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

Abstract

To provide a data collection instruction device capable of appropriately collecting probe data required for updating map information while suppressing an increase in communication traffic volume required for probe data collection.SOLUTION: A data collection instruction device comprises: storage units (52 and 53) which store a travel history of each of a plurality of vehicles 2; a selection unit 61 which selects one or more vehicles satisfying predetermined conditions relating to traveling in an update target zone of map information from among the plurality of vehicles 2 based on the travel history of each of the plurality of vehicles 2; and a notification processing unit 63 which instructs the selected one or more vehicles to collect probe data representing a predetermined feature in the update target zone via a communication unit 51 and instructs the vehicles other than the selected one or more vehicles in the plurality of vehicles 2 to collect probe data regarding a predetermined road section via the communication unit 51.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present invention relates to a data collection instruction device, a data collection instruction method, and a computer program for instructing data collection, which instruct the collection of data used to update a map. [Background technology]

[0002] High-precision maps, which are referenced by an automated driving system for a vehicle to control the vehicle's automated driving, are required to accurately represent information about roads. Therefore, data representing roads or features around roads within a specific area (hereinafter referred to as probe data) is collected from vehicles that have actually traveled through that area using sensors mounted on the vehicles. In particular, a technology for collecting information about new roads has been proposed (see Patent Document 1).

[0003] In the technology disclosed in Patent Document 1, when a vehicle (probe car) travels on a road that is not included in the navigation map data provided in the navigation device, the vehicle transmits driving history information as probe data to a map distribution center. Meanwhile, the map distribution center receives driving history information from the navigation device of each vehicle, collects the received data, and excludes driving history information that is predicted not to indicate that the vehicle has traveled on a new road, thereby narrowing down the target data. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2008-164831 Summary of the Invention [Problem to be solved by the invention]

[0005] Generally, traffic volume over a certain period of time varies from road section to road section. Therefore, there is a risk that the amount of probe data collected will be insufficient for some road sections. Furthermore, if the probe data collection period is extended or the planned number of probe data to be collected is increased so that a sufficient amount of probe data is collected for all road sections, an excessive amount of probe data will be transmitted to the server for some road sections. As a result, the amount of communication between the vehicle and the server will increase excessively.

[0006] Therefore, an object of the present invention is to provide a data collection instruction device that can appropriately collect probe data required for updating map information while suppressing an increase in the amount of communication required for collecting probe data. [Means for solving the problem]

[0007] According to one embodiment, there is provided a data collection instruction device including: a storage unit that stores driving histories of each of a plurality of vehicles; a selection unit that selects, from the plurality of vehicles, one or more vehicles that satisfy predetermined conditions related to driving in an area to be updated for map information based on the driving histories of each of the plurality of vehicles; and a notification processing unit that instructs, via the communication unit, the one or more selected vehicles to collect probe data representing predetermined features in the area to be updated, and that instructs, via the communication unit, vehicles other than the one or more selected vehicles among the plurality of vehicles, to collect probe data for a predetermined road section.

[0008] In addition, in this data collection instruction device, it is preferable that the selection unit refers to the driving history of each of the multiple vehicles and selects one or more vehicles from the multiple vehicles in order of the driving coverage rate of road sections that have actually been driven among the multiple road sections included in the update target area during the most recent specified period.

[0009] In this case, it is preferable that an importance level is set for each of the plurality of road sections included in the update target area, and the selection unit preferably calculates, for each of the plurality of vehicles, the ratio of the sum of the importance levels of the plurality of road sections that the vehicle has actually traveled in the most recent predetermined period to the sum of the importance levels of the plurality of road sections included in the update target area as the travel coverage rate for that vehicle.

[0010] In addition, in this data collection instruction device, it is preferable that the selection unit refers to the driving history of each of the multiple vehicles and select one or more vehicles from the multiple vehicles in order of the vehicle that has the highest ratio of the time spent driving in the update target area during a specified time period or on a specified day of the week to the total driving time during the most recent specified period.

[0011] According to another aspect of the present invention, there is provided a data collection instruction method, which includes selecting one or more vehicles from the plurality of vehicles based on the driving histories of each of the plurality of vehicles stored in a storage unit, which vehicles satisfy predetermined conditions related to driving in an area to be updated for map information, instructing the selected one or more vehicles via a communication unit to collect probe data representing predetermined features in the area to be updated, and instructing vehicles from the plurality of vehicles other than the selected one or more vehicles via the communication unit to collect probe data for a predetermined road section.

[0012] According to yet another aspect of the present invention, there is provided a computer program for instructing data collection, the computer program including instructions for causing a computer to select one or more vehicles from the plurality of vehicles that satisfy predetermined conditions related to travel in an area to be updated for map information, based on the travel histories of each of the plurality of vehicles stored in a storage unit, instruct the selected one or more vehicles via a communication unit to collect probe data representing predetermined features in the area to be updated, and instruct vehicles other than the selected one or more vehicles from the plurality of vehicles via the communication unit to collect probe data for a predetermined road section. [Effects of the Invention]

[0013] The data collection instruction device according to the present disclosure has the advantage 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 explanation of the drawings]

[0014] [Figure 1] 1 is a schematic diagram illustrating a configuration of a data collection system in which a data collection instruction device is implemented. [Figure 2] FIG. 1 is a schematic configuration diagram of a vehicle. [Figure 3] FIG. 2 is a hardware configuration diagram of a data collection device according to one embodiment. [Figure 4] FIG. 2 is a functional block diagram of a processor of the data collection device. [Figure 5] FIG. 2 is a hardware configuration diagram of a server that is an example of a data collection instruction device. [Figure 6] FIG. 2 is a functional block diagram of a processor of the server. [Figure 7] FIG. 10 is an explanatory diagram showing an example of a collection instruction for each vehicle. [Figure 8] 10 is an operational flowchart of a data collection instruction process. DETAILED DESCRIPTION OF THE INVENTION

[0015] The data collection instruction device, the data collection instruction method executed by the data collection instruction device, and the data collection instruction computer program will be described below with reference to the drawings. The data collection instruction device is used in a data collection system that collects probe data representing predetermined features on or around roads from multiple vehicles and updates map information based on the collected probe data.

