Apparatus and method for collecting map-generating data

Abstract

Device for collecting map-generating data, comprising: a communication unit capable of communicating with at least one vehicle; a storage unit; a reception processing unit which, when receiving from the at least one vehicle, via the communication unit, map-generating data representing a road environment around the vehicle together with information indicating a road section on which the map-generating data is obtained, stores the map-generating data in association with the road section and a date and time of reception in the storage unit; a counting unit that counts, for each of the road sections, the number of pieces of map-generating data received in a first period of time; an identification unit that identifies one of the road sections for which the number of pieces of map-generating data received in the first time period does not reach a target number for the one of the road sections; a forecasting unit that forecasts, for the identified road section, the number of pieces of map-generating data to be received in a second time period ahead of the first time period, based on a history of traffic volume under each environmental condition or a history of the number of pieces of map-generating data previously received for the road section, and an instruction unit that instructs a predetermined device via the communication unit to collect the map generating data of the identified road section when the sum of the number of pieces of map generating data received in the first period of time and the number of pieces of map generating data predicted to be received in the second period of time for the road section does not reach the target number for the road section.

Description

Area

[0001] The present invention relates to an apparatus and a method for collecting data to be used to generate or create a map. background

[0002] High-precision road maps, which an automated vehicle driving system references for automated driving control of a vehicle, are required to accurately represent road information. Technologies have been proposed to appropriately collect the information required to generate such accurate road maps (see, for example, JP 2007-58370 A and JP 2017-117154 A).

[0003] For example, JP 2007-58370 A discloses a technology in which each of the vehicle-mounted devices included in a road map providing system transmits travel history information along with information about a travel purpose and an attribute to a road map providing device. The road map providing device statistically processes the travel history information for each received travel purpose and attribute, generates road map information classified by travel purpose and attribute, and stores it in a database. JP 2017-117154 A discloses a technology in which a vehicle transmits image data of the vehicle's surroundings, in association with the traveling position and the time at which the vehicle receives the data, to a management center.The management center estimates the number of moving vehicles for each road section registered in a map database based on the received vehicle travel positions and times, and calculates a coverage ratio based on the ratio of the estimated number of moving vehicles to a reference number of vehicles defined for each road section. The management center determines image capture conditions such that the lower the coverage ratio, the shorter the interval between image captures, and communicates the determined condition to the vehicles.

[0004] Furthermore, JP 2020-46971 A discloses a data acquisition system consisting of a server device and one or more data acquisition vehicles, in which the server device collects the data acquired by the data acquisition vehicles. The server device comprises transmission means for transmitting to the data acquisition vehicle a map indicating a plurality of unit regions in which data is to be collected, the map including, for each unit region, a passing traffic volume of the data acquisition vehicle. The data acquisition vehicle comprises: acquisition means for acquiring the data in each unit area; and control means for transmitting the acquired data to the server device based on the map received from the server device. The control means determines the data to be transmitted to the server device from the acquired data based on the passing traffic volume for each unit region.

[0005] In addition, JP 2018 - 54 343 A discloses a traffic congestion risk display device connected to a traffic congestion information preparation server that prepares traffic congestion information including a current congestion level calculated from the current value of travel data transmitted from a vehicle as sounding data relating to routes and a statistical congestion level calculated from statistical values ​​for a certain past period, and to a meteorological information preparation server that prepares meteorological information.The device is equipped with traffic congestion risk display units that calculate and display predicted traffic congestion risk values ​​indicating the probability of occurrence of the traffic congestion risk on a given route during a prescribed future period on the routes based on the congestion information and the meteorological information prepared as data in tabular form. Summary

[0006] Because traffic volumes vary between road segments, the technologies described above may fail to collect as many pieces of map-generating data from some road segments as are needed to create or update a map in a predetermined period of time.

[0007] It is an object of the present invention to provide a map generating data collecting apparatus which can predict the number of pieces of map generating data to be collected in a preceding predetermined period for one of road sections for which the number of collected pieces of map generating data has not reached a target number, the road sections being included in a target area for generating or updating a map.

[0008] According to one embodiment, an apparatus for collecting map-generating data is provided. The apparatus comprises a communication unit capable of communicating with at least one vehicle; a storage unit; a reception processing unit which, upon receiving map-generating data representing a road environment around the vehicle, along with information indicating a road section on which the map-generating data is acquired, from the at least one vehicle via the communication unit, stores the map-generating data in association with the road section and a date and time of reception in the storage unit; and a counting unit which counts, for each of the road sections, the number of pieces of map-generating data received in a first period of time.The device further comprises an identification unit that identifies one of the road sections for which the number of pieces of map-generating data received in the first time period does not reach a target number for the one of the road sections; and a prediction unit that predicts, for the identified road section, the number of pieces of map-generating data to be received in a forward second time period after the first time period, based on a history of traffic volume under each environmental condition or a history of the number of pieces of map-generating data previously received for the road section.

[0009] The device further comprises an instruction unit that instructs a predetermined device via the communication unit to collect the map-generating data of the identified road section when the sum of the number of pieces of map-generating data received in the first time period and the number of pieces of map-generating data predicted to be received in the second time period for the road section does not reach the target number for the road section.

