Map update device, map update method, and computer program for updating map

Abstract

To provide a map update device capable of improving the accuracy of locations of features represented on a map.SOLUTION: A map update device includes: a data receiving unit 41 that receives, from a vehicle 2 travelling in a predetermined road section via a communication unit 31 capable of communicating with the vehicle 2, regarding at least one feature related to travel of a vehicle existing in the road section, feature data representing the location of the feature; an accuracy measuring unit 42 that measures the positional accuracy of the feature represented by the feature data obtained by the vehicle 2 based on difference between the position of the feature represented by the received feature data and a corresponding reference position of the feature; and a contribution level setting unit 43 that determines whether the positional accuracy satisfies a predetermined accuracy condition, and when the positional accuracy does not satisfy the accuracy condition, sets a contribution level of the feature data received from the vehicle 2 in updating map information representing the position of the feature to be lower than when the positional accuracy satisfies the accuracy condition.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present invention relates to a map updating device, a map updating method, and a computer program for updating a map. [Background technology]

[0002] A highly accurate map that an automatic driving system for a vehicle refers to in order to control the automatic driving of the vehicle is required to accurately represent information about features related to the vehicle's travel that are provided on roads or around the roads.Therefore, a technology has been proposed for collecting data representing features from vehicles that actually travel on roads (for example, see Patent Document 1).

[0003] For example, in the technology disclosed in Patent Document 1, a server device stores an advanced map including feature information on features in a storage unit. The server device receives difference information indicating a difference between the feature information and the actual feature corresponding to the feature information from multiple vehicle-mounted devices equipped with external sensors that measure the features. The server device also transmits a raw data request signal to the vehicle-mounted devices, requesting the transmission of raw data, which is measurement data of the actual feature, according to the reliability calculated based on the multiple difference information. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2017 / 212639 Summary of the Invention [Problem to be solved by the invention]

[0005] In order to record the exact position of a feature on a map based on collected data representing the feature, the vehicle that generates the data representing the feature is required to estimate the position of the feature with high accuracy. However, depending on the vehicle, the accuracy of the location of the feature represented in the data may be reduced, or the accuracy of the location of the feature represented in the data may differ from vehicle to vehicle. If collected data with low accuracy of the location of the feature is used to update the map, the accuracy of the location of the feature represented on the map may also be reduced.

[0006] Therefore, an object of the present invention is to provide a map updating device capable of improving the accuracy of the positions of features shown on a map. [Means for solving the problem]

[0007] According to one embodiment, there is provided a map updating device comprising: a data receiving unit that receives, from a vehicle traveling on a predetermined road section, feature data representing a position of at least one feature that is present on the road section and is related to the traveling of the vehicle, via a communication unit capable of communicating with the vehicle, an accuracy measuring unit that measures a position accuracy of the feature represented in the feature data obtained by the vehicle based on a difference between a position of the feature represented in each of the received feature data and a reference position of the corresponding feature, and a contribution setting unit that determines whether the position accuracy satisfies a predetermined accuracy condition and, if the position accuracy does not satisfy the accuracy condition, sets a contribution degree of the feature data received from the vehicle in updating of map information representing the position of the feature to be lower than when the position accuracy satisfies the accuracy condition.

[0008] In this map updating device, it is preferable that the accuracy measurement unit measures the position accuracy of the feature for each vehicle type based on the difference between the position of the feature represented in each of the feature data received from multiple vehicles belonging to that type and the reference position of the corresponding feature, and the contribution setting unit sets the contribution level for each vehicle type based on the position accuracy of the feature for each vehicle type.

[0009] In addition, in this map updating device, it is preferable that the feature data further includes information describing the environment around the vehicle at the time the feature data was generated, the accuracy measurement unit measures the position accuracy of the vehicle according to the environment, and the contribution degree setting unit sets a contribution degree according to the environment based on the position accuracy of the vehicle according to the environment.

[0010] Furthermore, it is preferable that the map updating device further has a correction information setting unit that sets correction information for correcting the positions of features represented in the feature data obtained by the vehicle so as to reduce the difference between the positions of the features represented in each of the received feature data and the reference positions of the corresponding features.

[0011] According to another aspect, there is provided a map updating method, which includes receiving, from a vehicle traveling on a predetermined road section, feature data representing a position of at least one feature that is present on the road section and is related to the traveling of the vehicle, via a communication unit capable of communicating with the vehicle, measuring a position accuracy of the feature represented in the feature data obtained by the vehicle based on a difference between a position of the feature represented in each of the received feature data and a reference position of the corresponding feature, determining whether the position accuracy satisfies a predetermined accuracy condition, and if the position accuracy does not satisfy the accuracy condition, setting a contribution rate of the feature data received from the vehicle in updating of map information representing the position of the feature to be lower than a case in which the position accuracy satisfies the accuracy condition.