[0016] A server that updates map information based on probe data detects points (hereinafter simply referred to as change points) where certain changes have occurred in specific features since the previous map information update in an area that may be subject to map information update (hereinafter sometimes referred to as the update target area). To determine whether or not such change points exist, it is sufficient to collect a relatively small amount of probe data for each of multiple road sections within the update target area. Furthermore, to accurately detect change points, it is necessary to achieve sufficient accuracy in aligning the features represented in the collected probe data with the corresponding features represented in the map information. Therefore, it is preferable for each vehicle to generate probe data for multiple features present in a certain length of section. On the other hand, for road sections where such change points exist (hereinafter sometimes referred to as the update target section), it is necessary to collect a relatively large amount of probe data in order to accurately reflect information about the changed features in the map information.

[0017] Therefore, the data collection instruction device selects one or more vehicles from among a plurality of vehicles capable of generating and collecting probe data that satisfy predetermined conditions regarding driving in the update target area. The data collection instruction device then instructs the selected one or more vehicles to collect probe data for the update target area. The data collection device also instructs vehicles other than the selected one or more vehicles from among the plurality of vehicles to collect probe data for a limited update target section within the update target area. In this way, the selected vehicles collect probe data for each road section within the update target area, thereby reducing the communication volume required for transmitting the probe data. Furthermore, since the selected vehicles generate probe data over a relatively continuous section, it is possible to collect the amount of probe data required to detect change points while maintaining alignment accuracy. Furthermore, since vehicles other than the selected vehicle are also instructed to collect probe data for the update target section, it becomes easy to collect the amount of probe data required to update the change point information.

[0018] Fig. 1 is a schematic configuration diagram of a data collection system in which a data collection instruction device is implemented. In this embodiment, the data collection system 1 includes a data collection device 3 mounted on each of a plurality of vehicles 2, and a server 4, which is 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 to which the server 4 is connected via a gateway (not shown). Note that, for simplification, only one wireless base station 6 is shown in Fig. 1, but multiple wireless base stations 6 may be connected to the communication network 5.

[0019] First, we will explain the vehicle 2 and the data collection device 3. As described above, the data collection system 1 includes multiple vehicles 2 each equipped with a data collection device 3, but with regard to data collection processing, each vehicle 2 and each data collection device 3 only needs to have the same configuration and execute the same processing. Therefore, the following will explain one vehicle 2 and one data collection device 3.

[0020] 2 is a schematic configuration diagram of the vehicle 2. The vehicle 2 has a camera 21 for capturing images of 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 communicably connected via an in-vehicle network that complies with a standard such as a controller area network. The vehicle 2 may further have a ranging sensor (not shown), such as a LiDAR sensor, for measuring distances to objects around the vehicle 2.

[0021] The camera 21 is an example of an imaging unit, and includes a two-dimensional detector configured with an array of photoelectric conversion elements, such as a CCD or C-MOS, that are sensitive to visible light, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector. The camera 21 is mounted, for example, inside the passenger compartment of the vehicle 2 so as to face forward of the vehicle 2. The camera 21 photographs the area in front of the vehicle 2 at predetermined photographing intervals (for example, 1 / 30 to 1 / 10 seconds) and generates an image of the area in front of the vehicle 2. The image obtained by the camera 21 may be a color image or a gray image. Note that the vehicle 2 may be provided with multiple cameras 21 with different photographing directions or focal lengths.

[0022] Every time the camera 21 generates an image, it outputs the generated image to the data collection device 3 via the in-vehicle network.

[0023] The GPS receiver 22 receives GPS signals from GPS satellites at predetermined intervals and determines the own position of the vehicle 2 based on the received GPS signals. Then, the GPS receiver 22 outputs positioning information representing the positioning results of the own position of the vehicle 2 based on the GPS signals to the data collection device 3 at predetermined intervals via the in-vehicle network. Note that the vehicle 2 may have a receiver that complies with a satellite positioning system other than the GPS receiver 22. In this case, it is sufficient that the receiver determines the own position of the vehicle 2.

[0024] The wireless communication terminal 23 is an example of a communication device, and is a device that executes wireless communication processing in accordance with a predetermined wireless communication standard. For example, by accessing the wireless base station 6, the wireless communication terminal 23 is connected to the server 4 via the wireless base station 6 and the communication network 5. 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. The wireless communication terminal 23 then receives a downlink wireless signal from the server 4, including collection area information, a collection instruction signal, or a collection stop signal, and outputs the received collection area information, collection instruction signal, or collection stop signal to the data collection device 3. The wireless communication terminal 23 also generates an uplink wireless signal including the driving history information, probe data, and an image or partial image received from the data collection device 3. The wireless communication terminal 23 then transmits the uplink wireless signal to the wireless base station 6, thereby transmitting the driving history information or probe data to the server 4.

[0025] 3 is a hardware configuration diagram of the data collection device 3. The data collection device 3 generates probe data based on images received from the camera 21 and transmits the generated probe data to the server 4 via the wireless communication terminal 23. Furthermore, the data collection device 3 generates driving history information representing the driving trajectory of the vehicle 2 and transmits the generated driving history information to the server 4 via the wireless communication terminal 23. To this end, the data collection device 3 has a communication interface 31, a memory 32, and a processor 33.

