Map data collection device and storage medium storing a computer program for map data collection

Abstract

Provided are a map data collection device and a storage medium storing a computer program for map data collection, which can determine whether to update map data with a small amount of processing. The map data collection device collects the position and attribute information of road features contained in map data used in automatic driving control of a mobile object, and comprises: a storage unit (42) storing map data containing the position and attribute information of one or more first road features; an input unit (41) inputting the position and attribute information of second road features detected by a sensor arranged on the mobile object; and a determination unit (51) referring to the map data stored in the storage unit, selecting a first road feature that exists at a position closest to the position of the second road feature, and determining whether to update the map data based on the attribute information of the first road feature, the attribute information of the second road feature, and the distance between the first road feature and the second road feature.

Description

Technical Field

[0001] The present invention relates to a map data collection device and a storage medium storing a computer program for map data collection. Background Art

[0002] High-precision road map data that a vehicle's autonomous driving system refers to for automatic vehicle control is required to accurately represent information about the road. The map data contains location information of road features such as lane markings, signs, or structures around the road.

[0003] Sometimes, road features such as lane markings, signs, or structures are changed or moved, so it is preferred that the information on these road features is always in a new state in the map data.

[0004] Therefore, the following scheme has been proposed: information on road features detected during the driving of a vehicle is sent to a server that manages map data. In the server, the information on road features sent by the vehicle is compared with the information on road features already registered in the map data, and the map data is updated (for example, refer to patent document 1).

[0005] Prior art literature

[0006] Patent Document 1: Japanese Patent Application Publication No. 2014-228526 Summary of the invention

[0007] Technical problem to be solved by the invention

[0008] Here, since the map data includes a lot of information on road features, it is desirable that the amount of processing associated with determining whether to update the information on the road features is small.

[0009] Therefore, an object of the present invention is to provide a map data collection device capable of determining whether to update map data with a small amount of processing.

[0010] Technical solutions to solve problems

[0011] According to one embodiment, a map data collection device is provided. The map data collection device is a map data collection device that collects the position and attribute information of road features contained in map data used in automatic driving control of a mobile object, and includes: a storage unit that stores map data containing the position and attribute information of one or more first road features; an input unit that inputs the position and attribute information of second road features detected by a sensor arranged on the mobile object; and a determination unit that refers to the map data stored in the storage unit, selects a first road feature that exists at a position closest to the position of the second road feature, and determines whether to update the map data based on the attribute information of the first road feature, the attribute information of the second road feature, and the distance between the first road feature and the second road feature.

[0012] In the map data collection device, the determination unit preferably determines to update the map data when the distance between the selected first road feature and the second road feature is less than a predetermined threshold and the attribute information of the selected first road feature is different from the attribute information of the second road feature.

[0013] In addition, in the map data collection device, the determination unit preferably determines to update the map data when the distance between a selected first road feature and a second road feature is greater than a predetermined threshold and the attribute information of the selected first road feature is the same as the attribute information of the second road feature.

[0014] In addition, in the map data collection device, the determination unit preferably determines to update the map data when the distance between a selected first road feature and a second road feature is greater than a predetermined threshold and the attribute information of the selected first road feature is different from the attribute information of the second road feature.

[0015] In addition, in the map data collection device, the determination unit preferably determines not to update the map data when the distance between a selected first road feature and a second road feature is less than a predetermined threshold and the attribute information of the selected first road feature is the same as the attribute information of the second road feature.

[0016] Furthermore, the map data collection device preferably further includes an updating unit that updates the map data stored in the storage unit based on the position and attribute information of the second road feature when determining that the update is to be performed.

[0017] In addition, in the map data collection device, it is preferred that the determination unit counts the number of times the map data is determined to be updated each time the map data is determined to be updated for a selected first road feature, and when the number of times the map data is determined to be updated for a selected first road feature reaches a predetermined number, the updating unit updates the map data based on the positions and attribute information of a predetermined number of second road features used in the determination of the first road feature.