[0012] According to yet another aspect, there is provided a computer program for updating a map, the computer program including instructions for causing a computer to execute the following: receive, from a vehicle traveling on a predetermined road section, feature data representing a position of at least one feature that is present on the road section and is related to the traveling of the vehicle, via a communication unit capable of communicating with the vehicle, measure a position accuracy of the feature represented in the feature data obtained by the vehicle based on a difference between a position of the feature represented in each of the received feature data and a reference position of the corresponding feature, determine whether the position accuracy satisfies a predetermined accuracy condition, and, if the position accuracy does not satisfy the accuracy condition, set a contribution rate of the feature data received from the vehicle in updating map information representing the position of the feature to be lower than when the position accuracy satisfies the accuracy condition. Effect of the Invention

[0013] The map updating device according to the present invention has an effect of improving the accuracy of the positions of features shown on a map. [Brief description of the drawings]

[0014] [Figure 1] 1 is a schematic configuration diagram of a map updating system in which a map updating device is implemented. [Diagram 2] FIG. 1 is a schematic configuration diagram of a vehicle. [Diagram 3] FIG. 2 is a hardware configuration diagram of a data acquisition device. [Figure 4] FIG. 2 is a hardware configuration diagram of a server that is an example of a map updating device. [Diagram 5] FIG. 4 is a functional block diagram of a processor of a server for a map update process. [Figure 6] 1A is a diagram showing an example of the relationship between the positions of features represented in feature data obtained by a vehicle with relatively high position accuracy of feature data and the positions of the corresponding reference features, and FIG. 1B is a diagram showing an example of the relationship between the positions of features represented in feature data obtained by a vehicle with relatively low position accuracy of feature data and the positions of the corresponding reference features. [Figure 7]13 is an operation flowchart of a map update process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] A map updating device, a map updating method executed by the map updating device, and a computer program for updating the map will be described below with reference to the drawings. The map updating device collects data representing features related to the travel of the vehicles (hereinafter referred to as feature data) from multiple vehicles with which communication is possible, for an area shown on a map to be generated or updated.

[0016] The feature data includes information that indicates the position of the feature represented in the data. In order to estimate the position of the feature, parameter information of the camera, such as the installation height of the on-board camera for photographing the feature and the photographing direction, is used. The parameter information of the camera is stored in the memory of the vehicle for each vehicle, for example, at the time of shipment from the factory. However, the installation height, etc., may change due to tire replacement of the vehicle, deterioration of the suspension over time, etc. If the parameter information is not updated despite such a change, the estimation accuracy of the feature's position will decrease. The same applies when the parameter information of the camera is set incorrectly. Therefore, in order to improve the accuracy of the position of the feature represented on the map, it is necessary to evaluate the estimation accuracy of the feature's position for each vehicle.

[0017] Therefore, this map updating device collects feature data including estimated positions of features present in a specific road section from each vehicle traveling in the road section where the positions of the features are previously determined with high accuracy. This map updating device calculates, for each vehicle, the difference between the estimated position of the feature represented in each of the feature data and the position (hereinafter referred to as the reference position) of the corresponding feature among the features whose positions are previously stored (hereinafter referred to as the reference feature). Based on the difference, this map updating device measures the position accuracy of the feature represented in the feature data obtained by the vehicle and determines whether the position accuracy satisfies a predetermined accuracy condition. Then, for a vehicle whose position accuracy does not satisfy the accuracy condition, this map updating device lowers the contribution degree of the feature data received from that vehicle in updating the map information compared to the contribution degree of the feature data received from a vehicle whose position accuracy satisfies the accuracy condition.

[0018] The features to be detected include, for example, various road signs, various road markings, traffic lights, and other features related to vehicle travel.

[0019] FIG. 1 is a schematic configuration diagram of a map updating system in which a map updating device is implemented. In this embodiment, the map updating system 1 has a plurality of vehicles 2 and a server 3 which is an example of a map updating device. Each vehicle 2 is connected to the server 3 via the wireless base station 5 and the communication network 4 by, for example, accessing the wireless base station 5 which is connected to the communication network 4 to which the server 3 is connected via a gateway (not shown). Note that, for simplification, only one vehicle 2 is illustrated in FIG. 1. Similarly, although only one wireless base station 5 is illustrated in FIG. 1, a plurality of wireless base stations 5 may be connected to the communication network 4. In addition, the server 3 may be communicably connected to a traffic information server (not shown) which manages traffic information via the communication network.

[0020] In this embodiment, with respect to collecting feature data, each vehicle 2 has the same configuration and function, so one vehicle 2 will be described below.

[0021] 2 is a schematic diagram of the vehicle 2. The vehicle 2 has a camera 11, 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 communicatively connected via an in-vehicle network conforming to a standard such as a controller area network. The vehicle 2 may further have a navigation device (not shown) that searches for a planned travel route of the vehicle 2 and navigates the vehicle 2 so that the vehicle 2 travels along the planned travel route.

[0022] The camera 11 is an example of an imaging unit for capturing images of the surroundings of the vehicle 2, and includes a two-dimensional detector configured with an array of photoelectric conversion elements sensitive to visible light, such as a CCD or C-MOS, and an imaging optical system for forming an image of an area to be captured on the two-dimensional detector. The camera 11 is attached, for example, inside the vehicle cabin of the vehicle 2 so as to face the front of the vehicle 2. The camera 11 captures an image of the area in front of the vehicle 2 at a predetermined capture period (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 11 may be a color image or a gray image. Note that the vehicle 2 may be provided with a plurality of cameras 11 with different capture directions or focal lengths.

