Data collection instruction device and method, and computer program product for data collection instruction

By selecting a suitable vehicle in the autonomous driving system to collect detection data in the update target area and instructing other vehicles to collect data in a specific range, the problem of excessive and insufficient traffic of detection data is solved, and efficient update of map information is achieved.

CN118936447APending Publication Date: 2024-11-12WOVEN BY TOYOTA INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410526118.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-05-09
Filing Date
2024-04-29
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In autonomous driving systems, it is difficult for the prior art to effectively collect and update the detection data required for map information, resulting in the problem of excessive communication volume and insufficient data.

Method used

Through the data collection indication device, a vehicle that meets the specific driving history conditions is selected, instructed to collect detection data within the updated object area, and instruct other vehicles to collect detection data within the necessary interval to reduce traffic and ensure the quality of the data.

Benefits of technology

It effectively suppresses the increase in traffic volume of detection data, and ensures the appropriate collection of data required for update of map information, improving data quality and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118936447A_ABST
    Figure CN118936447A_ABST
Patent Text Reader

Abstract

The invention relates to a data collection instruction apparatus, a data collection instruction method, and a computer program product for data collection instruction. A data collection instruction device is provided with: storage units (52, 53) that store travel histories for each of a plurality of vehicles (2); a selection unit (61) that selects, on the basis of the travel history of each of the plurality of vehicles (2), one or more vehicles among the plurality of vehicles (2) that satisfy a prescribed condition pertaining to travel in the region to be updated of the map information; and a notification processing unit (63) that instructs, via the communication unit (51), the selected one or more vehicles to collect probe data indicating a predetermined surface feature for the update target region, and instructs, via the communication unit (51), a vehicle other than the selected one or more vehicles among the plurality of vehicles (2) to collect probe data for a predetermined road section.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a data collection instruction device, a data collection instruction method and a computer program product for data collection instruction for instructing the collection of data for updating a map. Background Art

[0002] In the high-precision map that the vehicle's automatic driving system refers to in order to control the vehicle's automatic driving, it is required to accurately represent information related to roads. Therefore, data representing roads or features around roads in a predetermined area obtained by sensors mounted on the vehicle (hereinafter referred to as probe data) is collected from vehicles that have actually traveled in the predetermined area. In particular, a technology for collecting information related to new roads has been proposed (see Japanese Patent Publication No. 2008-164831).

[0003] In the technology disclosed in Japanese Patent Application Laid-Open No. 2008-164831, a vehicle serving as a probe car transmits travel history information when traveling on a road not included in the navigation map data possessed by the navigation device as probe data to a map distribution center. On the other hand, the map distribution center that receives the travel history information from the navigation devices of each vehicle collects the received data, excludes the travel history information for which it is predicted that the vehicle did not travel on the new road, and filters the target data. Summary of the invention

[0004] Generally, the traffic volume in a certain period varies according to the road section. Therefore, the amount of collected probe data may be insufficient depending on the road section. In addition, if the probe data collection period is extended or the predetermined amount of probe data collection is increased so that the amount of probe data collected for any road section is sufficient, an excessive amount of probe data may be sent to the server depending on the road section. As a result, the communication volume between the vehicle and the server may increase excessively.

[0005] Therefore, an object of the present invention is to provide a data collection instruction device capable of appropriately collecting probe data required for updating map information while suppressing an increase in the amount of communication required for collecting the probe data.

[0006] According to one embodiment, a data collection instruction device is provided. The data collection instruction device comprises: a storage unit storing driving history records of each of a plurality of vehicles; a selection unit selecting one or more vehicles from among the plurality of vehicles that meet predetermined conditions related to driving in an update target area of ​​map information based on the driving history records of each of the plurality of vehicles; and a notification processing unit instructing the selected one or more vehicles to collect detection data representing predetermined features for the update target area via a communication unit, and instructing vehicles other than the selected one or more vehicles from among the plurality of vehicles to collect detection data for a predetermined road section via the communication unit.

[0007] In addition, in the data collection indication device, it is preferred that the selection unit refers to the driving history records of each of the multiple vehicles and selects one or more vehicles from the multiple vehicles in descending order of the driving coverage rate of the road sections actually traveled within the most recent predetermined period among the multiple road sections included in the update object area.

[0008] In this case, preferably, importance is set for each of the plurality of road sections included in the update target area. Furthermore, preferably, the selection unit calculates, for each of the plurality of vehicles, a ratio of the sum of importance of the road sections that the vehicle actually traveled on in the most recent predetermined period of time, among the plurality of road sections, to the sum of importance of each of the plurality of road sections included in the update target area as the travel coverage rate for the vehicle.

[0009] In addition, in the data collection indication device, preferably, the selection unit refers to the driving history records of each of the multiple vehicles and selects one or more vehicles from the multiple vehicles in descending order according to the ratio of the time spent traveling in the update object area during a predetermined time period or a predetermined day of the week to the total driving time during the most recent predetermined period.

[0010] According to another embodiment of the present invention, a data collection instruction method is provided. The data collection instruction method includes: based on the driving history records of each of the plurality of vehicles stored in the storage unit, selecting one or more vehicles from the plurality of vehicles that meet predetermined conditions related to driving in the update target area of ​​the map information, instructing the selected one or more vehicles to collect detection data representing predetermined features for the update target area via the communication unit, and instructing vehicles other than the selected one or more vehicles from the plurality of vehicles to collect detection data for a predetermined road section via the communication unit.

[0011] According to another embodiment of the present invention, a computer program product for data collection instruction is provided. The computer program product for data collection instruction includes instructions that cause a computer to execute: based on the driving history records of each of the multiple vehicles stored in the storage unit, select one or more vehicles from the multiple vehicles that meet the predetermined conditions related to driving in the update target area of ​​the map information, instruct the selected one or more vehicles to collect detection data representing predetermined features for the update target area via the communication unit, and instruct vehicles other than the selected one or more vehicles from the multiple vehicles to collect detection data for a predetermined road section via the communication unit.