[0010] In this case, the instruction unit preferably does not instruct the predetermined device to collect the map generating data of the identified road section when the number of pieces of map generating data received in the first period for the road section, or the sum of the number of pieces of map generating data received in the first period and the number of pieces of map generating data predicted to be received in the second period for the road section reaches the target number for the road section.

[0011] The prediction unit of the device preferably determines a predicted value of the traffic volume under each environmental condition for the identified road section based on the history of the traffic volume under each environmental condition, and predicts the number of pieces of map-generating data to be received in the second period using a prediction model representing a relationship between the predicted value of the traffic volume under each environmental condition and the number of pieces of map-generating data to be received.

[0012] Alternatively, the prediction unit of the device preferably determines a predicted value of the traffic volume in the second time period for the identified road section based on the history of the traffic volume under each environmental condition, and predicts the number of pieces of map-generating data to be received in the second time period using a prediction model representing a relationship between the predicted value of the traffic volume and the number of pieces of map-generating data to be received.

[0013] According to another embodiment, a method for collecting map-generating data is provided. The method comprises: when receiving map-generating data representing a road environment around the vehicle, along with information indicating a road section on which the map-generating data is obtained, from at least one vehicle via a communication unit capable of communicating with the at least one vehicle, storing the map-generating data in association with the road section and a date and time of receipt in a storage unit;and counting the number of pieces of map-generating data for each of the road segments received in a first time period. The method further comprises: identifying one of the road segments for which the number of pieces of map-generating data received in the first time period does not reach a target number for the one of the road segments;Predicting the number of pieces of map-generating data to be received in a second time period ahead of the first time period for the identified road section based on a history of traffic volume under each environmental condition or a history of the number of pieces of map-generating data previously received for the road section, and instructing a predetermined device via the communication unit to collect the map-generating data of the identified road section if the sum of the number of pieces of map-generating data received in the first time period and the number of pieces of map-generating data predicted to be received in the second time period for the road section does not reach the target number for the road section;

[0014] The apparatus according to the present invention has an advantageous effect in that it is capable of predicting the number of pieces of map generating data to be collected in a forward predetermined period for one of road sections for which the number of collected pieces of map generating data has not reached a target number, the road sections being included in a target area for generating or updating a map. Short description of the figures Fig. 1 schematically illustrates the configuration of a map-generating data collecting system including a map-generating data collecting device. Fig. Figure 2 shows a schematic diagram of the configuration of a vehicle. Fig. 3 shows the hardware configuration of a data acquisition device. Fig. 4 illustrates the hardware configuration of a server corresponding to an example of the device for collecting map-generating data. Fig. 5 is a functional block diagram of a processor of the server relating to a process for collecting map generating data. Fig. 6 is a figure for explaining a target road section for predicting the number of collected parts and a target road section for collection instructions. Fig. Figure 7 is an operational flow diagram of the process for collecting map-generating data. Description of embodiments

[0015] Hereinafter, a map-generating data collecting device and a method therefor performed by the device will be described with reference to the accompanying drawings. For each of road sections included in a target area for generating or updating a map, the device collects data representing the road environment of the road section and used for generating or updating a map (hereinafter, "map-generating data") from at least one communication-capable vehicle. The device counts, for each of the road sections, the number of pieces of map-generating data collected in a preceding predetermined period (hereinafter, a "first period") and identifies one of the road sections for which the number of collected pieces of map-generating data does not reach a target number.For the identified road section, the device predicts the number of pieces of map-generating data to be collected in a predetermined upcoming or forward period of time (hereinafter a "second period") based on this predicted value of a traffic volume under each environmental condition for the road section, which is predicted from the history of the traffic volume under each environmental condition or from the history of the number of pieces of map-generating data collected for the road section before the first period of time.Additionally, the device instructs a predetermined device to collect map-generating data of a road section for which the sum of the number of pieces of map-generating data collected in the first period and the number of pieces of map-generating data predicted to be collected in the second period does not reach the target number. In this way, the device can predict the number of pieces of map-generating data to be collected in a predetermined advance period for a road section for which the number of collected pieces of map-generating data has not reached the target number.In particular, the device can facilitate the collection of a target number of pieces of data of a road section for which not only the number of pieces of map-generating data collected so far but also the number of pieces of map-generating data that are predicted to be collected is small.

[0016] The map-generating data includes, for example, an image representing a road generated by a vehicle-mounted camera, or a partial image obtained by cropping an area representing a road surface from such an image. The map-generating data may further include data representing the types of road features in a map to be generated or updated (e.g., traffic signs or road markings such as lane dividing lines or stop lines).

[0017] For example, individual road segments may be segments corresponding to individual connections of nodes and links representing a road network in a road map for a navigation system. However, individual road segments are not limited to this example and may be segments obtained by dividing individual roads in a target area for generating or updating a map in units of predetermined length (e.g., 100 m to 1 km).