[0026] 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 an 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. Every time the communication interface 31 receives an image from the camera 21, it passes the received image to the processor 33. Every time the communication interface 31 receives positioning information from the GPS receiver 22, it passes the received positioning information to the processor 33. Furthermore, every time the communication interface 31 receives information from the server 4, such as collection area information, from the wireless communication terminal 23, it passes the information to the processor 33. Furthermore, the communication interface 31 outputs the probe data or driving history information received from the processor 33 to the wireless communication terminal 23 via the in-vehicle network.

[0027] The memory 32 is an example of a storage unit and includes, for example, a volatile semiconductor memory and a nonvolatile semiconductor memory. The memory 32 may further include other storage devices such as a hard disk drive. The memory 32 stores various data used in processing related to data collection executed by the processor 33 of the data collection device 3. For example, the memory 32 stores identification information of the vehicle 2, camera 21 parameters such as the focal length, shooting direction, and installation position of the camera 21, various parameters for identifying a classifier for detecting features from images received from the camera 21, and positioning information received from the GPS receiver 22. The memory 32 also stores collection area information received from the server 4. The collection area information includes information representing the position and range of an update target area or update section from which probe data is to be collected (for example, coordinates of each endpoint of the update target area or update section). The memory 32 may also store computer programs for implementing the various processes executed by the processor 33.

[0028] Furthermore, the memory 32 temporarily stores the generated driving history information and probe data.

[0029] The processor 33 includes one or more central processing units (CPUs) and their peripheral circuits. The processor 33 may further include other arithmetic circuits such as a logic operation unit, a numerical operation unit, or a graphics processing unit. The processor 33 executes data collection processing while the vehicle 2 is traveling.

[0030] 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 probe data generation unit 42, and a communication processing unit 43. Each of these units in the processor 33 is, for example, a functional module realized by a computer program running on the processor 33. Alternatively, each of these units in the processor 33 may be a dedicated arithmetic circuit provided in the processor 33.

[0031] The driving history information generation unit 41 generates driving history information that represents the driving trajectory of the vehicle 2. Specifically, the driving history information generation unit 41 generates the driving history information by chronologically arranging the position coordinates of the vehicle 2 indicated by a series of positioning information obtained from the GPS receiver 22 from the time the ignition switch of the vehicle 2 is turned on until it is turned off. Furthermore, the driving history information generation unit 41 associates the position coordinates of the vehicle 2 indicated by each piece of the series of positioning information with the date and time at which the positioning information was obtained, i.e., the date and time at which the vehicle 2 passed the point of the position coordinates, in the driving history information. Furthermore, the driving history information generation unit 41 may estimate the position of the vehicle 2 during a period when no positioning information was obtained by referring to the coordinates of the vehicle 2's position before and after that period and the odometry information for that period. The driving history information generation unit 41 may then include the coordinates of the estimated position of the vehicle 2 during that period in the driving history information. Furthermore, the driving history information generation unit 41 includes in the driving history information the date and time when the ignition switch was turned on and the date and time when the ignition switch was turned off. Furthermore, the driving history information generation unit 41 includes in the driving history information the identification information of the vehicle 2. Note that 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 be the identification information of the data collection device 3 or the wireless communication terminal 23 mounted on the vehicle 2.

[0032] When the ignition switch of the vehicle 2 is turned off, the driving history information generating unit 41 transmits the driving history information to the server 4 via the wireless communication terminal 23.

[0033] The probe data generating unit 42 generates probe data at predetermined intervals while the vehicle 2 is traveling, or each time the vehicle 2 travels a predetermined distance.

[0034] To this end, the probe data generation unit 42 detects predetermined features from the latest images generated by the camera 21 at predetermined intervals while the vehicle 2 is traveling, or each time the vehicle 2 travels a predetermined distance. The predetermined features are features that are represented in the map information to be updated, such as various road markings, various road signs, curbs, guardrails, traffic lights, or poles for installing road signs.

[0035] For example, the probe data generation unit 42 inputs an image into a classifier to detect a predetermined feature depicted in the input image. The probe data generation unit 42 may use a deep neural network (DNN) with a convolutional neural network (CNN)-type architecture, such as Single Shot MultiBox Detector or Faster R-CNN, as the classifier. Alternatively, the probe data generation unit 42 may use a DNN with a self-attention network (SAN)-type architecture, such as Vision Transformer, as the classifier. Alternatively, the probe data generation unit 42 may use a classifier based on another machine learning method, such as an AdaBoost classifier, as the classifier. Such a classifier is trained in advance according to a predetermined learning method, such as backpropagation, using a large number of training images depicting the predetermined feature to be detected from the image. The classifier then outputs information representing an area in the input image containing the feature to be detected (e.g., a circumscribing rectangle of the feature to be detected, hereinafter referred to as an object area) and information representing the type of feature depicted in the object area.

[0036] The probe data generation unit 42 estimates the position of the feature depicted in the object region detected from the image based on parameters such as the direction from the camera 21, the position of the vehicle 2 at the time of image generation, the direction of travel, the shooting direction of the camera 21, the focal length, and the installation position, which correspond to the center of gravity of the object region. The probe data generation unit 42 may estimate the position of the feature using so-called Structure from Motion (SfM). In this case, the probe data generation unit 42 uses optical flow to associate object regions depicting the same feature between two images acquired at different times. The probe data generation unit 42 then estimates the position of the feature by triangulation based on the position and direction of travel of the vehicle 2 at the time each of the two images was acquired, the camera 21 parameters, and the position of the object region in each image. The probe data generation unit 42 then generates probe data including information indicating the type and estimated position of the detected feature. The probe data generation unit 42 may further include information indicating the position and direction of travel of the vehicle 2 at the time of image generation in the probe data. The probe data generation unit 42 may further include information indicating the size and position of the object region on the image in the probe data. Note that the probe data generation unit 42 generates one piece of probe data for each detected feature. Therefore, if multiple features are detected from one image, multiple pieces of probe data are generated from one image.