[0012] The data collection instruction device according to the present disclosure has an effect of being able to appropriately collect probe data required for updating map information while suppressing an increase in the amount of communication required for collecting probe data. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a schematic diagram of the data collection system equipped with a data collection instruction device.

[0014] Figure 2 This is a schematic diagram of the vehicle.

[0015] Figure 3 This is a hardware configuration diagram of a data collection device according to one embodiment.

[0016] Figure 4 It is a functional block diagram of a processor of a data collection device.

[0017] Figure 5 This is a hardware configuration diagram of a server as an example of a data collection instruction device.

[0018] Figure 6 It is a functional block diagram of a server's processor.

[0019] Figure 7 This is an explanatory diagram showing an example of a collection instruction for each vehicle.

[0020] Figure 8 It is a workflow diagram of data collection indication processing. DETAILED DESCRIPTION

[0021] Hereinafter, a data collection instruction device, a data collection instruction method executed in the data collection instruction device, and a data collection instruction computer program will be described with reference to the accompanying drawings. The data collection instruction device is used in a data collection system that collects detection data representing predetermined features on or around a road from a plurality of vehicles and updates map information based on the collected detection data.

[0022] The server that updates the map information based on the probe data detects the locations (hereinafter sometimes referred to as the change points) where certain changes have occurred with respect to the predetermined features since the last update of the map information in the area that may become the update target of the map information (hereinafter sometimes referred to as the update target area). In order to determine whether there is such a change point, it is sufficient to collect a relatively small amount of probe data for each of the multiple road sections in the update target area. In addition, in order to detect the change point with high accuracy, it is required to obtain sufficient accuracy for the alignment (position alignment) of the features represented by the collected probe data and the corresponding features represented by the map information. For this purpose, it is preferred that each vehicle can generate probe data for multiple features existing in the section within a certain length. On the other hand, for the road section (hereinafter sometimes referred to as the update target section) where such a change point exists, in order to correctly reflect the information related to the changed features in the map information, it is required to collect a relatively large amount of probe data.

[0023] Therefore, the data collection instruction device selects one or more vehicles that meet predetermined conditions related to driving in the update target area from among multiple vehicles that can generate and collect probe data. Moreover, the data collection instruction device instructs the selected one or more vehicles to collect probe data for the update target area. In addition, the data collection instruction device instructs vehicles other than the selected one or more vehicles among the multiple vehicles to collect probe data for the limited update target section in the update target area. In this way, by having the selected vehicle collect probe data on each road section in the update target area, the communication volume required for transmitting the probe data can be suppressed. Furthermore, since the selected vehicle generates probe data in a certain continuous section, it is possible to collect the number of probe data required to detect the change point while maintaining the alignment accuracy. Furthermore, for the update target section, vehicles other than the selected vehicle are also instructed to collect probe data, so it becomes easy to collect the number of probe data required for updating the information of the change point.

[0024] Figure 1 1 is a schematic diagram of a data collection system equipped with a data collection instruction device. In this embodiment, the data collection system 1 includes: data collection devices 3 respectively mounted on a plurality of vehicles 2; and a server 4 as an example of a data collection instruction device. The data collection device 3 is connected to the server 4 via the wireless base station 6 and the communication network 5 by, for example, accessing a wireless base station 6 connected to a communication network 5 connected to the server 4 via a gateway (not shown). In addition, in Figure 1 In the figure, for simplicity, only one wireless base station 6 is shown, but multiple wireless base stations 6 may be connected to the communication network 5.

[0025] First, the vehicle 2 and the data collection device 3 are described. As described above, the data collection system 1 includes a plurality of vehicles 2 equipped with the data collection device 3, and each vehicle 2 and each data collection device 3 has the same configuration regarding data collection processing and performs the same processing. Hereinafter, one vehicle 2 and one data collection device 3 are described.

[0026] Figure 2 2 is a schematic diagram of the structure of the vehicle 2. The vehicle 2 has a camera 21 for photographing the surroundings of the vehicle 2, a GPS receiver 22, a wireless communication terminal 23, and a data collection device 3. The camera 21, the GPS receiver 22, the wireless communication terminal 23, and the data collection device 3 are connected in a communicative manner via an in-vehicle network that complies with a standard such as a controller area network. In addition, the vehicle 2 may also have a distance measuring sensor (not shown) such as a LiDAR sensor for measuring the distance to objects around the vehicle 2.

[0027] The camera 21 is an example of a photographing unit, and has a two-dimensional detector and an imaging optical system. The two-dimensional detector is composed of an array of photoelectric conversion elements such as CCD or C-MOS that are sensitive to visible light, and the imaging optical system forms an image of the area serving as the photographing object on the two-dimensional detector. Moreover, the camera 21 is installed in the cabin of the vehicle 2, for example, in a manner facing the front of the vehicle 2. Moreover, the camera 21 photographs the front area of ​​the vehicle 2 at a predetermined shooting period (for example, 1 / 30 second to 1 / 10 second) to generate an image showing the front area. The image obtained by the camera 21 can be a color image or a grayscale image. In addition, a plurality of cameras 21 with different shooting directions or focal lengths can also be set in the vehicle 2.

[0028] Every time the camera 21 generates an image, it outputs the generated image to the data collection device 3 via the in-vehicle network.

