If the slope of the point (i) is equal to or greater than the result of the multiplication (step S131: NO), the process proceeds to step S124.
  • the ground is determined according to the speed at which the vehicle moves. This determination can be made.
  • the determination can be performed accurately according to the moving speed of the vehicle.
  • correction value ⁇ is smaller as the speed of movement of the vehicle is faster, a smaller object can be determined as the object as the vehicle moves at a higher speed, which can contribute to safer movement.
  • correction value ⁇ can be increased as the speed of movement of the vehicle is slower. In this case, when the vehicle moves at a low speed, determination accuracy corresponding to the low speed can be obtained.
  • FIG. 6 is a flowchart showing map data recording processing and the like according to the third embodiment.
  • a LiDAR sensor connected to the map server device The vertical inclination angle of the emitted light (that is, the pitch angle; the same applies hereinafter) ⁇ 1 according to the map data recording process and the pitch angle ⁇ 2 of the emitted light of the LiDAR sensor connected to the ground determination device The ground determination process is performed.
  • the same thing as the structure and process which concerns on 1st Example attaches
  • step S1 when the determination in step S1 according to the first embodiment or the area to be processed is determined in step S2 (step S1: YES or step S2), graph gradient calculation unit 13 then determines whether to perform a map data recording processing according to the pitch angle theta 1 (step S30).
  • the pitch angle ⁇ 1 in this case is detected by, for example, an acceleration sensor (not shown) provided in the LiDAR sensor 10.
  • the graph gradient calculation unit 13 a map data recording processing similar to step S3 and subsequent processing according to the first embodiment I do.
  • step S30 when performing the map data recording processing according to the pitch angle theta 1 is determined in step S30 (step S30: YES), the graph gradient calculation unit 13, for example, using a gradient calculation method or the like according to the embodiment
  • Is calculated for each piece of data as a correction slope based on the data from the LiDAR sensor 10 step S31.
  • step S4 and subsequent steps using the corrected inclination are executed.
  • the in-processing-area gradient threshold value comparison unit 24 determines whether or not to perform the ground determination processing according to the pitch angle ⁇ 2 (step S140).
  • the pitch angle ⁇ 2 in this case is detected by, for example, an acceleration sensor (not shown) provided in a vehicle on which the ground determination device C according to the third embodiment is mounted.
  • step S140: NO the process area gradient threshold value comparison part 24 is the process after step S122 similar to the ground determination process which concerns on 1st Example. I do.
  • step S140: YES the in-process area gradient threshold value comparison unit 24 determines the inclination of the point of interest (i) as the pitch angle ⁇ 2.
  • Step S141 a value obtained by dividing the parameter z at the inclination of the attention point (i) by the cosine of the pitch angle ⁇ 2 (that is, a value obtained by multiplying the parameter z by (1 / cos ⁇ 2 )) ) Is smaller than a threshold value associated with the point of interest (i) (step S141), and the corrected inclination of the point of interest (i) is smaller than the threshold value.
  • Step S141 YES
  • the process proceeds to step S123, and when the corrected inclination of the point of interest (i) is greater than or equal to the result of the threshold (step S141: NO), the step S 124.
  • the ground is determined according to the pitch angle ⁇ 2 of the emitted light from the LiDAR sensor 20. Since it determines, the said determination can be performed correctly.
  • programs corresponding to the flowcharts shown in FIGS. 4 and 5 are recorded on a recording medium such as an optical disk or a hard disk, or obtained via a network such as the Internet, and these are stored in a general-purpose microcomputer. It is possible to cause the microcomputer or the like to function as the in-process area gradient threshold value determination unit 16 or the in-process area gradient threshold value comparison unit 24 according to each embodiment.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Educational Technology (AREA)
  • Educational Administration (AREA)
  • Business, Economics & Management (AREA)
  • Mathematical Physics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Electromagnetism (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Traffic Control Systems (AREA)
  • Optical Radar Systems And Details Thereof (AREA)

Abstract

L'invention concerne un dispositif de détermination qui permet de déterminer avec précision l'inclinaison (pente) d'une surface de sol. Dans la présente invention, des informations de réception de lumière sont acquises par l'intermédiaire de la réception de lumière qui a été émise par un véhicule sur son environnement et réfléchie par une surface de sol, et l'inclinaison d'un point de réflexion de lumière est détectée sur la base des informations de réception de lumière. En outre, des informations de seuil indiquant un seuil pour identifier des types d'inclinaison sont acquises à partir d'une base de données cartographiques 17 ayant les informations de seuil enregistrées sur celle-ci en association avec des informations cartographiques correspondant à la surface de sol. Ensuite, le point de savoir si le point de réflexion est la surface de sol ou un objet sur la surface de sol est déterminé sur la base d'une comparaison de l'inclinaison et du seuil indiqué par les informations de seuil.
PCT/JP2018/007027 2017-03-31 2018-02-26 Dispositif de détermination, procédé de détermination, programme de détermination et structure de données WO2018180104A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2019509010A JPWO2018180104A1 (ja) 2017-03-31 2018-02-26 判定装置、判定方法並びに判定用プログラム及びデータ構造
JP2021170759A JP7174131B2 (ja) 2017-03-31 2021-10-19 判定装置、判定方法及び判定用プログラム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2017072480 2017-03-31
JP2017-072480 2017-03-31

Publications (1)