[0037] The probe data generating unit 42 writes the generated probe data into the memory 32 every time it generates the probe data.

[0038] The communication processing unit 43 transmits the probe data generated while the vehicle 2 is traveling in the update target area or update target section indicated by the collection area information and stored in the memory 32 to the server 4 via the wireless communication terminal 23.

[0039] The communication processing unit 43 determines whether the vehicle 2 has entered the update target area or the update target section by referring to the collection area information and the latest positioning information. When the vehicle 2 enters the update target area or the update target section, the communication processing unit 43 transmits the probe data stored in the memory 32 to the server 4 via the wireless communication terminal 23 in chronological order, starting with the oldest data. Note that the communication processing unit 43 stops transmitting the probe data when it receives a notification from the server 4 via the wireless communication terminal 23 to stop collecting the probe data. Alternatively, the communication processing unit 43 may transmit pre-judgment data to the server 4 via the wireless communication terminal 23 before starting to transmit the probe data, inquiring whether to transmit the probe data. In this case, the communication processing unit 43 may include, in the pre-judgment data, identification information of the vehicle 2, position information of the vehicle 2 indicated by the latest positioning information, or information for identifying the area or road section including the position of the vehicle 2. Then, after transmitting the pre-judgment data, the communication processing unit 43 may start transmitting the probe data only when it receives a probe data collection instruction signal from the server 4 via the wireless communication terminal 23.

[0040] Furthermore, the communication processing unit 43 erases from the memory 32 the probe data that has been transmitted to the server 4 via the wireless communication terminal 23 .

[0041] When the vehicle 2 exits the update target area or the update target section, the communication processing unit 43 refers to the memory 32 to identify probe data that has not been transmitted at the time of the exit. Then, the communication processing unit 43 ends transmission of the probe data when transmission of the identified probe data to the server 4 is completed. Note that, similar to determining whether the vehicle 2 has entered the update target area or the update target section, the communication processing unit 43 can determine whether the vehicle 2 has exited the update target area or the update target section by referring to the collection area information and the latest positioning information.

[0042] If the collection instruction signal instructs the collection of not only probe data but also images of the section to be updated, the communication processing unit 43 transmits a series of images generated while the vehicle 2 is traveling through the section to be updated, together with the probe data, to the server 4 via the wireless communication terminal 23. Furthermore, if the collection instruction signal instructs the collection of partial images of the section to be updated, the communication processing unit 43 generates partial images by cutting out a predetermined range from each of the series of images generated while the vehicle 2 is traveling through the section to be updated. The communication processing unit 43 then transmits the obtained series of partial images, together with the probe data, to the server 4 via the wireless communication terminal 23.

[0043] Next, the server 4, which is an example of a data collection instruction device, will be described. The server 4 selects a vehicle from among the multiple vehicles 2 to which it will instruct the collection of probe data for the update target area, and instructs the selected vehicle to collect probe data for the update target area. The server 4 also instructs the other vehicles to collect probe data for the update target section within the update target area. As described above, the update target area is, for example, an area that may be a target for updating map information, i.e., an area that is to be determined for the presence or absence of a change point, and the update target section is, for example, a road section that includes a detected change point.

[0044] Furthermore, the server 4 stores the probe data transmitted from the data collection devices 3 mounted on each vehicle 2. The server 4 then detects change points or updates map information based on the probe data. Furthermore, the server 4 notifies each vehicle 2 of collection area information.

[0045] 5 is a hardware configuration diagram of the server 4. The server 4 has a communication interface 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 signal lines. The server 4 may further have input devices such as a keyboard and a mouse, and a display device such as a liquid crystal display.

[0046] 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. 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 passes the driving history information, probe 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. The communication interface 51 also transmits the collection area information, collection instruction signals, 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.

[0047] The storage device 52 is an example of a storage unit, and includes, for example, a hard disk drive or an optical recording medium and an access device for the hard disk drive or an optical recording medium. The storage device 52 stores map information to be updated. The storage device 52 also stores information indicating an area to be updated within the range represented by the map information.

[0048] Note that multiple 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 move across the boundaries between the update target areas is minimized. For example, each update target area may be set so that a point that is a boundary of a traffic area, such as a mountainous area or a river, becomes the boundary of the update target area.

[0049] The storage device 52 further stores, for each update target area, the probe data, images, and partial images collected for each of the multiple road sections included in the update target area. The storage device 52 also stores driving history information received from each vehicle 2. The storage device 52 may also store a computer program to be executed on the processor 54 for executing a data collection instruction process.

[0050] The memory 53 is another example of a storage unit and includes, for example, a non-volatile semiconductor memory and a volatile semiconductor memory. The memory 53 temporarily stores various data generated during the execution of the data collection instruction process, and various data acquired through communication with each vehicle 2, such as probe data and driving history information.

[0051] The processor 54 is an example of a control unit and includes one or more central processing units (CPUs) and their peripheral circuits. The processor 54 may further include other arithmetic circuits, such as a logic operation unit or a numerical operation unit. Each time the processor 54 receives probe data, an image, a partial image, or driving history information from one of the vehicles 2, the processor 54 stores the received probe data, an image, a partial image, or driving history information in the storage device 52. In this case, the processor 54 may count the number of pieces of probe data received for each road section. In this case, each time the processor 54 receives probe data, the processor 54 references the position of the vehicle 2 included in the probe data, identifies the road section on which the vehicle 2 was traveling when the probe data was generated, and increments the count value of the probe data for the identified road section by one. Furthermore, the processor 54 executes a data collection instruction process.