[0018] Fig. Figure 1 schematically illustrates the configuration of a system for collecting map-generating data, which includes the device for collecting map-generating data. In the present embodiment, the system 1 comprises at least one vehicle 2 and a server 3, which corresponds to an example of the device for collecting map-generating data. The vehicle 2 accesses a wireless base station 5, which is connected, for example, via a gateway (not shown) to a communication network 4 connected to the server 3, thereby establishing a connection to the server 3 via the wireless base station 5 and the communication network 4. Although in Fig. 1 only one vehicle 2 is shown, the system 1 can comprise several vehicles 2. Likewise, the communication network 4 can be connected to several wireless base stations 5.

[0019] Fig. Figure 2 schematically illustrates the configuration of the vehicle 2. The vehicle 2 includes a camera 11 for capturing the surroundings of the vehicle 2, a GPS receiver 12, a wireless communication terminal 13, and a data acquisition device 14. The camera 11, the GPS receiver 12, the wireless communication terminal 13, and the data acquisition device 14 are connected so that they can communicate via an in-vehicle network conforming to a standard, such as a controller area network. The vehicle 2 may further include a navigation device (not shown) for searching for a planned route of the vehicle 2 and for navigation so that the vehicle 2 can travel along the planned route.

[0020] The camera 11, which corresponds to an example of an image recording unit, comprises a two-dimensional detector constructed from an array of optoelectronic transducers, such as CCD or C-MOS, with a sensitivity to visible light, and a focusing optical system that focuses an image of a target area onto the two-dimensional detector. The camera 11 is mounted, for example, in the interior of the vehicle 2 such that it is aligned, for example, towards the front of the vehicle 2. The camera 11 records an area in front of the vehicle 2 at every predetermined recording period (e.g., 1 / 30 to 1 / 10 of a second) and generates images of this area. The images obtained by the camera 11 can be color or gray images. The vehicle 2 can comprise several cameras 11 that record images in different orientations or have different focal lengths.

[0021] At each time of image generation, the camera 11 outputs the generated image to the data acquisition device 14 via the in-vehicle network.

[0022] The GPS receiver 12 receives a GPS signal from a GPS satellite at every predetermined time and determines the position of the vehicle 2 based on the received GPS signal. The GPS receiver 12 then outputs position information indicating the result of determining the position of the vehicle 2 based on the GPS signal to the data acquisition device 14 via the in-vehicle network at every predetermined time. The vehicle 2 may include a receiver that conforms to a different satellite positioning system than the GPS receiver 12. In this case, the receiver can determine the position of the vehicle 2.

[0023] The wireless communication terminal 13, which corresponds to an example of a communication unit, is a device for executing a wireless communication process conforming to a predetermined wireless communication standard, and accesses, for example, the wireless base station 5 to connect to the server 3 via the wireless base station 5 and the communication network 4. The wireless communication terminal 13 generates an uplink radio signal including data received from the data acquisition device 14, such as map generating data and position information indicating the position of a spot or road feature represented in the map generating data. The wireless communication terminal 13 transmits the uplink radio signal to the wireless base station 5 to transmit the map generating data, position information, and other data to the server 3.In addition, the wireless communication terminal 13 receives a downlink radio signal from the wireless base station 5 and forwards various types of information from the server 3 included in the radio signal to the data acquisition device 14 or an electronic control unit (ECU) (not shown) that controls the travel of the vehicle 2.

[0024] Fig. Figure 3 illustrates the hardware configuration of the data acquisition device. The data acquisition device 14 generates map-generating data and position information based on images captured by the camera 11. The position information corresponds to an example of information indicating a road section where map-generating data is acquired. To perform its functions, the data acquisition device 14 includes a communication interface 21, a memory 22, and a processor 23.

[0025] The communication interface 21, which is an example of an in-vehicle communication unit, includes an interface circuit for connecting the data acquisition device 14 to the in-vehicle network. In other words, the communication interface 21 is connected to the camera 11, the GPS receiver 12, and the wireless communication terminal 13 via the in-vehicle network. Each time an image is received from the camera 11, the communication interface 21 forwards the received image to the processor 23. Each time position information is received from the GPS receiver 12, the communication interface 21 forwards the received position information to the processor 23. In addition, the communication interface 21 outputs data received from the processor 23, such as map generation data and position information, to the wireless communication terminal 13 via the in-vehicle network.

[0026] The memory 22, which corresponds to one example of a storage unit, includes, for example, volatile and non-volatile semiconductor memories. The memory 22 may further include other memories, such as a hard disk drive. The memory 22 stores various types of data used in a process related to collecting map-generating data, which is executed by the processor 23 of the data acquisition device 14. Such data includes, for example, identification information of the vehicle 2, internal parameters of the camera 11, a set of parameters for specifying a classifier for detecting a road feature from an image, road maps for the navigation system used to identify individual road sections, images received by the camera 11, and position information received by the GPS receiver 12.

[0027] The memory 22 may also store computer programs for various processes executed on the processor 23.