[0029] The GPS receiver 22 receives GPS signals from GPS satellites at a predetermined period, and locates the position of the vehicle 2 based on the received GPS signals. Furthermore, the GPS receiver 22 outputs positioning information indicating the positioning result of the vehicle 2 based on the GPS signals to the data collection device 3 via the in-vehicle network at a predetermined period. In addition, the vehicle 2 may also have a receiver that complies with the satellite positioning system other than the GPS receiver 22. In this case, the receiver may locate the position of the vehicle 2.

[0030] The wireless communication terminal 23 is an example of a communication device, and is a device that performs wireless communication processing in accordance with a predetermined wireless communication standard. For example, by accessing the wireless base station 6, the wireless base station 6 and the communication network 5 are connected to the server 4. That is, a communication line is established between the wireless communication terminal 23 and the server 4 via the wireless base station 6 and the communication network 5. In addition, the wireless communication terminal 23 receives a downlink wireless signal including the collection area information, the collection instruction signal, or the collection stop signal from the server 4, and outputs the received collection area information, the collection instruction signal, or the collection stop signal to the data collection device 3. In addition, the wireless communication terminal 23 generates an uplink wireless signal including the driving history information, the detection data, the image, or the partial image received from the data collection device 3. In addition, the wireless communication terminal 23 transmits the driving history information or the detection data to the server 4 by transmitting the uplink wireless signal to the wireless base station 6.

[0031] Figure 3 : is a hardware configuration diagram of the data collection device 3. The data collection device 3 generates detection data based on the image received from the camera 21, etc., and sends the generated detection data to the server 4 via the wireless communication terminal 23. Furthermore, the data collection device 3 generates travel history information representing the travel trajectory of the vehicle 2, and sends the generated travel history information to the server 4 via the wireless communication terminal 23. To this end, the data collection device 3 has a communication interface (I / F) 31, a memory 32, and a processor 33.

[0032] The communication interface 31 is an example of an in-vehicle communication unit, and has an interface circuit for connecting the data collection device 3 to the in-vehicle network. That is, the communication interface 31 is connected to the camera 21, the GPS receiver 22, and the wireless communication terminal 23 via the in-vehicle network. Moreover, whenever the communication interface 31 receives an image from the camera 21, it hands over the received image to the processor 33. In addition, whenever the communication interface 31 receives positioning information from the GPS receiver 22, it hands over the received positioning information to the processor 33. Furthermore, whenever the communication interface 31 receives information from the server 4 such as collection area information from the wireless communication terminal 23, it hands over the information to the processor 33. In addition, the communication interface 31 outputs the detection data or driving history information received from the processor 33 to the wireless communication terminal 23 via the in-vehicle network.

[0033] The memory 32 is an example of a storage unit, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 32 may also include other storage devices such as a hard disk device. Moreover, the memory 32 stores various data used in the processing associated with data collection performed by the processor 33 of the data collection device 3. For example, the memory 32 stores the identification information of the vehicle 2, the parameters of the camera 21 such as the focal length, shooting direction, and installation position of the camera 21, various parameters for determining the identifier for detecting the ground object based on the image received from the camera 21, and the positioning information received from the GPS receiver 22. Furthermore, the memory 32 stores the collection area information received from the server 4. In addition, the collection area information includes information indicating the position and range of the update object area or update interval that is the collection object of the detection data (for example, the coordinates of each end point of the update object area or update interval). Furthermore, the memory 32 may also store computer programs for implementing each processing performed by the processor 33.

[0034] Furthermore, the generated travel history information and probe data are temporarily stored in the memory 32 .

[0035] The processor 33 has one or more CPUs (Central Processing Units) and their peripheral circuits. The processor 33 may also have other computing circuits such as a logic operation unit, a numerical operation unit, or a graphics processing unit. In addition, the processor 33 performs data collection processing while the vehicle 2 is traveling.

[0036] Figure 4 : is a functional block diagram of the processor 33 of the data collection device 3. The processor 33 has a driving history information generation unit 41, a detection data generation unit 42, and a communication processing unit 43. These units of the processor 33 are, for example, functional modules implemented by a computer program running on the processor 33. Alternatively, these units of the processor 33 may also be dedicated computing circuits provided in the processor 33.

[0037] The travel history information generating unit 41 generates travel history information indicating the travel trajectory of the vehicle 2. Specifically, the travel history information generating unit 41 generates the travel history information by arranging the position coordinates of the vehicle 2 indicated by a series of positioning information obtained from the GPS receiver 22 during the period from when the ignition switch of the vehicle 2 is turned on (ON) to when it is turned off (OFF) in time order. Furthermore, the travel history information generating unit 41 includes the date and time when the positioning information is obtained, that is, the date and time when the vehicle 2 passes the location of the position coordinates, in the travel history information in association with the position coordinates of the vehicle 2 indicated by each of the series of positioning information. In addition, the travel history information generating unit 41 may also estimate the position of the vehicle 2 during the period by referring to the coordinates of the position of the vehicle 2 before and after the period when the positioning information is not obtained and the odometer (odometry) information during the period. Moreover, the travel history information generating unit 41 may also include the coordinates of the estimated position of the vehicle 2 during the period in the travel history information. Furthermore, the travel history information generating unit 41 includes the date and time of the timing when the ignition switch is turned on and the date and time of the timing when the ignition switch is turned off in the travel history information. Furthermore, the driving history information generating unit 41 causes the driving history information to include the identification information of the vehicle 2. Furthermore, the identification information of the vehicle 2 included in the driving history information is not limited to the identification information of the vehicle 2 itself, but may also be the identification information of the data collection device 3 or the wireless communication terminal 23 mounted on the vehicle 2.

[0038] The travel history information generating unit 41 transmits the travel history information to the server 4 via the wireless communication terminal 23 when the ignition switch of the vehicle 2 is turned off.

[0039] The probe data generating unit 42 generates probe data at a predetermined period while the vehicle 2 is traveling, or every time the vehicle 2 travels a predetermined distance.