[0018] In addition, in the map data collection device, it is preferred that the storage unit stores map data including the position and attribute information of one or more first road features associated with the road section for each of the second road features located in the road section input via the input unit, and the determination unit selects a first road feature that is located closest to the position of the second road feature from the first road features associated with the road section in the map data for each of the second road features located in the road section input via the input unit, and determines whether to update the map data based on the attribute information of the selected first road feature, the attribute information of the second road feature, and the distance between the selected first road feature and the second road feature, and determines the second road feature that is not the object of determination as a new road feature.

[0019] According to another embodiment, a non-transient storage medium storing a computer program for collecting map data is provided. The computer program for collecting map data is a computer program for collecting the position and attribute information of road features contained in map data used in automatic driving control of a mobile object, and causes a processor to execute: inputting the position and attribute information of a second road feature detected by a sensor arranged on the mobile object through an input unit; referring to map data containing the position and attribute information of one or more first road features stored in a storage unit, selecting one of the first road features that exists at a position closest to the position of the second road feature, and determining whether to update the map data based on the attribute information of the first road feature, the attribute information of the second road feature, and the distance between the first road feature and the second road feature.

[0020] Effects of the Invention

[0021] The map data collection device according to the present invention achieves an effect of being able to determine whether to update map data with a small amount of processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a schematic diagram of the structure of a map data collection system equipped with a map data collection device.

[0023] Figure 2This is a schematic diagram of the vehicle.

[0024] Figure 3 This is the hardware structure diagram of the server.

[0025] Figure 4 This is a flow chart of the operation of the vehicle during the map data collection process.

[0026] Figure 5 This is a flow chart of the operation of the server in the map data collection process.

[0027] Figure 6 This is a flowchart of the operation of the determination unit of the server processor.

[0028] Figure 7 This is a flowchart of the operation of the update unit of the server processor.

[0029] Description of symbols

[0030] 1 Map Data Collection System

[0031] 2 Vehicles

[0032] 11. Camera

[0033] 12 Wireless communication terminal

[0034] 13 Positioning information receiver

[0035] 14 Navigation Device

[0036] 15 Map data acquisition device

[0037] 16 In-car network

[0038] 21 Communication Interface

[0039] 22 Memory

[0040] 23 Processor

[0041] 24 Signal lines

[0042] 31. Inspection Department

[0043] 32 Data Generation Department

[0044] 3 Server

[0045] 41 Communication interface

[0046] 42 Storage Devices

[0047] 421 Map Data

[0048] 43 Memory

[0049] 44 Processor

[0050] 45 Signal line

[0051] 51 Judgment Department

[0052] 52 Update Department

[0053] 4 Network

[0054] 5 Base Station DETAILED DESCRIPTION

[0055] Figure 1 This is a schematic diagram of a map data collection system equipped with a map data collection device. Figure 1 The outline of the map data collection system 1 disclosed in this specification will be described.

[0056] In this embodiment, the map data collection system 1 includes a map data acquisition device 15 mounted on at least one vehicle 2 and a server 3. The map data acquisition device 15 is connected to the server 3 via the base station 5 and the communication network 4 by, for example, accessing a wireless base station 5 connected to the communication network 4 connected to the server 3 via a gateway (not shown). Figure 1 In FIG. 1 , only one vehicle 2 is shown in the figure, but the map data collection system 1 may include a plurality of vehicles 2 . Similarly, a plurality of base stations 5 may be connected to the communication network 4 .

[0057] While the vehicle 2 is traveling on the road R, the map data acquisition device 15 uses the camera 11, which is an example of a sensor disposed on the vehicle 2, to acquire a camera image C showing the environment around the vehicle. Figure 1 In the example shown, the map data acquisition device 15 acquires a camera image C including a road sign X1 indicating that the maximum speed is 50 km / h.

[0058] The map data acquisition device 15 detects the position and attribute information of the road feature X1 represented in the camera image C. The position of the road feature is represented by, for example, a world coordinate system with a predetermined reference position in the real space as the origin. The attribute information of the road feature, for example, indicates the type of road markings such as lane dividing lines, stop lines, or speed indicators, or road signs such as speed indicators or traffic lights. The map data acquisition device 15 sends the position and attribute information of the detected road feature (hereinafter also referred to as detected road feature) X1 to the server 3 via the base station 5 and the communication network 4.