[0023] Each time the camera 11 generates an image, it outputs the generated image to the data acquisition device 14 via the in-vehicle network.

[0024] The GPS receiver 12 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 12 outputs positioning information indicating the positioning result of the own position of the vehicle 2 based on the GPS signals to the data acquisition device 14 via the in-vehicle network at predetermined intervals. Note that the vehicle 2 may have a receiver that complies with a satellite positioning system other than the GPS receiver 12. In this case, it is sufficient that the receiver determines the own position of the vehicle 2.

[0025] The wireless communication terminal 13 is an example of a communication unit, and is a device that executes wireless communication processing conforming to a predetermined wireless communication standard. For example, by accessing the wireless base station 5, the wireless communication terminal 13 is connected to the server 3 via the wireless base station 5 and the communication network 4. The wireless communication terminal 13 generates an uplink wireless signal including feature data and the like received from the data acquisition device 14. The wireless communication terminal 13 transmits the uplink wireless signal to the wireless base station 5 to transmit the feature data and the like to the server 3. The wireless communication terminal 13 also receives a downlink wireless signal from the wireless base station 5, and passes on collection instructions and the like from the server 3, which are included in the wireless signal, to the data acquisition device 14 or an electronic control unit (ECU, not shown) that controls the running of the vehicle 2.

[0026] 3 is a hardware configuration diagram of the data acquisition device. The data acquisition device 14 generates feature data based on the image generated by the camera 11. Furthermore, the data acquisition device 14 generates driving information of the vehicle 2. To this end, the data acquisition device 14 has a communication interface 21, a memory 22, and a processor 23.

[0027] The communication interface 21 is an example of an in-vehicle communication unit, and has an interface circuit for connecting the data acquisition device 14 to the in-vehicle network. That is, 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. Then, every time the communication interface 21 receives an image from the camera 11, it passes the received image to the processor 23. Also, every time the communication interface 21 receives positioning information from the GPS receiver 12, it passes the received positioning information to the processor 23. Furthermore, the communication interface 21 outputs the feature data received from the processor 23 to the wireless communication terminal 13 via the in-vehicle network.

[0028] The memory 22 includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 22 may further include other storage devices such as a hard disk device. The memory 22 stores various data used in the process related to the generation of feature data executed by the processor 23 of the data acquisition device 14. Such data includes, for example, a road map, identification information of the vehicle 2, parameters of the camera 11 such as the installation height of the camera 11, the shooting direction and the angle of view, and a parameter set for identifying a classifier for detecting features from an image. The road map may be, for example, a map used in a navigation device, and has information such as the position and length of each road section included in the area shown on the road map, and the connection relationship between the road sections at each intersection. The memory 22 may also store the image received from the camera 11 and the positioning information received from the GPS receiver 12 for a certain period of time. The memory 22 also stores information indicating an area to be the target of the generation and collection of feature data (hereinafter, sometimes referred to as the collection target area) designated in the collection instruction of the feature data. Furthermore, the memory 22 may store computer programs for implementing each process executed by the processor 23, etc.

[0029] The processor 23 has one or more CPUs (Central Processing Units) and their peripheral circuits. The processor 23 may further have other arithmetic circuits such as a logic arithmetic unit, a numerical arithmetic unit, or a graphic processing unit. The processor 23 stores images received from the camera 11 and positioning information received from the GPS receiver 12 in the memory 22. Furthermore, the processor 23 executes processes related to the generation of feature data at predetermined intervals (for example, every 0.1 to 10 seconds) while the vehicle 2 is traveling.

[0030] As a process related to the generation of feature data, the processor 23 determines whether or not the vehicle position of the vehicle 2 represented by the positioning information received from the GPS receiver 12 is included in the collection target area. If the vehicle position is included in the collection target area, the processor 23 generates feature data based on the image received from the camera 11.

[0031] For example, the processor 23 detects features shown in the input image (hereinafter, sometimes simply referred to as an input image) by inputting the image received from the camera 11 to a classifier that has been trained in advance to detect features to be detected. The processor 23 then generates information representing the type of the detected features as feature data. As such a classifier, the processor 23 can use, for example, a deep neural network (DNN) that has been trained in advance to detect features shown in the input image from the input image. As such a DNN, for example, a DNN having a convolutional neural network (CNN) type architecture such as Single Shot MultiBox Detector (SSD) or Faster R-CNN is used. In this case, the classifier calculates a certainty that represents the likelihood that a feature to be detected is shown in various regions on the input image for each type of feature (for example, a lane marking, a pedestrian crossing, a stop line, etc.). The classifier determines that a feature of a certain type is shown in a region where the certainty for that type of feature is equal to or greater than a predetermined detection threshold. The classifier outputs information representing an area in the input image that contains the feature to be detected (for example, a circumscribing rectangle of the feature to be detected, hereinafter referred to as an object area) and information representing the type of feature represented in the object area. Therefore, the processor 23 may generate feature data so as to include information representing the type of feature represented in the detected object area.