[0040] To this end, the detection data generating unit 42 detects predetermined features from the latest image generated by the camera 21 at a predetermined period or every time the vehicle 2 travels a predetermined distance during the travel of the vehicle 2. The predetermined features are features indicated by the map information to be updated, such as various road signs, various road markings, curbs, guardrails, and poles for setting traffic lights or road markings.

[0041] For example, the detection data generation unit 42 detects a predetermined feature represented by the input image by inputting the image to the recognizer. As such a recognizer, the detection data generation unit 42 can use a deep neural network (DNN) having a convolutional neural network (CNN) type architecture such as SSD (Single Shot MultiBox Detector) or Faster R-CNN. Alternatively, as such a recognizer, the detection data generation unit 42 can also use a DNN having a self-attention network (SAN: self attention network) type architecture such as Vision Transformer. Alternatively, as such a recognizer, the detection data generation unit 42 can also use a recognizer based on other machine learning methods such as AdaBoost recognizer. Such a recognizer learns in advance to detect the feature from the image according to a predetermined learning method such as the error back propagation method and using a plurality of teacher images representing the predetermined feature to be detected. In addition, the recognizer outputs information indicating an area containing the feature to be detected on the input image (for example, a circumscribed rectangle of the feature to be detected, hereinafter referred to as the object area), and information indicating the type of the feature represented by the object area.

[0042] The detection data generating unit 42 estimates the position of the feature represented by the object region based on the parameters such as the orientation relative to the camera 21 corresponding to the center of gravity of the object region detected from the image, the position of the vehicle 2 at the time of image generation, the traveling direction, and the shooting direction, focal length, and installation position of the camera 21. At this time, the detection data generating unit 42 may estimate the position of the feature by the so-called Structure from Motion (SfM). In this case, the detection data generating unit 42 associates the object regions representing the same feature with each other using optical flow between two images obtained at different timings. Moreover, the detection data generating unit 42 may estimate the position of the feature by triangulation based on the position and traveling direction of the vehicle 2 when the two images were obtained, the parameters of the camera 21, and the position of the object region in each image. Moreover, the detection data generating unit 42 generates detection data including information indicating the type of the detected feature and the estimated position. The detection data generating unit 42 may also include information indicating the position and traveling direction of the vehicle 2 at the time of image generation in the detection data. The detection data generating unit 42 may also include information indicating the size of the object area and the position on the image in the detection data. In addition, the detection data generating unit 42 generates one detection data for each detected object. Therefore, when multiple objects are detected from one image, multiple detection data are generated based on one image.

[0043] The probe data generating unit 42 writes the generated probe data into the memory 32 every time the probe data is generated.

[0044] The communication processing unit 43 transmits the probe data stored in the memory 32 , which is generated while the vehicle 2 is traveling in the update target area or update target section indicated by the collection area information, to the server 4 via the wireless communication terminal 23 .

[0045] The communication processing unit 43 refers to the collection area information and the latest positioning information to determine whether the vehicle 2 has entered the update target area or the update target section. Moreover, when the vehicle 2 enters the update target area or the update target section, the communication processing unit 43 sends the detection data stored in the memory 32 to the server 4 via the wireless communication terminal 23 in the order from the old to the new. In addition, when the communication processing unit 43 receives a notification to stop collecting detection data from the server 4 via the wireless communication terminal 23, it stops sending the detection data. Alternatively, the communication processing unit 43 may send preliminary determination data for inquiring whether to send the detection data to the server 4 via the wireless communication terminal 23 before starting to send the detection data. In this case, the communication processing unit 43 may also make the preliminary determination data include the identification information of the vehicle 2, the position information of the vehicle 2 represented by the latest positioning information, or the information for determining the area or road section containing the position of the vehicle 2. Moreover, after sending the preliminary determination data, it is also possible to start sending the detection data only when a detection data collection instruction signal is received from the server 4 via the wireless communication terminal 23.

[0046] In addition, the communication processing unit 43 erases the detection data transmitted to the server 4 via the wireless communication terminal 23 from the memory 32 .

[0047] When the vehicle 2 exits the update target area or update target section, the communication processing unit 43 refers to the memory 32 to determine the detection data that has not been sent at the exit time point. Moreover, the communication processing unit 43 ends the transmission of the detection data at the time point when the transmission of the determined detection data to the server 4 is completed. In addition, similar to the determination of whether the vehicle 2 has entered the update target area or update target section, the communication processing unit 43 can determine whether the vehicle 2 has exited the update target area or update target section by referring to the collection area information and the latest positioning information.

[0048] In addition, when the collection instruction signal indicates that not only the detection data but also the images of the update target section are to be collected, the communication processing unit 43 transmits a series of images generated while the vehicle 2 travels in the update target section together with the detection data to the server 4 via the wireless communication terminal 23. Furthermore, when the collection of partial images of the update target section is instructed, the communication processing unit 43 generates a partial image by cutting out a predetermined range from a series of images generated while the vehicle 2 travels in the update target section. Then, the communication processing unit 43 transmits the obtained series of partial images together with the detection data to the server 4 via the wireless communication terminal 23.

[0049] Next, the server 4 as an example of the data collection instruction device is described. The server 4 selects a vehicle to be instructed to collect detection data for the update target area from among the plurality of vehicles 2, and issues an instruction to collect detection data for the update target area to the selected vehicle. In addition, the server 4 issues an instruction to collect detection data for the update target section within the update target area to the other vehicles. As described above, the update target area is, for example, an area that may become an update target for map information, that is, an area that becomes an object of determination of whether or not there is a change point, and the update target section is, for example, a road section that includes a detected change point.