[0052] 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. Each of these units in the processor 54 is a functional module realized by, for example, a computer program running on the processor 54. Alternatively, each of these units in the processor 54 may be a dedicated arithmetic circuit provided in the processor 54.

[0053] 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 that satisfy predetermined conditions related to driving in the update target area from the plurality of vehicles 2. Note that the predetermined timing is set in advance, and can be, for example, a predetermined date and time each month, or a predetermined time on a predetermined day of the week.

[0054] If multiple update target regions are set, the selection unit 61 may execute the following process for each update target region. Therefore, the process for one update target region will be described below.

[0055] In this embodiment, the selection unit 61 refers to the driving history information of each of the multiple vehicles 2 and calculates a driving coverage rate, which is the ratio of road sections actually driven to the multiple road sections included in the update target area during the most recent predetermined period (for example, one week to one month).The selection unit 61 then selects one or more vehicles from the multiple vehicles 2 in descending order of driving coverage rate as vehicles for which to instruct the collection of probe data used to determine the presence or absence of a change point.In this way, the selection unit 61 can appropriately select vehicles so that probe data can be collected from the entire update target area with a relatively small number of vehicles.

[0056] The selection unit 61 selects, from among the position coordinates of each vehicle 2 included in the driving history information, position coordinates associated with a date and time included in the most recent specified period. Then, for each selected position coordinate, the selection unit 61 compares the position coordinate with the position and range of each road section included in the update target area shown in the map information, and identifies the road section including the position coordinate. The selection unit 61 then determines the identified road section as the road section on which the vehicle 2 has traveled. In this way, the selection unit 61 can calculate the driving coverage rate by identifying, from among the road sections included in the update target area, each road section on which the vehicle 2 has traveled in the most recent specified period.

[0057] Note that even if the vehicle 2 has traveled the same road section multiple times within the most recent specified period, the selection unit 61 counts that road section only once. The selection unit 61 may also 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 travel coverage rate as the ratio of the total length of the road sections traveled by the vehicle 2 to the total length of each road section included in the update target area. Furthermore, importance may be set in advance for each road section. For example, the highest importance may be set for road sections that are expressways, the next highest importance may be set for road sections that are national highways, and the lowest importance may be set for other road sections. In this case, the selection unit 61 may calculate the travel coverage rate as the ratio of the total importance of the road sections that the vehicle 2 has actually traveled within the most recent specified period to the total importance of each of the multiple road sections included in the update target area. By calculating the travel coverage rate based on importance in this way, vehicles that frequently travel on road sections with higher importance are more likely to be selected among the multiple vehicles 2.

[0058] The selection unit 61 selects vehicles 2 in descending order of travel coverage rate until a predetermined percentage (e.g., 80% to 90%) or more of the road sections in the update target area are road sections that have been traveled by the selected vehicle 2. If there is a road section that has not been traveled by any of the vehicles 2 selected up to that point, the selection unit 61 may additionally select a vehicle 2 that has traveled that road section.

[0059] Alternatively, the selection unit 61 may select a preset number of vehicles 2 in descending order of travel coverage rate. In this case, if there is a road section on which none of the previously selected vehicles 2 has traveled, the selection unit 61 may additionally select a vehicle 2 that has traveled on that road section.

[0060] According to a modified example, the selection unit 61 may refer to the driving history of each of the multiple vehicles 2 and calculate a specific time period ratio, which is the ratio of the time the vehicle spent driving in the update target area during a specific time period or on a specific day of the week to the total driving time during the most recent specified period. The selection unit 61 may then select one or more vehicles 2 from the multiple vehicles 2 in descending order of the specific time period ratio. This allows the selection unit 61 to select vehicles 2 that have a high probability of driving in the update target area during a specific time period or on a specific day of the week. The specific time period or the specific day of the week may be a time period or day of the week when features to be detected are expected to be clearly visible in images generated by the camera 21, such as early morning hours when features in specific lanes are not obscured by parked vehicles or other obstacles. Therefore, the selection unit 61 can select vehicles 2 that are likely to pass through the update target area at a time appropriate for collecting probe data for change point detection.

[0061] In this case, the selection unit 61 refers to the date and time when the ignition switch was turned on or off, which is included in the driving history information, and determines the total driving time as the sum of the individual periods from when the ignition switch was turned on to when it was turned off within the most recent predetermined period. Furthermore, the selection unit 61 selects, from the individual position coordinates included in the driving history information, position coordinates whose associated date and time fall within a predetermined time period or a predetermined day of the week. From the selected position coordinates, the selection unit 61 further selects position coordinates that fall within the update target area. Then, based on the date and time associated with the individual position coordinates finally selected, the selection unit 61 calculates the total period from when the vehicle 2 entered the update target area to when it exited it as the time the vehicle 2 spent driving within the update target area within the predetermined time period or on a predetermined day of the week.

[0062] The selection unit 61 refers to the travel history information of each of the selected one or more vehicles, identifies the identification information of each of the selected vehicles, and notifies the notification processing unit 63 of the identification information of each of the selected vehicles.

[0063] The detection unit 62 determines whether or not there is a change point for each road section within 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 then detects road sections within the update target area that include a change point.

[0064] When a predetermined period of time has elapsed since a probe data collection instruction was sent to one or more selected vehicles 2, the detection unit 62 reads the probe data collected for the update target area from the storage device 52. Then, for each vehicle 2, the detection unit 62 aligns each feature represented in the series of probe data generated while the vehicle 2 traveled through the update target area with the corresponding feature represented in the map information to be updated. In this process, the detection unit 62 calculates affine transformation coefficients according to a predetermined optimization method, such as the steepest descent method, so as to minimize the sum of squares of the distances between the positions of each feature represented in the series of probe data and the corresponding feature represented in the map information. The detection unit 62 then uses the calculated affine transformation coefficients to move the positions of each feature represented in the series of probe data, thereby aligning the features with the corresponding feature represented in the map information.