[0028] The processor 23 includes one or more central processing units (CPUs) and peripheral circuitry thereof. The processor 23 may further include other operating circuitry, such as a logic-arithmetic unit, an arithmetic unit, or a graphics processing unit. The processor 23 stores the images received from the camera 11 and the position information received from the GPS receiver 12 in the memory 22. In addition, the processor 23 executes a process related to collecting map-generating data while the vehicle 2 is traveling, to generate map-generating data and position information every predetermined time (e.g., 0.1 to 10 seconds).

[0029] For example, the processor 23 generates map-generating data at every predetermined time based on an image received from the camera 11. For example, the processor 23 uses an image received from the camera 11 itself (hereinafter, an "entire image") as the map-generating data. Alternatively, the processor 23 cuts out a partial image including an area representing a road surface from an entire image received from the camera 11 and uses the cutout partial image as the map-generating data. Information indicating an area to represent a road surface in an entire image may be stored in advance in the memory 22. The processor 23 can refer to this information to identify the area to be cut out from an entire image.

[0030] Alternatively, the processor 23 may input an entire image or a partial image into a classifier to detect a road feature depicted in the input entire image or partial image (hereinafter simply the "input image") and generate information indicating the type of the detected road feature as the map-generating data. As such a classifier, the processor 23 may use, for example, a deep neural network (DNN) trained to detect a road feature depicted in an input image from the input image. For example, a DNN having a convolutional neural network (CNN) architecture, such as a Single-Shot MultiBox Detector (SSD) or a Faster-R CNN, is used as such a DNN.In this case, for each type of road feature to be detected (e.g., a lane dividing line, a pedestrian crossing, and a stop line), the classifier calculates a score that indicates the probability that the road feature is present in a region of the input image. The classifier calculates this score for each of several regions of the input image. The classifier determines that the region where the score for a particular type of road feature is not below a predetermined detection threshold represents that type of road feature. The classifier then outputs information indicating an area in the input image that encompasses the road feature to be detected, for example, a circumscribed rectangle of that road feature (hereinafter, an "object region"), and information indicating the type of road feature represented in the object region.The processor 23 may generate map generating data to include information indicating the type of road feature represented in the detected object area.

[0031] In addition, the processor 23 generates position information indicating the position in real space of a location or road feature represented in the map-generating data. For example, the processor 23 determines that the position of the vehicle 2 upon receiving an image used to generate map-generating data corresponds to the position of the location represented in the map-generating data. To this end, the processor 23 may determine that the position indicated by the position information received from the GPS receiver 12 at the time closest to receiving the image used to generate the map-generating data corresponds to the position of the vehicle 2.Alternatively, when the ECU (not shown) estimates the position of the vehicle 2, the processor 23 may obtain information indicating the estimated position of the vehicle 2 from the ECU via the communication interface 21. Alternatively, when the map-generating data is an entire image or a partial image, the processor 23 may estimate the position in real space corresponding to the center of the entire image or the partial image as the position of the location represented in the map-generating data. In this case, the processor 23 may estimate the position of the location corresponding to the center of the entire image or the partial image based on the orientation or direction of the camera 11, the position and direction of travel of the vehicle 2, and the internal parameters of the camera 11, such as its orientation and angle of view.Alternatively, if the map-generating data includes information indicating the type of road feature captured from an image, the processor 23 estimates the position of the road feature represented in an object region captured from the image based on the orientation of the position corresponding to the object region center with respect to the camera 11, the position and direction of travel of the vehicle 2, and the internal parameters of the camera 11, such as its orientation and angle of view.

[0032] The processor 23 refers to a road map to identify a link, which is a road segment that includes or is closest to the position of a location or road feature depicted in the map-generating data. The processor 23 also includes, in the position information, an identification number of the identified link as information indicating the position of a location or road feature depicted in the map-generating data. Alternatively, the processor 23 may include, in the position information, the latitude and longitude indicating the position of a location or road feature depicted in the map-generating data as information indicating the position of a location or road feature depicted in the map-generating data.As described above, the position information includes information indicating the position of a location or road feature depicted in the map-generating data, and this position is located in or near one of the road segments. Therefore, the position information indicates the road segment from which the map-generating data is acquired.

[0033] The processor 23 can generate two or more types of map-generating data selected from an entire image, a partial image, and information indicating the type of road feature. The processor 23 can change the type of map-generating data to be generated depending on the position of the vehicle 2 during the generation of the map-generating data. In this case, the data acquisition device 14 receives, in advance, type-specific information for specifying the type of map-generating data to be collected for each district or each road section from the server 3 via the wireless base station 5 and stores it in the memory 22. The processor 23 can refer to the type-specific information to identify the type of map-generating data to be generated.If the position of the vehicle 2 is included in a district or road section for which the type-specific information specifies that no map-generating data is collected, the processor 23 does not need to generate any map-generating data. Alternatively, the type of map-generating data to be generated may be changed depending on the road environment around the vehicle 2. For example, the processor 23 may select an entire image as the map-generating data when the vehicle 2 is within a predetermined area of ​​an intersection, and select a partial image or information indicating the type of road feature when the vehicle 2 is outside this predetermined area. In this case, the processor 23 may refer to the position of the vehicle 2 and a road map stored in the memory 22 to determine whether the vehicle 2 is within a predetermined area of ​​an intersection.