[0059] The server 3 includes a communication I / F 41 to which the position and attribute information of the road feature X1 detected by the map data acquisition device 15 are input, a storage device 42 storing map data 421 , and a determination unit 51 determining whether to update the map.

[0060] The determination unit 51 refers to the map data 421 including the positions and attribute information of one or more registered road features, and selects a road feature (hereinafter also referred to as a registered road feature) X2 registered in the map data 421 and located at the closest position to the detected road feature X1.

[0061] The determination unit 51 determines whether to update the map data 421 based on the attribute information of the selected registered road feature X2 , the attribute information of the detected road feature X1 , and the distance between the selected registered road feature X2 and the detected road feature X1 . Figure 1 The map D is a map obtained by extracting a part of the map data 421 , and is a map in which the detected road feature X1 and the registered road feature X2 are arranged along the road R based on the position information.

[0062] The map data collection system 1 may include a plurality of vehicles 2 . However, as for the map data collection process, each vehicle 2 may have the same configuration and execute the same process, and therefore, one vehicle 2 will be described below.

[0063] Figure 2 This is a schematic diagram of the structure of the vehicle 2. The vehicle 2 has a camera 11 for photographing the environment in front of the vehicle 2, a wireless communication terminal 12, a positioning information receiver 13, a navigation device 14, and a map data acquisition device 15. Furthermore, the vehicle 2 may also have a distance measuring sensor (not shown) for measuring the distance to objects around the vehicle 2, such as a LiDAR sensor.

[0064] The camera 11 , the wireless communication terminal 12 , the positioning information receiver 13 , the navigation device 14 , and the map data acquisition device 15 are connected to each other in a communicable manner via an in-vehicle network 16 conforming to a standard such as a controller area network.

[0065] The camera 11 is installed in the cabin of the vehicle 2, for example, in a manner facing the front of the vehicle 2. The camera 11 obtains a camera image C representing the environment of a predetermined area in front of the vehicle 2 at a predetermined period. The camera image C can represent road features such as lane markings on the road surface contained in the predetermined area in front of the vehicle 2. The image generated by the camera 11 can be either a color image or a grayscale image. The camera 11 is an example of a sensor arranged in the vehicle 2, and has a two-dimensional detector composed of an array of photoelectric conversion elements sensitive to visible light, such as CCD or C-MOS, and a shooting optical system that forms an image of the area to be shot on the two-dimensional detector.

[0066] The wireless communication terminal 12 is an example of a communication unit and is a device that performs wireless communication processing in compliance with a predetermined wireless communication standard. For example, the wireless communication terminal 12 accesses the base station 5 and is connected to the server 3 via the base station 5 and the communication network 4 .

[0067] The positioning information receiver 13 outputs positioning information indicating the current location of the vehicle 2. For example, the positioning information receiver 13 may be a GPS receiver. Whenever the positioning information is acquired in a predetermined reception cycle, the positioning information receiver 13 outputs the positioning information and the time at which the positioning information is acquired to the navigation device 14 and the map data acquisition device 15.

[0068] The navigation device 14 generates a driving route from the current location to the destination of the vehicle 2 based on the navigation map data, the destination of the vehicle 2, and the current location of the vehicle 2. The navigation device 14 uses the positioning information output by the positioning information receiver 13 as the current location of the vehicle 2. Whenever the navigation device 14 generates a driving route, it outputs the driving route to the map data acquisition device 15 via the in-vehicle network 16.

[0069] The map data acquisition device 15 performs: a detection process to detect the position and attribute information of the road feature represented in the camera image C; and a data generation process to generate acquisition data including the position and attribute information of the detected road feature, and transmit the acquisition data to the server 3. To this end, the map data acquisition device 15 has a communication interface 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 are connected via a signal line 24.

[0070] The communication interface (I / F) 21 is an example of an in-vehicle communication unit, and has an interface circuit for connecting the map data acquisition device 15 to the in-vehicle network 16. That is, the communication interface 21 is connected to the camera 11, the wireless communication terminal 12, the positioning information receiver 13, and the navigation device 14 via the in-vehicle network 16. Whenever the position and attribute information of the detected road feature are given from the processor 23, the communication interface 21 transmits the given position and attribute information of the detected road feature to the wireless communication terminal 12.