[0065] Once the above-described alignment is completed for each vehicle 2, the detection unit 62 detects, for each road section included in the update target area, points where features represented in the collected probe data do not match corresponding features represented in the map information as change points. For example, if there are features of the same type represented in each of the collected predetermined number of probe data in a certain road section, and the features are within a predetermined distance from each other, the detection unit 62 determines that the features represented in the probe data are the same feature. If there is no corresponding feature represented in the map information within a predetermined distance from the same feature represented in the probe data, it is possible that a new feature has been added since the last update of the map information. Therefore, the detection unit 62 detects the average position of the positions of the features represented in the predetermined number of probe data as a change point.

[0066] Furthermore, if probe data representing a corresponding feature within a predetermined distance from the location of a specific feature shown in map information has not been collected, the feature shown in the map information may have been removed. Therefore, the detection unit 62 detects the location of the feature shown in the map information as a change point. Furthermore, if the distance between the specific feature shown in the map information and a corresponding feature of the same type shown in the probe data is greater than a predetermined distance, the specific feature may have been moved since the last update of the map information. Therefore, the detection unit 62 may detect the location of the specific feature shown in the map information and the location of the corresponding feature shown in the probe data as change points.

[0067] Furthermore, if the type of a specific feature shown in the map information differs from the type of a corresponding feature shown in the probe data that is located within a specific distance from the location of the specific feature, it is possible that the type of the specific feature has changed since the last update of the map information. Therefore, in this case as well, the detection unit 62 may detect the position of the specific feature shown in the map information as a change point.

[0068] The detection unit 62 refers to map information for each detected change point and identifies the road section including the position coordinates of the change point as the update target section. Then, the detection unit 62 notifies the notification processing unit 63 of information indicating the update target section including each detected change point.

[0069] The detection unit 62 may further set, as an update target section, a road section for which the number of collected probe data has not reached the planned number to be collected even after a predetermined period has elapsed since the instruction to collect probe data for the update target area was notified.The detection unit 62 may then notify the notification processing unit 63 of information indicating the update target section for which the number of collected probe data has not reached the planned number to be collected.

[0070] The notification processing unit 63 instructs each of one or more vehicles 2 selected by the selection unit 61 from among the multiple vehicles 2 to collect probe data for the update target area. To do so, the notification processing unit 63 identifies each of the selected one or more vehicles 2 based on the identification information received from the selection unit 61. The notification processing unit 63 then generates collection area information for the entire update target area as a probe data collection target area, and notifies each of the identified vehicles 2 of the generated collection area information via the communication interface 51. Furthermore, the notification processing unit 63 generates a collection instruction signal instructing the collection of probe data, and notifies each of the identified vehicles 2 of the generated collection instruction signal via the communication interface 51. Note that when the server 4 receives pre-assessment data, the notification processing unit 63 may determine whether to instruct the collection of probe data based on the pre-assessment data. For example, if the number of pieces of probe data collected for a road section including the position of the vehicle 2 represented in the pre-assessment data has reached the planned number of pieces of probe data to be collected, the notification processing unit 63 may determine not to instruct the collection of probe data. On the other hand, if the number of collected probe data does not reach the planned number of collections, the notification processing unit 63 may determine to instruct the collection of probe data. In this case, the notification processing unit 63 notifies the vehicle 2 that transmitted the pre-evaluation data of a collection instruction signal via the communication interface 51. Note that if multiple update target areas are set, a vehicle will be selected for each update target area. Therefore, the notification processing unit 63 may instruct the collection of probe data for update target areas that differ depending on the vehicle.

[0071] Furthermore, after a predetermined period of time has elapsed since the collection area information was notified to each of the one or more selected vehicles 2, the notification processing unit 63 may notify each of the one or more selected vehicles 2 of a collection stop signal via the communication interface 51 to stop the collection of probe data.

[0072] Furthermore, upon receiving information indicating the update target section from the detection unit 62, the notification processing unit 63 generates collection area information specifying the update target section as a probe data collection target area. The notification processing unit 63 then notifies each vehicle 2 other than the one or more selected vehicles of the generated collection area information via the communication interface 51. The notification processing unit 63 then generates a collection instruction signal instructing the collection of probe data for the update target section, and notifies each vehicle 2 other than the one or more selected vehicles of the generated collection instruction signal via the communication interface 51. Note that the notification processing unit 63 may instruct the collection of not only probe data but also images or partial images in the collection instruction signal for the update target section. Furthermore, when the server 4 is receiving pre-assessment data, the notification processing unit 63 may also instruct the collection of probe data for the update target section only if the number of collected probe data has not reached the planned number of data to be collected.

[0073] The notification processing unit 63 may also notify each vehicle selected by the selection unit 61 from among the plurality of vehicles 2 of the collection instruction signal for the update target section via the communication interface 51.

[0074] FIG. 7 is an explanatory diagram showing an example of collection instructions for each vehicle. In this example, the update target area 700 includes 15 road sections {A, B, C, ..., O}. Here, as shown in a travel trajectory 721 (note that this travel trajectory is not limited to one travel, but may be the result of multiple travels) for the most recent predetermined period represented in the travel history information of vehicle 711, vehicle 711 has traveled in nine road sections. That is, the travel coverage rate of vehicle 711 is 60%. In contrast, as shown in a travel trajectory 722 for the most recent predetermined period represented in the travel history information of vehicle 712, vehicle 712 has traveled in three road sections. That is, the travel coverage rate of vehicle 712 is 20%. Furthermore, as shown in a travel trajectory 723 for the most recent predetermined period represented in the travel history information of vehicle 713, vehicle 713 has traveled in eight road sections. That is, the travel coverage rate of vehicle 713 is 53%. Let us assume that vehicles with a travel coverage rate of 50% or more are selected. Therefore, vehicles 711 and 713 are selected, and a probe data collection instruction signal for detecting a change point is sent to them. On the other hand, vehicle 712 is not selected, and a probe data collection instruction signal for detecting a change point is not sent to them. However, after a change point is detected, a collection instruction signal for the update target section including the change point is sent to vehicle 712. For example, if a change point is detected in road section G, a collection instruction signal instructing the collection of probe data for road section G is sent to vehicle 712.