[0050] Furthermore, the server 4 stores the detection data transmitted from the data collection device 3 mounted on each vehicle 2. Furthermore, the server 4 detects a change point or updates the map information based on the detection data. Furthermore, the server 4 notifies each vehicle 2 of the collection area information.

[0051] Figure 5 : is a hardware configuration diagram of the server 4. The server 4 has a communication interface (I / F) 51, a storage device 52, a memory 53, and a processor 54. The communication interface 51, the storage device 52, and the memory 53 are connected to the processor 54 via a signal line. The server 4 may also have an input device such as a keyboard and a mouse, and a display device such as a liquid crystal display.

[0052] The communication interface 51 is an example of a communication unit, and has an interface circuit for connecting the server 4 to the communication network 5. Moreover, the communication interface 51 is configured to be able to communicate with the data collection device 3 mounted on each vehicle 2 via the communication network 5 and the wireless base station 6. That is, the communication interface 51 delivers the driving history information and detection data, etc. received from the data collection device 3 of each vehicle 2 via the wireless base station 6 and the communication network 5 to the processor 54. In addition, the communication interface 51 sends the collection area information and collection instruction signal, etc. received from the processor 54 to the data collection device 3 of each vehicle 2 via the communication network 5 and the wireless base station 6.

[0053] The storage device 52 is an example of a storage unit, and includes, for example, a hard disk device or an optical recording medium and an access device thereof. The storage device 52 stores map information to be updated. The storage device 52 also stores information indicating an update target area within a range indicated by the map information.

[0054] In addition, a plurality of update target areas may be set. In this case, it is preferable to set the boundaries between the update target areas so that the number of vehicles 2 that cross the boundaries between the update target areas is as small as possible. For example, each update target area may be set so that a point that serves as a boundary of a traffic circle, such as a mountain or a river, serves as a boundary of the update target area.

[0055] The storage device 52 also stores, for each update target area, the detection data, images, and partial images collected for each of the multiple road sections included in the update target area. Furthermore, the storage device 52 stores the travel history information received from each vehicle 2. In addition, the storage device 52 may also store a computer program executed on the processor 54 for executing the data collection instruction process.

[0056] The memory 53 is another example of a storage unit, and includes, for example, a nonvolatile semiconductor memory and a volatile semiconductor memory. The memory 53 temporarily stores various data generated during the execution of the data collection instruction process, various data acquired through communication with each vehicle 2, such as detection data and driving history information, and the like.

[0057] The processor 54 is an example of a control unit, and has one or more CPUs (Central Processing Units) and their peripheral circuits. The processor 54 may also have other operation circuits such as a logic operation unit or a numerical operation unit. Moreover, whenever the processor 54 receives detection data, images, partial images, or travel history information from one of the multiple vehicles 2, it saves the received detection data, images, partial images, or travel history information in the storage device 52. At this time, the processor 54 may also count the number of received detection data by road section. In this case, whenever the processor 54 receives detection data, it refers to the position of the vehicle 2 contained in the detection data, determines the road section on which the vehicle 2 traveled when the detection data was generated, and adds 1 to the count value of the detection data for the determined road section. Furthermore, the processor 54 performs data collection instruction processing.

[0058] Figure 6: is a functional block diagram of the processor 54 of the server 4. The processor 54 has a selection unit 61, a detection unit 62, a notification processing unit 63, and an update unit 64. These units of the processor 54 are, for example, functional modules implemented by a computer program running on the processor 54. Alternatively, these units of the processor 54 may also be dedicated operation circuits provided in the processor 54.

[0059] At a predetermined timing, the selection unit 61 refers to the driving history information received from each of the plurality of vehicles 2, and selects one or more vehicles from the plurality of vehicles 2 that meet the predetermined conditions related to driving in the update target area. The predetermined timing is preset, for example, and can be set to a predetermined date and time in each month, or a predetermined time on a predetermined day of the week.

[0060] When a plurality of update target regions are set, the selection unit 61 may perform the following processing for each update target region. The following describes processing for one update target region.

[0061] In this embodiment, the selection unit 61 refers to the driving history information of each of the multiple vehicles 2 and calculates the driving coverage rate, which is the ratio of the road sections actually traveled in the multiple road sections included in the update target area within the most recent predetermined period (for example, 1 week to 1 month). In addition, the selection unit 61 selects one or more vehicles from the multiple vehicles 2 in descending order of driving coverage rate as vehicles to be instructed to collect detection data for determining the presence or absence of change points. In this way, the selection unit 61 can appropriately select vehicles so that detection data can be collected from the entire update target area with a smaller number of vehicles.

[0062] In addition, the selection unit 61 selects the position coordinates of each vehicle 2 included in the travel history information, which are associated with the date and time included in the most recent predetermined period. Furthermore, the selection unit 61 compares the selected position coordinates with the position and range of each road section included in the update target area indicated by the map information, and determines the road section including the position coordinates. Furthermore, the selection unit 61 uses the determined road section as the road section traveled by the vehicle 2. The selection unit 61 can calculate the travel coverage rate by determining each road section traveled by the vehicle 2 in the most recent predetermined period among the road sections included in the update target area.

[0063] In addition, even if the vehicle 2 travels on the same road section multiple times within the most recent predetermined period, the selection unit 61 only counts the road section once. In addition, the selection unit 61 may calculate the travel coverage rate by taking into account the length of each road section. In this case, the selection unit 61 may calculate the ratio of the total length of the road section traveled by the vehicle 2 to the total length of each road section included in the update target area as the travel coverage rate. Furthermore, the importance may be pre-set for each road section. For example, the highest importance may be set for a road section that is a dedicated lane for automobiles, the second highest importance may be set for a road section that is a national highway, and the lowest importance may be set for other road sections. In this case, the selection unit 61 may calculate the ratio of the total importance of the road section that the vehicle 2 actually traveled on within the most recent predetermined period to the total importance of each of the plurality of road sections included in the update target area as the travel coverage rate. By calculating the travel coverage rate based on the importance in this way, the vehicle 2 that travels more in the road section with a higher importance is more likely to be selected.