[0032] Furthermore, the processor 23 identifies the position of the feature represented in the feature data in the real space, and includes information representing the position in the feature data. Here, the position of each pixel on the image corresponds one-to-one to the direction from the camera 11 to the object represented in that pixel. Therefore, the processor 23 estimates the position of the feature represented in the object region based on the direction from the camera 11 corresponding to the center of gravity of the object region on the image, the vehicle position of the vehicle 2 when the image used to generate the feature data was generated, the traveling direction, and the parameters of the camera 11. At that time, the processor 23 can set the position represented by the positioning information received from the GPS receiver 12 at the timing closest to the generation of the image used to generate the feature data as the vehicle position of the vehicle 2. Alternatively, when an ECU (not shown) estimates the vehicle position of the vehicle 2, the processor 23 may obtain information representing the estimated vehicle position of the vehicle 2 from the ECU via the communication interface 21. Furthermore, the processor 23 may obtain information representing the traveling direction of the vehicle 2 from the ECU (not shown). Alternatively, the processor 23 may estimate the position of the feature represented in the feature data by so-called Structure from Motion (SfM). In this case, the processor 23 associates object regions in which the same feature is represented between two images obtained at different times using optical flow. The processor 23 can then estimate the position of the feature by triangulation based on the position and traveling direction of the vehicle 2 when each of the two images was obtained, the parameters of the camera 11, and the position of the object region in each image.

[0033] The processor 23 includes the latitude and longitude representing the position of the feature represented in the feature data in the feature data as information representing the position of the feature represented in the feature data. Furthermore, the processor 23 refers to the road map to identify a link that is a road section that includes the position of the feature represented in the feature data or is closest to that position. The processor 23 then includes an identification number of the identified link in the feature data.

[0034] The processor 23 may further include the identification information of the vehicle 2 in the feature data. The processor 23 may also include information used to estimate the position of the feature, such as the parameters of the camera 11 and the position of the feature on the image, in the feature data. The processor 23 may also include the position of the vehicle 2 at the time of generating the feature data, the traveling direction, and the reception strength of the GPS signal used to measure the vehicle position of the vehicle 2, which were used when estimating the position of the feature, in the feature data. The processor 23 may also include the image itself generated by the camera 11, or a partial image obtained by cutting out an area showing the road surface from the image, in the feature data. Then, every time the processor 23 generates feature data, it outputs the generated feature data to the wireless communication terminal 13 via the communication interface 21. As a result, the feature data is transmitted to the server 3. The processor 23 may transmit information used to estimate the position of the feature together with the identification information of the vehicle 2 to the server 3 via the wireless communication terminal 13, separately from the feature data.

[0035] Next, the server 3, which is an example of a map updating device, will be described. 4 is a hardware configuration diagram of a server 3 which is an example of a map updating device. The server 3 has a communication interface 31, a storage device 32, a memory 33, and a processor 34. The communication interface 31, the storage device 32, and the memory 33 are connected to the processor 34 via signal lines. The server 3 may further have input devices such as a keyboard and a mouse, and a display device such as a liquid crystal display.

[0036] The communication interface 31 is an example of a communication unit, and has an interface circuit for connecting the server 3 to the communication network 4. The communication interface 31 is configured to be able to communicate with the vehicle 2 via the communication network 4 and the wireless base station 5. That is, the communication interface 31 passes the feature 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 also transmits the collection instruction received from the processor 34 to the vehicle 2 via the communication network 4 and the wireless base station 5.

[0037] The storage device 32 is an example of a storage unit, and includes, for example, a hard disk device or an optical recording medium and an access device therefor. The storage device 32 stores various data and information used in the map data collection process. For example, the storage device 32 stores the map to be updated and the reference positions of one or more reference features of a predetermined road section that serve as a reference when estimating the position accuracy of the features of each vehicle 2. The predetermined road section and the reference positions will be described in detail later. Furthermore, the storage device 32 stores identification information of each vehicle 2 and feature data received from each vehicle 2. Furthermore, the storage device 32 may store information used to estimate the position of the features in each vehicle 2. Furthermore, the storage device 32 may store a computer program for executing the map update process, which is executed on the processor 34.

[0038] The memory 33 is another example of a storage unit, and includes, for example, a non-volatile semiconductor memory and a volatile semiconductor memory. The memory 33 temporarily stores various data generated during the execution of the map update process.

[0039] The processor 34 is an example of a control unit and includes one or more central processing units (CPUs) and their peripheral circuits. The processor 34 may further include other arithmetic circuits such as a logic arithmetic unit or a numerical arithmetic unit. The processor 34 executes a map update process.

[0040] 5 is a functional block diagram of the processor 34 related to the map update process. The processor 34 has a data receiving unit 41, an accuracy measuring unit 42, a contribution setting unit 43, a correction information setting unit 44, and a map update unit 45. Each of these units in the processor 34 is a functional module realized by, for example, a computer program running on the processor 34. Alternatively, each of these units in the processor 34 may be a dedicated arithmetic circuit provided in the processor 34.