[0075] The update unit 64 updates information about specific features in the update target section, which are represented in the map information, based on the probe data collected for the update target section. To do this, the update unit 64 aligns, for each vehicle 2 that has traveled through the update target section, each feature represented in a series of probe data received from that vehicle 2 with a corresponding feature represented in the map information. In this case, the update unit 64 may perform processing similar to the alignment processing performed by the detection unit 62. Then, if a feature represented in probe data received from a predetermined number or more vehicles 2 and presumed to be the same feature does not have a corresponding feature represented in the map information, the update unit 64 adds the type and position of the feature to the map information. Conversely, for a feature represented in the map information for which probe data representing a corresponding feature located within a predetermined distance from the feature has not been collected, the update unit 64 deletes information about the feature from the map information. Furthermore, it is assumed that the distance between the specific feature represented in the map information and a feature of the same type as the specific feature, which is represented in a predetermined number or more of received probe data, is greater than a predetermined distance. In this case, the update unit 64 corrects the position of the feature shown in the map information to the average value of the positions of the feature shown in at least a predetermined number of received probe data.

[0076] Furthermore, if the update unit 64 can detect a feature from an image or partial image received from a vehicle that has traveled through the section to be updated, the update unit 64 may add information about the detected feature to the map information. In this case, the update unit 64 may detect the feature by inputting the image or partial image into a classifier similar to the classifier used in the probe data generation unit 42 of the data collection device 3. Furthermore, the update unit 64 may estimate the position of the detected feature based on the position and traveling direction of the vehicle 2 at the time of image generation, the parameters of the camera 21, and the position of the feature on the image or partial image.

[0077] The update unit 64 stores the updated map information in the storage device 52. Furthermore, the notification processing unit 63 may output the updated map information to another device via the communication interface 51 and the communication network 5. Furthermore, the notification processing unit 63 may distribute the updated map information to any one of the multiple vehicles 2 or another vehicle that uses the map information for autonomous driving control via the communication interface 51, the communication network 5, and the wireless base station 6.

[0078] 8 is an operational flowchart of the data collection instruction process. The processor 54 of the server 4 executes the data collection instruction process in accordance with the following operational flowchart.

[0079] The selection unit 61 of the processor 54 selects one or more vehicles 2 that satisfy predetermined conditions related to traveling in the update target area from among the multiple vehicles 2 (step S101). Then, the notification processing unit 63 of the processor 54 notifies each of the one or more selected vehicles via the communication interface 51 of collection area information that sets the update target area as a collection target area, and a collection instruction signal that instructs the collection of probe data for the update target area (step S102).

[0080] After a predetermined period of time has elapsed since the notification of the collection instruction, the detection unit 62 of the processor 54 identifies, based on the collected probe data, road sections within the area to be updated that include change points and road sections for which the number of collected probe data is less than the planned number to be collected, as sections to be updated (step S103).

[0081] Then, the notification processing unit 63 notifies vehicles 2 other than the one or more selected vehicles of collection area information that sets the update target section as a collection target area, and a collection instruction signal that instructs the vehicles to collect probe data for the update target section via the communication interface 51 (step S104). Note that, as described above, the notification processing unit 63 may also instruct the one or more vehicles selected in step S102 to collect probe data for the update target section.

[0082] The update unit 64 of the processor 54 updates the map information based on the probe data collected for the update target section (step S105), and the processor 54 then ends the data collection instruction process.

[0083] As described above, the data collection instruction device selects one or more vehicles from among a plurality of vehicles capable of generating and collecting probe data that satisfy predetermined conditions related to driving in the update target area. The data collection instruction device then instructs the selected one or more vehicles to collect probe data for the update target area. The data collection device also instructs vehicles other than the selected one or more vehicles to collect probe data for the update target section, such as a road section including a change point within the update target area. In this way, the selected vehicles collect probe data for each road section within the update target area, thereby reducing the amount of communication required to transmit the probe data. Furthermore, because the selected vehicles generate probe data over a relatively continuous section, it is possible to collect the amount of probe data necessary to detect change points while maintaining 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, thereby collecting the amount of probe data necessary to update the change point information.

[0084] As described above, those skilled in the art can make various modifications to the embodiments within the scope of the present invention. [Explanation of symbols]

[0085] 1. Data Collection System 2 vehicles 21 Camera 22 GPS receiver 23 Wireless communication terminal 3 Data collection equipment 31 Communication Interface 32 memory 33 processors 41 Driving history information generation unit 42 Probe data generation unit 43 Communication processing unit 4 Server 51 Communication Interface 52 Storage devices 53 Memory 54 processors 61 Selection section 62 Detection unit 63 Notification processing section 64 Update section 5. Communication Network 6. Radio base stations

Claims

1. a storage unit that stores the driving history of each of a plurality of vehicles; a selection unit that selects one or more vehicles from the plurality of vehicles based on the driving history of each of the plurality of vehicles; a notification processing unit that instructs the one or more selected vehicles, via a communication unit, to collect probe data representing predetermined features in an area to be updated in map information, and that instructs vehicles other than the one or more selected vehicles among the plurality of vehicles, via the communication unit, to collect the probe data for predetermined road sections among a plurality of road sections included in the area to be updated; and the selection unit refers to the driving history of each of the plurality of vehicles, and selects one or more vehicles from the plurality of vehicles in descending order of driving coverage rate of road sections that have actually been driven among the plurality of road sections included in the update target area during a most recent predetermined period; The predetermined road section is a road section where the number of probe data collected from the one or more vehicles is less than a predetermined number, or where there is a change between a feature represented in the probe data collected from the one or more vehicles and a corresponding feature represented in the map information. Data collection indicator.