[0034] Each time map-generating data and position information are generated, the processor 23 outputs the generated map-generating data and position information to the wireless communication terminal 13 via the communication interface 21. In this way, the map-generating data and position information are transmitted to the server 3.

[0035] The server 3, which corresponds to an example of the device for collecting map-generating data, will be described below. Fig. Figure 4 illustrates the hardware configuration of server 3, which corresponds to an example of the device for collecting map-generating data. Server 3 includes a communication interface 31, a storage device 32, a memory 33, and a processor 34. Communication interface 31, storage device 32, and memory 33 are connected to processor 34 via a signal line. Server 3 may further include an input device, such as a keyboard and a mouse, and a display device, such as a liquid crystal display.

[0036] The communication interface 31, which corresponds to an example of the communication unit, comprises an interface circuit for connecting the server 3 to the communication network 4. The communication interface 31 is configured to communicate with the vehicle 2 via the communication network 4 and the wireless base station 5. In particular, the communication interface 31 forwards map-generating data, position information, and other data received from the vehicle 2 via the wireless base station 5 and the communication network 4 to the processor 34. The communication interface 31 transmits, for example, a notification signal comprising the type-specific information received from the processor 34 to the vehicle 2 via the communication network 4 and the wireless base station 5.Additionally, the communication interface 31 receives, via the communication network 4, information indicating traffic volume for each road section included in a target area for map creation or update from another server (not shown) that manages traffic volume, and forwards the information to the processor 34. The information indicates the traffic volume for each day of the week, each weather condition, each temperature, each season, each location, or each road type.

[0037] The storage device 32, which corresponds to an example of the storage unit, includes, for example, a hard disk drive or an optical recording medium and an access device therefor. The storage device 32 stores various types of data and information used in a process for collecting map-generating data. The storage device 32 stores, for example, target numbers for corresponding road sections included in a target area for generating or updating a map. For each of the road sections included in the target area for generating or updating a map, the storage device 32 further stores the collected pieces of map-generating data, the date and time of acquisition, and position information of each piece of map-generating data, as well as the number of collected pieces of map-generating data.In other words, the storage device 32 stores a history of the number of pieces of map-generating data previously received for each road section. Furthermore, for the target area for generating or updating a map, the storage device 32 stores information indicating the history of traffic volume under each environmental condition (for example, information indicating traffic volume for each day of the week, weather condition, temperature, season, location, or road type). The storage device 32 may further store the type-specific information and an address to which a signal is sent to instruct a predetermined device to collect map-generating data.Storage device 32 may further store road maps for the navigation system used to identify individual road segments, and a computer program executing on processor 34 for executing the process of collecting map-generating data. Storage device 32 may further store a map to be created or updated using the map-generating data.

[0038] Memory 33, which corresponds to another example of the storage unit, includes, for example, non-volatile and volatile semiconductor memories. Memory 33 temporarily stores various types of data generated during the execution of the map generation data collection process and various types of data acquired through communication with vehicle 2.

[0039] The processor 34, which corresponds to an example of a control unit, includes one or more central processing units (CPUs) and peripheral circuitry thereof. The processor 34 may further include other operating circuitry, such as a logic-arithmetic unit or an arithmetic unit. The processor 34 writes data received from another device via the communication network 4 into the storage device 32 or memory 33 and executes the process for collecting the map-generating data.

[0040] Fig. Figure 5 is a functional block diagram of processor 34, which relates to the process for collecting card-generating data. Processor 34 includes a reception processing unit 41, a counting unit 42, an identification unit 43, a prediction unit 44, and an instruction unit 45. These units included in processor 34 are, for example, functional modules implemented by a computer program executing on processor 34, or they may be dedicated operating circuits provided in processor 34.

[0041] The reception processing unit 41 receives map generating data and position information from the vehicle 2 via the communication interface 31 and writes the received map generating data and position information into the storage device 32. The reception processing unit 41 also writes the date and time of receipt of the map generating data and position information (the acquisition date and time) in association with the map generating data into the storage device 32. In this way, a history of the number of pieces of map generating data received in any past period can be obtained for each road section based on the map generating data, the position information, and the acquisition date and time stored in the storage device 32.

[0042] The counting unit 42 counts the number of pieces of map-generating data received in a previous predetermined period (first period) for each of the road sections. The first period may be, for example, one day to one month. The counting unit 42 refers to the date and time of acquisition of each piece of map-generating data stored in the storage device 32 to select pieces of map-generating data included in the first period. The counting unit 42 then refers to the position information of the selected pieces of map-generating data to identify, for each road section, pieces of map-generating data of the position corresponding to the road section, and counts the number of identified pieces of map-generating data for each road section.If the position information includes a road section identification number, the counting unit 42 may identify pieces of map-generating data of the position corresponding to each road section based on this identification number. If the position information includes the latitude and longitude of the position of a place or road feature represented by the map-generating data, the counting unit 42 may refer to a road map to identify the road section located at the position of this latitude and longitude.