[0071] The memory 22 is an example of a storage unit, and includes, for example, a volatile semiconductor memory and a nonvolatile semiconductor memory. The memory 22 stores computer programs and various data of applications used in information processing executed by the processor 23 of the map data acquisition device 15, a vehicle ID for identifying the vehicle 2, and the like. The vehicle ID can be used, for example, to identify each vehicle 2 when the server 3 communicates with a plurality of vehicles 2.

[0072] The processor 23 has one or more CPUs (Central Processing Units) and their peripheral circuits. The processor 23 may also have other operation circuits such as a logic operation unit, a numerical operation unit, or a graphics processing unit. When the processor 23 has multiple CPUs, it may also have a memory for each CPU. The processor 23 performs detection processing and data generation processing.

[0073] The processor 23 includes: a detection unit 31 that detects the position and attribute information of the road feature represented in the camera image C; and a data generation unit 32 that generates data including the position and attribute information of the detected road feature, and transmits the data to the server 3. These units of the processor 23 are, for example, functional modules implemented by a computer program running on the processor 23. Alternatively, these units of the processor 23 may also be dedicated computing circuits provided in the processor 23.

[0074] Figure 3 4 is a hardware structure diagram of the server 3. The server 3 has a communication interface 41, a storage device 42, a memory 43, and a processor 44. The communication interface 41, the storage device 42, the memory 43, and the processor 44 are connected via a signal line 45. The server 3 may also have an input device such as a keyboard and a mouse, and a display device such as a liquid crystal display.

[0075] The communication interface 41 is an example of an input unit, and has an interface circuit for connecting the server 3 to the communication network 4 . The communication interface 41 is configured to be able to communicate with the vehicle 2 via the communication network 4 and the base station 5 .

[0076] The storage device 42 is an example of a storage unit, and includes, for example, a hard disk device or an optical recording medium and an access device thereof. The storage device 42 stores map data 421 updated by the processor 44, etc. The storage device 42 may also store the vehicle ID of the vehicle 2. Furthermore, the storage device 42 may also store a computer program executed on the processor 44 for executing the processing of the server 3 associated with the map data collection processing.

[0077] The map data 421 has the position and attribute information of road features (e.g., lane demarcation lines, stop lines, road markings such as speed indicators, road signs, or traffic lights) that define the driving conditions of each road shown on the map. A plurality of road features (registered road features) registered in the map data 421 are identified based on road feature identification information (road feature ID) that identifies the road features. The position and attribute information of the registered road features are registered in the map data 421 in association with the road feature ID. The registered road features are registered in the map data 421 in association with the road section where the registered road features are located.

[0078] The memory 43 is another example of a storage unit, and includes, for example, a nonvolatile semiconductor memory and a volatile semiconductor memory. The memory 43 temporarily stores various data generated during the execution of the processing associated with the server 3 in the map data collection processing, and various data obtained through communication with the vehicle 2, such as the position and attribute information of the detected road feature received from the vehicle 2.

[0079] The processor 44 has one or more CPUs (Central Processing Units) and their peripheral circuits. The processor 44 may also have other operation circuits such as a logic operation unit or a numerical operation unit. In addition, the processor 44 performs the processing associated with the server 3 in the map data collection process.

[0080] The processor 44 includes: a determination unit 51 that determines whether to update the map data 421 based on the position and attribute information of the detected road feature; and an update unit 52 that updates the map data. These units of the processor 44 are, for example, functional modules implemented by a computer program running on the processor 44. Alternatively, these units of the processor 44 may also be dedicated operation circuits provided in the processor 44.

[0081] Figure 4 1 is a flowchart of the vehicle operation in the map data collection process. In the map data collection system 1, the data acquisition device 15 of the vehicle 2 performs the following operations during the travel of the vehicle 2: Figure 4The operation flowchart shown is a flowchart for repeatedly executing the map data acquisition process.