[0064] Furthermore, the selection unit 61 selects vehicles 2 in descending order of travel coverage until a predetermined proportion (e.g., 80% to 90%) of the road sections in the update target area or more of the road sections are road sections traveled by the selected vehicles 2. Furthermore, if there is a road section that no previously selected vehicle 2 has traveled, the selection unit 61 may additionally select a vehicle 2 that has traveled on the road section.

[0065] Alternatively, the selection unit 61 may select a preset number of vehicles 2 in descending order of travel coverage. In this case, if there is a road section that no previously selected vehicle 2 has traveled, the selection unit 61 may also select additional vehicles 2 that have traveled on the road section.

[0066] According to a modified example, the selection unit 61 may also calculate a specific time period ratio for each of the plurality of vehicles 2, referring to the driving history record of the vehicle, the specific time period ratio being the ratio of the time of driving in the update target area in a predetermined time period or a predetermined day of the week to the total driving time in the most recent predetermined period. Furthermore, the selection unit 61 may also select one or more vehicles from the plurality of vehicles 2 in descending order of the specific time period ratio. Thus, the selection unit 61 can select a vehicle 2 having a high ratio of driving in the update target area in a predetermined time period or a predetermined day of the week. In addition, the predetermined time period or the predetermined day of the week may be set as a time period or a day of the week in which the feature to be detected is expected to be clearly reflected in the image generated by the camera 21, such as a time period in the morning when the feature of a specific lane is not blocked by parked vehicles, etc. Therefore, the selection unit 61 can select a vehicle 2 having a high probability of passing through the update target area at a timing suitable for collecting detection data to collect detection data for detecting a change point.

[0067] In this case, the selection unit 61 refers to the date and time when the ignition switch is turned on or off included in the driving history record information, and takes the total of each period from the timing when the ignition switch is turned on to the timing when the ignition switch is turned off within the most recent predetermined period as the total driving time. In addition, the selection unit 61 selects a position coordinate whose date and time associated with each position coordinate included in the driving history record information is included in the predetermined time period or coincides with the predetermined day of the week. The selection unit 61 further selects a position coordinate included in the update object area from the selected position coordinates. Moreover, the selection unit 61 calculates the total of the period from when the vehicle 2 enters the update object area to when it exits, based on the date and time associated with each position coordinate finally selected, as the time when the vehicle 2 travels in the update object area in the predetermined time period or the predetermined day of the week.

[0068] The selection unit 61 refers to the travel history information of each of the selected one or more vehicles to determine the identification information of each selected vehicle. Furthermore, the selection unit 61 notifies the notification processing unit 63 of the identification information of each selected vehicle.

[0069] The detection unit 62 determines the presence or absence of a change point for each road section in the update target area based on the probe data collected from one or more vehicles 2 selected by the selection unit 61. The detection unit 62 detects a road section including a change point among the road sections in the update target area.

[0070] When a predetermined period has passed since the detection data collection instruction was notified to one or more selected vehicles 2, the detection unit 62 reads the detection data collected for the update target area from the storage device 52. Moreover, the detection unit 62 aligns, for each vehicle 2, each feature represented by a series of detection data generated during the vehicle 2's travel in the update target area with the corresponding feature represented by the map information of the update target. At this time, the detection unit 62 calculates the affine transformation coefficient according to a predetermined optimization method such as the steepest descent method so as to minimize the sum of the squares of the distances between the positions of each feature represented by a series of detection data and the corresponding feature represented by the map information. Moreover, the detection unit 62 uses the calculated affine transformation coefficient to move the positions of each feature represented by a series of detection data, thereby aligning these features with the corresponding features represented by the map information.

[0071] For each vehicle 2, when the above-mentioned alignment is completed, the detection unit 62 detects the location where the feature represented by the collected detection data is inconsistent with the corresponding feature represented by the map information according to each road section included in the update target area as a change point. For example, in a certain road section, if there are features of the same type and within a predetermined distance from each other represented by a predetermined number of collected detection data, the detection unit 62 determines that the features represented by these detection data are the same feature. Moreover, when there is no corresponding feature represented by the map information within a predetermined distance from the same feature represented by these detection data, it is possible that a new feature has been set after the last update of the map information. Therefore, the detection unit 62 detects the average position of the positions of the features represented by the predetermined number of detection data as a change point.

[0072] In addition, for a predetermined feature represented by the map information, if detection data indicating that a corresponding feature exists within a predetermined distance from the position of the feature is not collected, the feature represented by the map information may have been removed. Therefore, the detection unit 62 detects the position of the feature represented by the map information as a change point. Furthermore, if the distance between the predetermined feature represented by the map information and the corresponding feature represented by the detection data of the same type as the predetermined feature is farther than the predetermined distance, the predetermined feature may have been moved after the last update of the map information. Therefore, the detection unit 62 may also detect the position of the predetermined feature represented by the map information and the position of the corresponding feature represented by the detection data as change points, respectively.

[0073] Furthermore, if the type of a predetermined feature indicated by the map information is different from the type of a corresponding feature indicated by the detection data and existing within a predetermined distance from the position of the feature, the type of the predetermined feature may have been changed after the map information was last updated. In this case, the detection unit 62 may also detect the position of the predetermined feature indicated by the map information as a change point.

[0074] The detection unit 62 refers to the map information for each of the detected change points and determines the road section including the position coordinates of the change point as the update target section. Furthermore, the detection unit 62 notifies the notification processing unit 63 of information indicating the update target section including the change point for each detected change point.