[0043] For each road section, the counting unit 42 informs the identification unit 43 and the instruction unit 45 of the number of pieces of map-generating data collected in the first period (this number may be referred to as the “actual number” hereinafter).

[0044] The identification unit 43 identifies one or more of the road sections for which the actual number of pieces of map-generating data collected in the first period does not reach the target number for the road section. The target number may be set for each road section or set to the same value for a target area for generating or updating a map. Alternatively, the target number may be set for each road type (e.g., expressways, national highways, and urban roads).

[0045] For each of the road sections, the identification unit 43 loads the target number for the road section from the storage device 32 and compares the target number with the actual number of pieces of map-generating data collected for the road section. The identification unit 43 then identifies one of the road sections for which the actual number is less than the target number as a road section for which the actual number of collected pieces of map-generating data does not reach the target number for the road section. The identification unit 43 informs the prediction unit 44 of the identification number(s) of the one or more identified road sections.

[0046] The prediction unit 44 calculates, for each of the one or more identified road sections, the number of pieces of map-generating data predicted to be received in a second time period after the first time period (this number may be referred to hereinafter as the "predicted number") based on a history of the number of pieces of map-generating data previously received for the road section or a history of the traffic volume of the road section. The length of the second time period may be the same as or different from that of the first time period.

[0047] For example, the forecasting unit 44 references the history of the number of previously received map-generating data pieces to calculate, for each of the one or more identified road segments, the average of the number of pieces of map-generating data collected for the road segment in a day during the first time period, based on the length of the first time period and the actual number of pieces of map-generating data collected for the road segment. Then, for each of the one or more identified road segments, the forecasting unit 44 multiplies the average of the number of pieces of map-generating data collected for the road segment in a day by the length of the second time period to calculate the forecasted number of pieces of map-generating data to be collected for the road segment.

[0048] Alternatively, the prediction unit 44 may refer to the history of the number of previously received pieces of map-generating data to count, for each of the one or more identified road sections, the number of pieces of map-generating data collected for the road section in the previous year's period corresponding to the second period, and use the counted number as the predicted number of pieces of map-generating data to be collected for the road section. For this purpose, the prediction unit 44 may count the number of pieces of map-generating data collected in the previous year's period corresponding to the second period through the same processing as performed by the counting unit 42.

[0049] Alternatively, the forecasting unit 44 may reference the history of past traffic volume to calculate the predicted number of pieces of map-generating data to be collected for each of the one or more identified road segments. For example, the forecasting unit 44 may calculate the predicted number of pieces of map-generating data to be collected for each of the one or more identified road segments using a forecasting model based on past traffic volume under each environmental condition.In this case, the forecasting unit 44 loads information indicating the traffic volume under each environmental condition from the storage device 32, such as information indicating the traffic volume for each day of the week, each weather condition, each temperature, each season, each location, or each road type, and forecasts the traffic volume under each environmental condition in the second time period for the identified road section. Note that the forecasted traffic volume values ​​under each environmental condition are typical forecasted traffic volume values ​​corresponding to these environmental conditions, and the sum of the forecasted traffic volume values ​​under each environmental condition does not equal the forecasted traffic volume value of the identified road section in the second time period.

[0050] For example, the forecasting unit 44 determines the total of the traffic volume of the respective days of the week included in the second time period as forecast values ​​of the traffic volume with respect to days of the week, and the traffic volume of the season including the second time period as a forecast value of the traffic volume with respect to seasons.The forecasting unit 44 obtains, via the communication network 4 and the communication interface 31, information about the forecast weather and the forecast average temperature in the area including the identified road section from another server that provides weather information, and determines the traffic volume corresponding to this forecast weather as a forecast value of the traffic volume with respect to weather, and the traffic volume corresponding to this forecast average temperature as a forecast value of the traffic volume with respect to temperatures.In addition, the prediction unit 44 refers to the position and the road type of the identified road section, and determines the traffic volume of the location corresponding to the position of the identified road section as a predicted value of the traffic volume with respect to locations, and the traffic volume of the road type corresponding to the identified road section as a predicted value of the traffic volume with respect to road types.

[0051] After determining the predicted values ​​of traffic volume under the respective environmental conditions, the prediction unit 44 calculates the predicted number of pieces of map-generating data to be collected for the identified road section, for example, using a prediction model represented by a regression model such as the following equation. y=∑i=1Mwixi

[0052] Where M is the number of environmental conditions for which individually predicted traffic volume values ​​are calculated; x i (i = 1, 2, ..., M) corresponds to a predicted value of the traffic volume under the environmental condition i; w i (i = 1, 2, ..., M) corresponds to a weighting factor for the environmental condition i; and y corresponds to a predicted number. Using such a prediction model to calculate the predicted number, the prediction unit 44 can correctly predict the number of pieces of map-generating data to be collected in the second time period for the identified road section.

[0053] The prediction unit 44 informs the instruction unit 45 of these predicted numbers of pieces of map-generating data to be collected, which have been determined for the one or more identified road sections.