[0082] The camera 11, which is an example of a sensor disposed in the vehicle 2, acquires a camera image C representing the environment around the vehicle 2 during the travel of the vehicle 2 (step S101). Whenever the camera 11 acquires the camera image C, it outputs the camera image C and the camera image acquisition time when the camera image C is acquired to the map data acquisition device 15 via the in-vehicle network 16. In addition, the camera image C can also be used for the process of estimating the current location of the vehicle 2 and for the process of detecting other objects around the vehicle 2.

[0083] The data acquisition device 15 of the vehicle 2 detects the road feature represented in the camera image C and estimates the position of the road feature (step S102). The detection unit 31 of the processor 23 in the data acquisition device 15 detects the road feature represented in the camera image C input from the camera 11, detects the attribute information of the road feature detected in the camera image C, and estimates the position of the road feature.

[0084] For example, the detection unit 31 detects the road feature represented in the input camera image C by inputting the camera image C into the recognizer. The detection unit 31 may use, for example, a deep neural network (DNN) that has been pre-learned to detect the road feature represented by the camera image C from the input camera image C as such a recognizer. The detection unit 31 may use, for example, a DNN having a convolutional neural network architecture such as Single Shot MultiBox Detector (SSD) or FasterR-CNN as such a DNN. In this case, the camera image C is input to the recognizer by the detection unit 31, and the recognizer calculates the confidence indicating the reliability of the road feature being represented in the region according to the type of the road feature to be detected (e.g., lane markings, crosswalks, temporary stop lines, etc.) in various regions on the input camera image C, and determines that the road feature of a certain type is represented in the region where the confidence for the road feature of that type is greater than a predetermined detection threshold. In addition, the identifier outputs information representing an area on the input camera image C that contains a road feature object that is to be detected (for example, a circumscribed rectangle of the road feature object that is to be detected, hereinafter referred to as the object area), as well as attribute information representing the type of road feature object represented by the object area.

[0085] Alternatively, the detection unit 31 may also use a recognizer other than DNN. For example, the detection unit 31 may also use a support vector machine (SVM) as a recognizer, and the support vector machine (SVM) is pre-learned so as to take as input a feature quantity (e.g., Histograms of Oriented Gradients (Histogram of Oriented Gradients), HOG) calculated from a window set on an image, and output a confidence level that a road feature object to be detected is represented in the window. The detection unit 31 calculates a feature quantity from the window while making various changes to the position, size, and aspect ratio of the window set on the camera image C, and inputs the calculated feature quantity into the SVM, thereby obtaining confidence for the window. Furthermore, when the confidence level is above a predetermined detection threshold, the detection unit 31 regards the window as an object area representing a road feature object to be detected.

[0086] The detection unit 31 estimates the position of the feature represented in the object area based on the internal parameters such as the direction from the camera 11 corresponding to the center of gravity of the object area detected from the camera image C, the position of the vehicle 2, the travel direction, and the shooting direction and field angle of the camera 11. In addition, the detection unit 31 notifies the data generation unit 32 of the attribute information and the estimated position of the detected road feature (detected road feature). The number of road features detected from one camera image C is sometimes zero and sometimes one or more. Whenever the detection unit 31 detects the position and attribute information of the detected road feature, it notifies the data generation unit 32 of this information.

[0087] When the data generation unit 32 of the processor 23 in the data acquisition device 15 is notified of the position and attribute information of the detected road feature from the detection unit 31, it acquires the road section ID representing the road section where the detected road feature is located based on the position of the detected road feature and the driving route (step S103). The driving route is generated by connecting the road sections from the current location of the vehicle 2 to the destination. Each road section is identified by the road section identification information (road section ID) representing the road section. For example, the data generation unit 32 selects the road section closest to the detected road feature from the plurality of road sections forming the driving route as the road section where the road feature is located.

[0088] The data generation unit 32 determines whether the road section where the detected road feature is located has changed (step S104). The data generation unit 32 monitors the road section IDs obtained in sequence, and when a road section ID (second road section ID) different from the road section ID (first road section ID) obtained previously is selected twice in succession, it is determined that the road section where the detected road feature is located has changed.