Publication Number Publication Date
WO2018180104A1 true WO2018180104A1 (fr) 2018-10-04

Family

ID=63675310

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/007027 WO2018180104A1 (fr) 2017-03-31 2018-02-26 Dispositif de détermination, procédé de détermination, programme de détermination et structure de données

Country Status (2)

Country Link
JP (2) JPWO2018180104A1 (fr)
WO (1) WO2018180104A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110163871A (zh) * 2019-05-07 2019-08-23 北京易控智驾科技有限公司 一种多线激光雷达的地面分割方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003065740A (ja) * 2001-08-27 2003-03-05 Nissan Motor Co Ltd 前方路面勾配判定装置
JP2008186384A (ja) * 2007-01-31 2008-08-14 Toyota Motor Corp 車両の制御装置
JP2012192862A (ja) * 2011-03-17 2012-10-11 Toyota Motor Corp 車両制御装置
JP2014095562A (ja) * 2012-11-07 2014-05-22 Denso Corp 車載レーダ装置
JP2015127937A (ja) * 2013-11-29 2015-07-09 富士通株式会社 運転支援装置、方法、及びプログラム

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050015201A1 (en) 2003-07-16 2005-01-20 Sarnoff Corporation Method and apparatus for detecting obstacles
US8466810B2 (en) 2008-05-30 2013-06-18 Navteq B.V. Data mining in a digital map database to identify intersections located at hill bottoms and enabling precautionary actions in a vehicle
JP6464410B2 (ja) * 2014-09-26 2019-02-06 シャープ株式会社 障害物判定装置および障害物判定方法
US10183659B2 (en) 2014-11-24 2019-01-22 Ford Global Technologies, Llc Vehicle underside impact avoidance
JP2017015409A (ja) * 2015-06-26 2017-01-19 シャープ株式会社 路面検知装置、移動体、路面検知方法、および路面検知プログラム
JP2017015601A (ja) 2015-07-02 2017-01-19 シャープ株式会社 路面検知装置、移動体、路面検知方法、および路面検知プログラム
US9761000B2 (en) 2015-09-18 2017-09-12 Qualcomm Incorporated Systems and methods for non-obstacle area detection

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003065740A (ja) * 2001-08-27 2003-03-05 Nissan Motor Co Ltd 前方路面勾配判定装置
JP2008186384A (ja) * 2007-01-31 2008-08-14 Toyota Motor Corp 車両の制御装置
JP2012192862A (ja) * 2011-03-17 2012-10-11 Toyota Motor Corp 車両制御装置
JP2014095562A (ja) * 2012-11-07 2014-05-22 Denso Corp 車載レーダ装置
JP2015127937A (ja) * 2013-11-29 2015-07-09 富士通株式会社 運転支援装置、方法、及びプログラム

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110163871A (zh) * 2019-05-07 2019-08-23 北京易控智驾科技有限公司 一种多线激光雷达的地面分割方法
CN110163871B (zh) * 2019-05-07 2021-04-13 北京易控智驾科技有限公司 一种多线激光雷达的地面分割方法及装置

Also Published As

Publication number Publication date
JPWO2018180104A1 (ja) 2020-05-14
JP2022009231A (ja) 2022-01-14
JP7174131B2 (ja) 2022-11-17

Similar Documents

Publication Publication Date Title
US20210350149A1 (en) Lane detection method and apparatus,lane detection device,and movable platform
JP6349742B2 (ja) 多車線の検出方法と検出システム
KR101609303B1 (ko) 카메라 캘리브레이션 방법 및 그 장치
JP4858574B2 (ja) 物体検出装置
CN110794406B (zh) 多源传感器数据融合系统和方法
CN109635816B (zh) 车道线生成方法、装置、设备以及存储介质
CN109444916B (zh) 一种无人驾驶可行驶区域确定装置及方法
EP3601001B1 (fr) Procédé et système pour l'estimation en temps réel d'états de route et de comportement de véhicule
KR20210048552A (ko) Lidar 센서가 장착된 자동차의 도로 감지 방법
JP4052291B2 (ja) 車両用画像処理装置
JP4662147B2 (ja) 物体認識装置
JP7174131B2 (ja) 判定装置、判定方法及び判定用プログラム
JP3925285B2 (ja) 走行路環境検出装置
JP5375249B2 (ja) 移動経路計画装置、移動体制御装置及び移動体
CN113434788B (zh) 建图方法、装置、电子设备及车辆
JP2010250743A (ja) 自動走行車両及び道路形状認識装置
JP7344744B2 (ja) 路側端検出方法、及び、路側端検出装置
JP2007093347A (ja) 停止車両判別装置、自動車及び停止車両判別方法
WO2018180103A1 (fr) Dispositif d'enregistrement d'informations, procédé d'enregistrement d'informations, programme d'enregistrement d'informations et structure de données
JP2023068009A (ja) 地図情報作成方法
JP4618506B2 (ja) 物体認識装置
JP6813436B2 (ja) 情報処理装置、移動体、情報処理方法、およびプログラム
Tripathy et al. Image-Based Pothole Detection System Using YoloV8 Algorithm
JP7165630B2 (ja) 認識システム、車両制御システム、認識方法、およびプログラム
WO2020095673A1 (fr) Dispositif de commande embarqué

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: 18774416

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2019509010

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18774416

Country of ref document: EP

Kind code of ref document: A1