[0041] The data receiving unit 41 receives feature data representing each feature present in a specific road section from a vehicle 2 traveling in that road section among the vehicles 2 via the wireless base station 5, the communication network 4, and the communication interface 31. The data receiving unit 41 then stores the received feature data in the memory 33 or the storage device 32. Note that, in order to determine whether the feature data represents a feature of the specific road section, the data receiving unit 41 may refer to the identification number of the link of the road section contained in the feature data. Then, when the identification number of the link contained in the feature data matches the identification number of the link corresponding to the specific road section, the data receiving unit 41 may determine that the feature data is feature data representing a feature of the specific road section.

[0042] As described above, the feature data may include the image itself or a partial image generated by the camera 11. In this case, the data receiving unit 41 may detect the position of the feature by performing the same process on the image or partial image as the process performed by the processor 23 of the data acquisition device 14 to detect the position of the feature.

[0043] The accuracy measurement unit 42 calculates, for each individual vehicle 2, the difference between the position of the feature represented in each piece of feature data for a specific road section received from that vehicle 2 and the corresponding reference position of the reference feature stored in the server 3. Then, the accuracy measurement unit 42 measures the position accuracy of the feature represented in the feature data obtained by that vehicle 2, based on the difference in position for the feature represented in each piece of feature data.

[0044] In this embodiment, the predetermined road section may be a road section in which the position of each feature in the road section is determined with high accuracy. For example, the predetermined road section may be a road section on a motorway in which the position of each feature shown on the map is confirmed to be highly accurate, such as a road section in which it is confirmed that no road construction has been carried out since the last map update. In addition, when the position of each feature on the map is represented by a probability distribution of the reliability of the position, the predetermined road section may be a section in which the spread of the probability distribution for each feature is equal to or smaller than a certain value, and the positioning accuracy by satellite positioning is equal to or larger than a predetermined accuracy threshold. The spread of the probability distribution is represented, for example, by a variance value in a predetermined direction (for example, the extension direction of the road section and a direction perpendicular to the extension direction).

[0045] The accuracy measurement unit 42 regards, for each feature data of a predetermined road section received from the vehicle 2 of interest, a reference feature that is the same type as the feature represented by the feature data and is closest to the position of the feature as a reference feature corresponding to the feature represented by the feature data. Then, for each feature data of a predetermined road section received from the vehicle 2 of interest, the accuracy measurement unit 42 calculates, for each feature represented in the feature data, a distance and a direction from the reference position of the corresponding reference feature to the position of the feature. The accuracy measurement unit 42 calculates the average value of the absolute values ​​of the distances calculated for each feature data, or the root mean square of the distances calculated for each feature data, as an accuracy index representing the position accuracy of the feature data by the vehicle 2 of interest. Note that, when the position of each feature is represented by a probability distribution of the reliability of the position, the distance from the reference position to the position of the feature represented in the feature data may be represented by the Mahalanobis distance. Furthermore, for each piece of feature data, the accuracy measurement unit 42 calculates the angle (hereinafter referred to as the angular error) between the traveling direction of the vehicle 2 at the time that the feature data was generated and the direction from the reference position of the reference feature to the position of the feature represented in that feature data. Then, the accuracy measurement unit 42 sets the angular error and distance calculated for each piece of feature data as a correction index used to correct the position of the feature for the vehicle 2 of interest. By executing the above processing for each vehicle 2, the accuracy measurement unit 42 can calculate the accuracy index and correction index for each vehicle 2.

[0046] Fig. 6(a) is a diagram showing an example of the relationship between the position of a feature represented in feature data obtained by a vehicle 2 with a relatively high positional accuracy of the feature data, and the position of the corresponding reference feature. On the other hand, Fig. 6(b) is a diagram showing an example of the relationship between the position of a feature represented in feature data obtained by a vehicle 2 with a relatively low positional accuracy of the feature data, and the position of the corresponding reference feature. In Figs. 6(a) and 6(b), the road markings indicated by dashed lines are the reference features.

[0047] As shown in Fig. 6(a), when the positional accuracy of the feature data is relatively high, the position of the corresponding feature 602 represented in the feature data is sufficiently close to the reference position of the reference feature 601. In contrast, as shown in Fig. 6(b), when the positional accuracy of the feature data is relatively low, the distance between the reference position of the reference feature 601 and the position of the corresponding feature 602 represented in the feature data becomes large.

[0048] The accuracy measurement unit 42 notifies the contribution degree setting unit 43 of the accuracy index calculated for each vehicle 2. In addition, the accuracy measurement unit 42 notifies the correction information setting unit 44 of the accuracy index and correction index calculated for each vehicle 2.