2. an importance level is set for each of a plurality of road sections included in the update target area; 2. The data collection instruction device according to claim 1, wherein the selection unit calculates, for each of the plurality of vehicles, a ratio of the sum of the importance of road sections that the vehicle has actually traveled among the plurality of road sections in the most recent specified period to the sum of the importance of each of the plurality of road sections, as the travel coverage rate for the vehicle.

3. A storage unit that stores the driving history of each of a plurality of vehicles; a selection unit that selects one or more vehicles from the plurality of vehicles based on the driving history of each of the plurality of vehicles; a notification processing unit that instructs the one or more selected vehicles, via a communication unit, to collect probe data representing predetermined features in an area to be updated in map information, and that instructs vehicles other than the one or more selected vehicles among the plurality of vehicles, via the communication unit, to collect the probe data for predetermined road sections among a plurality of road sections included in the area to be updated; and the selection unit refers to the driving history of each of the plurality of vehicles, and selects one or more vehicles from the plurality of vehicles in descending order of a ratio of a time that the vehicle has been driving in the update target area during a predetermined time period or a predetermined day of the week to a total driving time during a most recent predetermined period; The predetermined road section is a road section where the number of probe data collected from the one or more vehicles is less than a predetermined number, or where there is a change between a feature represented in the probe data collected from the one or more vehicles and a corresponding feature represented in the map information. Data collection indicator.

4. A data collection instruction device selects one or more vehicles from among the plurality of vehicles based on the driving history of each of the plurality of vehicles stored in a memory unit, the data collection instruction device instructs the selected one or more vehicles via a communication unit to collect probe data representing predetermined features in an area to be updated for map information; the data collection instruction device instructs, via the communication unit, vehicles other than the one or more selected vehicles among the plurality of vehicles to collect probe data for a predetermined road section among a plurality of road sections included in the update target area. This includes: selecting the one or more vehicles includes referring to the driving history of each of the plurality of vehicles and selecting, from the plurality of vehicles, one or more vehicles in descending order of driving coverage rate of road sections that have actually been driven among the plurality of road sections included in the update target area during a most recent predetermined period; The predetermined road section is a road section where the number of probe data collected from the one or more vehicles is less than a predetermined number, or where there is a change between a feature represented in the probe data collected from the one or more vehicles and a corresponding feature represented in the map information. Data collection instructions.

5. A data collection instruction device selects one or more vehicles from among the plurality of vehicles based on the driving history of each of the plurality of vehicles stored in a memory unit, the data collection instruction device instructs the selected one or more vehicles via a communication unit to collect probe data representing predetermined features in an area to be updated for map information; the data collection instruction device instructs, via the communication unit, vehicles other than the one or more selected vehicles among the plurality of vehicles to collect probe data for a predetermined road section among a plurality of road sections included in the update target area. This includes: selecting the one or more vehicles includes referring to the driving history of each of the plurality of vehicles and selecting one or more vehicles from the plurality of vehicles in descending order of the ratio of the time that the vehicles have been driving in the update target area during a specified time period or on a specified day of the week to the total driving time during a most recent specified period; The predetermined road section is a road section where the number of probe data collected from the one or more vehicles is less than a predetermined number, or where there is a change between a feature represented in the probe data collected from the one or more vehicles and a corresponding feature represented in the map information. Data collection instructions.

6. selecting one or more vehicles from the plurality of vehicles based on the driving histories of the plurality of vehicles stored in the storage unit; instructing the one or more selected vehicles via a communication unit to collect probe data representing predetermined features in an area to be updated for map information; instructing, via the communication unit, vehicles other than the one or more selected vehicles among the plurality of vehicles to collect probe data for a predetermined road section among a plurality of road sections included in the update target area; Let the computer do that, selecting the one or more vehicles includes referring to the driving history of each of the plurality of vehicles and selecting, from the plurality of vehicles, one or more vehicles in descending order of driving coverage rate of road sections that have actually been driven among the plurality of road sections included in the update target area during a most recent predetermined period; The predetermined road section is a road section where the number of probe data collected from the one or more vehicles is less than a predetermined number, or where there is a change between a feature represented in the probe data collected from the one or more vehicles and a corresponding feature represented in the map information. Computer program for directing data collection.

7. Selecting one or more vehicles from among the plurality of vehicles based on the driving histories of each of the plurality of vehicles stored in a memory unit; instructing the one or more selected vehicles via a communication unit to collect probe data representing predetermined features in an area to be updated for map information; instructing, via the communication unit, vehicles other than the one or more selected vehicles among the plurality of vehicles to collect probe data for a predetermined road section among a plurality of road sections included in the update target area; Let the computer do that, selecting the one or more vehicles includes referring to the driving history of each of the plurality of vehicles and selecting one or more vehicles from the plurality of vehicles in descending order of the ratio of the time that the vehicles have been driving in the update target area during a specified time period or on a specified day of the week to the total driving time during a most recent specified period; The predetermined road section is a road section where the number of probe data collected from the one or more vehicles is less than a predetermined number, or where there is a change between a feature represented in the probe data collected from the one or more vehicles and a corresponding feature represented in the map information. Computer program for directing data collection.

Images