[0075] The detection unit 62 may set, as an update target section, a road section in which the number of collected probe data has not reached the predetermined collection number even though a predetermined period has passed since the notification of the collection instruction of the probe data for the update target area. Furthermore, the detection unit 62 may notify the notification processing unit 63 of information indicating that the number of collected probe data has not reached the predetermined collection number.

[0076] The notification processing unit 63 issues an instruction to collect probe data for the update target area to each of the one or more vehicles 2 selected by the selection unit 61 among the plurality of vehicles 2. To this end, the notification processing unit 63 identifies each of the one or more selected vehicles 2 based on the identification information received from the selection unit 61. Furthermore, the notification processing unit 63 generates collection area information that uses the entire update target area as the collection target area for probe data, and notifies the generated collection area information to each of the identified vehicles 2 via the communication interface 51. Furthermore, the notification processing unit 63 generates a collection instruction signal that instructs the collection of probe data, and notifies the generated collection instruction signal to each of the identified vehicles 2 via the communication interface 51. In addition, when the server 4 receives the preliminary determination data, the notification processing unit 63 may determine whether to issue an instruction to collect probe data based on the preliminary determination data. For example, if the number of probe data collected for the road section including the position of the vehicle 2 indicated by the preliminary determination data reaches a predetermined collection number, the notification processing unit 63 may determine not to instruct the collection of probe data. On the other hand, if the amount of collected probe data does not reach the predetermined collection amount, the notification processing unit 63 may also determine that it is an instruction to collect probe data. Moreover, in this case, the notification processing unit 63 notifies the vehicle 2 that has sent the pre-determination data of the collection instruction signal via the communication interface 51. In addition, when multiple update target areas are set, a vehicle will be selected according to each update target area. Therefore, the notification processing unit 63 may also instruct to collect probe data for update target areas that are different for each vehicle.

[0077] Furthermore, when a predetermined period has elapsed since the collection area information was notified to each of the selected one or more vehicles 2 , the notification processing unit 63 may notify each of the selected one or more vehicles 2 via the communication interface 51 of a collection stop signal for stopping the collection of the probe data.

[0078] In addition, when the notification processing unit 63 receives information indicating the update target interval from the detection unit 62, it generates collection area information that uses the update target interval as the collection target area of ​​the probe data. Moreover, the notification processing unit 63 notifies each vehicle other than the selected one or more vehicles among the plurality of vehicles 2 of the generated collection area information via the communication interface 51. Furthermore, the notification processing unit 63 generates a collection instruction signal that instructs the collection of probe data for the update target interval, and notifies each vehicle other than the selected one or more vehicles among the plurality of vehicles 2 of the generated collection instruction signal via the communication interface 51. In addition, the notification processing unit 63 may also instruct, in the collection instruction signal regarding the update target interval, to collect not only the probe data but also the image itself or the partial image. Furthermore, when the server 4 receives the preliminary determination data, for the update target interval, the notification processing unit 63 may also instruct the collection of probe data only when the number of collected probe data does not reach the predetermined collection number.

[0079] Furthermore, the notification processing unit 63 may also notify each vehicle selected by the selection unit 61 among the plurality of vehicles 2 of the collection instruction signal regarding the update target section via the communication interface 51 .

[0080] Figure 7 : is an explanatory diagram showing an example of a collection instruction for each vehicle. In this example, the update target area 700 includes 15 road sections {A, B, C, ..., O}. Here, as shown in the driving trajectory 721 (in addition, the driving trajectory is not limited to the driving trajectory of one driving, but can also be a driving trajectory of multiple driving. The same applies below) in the recent predetermined period represented by the driving history information of the vehicle 711, the vehicle 711 has traveled in 9 road sections. That is, the driving coverage rate of the vehicle 711 is 60%. On the other hand, as shown in the driving trajectory 722 in the recent predetermined period represented by the driving history information of the vehicle 712, the vehicle 712 has traveled in 3 road sections. That is, the driving coverage rate of the vehicle 712 is 20%. Furthermore, as shown in the driving trajectory 723 in the recent predetermined period represented by the driving history information of the vehicle 713, the vehicle 713 has traveled in 8 road sections. That is, the driving coverage rate of the vehicle 713 is 53%. In addition, it is assumed that vehicles with a driving coverage rate of 50% or more are selected. Therefore, the vehicle 711 and the vehicle 713 are selected, and the probe data collection instruction signal for detecting the change point is notified. On the other hand, the vehicle 712 is not selected, and the probe data collection instruction signal for detecting the change point is not notified. However, after the change point is detected, the collection instruction signal for the update target section containing the change point is notified to the vehicle 712. For example, when the change point is detected in the road section G, the collection instruction signal for instructing to collect the probe data for the road section G is notified to the vehicle 712.

[0081] The updating unit 64 updates the information related to the predetermined features in the update target section represented by the map information based on the probe data collected for the update target section. To this end, the updating unit 64 aligns each feature represented by a series of probe data received from each vehicle 2 that travels in the update target section with the corresponding feature represented by the map information. At this time, the updating unit 64 may perform the same processing as the alignment processing performed by the detection unit 62. Moreover, the updating unit 64 adds the type and position of the feature represented by the probe data received from more than a predetermined number of vehicles 2 and estimated to be the same feature to the map information if the map information does not represent the corresponding feature. On the contrary, for the feature represented by the map information for which the probe data indicating the corresponding feature existing within a predetermined distance from the feature has not been collected, the updating unit 64 deletes the information related to the feature from the map information. Furthermore, assuming that the distance between the predetermined feature represented by the map information and the feature of the same type as the predetermined feature represented by the received detection data of more than the predetermined number is greater than the predetermined distance, in this case, the updating unit 64 corrects the position of the feature represented by the map information to the average value of the positions of the feature represented by the received detection data of more than the predetermined number.