[0049] The contribution degree setting unit 43 sets, for each vehicle 2, the contribution degree of the feature data received from that vehicle 2 in updating the map based on the accuracy index received from the accuracy measurement unit 42. In this embodiment, for each vehicle 2, when the position accuracy of the feature included in the feature data, represented by the accuracy index, does not satisfy the accuracy condition, the contribution degree of the feature data received from that vehicle 2 is set to be lower than the contribution degree of the feature data received from that vehicle 2 when the position accuracy satisfies the accuracy condition. Therefore, the contribution degree of the feature data received from a vehicle whose position accuracy satisfies the accuracy condition is higher than the contribution degree of the feature data received from another vehicle whose position accuracy does not satisfy the accuracy condition. As a result, the position of the feature represented in the feature data received from the vehicle whose position accuracy satisfies the accuracy condition is reflected by the map, and the accuracy of the position of the feature represented on the map is improved.

[0050] The accuracy condition is set, for example, so that the error in the position of a feature shown on a map updated using feature data whose position accuracy satisfies the accuracy condition is within an allowable range for automatic driving control of a vehicle. As described above, when the accuracy index is expressed as the average value of the absolute value of the distance between a feature shown in each feature data and a corresponding reference feature or the mean square of that distance, the accuracy condition is set so that the value of the accuracy index is equal to or less than the allowable error in the position of the feature (for example, 10 cm to several tens of cm) or a value equivalent to the square of that error. In addition, when the position of each feature on a map is expressed by a probability distribution of the reliability of the position, the accuracy condition may be set so that the value of the accuracy index is equal to or less than a predetermined distance threshold value expressed by the Mahalanobis distance.

[0051] The contribution degree setting unit 43 sets a first contribution degree (for example, 1.0) for vehicles 2 whose position accuracy of the feature data satisfies the accuracy condition among the vehicles 2. On the other hand, the contribution degree setting unit 43 sets a second contribution degree (for example, 0.0 to 0.5) lower than the first contribution degree for vehicles 2 whose position accuracy of the feature data does not satisfy the accuracy condition among the vehicles 2. The contribution degree setting unit 43 may lower the second contribution degree as the deviation between the accuracy index value and the accuracy condition increases.

[0052] The contribution degree setting unit 43 notifies the map update unit 45 of the contribution degree set for each vehicle 2 .

[0053] The correction information setting unit 44 sets correction information for correcting the positions of features in the feature data received from each vehicle 2 for a vehicle 2 whose position accuracy does not satisfy the accuracy condition.

[0054] The positional accuracy of the feature data depends on the accuracy of the parameters used to estimate the position of the feature represented in the feature data. In this embodiment, the position of the feature in the real space is estimated based on the position of the feature on the image generated by the camera 11 mounted on the vehicle 2 and the vehicle position of the vehicle 2. Therefore, parameters such as the shooting direction and installation height of the camera 11, and the strength of the GPS signal affect the positional accuracy of the feature data. In particular, the more the parameter values ​​of the camera 11 stored in the data acquisition device 14 of the vehicle 2 deviate from the actual values, the lower the positional accuracy of the feature data. For example, as described above, the installation height of the camera 11 changes due to tire replacement of the vehicle 2, deterioration of the suspension over time, etc., and the like, the parameter values ​​of the camera 11 stored in the data acquisition device 14 may deviate from the actual values.

[0055] If the parameter values, such as the shooting direction or installation height of the camera 11, deviate from the actual values, the position of the feature represented in the feature data will deviate from the actual position by the direction and distance caused by the deviation. Therefore, the correction information setting unit 44 sets the correction information so as to reduce the difference between the position of the feature represented in the feature data for a specific road section and the reference position of the corresponding reference feature. In this example, the correction information setting unit 44 calculates the average value of the angle error and the average value of the distance for each feature data, which are represented in the correction index. Then, the correction information setting unit 44 sets the angle and the average value of the distance in the opposite direction to the average value of the angle error with respect to the traveling direction of the vehicle 2, in the correction information.

[0056] The correction information setting unit 44 notifies the map update unit 45 of the correction information that has been set for the vehicle 2 whose position accuracy does not satisfy the accuracy condition.

[0057] The map update unit 45 generates or updates the map read from the storage device 32 based on the feature data collected from each vehicle 2. For example, the map update unit 45 selects features of the same type located within a predetermined range from among the features represented in each feature data, as feature data representing the same feature. When the position of each feature is represented by a probability distribution of the reliability of the position, the predetermined range may be represented by the Mahalanobis distance. Then, the map update unit 45 specifies the position of the feature by weighting the position of the feature included in each feature data representing the same feature by the contribution degree set for the vehicle 2 that generated the feature data. Then, the map update unit 45 generates or updates the map by including, for each feature whose position has been specified, information representing the type of the feature and the specified position in the map.

[0058] Furthermore, for feature data received from a vehicle 2 whose position accuracy does not satisfy the accuracy condition, the map update unit 45 may correct the position of the feature by using correction information set for that vehicle 2, and then use the corrected position for the above-mentioned weighted averaging. Specifically, the map update unit 45 corrects the position of the feature by moving the position of the feature included in the feature data by the direction and distance indicated by the correction information relative to the traveling direction of the vehicle 2 included in the feature data.

[0059] 7 is an operational flowchart of the map update process in the server 3. The processor 34 of the server 3 may execute the map update process at predetermined intervals in accordance with the operational flowchart shown below.