[0089] When the road section where the detected road feature is located has changed (step S104: Yes), the data generation unit 32 sends the information of the detected road feature located in one road section (first road section ID) to the server 3 (step S105). The data generation unit 32 outputs the road section ID indicating the road section where the detected road feature is located, the position and attribute information of one or more detected road features to the wireless communication terminal 12 via the communication interface 21, thereby sending the road section ID, the position and attribute information of the detected road feature to the server 3 via the wireless base station 5 and the communication network 4.

[0090] On the other hand, if the road section where the detected road feature is located has not changed (step S104: No), the process returns to step S101. In addition, the method in which the data generation unit 32 sends the road section ID, the position of the detected road feature, and the attribute information to the server 3 is not limited to the above method. For example, the data generation unit 32 may send the position and attribute information of the detected road feature to the server 3 every time the detection unit 31 notifies the data generation unit 32 of the detected road feature. In addition, the data generation unit 32 may send the information of the detected road feature to the server 3 at a predetermined interval.

[0091] Figure 5 2 is an operation flow chart of the server 3 in the map data collection process. The communication interface 41 of the server 3 receives the road section ID, the position of the detected road feature, and the attribute information of one or more detected road features detected in the same road section from the vehicle 2 (step S201). The communication interface 41 passes the road section ID, the position of the detected road feature, and the attribute information received from the vehicle 2 via the base station 5 and the communication network 4 to the processor 44.

[0092] The determination unit 51 of the processor 44 selects a registered road feature associated with the same road section as the road section where the detected road feature is located (step S202). The determination unit 51 refers to the map data 421 stored in the storage device 42, selects a registered road feature associated with a road section that is identical to the road section ID representing the road section where the detected road feature is located, and reads the position and attribute information of the selected registered road feature.

[0093] The determination unit 51 of the processor 44 determines whether to update the map data 421 for each detected road feature based on the attribute information of the detected road feature, the attribute information of the selected registered road feature, and the distance between the detected road feature and the selected registered road feature (step S203). For details of the determination process of the determination unit 51, please refer to Figure 6This will be described later.

[0094] When the updating unit 52 of the processor 44 determines that the detected road feature is to be updated, the map data 421 stored in the storage device 42 is updated based on the position and attribute information of the registered road feature (step S204). For details of the updating process of the updating unit 52, please refer to Figure 7 This will be described later.

[0095] Figure 6 This is an operation flow chart of the determination unit 51 of the processor 44 of the server 3. Figure 6 The operation flowchart shown in FIG. 2 will explain the determination processing of the determination unit 51 in step S203.

[0096] The determination unit 51 executes the loop process of steps S302 to S311 for each of one or more detected road feature objects (steps S301 to S312 ).

[0097] The determination unit 51 refers to the map data 421, and selects the registered road feature whose position is closest to the position of the detected road feature from the registered road features associated with the road section where the detected road feature is located (step S302). As described above, the position of the detected road feature corresponds to the position of the center of gravity of the object area, so the distance between the position of the detected road feature and the position of the registered road feature becomes a three-dimensional distance. The determination unit 51 calculates the distance between the one or more registered road features selected in step S302 and the detected road feature, and selects the registered road feature representing the shortest distance as the registered road feature to be compared with the detected road feature in the loop processing. The registered road feature that has been selected once is excluded from the comparison object in the next loop processing.

[0098] The determination unit 51 determines whether the distance between the selected registered road feature and the detected road feature is less than a predetermined distance threshold Dth, and the attribute information of the selected registered road feature is the same as the attribute information of the detected road feature (step S303). The distance threshold Dth can be determined based on the accuracy of the position of the sensor that detects the detected road feature, etc. For example, in the present embodiment, the position of the detected road feature is estimated based on the camera image C obtained by the camera 11 as an example of a sensor, and the threshold Dth is determined based on the accuracy of the position in the detection method. Specifically, the accuracy of the position in the detection method is determined based on the position accuracy of the vehicle 2, the resolution of the camera image C, the installation accuracy of the camera 11 relative to the vehicle 2, etc.