[0082] Furthermore, the updating unit 64 may also add information related to the detected feature to the map information when a feature is detected based on an image or a partial image received from a vehicle traveling in the update target section. In this case, the updating unit 64 may detect the feature by inputting the image or the partial image to the same identifier as the identifier used in the detection data generating unit 42 of the data collection device 3. In addition, the updating unit 64 may estimate the position of the detected feature based on the position and the traveling direction of the vehicle 2 when the image was generated, the parameters of the camera 21, and the position of the feature on the image or the partial image.

[0083] The updating unit 64 stores the updated map information in the storage device 52. Furthermore, the notification processing unit 63 may also output the updated map information to other devices via the communication interface 51 and the communication network 5. In addition, the notification processing unit 63 may also distribute the updated map information to any one of the plurality of vehicles 2 or other vehicles that use the map information for automatic driving control via the communication interface 51, the communication network 5, and the wireless base station 6.

[0084] Figure 8 The processor 54 of the server 4 may execute the data collection instruction process according to the following workflow diagram.

[0085] The selection unit 61 of the processor 54 selects one or more vehicles that satisfy the predetermined condition related to the travel in the update target area from among the plurality of vehicles 2 (step S101). Furthermore, the notification processing unit 63 of the processor 54 notifies each of the selected one or more vehicles of the collection area information that takes the update target area as the collection target area and a collection instruction signal that instructs the vehicle to collect the detection data for the update target area via the communication interface 51 (step S102).

[0086] After a predetermined period has passed from the notification of the collection indication, the detection unit 62 of the processor 54 determines, based on the collected detection data, the road sections containing change points and the road sections where the number of collected detection data is less than the predetermined collection number among the road sections within the update object area as update object sections (step S103).

[0087] Furthermore, the notification processing unit 63 notifies the vehicles other than the selected one or more vehicles among the plurality of vehicles 2 of the collection area information that uses the update target section as the collection target area and the collection instruction signal instructing them to collect the detection data for the update target section via the communication interface 51 (step S104). In addition, as described above, the notification processing unit 63 may also issue an instruction to collect the detection data for the update target section to the one or more vehicles selected in step S102.

[0088] The updating unit 64 of the processor 54 updates the map information based on the probe data collected for the update target section (step S105 ). Then, the processor 54 ends the data collection instruction process.

[0089] As described above, the data collection instruction device selects one or more vehicles that meet predetermined conditions related to driving in the update target area from among a plurality of vehicles that can generate and collect probe data. Furthermore, the data collection instruction device instructs the selected one or more vehicles to collect probe data for the update target area. In addition, the data collection instruction device instructs vehicles other than the selected one or more vehicles among a plurality of vehicles to collect probe data for update target sections such as road sections containing change points in the update target area. In this way, by having the selected vehicle collect probe data for each road section in the update target area, the amount of communication required to send the probe data can be suppressed. Furthermore, since the selected vehicle generates probe data in a certain continuous section, it is possible to collect the number of probe data required to detect the change point while maintaining the alignment accuracy. Furthermore, the data collection instruction device also instructs vehicles other than the selected vehicle to collect probe data for the update target section, so that the number of probe data required to update the information of the change point can be collected.

[0090] As described above, those skilled in the art can make various changes according to the embodiments within the scope of the present invention.

Claims

1. A data collection indicating device, comprising: A storage unit for storing the driving history records of each of the plurality of vehicles; A selection unit that selects one or more vehicles from among the plurality of vehicles that satisfy a predetermined condition related to traveling in an update target area of ​​map information based on the travel history records of each of the plurality of vehicles; and The notification processing unit instructs the one or more selected vehicles via the communication unit to collect detection data representing predetermined features for the update target area, and instructs vehicles other than the one or more selected vehicles among the multiple vehicles via the communication unit to collect the detection data for a predetermined road section.

2. The data collection indicating device according to claim 1, The selection unit refers to the travel history records of each of the multiple vehicles and selects one or more vehicles from the multiple vehicles in descending order of travel coverage of road sections actually traveled within a recent predetermined period among multiple road sections included in the update target area.

3. The data collection indicating device according to claim 2, An importance is set for each of a plurality of road sections included in the update target area. The selection unit calculates, for each of the plurality of vehicles, a ratio of a sum of the importance levels of the road segments among the plurality of road segments that the vehicle actually traveled during the most recent predetermined period to a sum of the importance levels of each of the plurality of road segments as the travel coverage rate for the vehicle.

4. The data collection indicating device according to claim 1, The selection unit refers to the driving history records of each of the multiple vehicles and selects one or more vehicles from the multiple vehicles in descending order of the ratio of the time spent traveling in the update target area during a predetermined time period or a predetermined day of the week to the total driving time during the most recent predetermined period.

5. A data collection instruction method, comprising: Based on the travel history records of each of the plurality of vehicles stored in the storage unit, one or more vehicles satisfying a predetermined condition related to travel in the update target area of ​​the map information are selected from among the plurality of vehicles; instructing the one or more selected vehicles to collect detection data representing a predetermined feature in the update target area via the communication unit, The communication unit instructs vehicles other than the one or more selected vehicles among the plurality of vehicles to collect probe data for a predetermined road section.

6. A computer program product for data collection instructions, comprising instructions for causing a computer to execute: Based on the travel history records of each of the plurality of vehicles stored in the storage unit, one or more vehicles satisfying a predetermined condition related to travel in the update target area of ​​the map information are selected from among the plurality of vehicles; instructing the one or more selected vehicles to collect detection data representing a predetermined feature in the update target area via the communication unit, The communication unit instructs vehicles other than the one or more selected vehicles among the plurality of vehicles to collect probe data for a predetermined road section.