[0054] For each of the one or more identified road sections, the instruction unit 45 calculates the sum of the actual number of pieces of map-generating data collected in the first time period and the predicted number of pieces of map-generating data to be collected in the second time period, and compares the sum with the target number. For one of the identified road sections for which the sum does not reach the target number, the instruction unit 45 sends an instruction signal to a predetermined device via the communication interface 31 and the communication network 4 to specify instructions for collecting map-generating data for this road section.In this way, the server 3 can facilitate the collection of a target number of pieces of map-generating data for a road section for which the number of collected pieces of map-generating data is expected to not reach the target number even after the second period. The instruction unit 45 does not send an instruction signal for a road section for which the actual number of pieces of map-generating data collected in the first period, or the sum of the actual number and the predicted number in the second period, reaches the target number. This prevents unnecessary data collection costs from being incurred.

[0055] The instruction signal includes, for example, information indicating a road section from which map-generating data is collected (e.g., an identification number of that road section) and information indicating the type of map-generating data to be collected. The instruction signal may further include information indicating the time limit for collecting map-generating data. The predetermined device may be, for example, a survey vehicle (or an ECU mounted thereon) prepared to collect map-generating data, or a management device of a specific company that can have vehicles capable of generating map-generating data travel on identified road sections, such as a taxi company.

[0056] Fig. 6 is a diagram for explaining a target road section for the forecast of the number of collected parts and a target road section for collection instructions. With reference to a road section 601 in a Fig. 6, the actual number 611 of pieces of map-generating data collected in the first time period exceeds a target number. Therefore, for the road section 601, the predicted number of pieces of map-generating data to be collected in the second time period is not calculated, and no signal for specifying instructions for collecting map-generating data is transmitted. In contrast, with respect to a road section 602, the actual number 612 of pieces of map-generating data collected in the first time period does not reach the target number. Therefore, for the road section 602, the predicted number 622 of pieces of map-generating data to be collected in the second time period is calculated. With respect to the road section 602, the sum of the actual number 612 and the predicted number 622 exceeds the target number.Therefore, for road section 602, no signal for specifying instructions for collecting map-generating data is transmitted. With respect to a road section 603, the actual number 613 of pieces of map-generating data collected in the first period does not reach the target number. Thus, for road section 603, the predicted number 623 of pieces of map-generating data to be collected in the second period is also calculated. With respect to road section 603, the sum of the actual number 613 and the predicted number 623 does not reach the target number. Thus, for road section 603, a signal for specifying instructions for collecting map-generating data is transmitted to a predetermined device.

[0057] Fig.Figure 7 is an operational flowchart of the map-generating data collection process. The processor 34 of the server 3 can execute the map-generating data collection process in accordance with the following operational flowchart.

[0058] Upon receiving map-generating data and position information from the vehicle 2 via the wireless base station 5 and the communication network 4, the reception processing unit 41 of the processor 34 stores the map-generating data in association with the road section indicated by the position information and the date and time of reception (acquisition date and time) in the storage device 32 (step S101). The counting unit 42 of the processor 34 determines whether the first time period has elapsed (step S102). If the first time period has not elapsed (No in step S102), the reception processing unit 41 repeats the processing of step S101.

[0059] After the first period of time has elapsed (Yes in step S102), the counting unit 42 counts, for each road section, the actual number of pieces of map-generating data collected in the first period of time (step S103).

[0060] The identification unit 43 of the processor 34 identifies one or more of the road sections for which the actual number does not reach the target number (step S104). The prediction unit 44 of the processor 34 calculates, for each of the one or more identified road sections, the predicted number of pieces of map-generating data to be collected in the preceding or upcoming second time period (step S105).

[0061] The instruction unit 45 of the processor 34 transmits a signal to a predetermined device via the communication network 4 to provide instructions for collecting map-generating data from one of the one or more identified road sections for which the sum of the actual count in the first period and the predicted count in the second period does not reach the target count (step S106). After step S106, the processor 34 terminates the map-generating data collection process.

[0062] As described above, the map-generating data collecting device collects map-generating data for each of road sections included in a target area for generating or updating a map from at least one communication-capable vehicle. For each of the road sections, the device counts the actual number of pieces of map-generating data collected in a first period of time and identifies one of the road sections for which the actual number does not reach a target number. For the identified road section, the device calculates the predicted number of pieces of map-generating data to be collected in a future second period of time.For this reason, the device can predict the number of pieces of map-generating data to be collected in the second period for a road section for which the number of collected pieces of map-generating data has not reached the target number. In addition, the device instructs a predetermined device to collect map-generating data from one or more of the identified road sections for which the sum of the actual number in the first period and the predicted number in the second period does not reach the target number. For this reason, the device can facilitate the collection of a target number of map-generating data of a road section for which the sum of the actual number in the first period and the predicted number in the second period does not reach the target number.