[0060] The data receiving unit 41 of the processor 34 receives feature data for a predetermined road section from each vehicle 2 and stores the feature data in the storage device 32 (step S101). In addition, the accuracy measuring unit 42 of the processor 34 measures the accuracy of the position of the feature represented in the feature data for each of the individual vehicles 2, based on the difference between the position of the feature represented in each piece of received feature data and the reference position of the corresponding reference feature (step S102).

[0061] The contribution setting unit 43 of the processor 23 sets the contribution of each vehicle 2 so that the contribution of feature data received from a vehicle 2 whose feature position accuracy does not satisfy the accuracy condition is lower than the contribution of feature data received from a vehicle 2 whose position accuracy satisfies the accuracy condition (step S103). Furthermore, the correction information setting unit 44 of the processor 23 sets correction information for a vehicle 2 whose position accuracy does not satisfy the accuracy condition so that the difference between the position of the feature represented in each of the feature data of a predetermined road section and the reference position of the corresponding reference feature is reduced (step S104).

[0062] The map update unit 45 of the processor 23 identifies the position of the feature represented in the feature data received from each vehicle 2 using the correction information set for the vehicle 2 whose contribution degree and position accuracy do not satisfy the accuracy condition (step S105). The map update unit 45 then generates or updates the map by including the identified position and type of the feature in the map (step S106). After that, the processor 34 ends the map update process.

[0063] As described above, the map updating device collects feature data including estimated positions of features present in a specific road section from each vehicle traveling in the specific road section for which the reference position of the feature is required. The map updating device measures the position accuracy of the feature represented in the feature data obtained by each vehicle based on the difference between the estimated position of the feature represented in each feature data and the reference position of the corresponding feature, and determines whether the position accuracy satisfies a specific accuracy condition. For a vehicle whose position accuracy does not satisfy the accuracy condition, the map updating device reduces the contribution of feature data received from the vehicle in updating the map information to a level lower than the contribution of feature data received from a vehicle whose position accuracy satisfies the accuracy condition. In this way, the map updating device reduces the contribution of feature data received from a vehicle whose feature position accuracy is low to the map to be generated or updated, thereby improving the accuracy of the positions of the features represented on the map.

[0064] It is assumed that, among the multiple vehicles 2, cameras of the same type are attached to two or more vehicles of the same vehicle model so as to have the same shooting direction and the same installation position. Thus, according to a modified example, the parameters of the camera 11 may be set for each vehicle model, not for each vehicle. In this case, the data acquisition device 14 of each vehicle 2 may include identification information of the vehicle model of the vehicle 2 in the feature data. Alternatively, the storage device 32 of the server 3 may store, for each vehicle 2, the identification information of the vehicle model of the vehicle 2 together with the identification information of the vehicle 2.

[0065] In this case, the accuracy measurement unit 42 may measure the position accuracy for each vehicle type by performing the same process as in the above embodiment on feature data of a specific road section received from multiple vehicles belonging to that vehicle type. The contribution degree setting unit 43 may also set the contribution degree for each vehicle type by performing the same process as in the above embodiment. Furthermore, the correction information setting unit 44 may also set correction information for a vehicle type whose position accuracy does not satisfy the accuracy condition by performing the same process as in the above embodiment.

[0066] According to this modification, the map updating device sets the contribution degree and the correction information for each vehicle model, rather than for each individual vehicle, and therefore it is possible to facilitate management of the contribution degree and the correction information.

[0067] In addition, the environmental conditions around the vehicle 2 when the feature data is generated may affect the position accuracy of the feature. For example, when the reception strength of the GPS signal decreases due to the environment around the vehicle 2, the estimation accuracy of the vehicle's own position decreases, and as a result, the position accuracy of the feature also decreases. Therefore, in the above embodiment or modification, the data acquisition device 14 provided in each vehicle 2 may include information (weather, temperature, etc.) representing the environment around the vehicle 2 when the feature data was generated in the feature data. In this case, the data acquisition device 14 may acquire information representing the environment around the vehicle 2 based on, for example, a sensor signal from a sensor such as a temperature sensor provided in the vehicle 2, or weather information around the current position of the vehicle 2 received via the wireless communication terminal 13. Then, the accuracy measurement unit 42 of the map update device may measure the position accuracy according to the environment for each vehicle 2 by performing the same process as in the above embodiment on the feature data of a predetermined road section received from the vehicle for each identical environmental condition. The contribution degree setting unit 43 may also set a contribution degree corresponding to the environment for each vehicle 2 by executing the same process as in the above embodiment for each environmental condition for that vehicle. Furthermore, the correction information setting unit 44 may also set correction information corresponding to the environment for that vehicle by executing the same process as in the above embodiment for a vehicle and environmental condition whose position accuracy does not satisfy the accuracy condition.

[0068] According to this variant, the map updating device sets the contribution degree and correction information taking into account not only the camera parameters of each vehicle but also the environmental conditions, thereby further improving the accuracy of the positions of features shown on the map.

[0069] In the above embodiment or modified example, the processing of either the contribution degree setting unit 43 or the correction information setting unit 44 may be omitted. When the processing of the contribution degree setting unit 43 is omitted, the same contribution degree may be set for each vehicle, each vehicle type, or each environmental condition, regardless of the position accuracy of the feature. Even in this case, the position of the feature is corrected using the correction information for feature data obtained from a vehicle or the like whose position accuracy does not satisfy the accuracy standard, so that the map updating device can improve the accuracy of the position of the feature shown on the map. Also, even when the processing of the correction information setting unit 44 is omitted, the contribution degree of feature data obtained from a vehicle or the like whose position accuracy does not satisfy the accuracy standard is set relatively low, so that the map updating device can improve the accuracy of the position of the feature shown on the map.

[0070] Furthermore, a computer program that causes a computer to realize the functions of each unit of the processor of the map updating device according to each of the above embodiments or modifications may be provided in a form stored in a computer-readable recording medium. Note that the computer-readable recording medium may be, for example, a magnetic recording medium, an optical recording medium, or a semiconductor memory.

[0071] 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]

[0072] 1 Map Update System 2 Vehicles 11 Camera 12 GPS receiver 13 Wireless communication terminals 14 Data acquisition device 21 Communication Interface 22 Memory 23 Processors 3 Server 31 Communication Interface 32 Storage Device 33 Memory 34 processors 41 Data receiving section 42 Accuracy Measurement Section 43 Contribution setting section 44 Correction information setting section 45 Map Update Division 4. Communication Network 5. Radio base station

Claims

1. a data receiving unit that receives, from a vehicle traveling on a predetermined road section, feature data that indicates a position of each feature that is present on the road section and is related to the traveling of the vehicle, via a communication unit that is capable of communicating with the vehicle; an accuracy measurement unit that measures the position accuracy of the feature represented in the feature data obtained by the vehicle based on a difference between a position of the feature represented in each of the received feature data and a reference position of the corresponding feature; a contribution degree setting unit that determines whether or not the position accuracy satisfies a predetermined accuracy condition, and when the accuracy condition is not satisfied, sets a contribution degree of the feature data received from the vehicle in updating map information representing the position of the feature to be lower than when the accuracy condition is satisfied; having the accuracy measurement unit measures, for each vehicle type, the position accuracy of the feature based on a difference between the position of the feature represented in each of the feature data received from a plurality of the vehicles belonging to that vehicle type and the reference position of the corresponding feature; the contribution degree setting unit sets the contribution degree for each type of vehicle based on the positional accuracy of the feature for each type of vehicle. Map update device.

2. The feature data further includes information describing an environment surrounding the vehicle at the time the feature data was generated; the accuracy measurement unit measures the position accuracy of the vehicle according to the environment; The map updating device according to claim 1 , wherein the contribution degree setting unit sets the contribution degree according to the environment based on the position accuracy according to the environment for the vehicle.

3. 3. The map updating device according to claim 1, further comprising a correction information setting unit that sets correction information for correcting the positions of the features represented in the feature data obtained by the vehicle so that a difference between a position of the feature represented in each of the received feature data and the reference position of the corresponding feature is reduced.

4. receiving, from a vehicle traveling on a predetermined road section, feature data that indicates a position of each feature that is present on the road section and is related to the traveling of the vehicle, via a communication unit that is capable of communicating with the vehicle; measuring the positional accuracy of the feature represented in the feature data obtained by the vehicle based on a difference between the position of the feature represented in each of the received feature data and a reference position of the corresponding feature; determining whether the position accuracy satisfies a predetermined accuracy condition; When the accuracy condition is not satisfied, a contribution rate of the feature data received from the vehicle in updating map information representing the positions of the features is set to be lower than that when the accuracy condition is satisfied. Including, Measuring the positional accuracy of the feature includes measuring the positional accuracy of the feature for each vehicle type based on a difference between the position of the feature represented in each of the feature data received from a plurality of the vehicles belonging to that vehicle type and the reference position of the corresponding feature; and setting the degree of contribution of the feature data includes setting the degree of contribution for each vehicle type based on the positional accuracy of the feature for each vehicle type. A map update method comprising:

5. receiving, from a vehicle traveling on a predetermined road section, feature data that indicates a position of each feature that is present on the road section and is related to the traveling of the vehicle, via a communication unit that is capable of communicating with the vehicle; measuring the positional accuracy of the feature represented in the feature data obtained by the vehicle based on a difference between the position of the feature represented in each of the received feature data and a reference position of the corresponding feature; determining whether the position accuracy satisfies a predetermined accuracy condition; When the accuracy condition is not satisfied, a contribution rate of the feature data received from the vehicle in updating map information representing the positions of the features is set to be lower than that when the accuracy condition is satisfied. Have the computer do this, Measuring the positional accuracy of the feature includes measuring the positional accuracy of the feature for each vehicle type based on a difference between the position of the feature represented in each of the feature data received from a plurality of the vehicles belonging to that vehicle type and the reference position of the corresponding feature; and setting the degree of contribution of the feature data includes setting the degree of contribution for each vehicle type based on the positional accuracy of the feature for each vehicle type. A computer program for updating maps, comprising:

Images