[0063] According to a modified example, the forecasting unit 44 may obtain a forecast value of the traffic volume in the second period based on the traffic volume history under each environmental condition for a road section for which it is determined that the actual number of pieces of map-generating data collected in the first period does not reach the target number. In this case, the server 3 receives the traffic volume under each combination of environmental conditions, for example, the traffic volume for each combination of two or more days of the week, weather conditions, temperatures, seasons, locations, and road types, via the communication network 4 from another server (not shown) that manages the traffic volume, and stores it in the storage device 32.From the traffic volume values ​​under respective combinations of environmental conditions, the forecasting unit 44 determines, for each day included in the second time period, the traffic volume corresponding to the combination of day of the week, season, forecast weather, and forecast average temperature corresponding to that day, and the position and road type of the identified road section, as a forecast value of the traffic volume of the identified road section for that day. The forecasting unit 44 then determines the total of the forecast values ​​of the traffic volume of the identified road section for the respective days included in the second time period as a forecast value of the traffic volume of the identified road section in the second time period.The prediction unit 44 then calculates the predicted number of pieces of map-generating data to be collected in the second period using a prediction model representing the relationship between the predicted value of the traffic volume of the identified road section in the second period and the predicted number of pieces of map-generating data to be received, that is, the predicted number of pieces thereof to be collected.This forecast model is expressed, for example, as a function that defines the relationship between the forecast traffic volume value and the forecast number of pieces of map-generating data to be collected (for example, a linear function or a polynomial such that the larger the forecast traffic volume value, the larger the forecast number of pieces of map-generating data to be collected), and is stored in the memory 22 in advance. Thus, the forecasting unit 44 can load such a forecast model from the memory 22 and use it to forecast the number of pieces of map-generating data to be received in the second time period.

[0064] According to this modified example, the prediction unit 44 can more accurately predict the number of pieces of map-generating data to be collected in the second period.

[0065] According to another modified example, the prediction unit 44 may calculate the predicted number of pieces of map generating data to be collected in the second period for a road section for which the actual number of pieces of map generating data collected in the first period reaches the target number.

[0066] A computer program that causes a computer to execute the functions of the units included in the processor of the device according to the embodiment or the modified examples may be provided in a form recorded on a computer-readable recording medium. The computer-readable recording medium may be, for example, a magnetic recording medium, an optical recording medium, or a semiconductor memory.

[0067] As described above, those skilled in the art can make various modifications according to the embodiments within the scope of the present invention.

Claims

[1] Device for collecting map-generating data, comprising: a communication unit capable of communicating with at least one vehicle; a storage unit; a reception processing unit which, when receiving from the at least one vehicle, via the communication unit, map-generating data representing a road environment around the vehicle together with information indicating a road section on which the map-generating data is obtained, stores the map-generating data in association with the road section and a date and time of reception in the storage unit; a counting unit that counts, for each of the road sections, the number of pieces of map-generating data received in a first period of time; an identification unit that identifies one of the road sections for which the number of pieces of map-generating data received in the first time period does not reach a target number for the one of the road sections; a forecasting unit that forecasts, for the identified road section, the number of pieces of map-generating data to be received in a second time period ahead of the first time period, based on a history of traffic volume under each environmental condition or a history of the number of pieces of map-generating data previously received for the road section, and an instruction unit that instructs a predetermined device via the communication unit to collect the map generating data of the identified road section when the sum of the number of pieces of map generating data received in the first period of time and the number of pieces of map generating data predicted to be received in the second period of time for the road section does not reach the target number for the road section. [2] The apparatus according to claim 1, wherein the instruction unit does not instruct the predetermined apparatus to collect the map generating data of the identified road section when the number of pieces of map generating data received in the first period for the road section or the sum of the number of pieces of map generating data received in the first period and the number of pieces of map generating data predicted to be received in the second period for the road section reaches the target number for the road section. [3] The apparatus according to claim 1 or 2, wherein the prediction unit determines a predicted value of traffic volume under each environmental condition for the identified road section based on the history of traffic volume under each environmental condition, and predicts the number of pieces of map-generating data to be received in the second period using a prediction model representing a relationship between the predicted value of traffic volume under each environmental condition and the number of pieces of map-generating data to be received. [4] The apparatus according to claim 1 or 2, wherein the prediction unit determines a predicted value of the traffic volume in the second period for the identified road section based on the history of the traffic volume under each environmental condition, and predicts the number of pieces of map-generating data to be received in the second period using a prediction model representing a relationship between the predicted value of the traffic volume and the number of pieces of map-generating data to be received. [5] A method for collecting map-generating data, comprising: when map-generating data representing a road environment around the vehicle, together with information indicating a road section on which the map-generating data is obtained, is received from at least one vehicle via a communication unit capable of communicating with the at least one vehicle, storing the map-generating data in association with the road section and a date and time of reception in a storage unit; Counting the number of pieces of map-generating data for each of road segments received in a first period of time; identifying one of the road sections for which the number of pieces of map-generating data received in the first time period does not reach a target number for the one of the road sections; Predicting the number of pieces of map-generating data to be received in a second time period preceding the first time period for the identified road segment based on a history of traffic volume under each environmental condition or a history of the number of pieces of map-generating data previously received for the road segment; and Instructing a predetermined device via the communication unit to collect the map-generating data of the identified road section if the sum of the number of pieces of map-generating data received in the first time period and the number of pieces of map-generating data predicted to be received in the second time period for the road section does not reach the target number for the road section.

Images