[0099] When the distance between the selected registered road feature and the detected road feature is less than the distance threshold Dth and the attribute information of the selected registered road feature is the same as the attribute information of the detected road feature (step S303: Yes), the determination unit 51 determines not to update the map data (step S304). This is because it is estimated that the selected registered road feature is the same as the detected road feature.

[0100] On the other hand, in the case where it is denied that the distance between the selected registered road feature and the detected road feature is below the distance threshold Dth, and the attribute information of the selected registered road feature is the same as the attribute information of the detected road feature (step S303: No), the determination unit 51 determines whether the distance between the selected registered road feature and the detected road feature is below the distance threshold Dth, and the attribute information of the selected registered road feature is different from the attribute information of the detected road feature (step S305).

[0101] When the distance between the selected registered road feature and the detected road feature is less than the distance threshold Dth, and the attribute information of the selected registered road feature is different from the attribute information of the detected road feature (step S305: yes), the determination unit 51 increments the first count value for the selected registered road feature (step S308). When the first count value is incremented for the first time, after step S308, the first count value becomes 1. With respect to the selected registered road feature, when the first count value is N, the first count value after step S308 becomes N+1. The determination unit 51 associates the position and attribute information of the detected road feature with respect to the registered road feature whose first count value is incremented, and stores them in the memory 43 or the storage device 42.

[0102] On the other hand, in the case where it is denied that the distance between the selected registered road feature and the detected road feature is less than the distance threshold Dth, and the attribute information of the selected registered road feature is different from the attribute information of the detected road feature (step S305: No), the determination unit 51 determines whether the distance between the selected registered road feature and the detected road feature is greater than the distance threshold Dth, and the attribute information of the selected registered road feature is the same as the attribute information of the detected road feature (step S306).

[0103] When the distance between the selected registered road feature and the detected road feature is greater than the distance threshold Dth, and the attribute information of the selected registered road feature is the same as the attribute information of the detected road feature (step S306: Yes), the determination unit 51 increments the second count value for the selected registered road feature (step S309). The determination unit 51 associates the position of the detected road feature with the attribute information for the registered road feature whose second count value is incremented and stores the information in the memory 43 or the storage device 42.

[0104] On the other hand, when it is denied that the distance between the selected registered road feature and the detected road feature is greater than the distance threshold Dth, and the attribute information of the selected registered road feature is the same as the attribute information of the detected road feature (step S306: No), the determination unit 51 determines that the distance between the selected registered road feature and the detected road feature is greater than the distance threshold Dth, and the attribute information of the selected registered road feature is different from the attribute information of the detected road feature (step S307). The determination unit 51 increments the third count value for the selected registered road feature (step S310). The determination unit 51 associates the position and attribute information of the detected road feature with the registered road feature whose third count value is incremented and stores them in the memory 43 or the storage device 42.

[0105] The determination unit 51 sets an update flag for a registered road feature whose count value among any of the first count value to the third count value is incremented, when the count value exceeds the reference value (step S311). Specifically, the determination unit 51 sets the first update flag for a registered road feature whose first count value exceeds the reference value, sets the second update flag for a registered road feature whose second count value exceeds the reference value, and sets the third update flag for a registered road feature whose third count value exceeds the reference value. The reference value may be different for the first count value to the third count value, or may be the same for the first count value to the third count value. In the present embodiment, the same reference value is used for the first count value to the third count value. From the viewpoint of eliminating erroneous detection of road features, the reference value is preferably set to, for example, about 5 to 10. In addition, the reference value may also be 1.

[0106] After the loop processing of steps S302 to S311 described above is performed on one or more detected road features, the determination unit 51 determines that the detected road features that are not compared with the registered road features in the loop processing are new road features that are not registered in the map data 421 (step S313). The determination unit 51 notifies the updating unit 52 of the position and attribute information of the detected road features that are determined to be new road features. When the number of road features detected in a road section is greater than the number of registered road features registered in the map data 421, the detected road features that are not compared with the registered road features are presumed to be new road features. The above is an explanation of the determination processing of the determination unit 51 in step S203.

[0107] Figure 7 This is a flowchart of the operation of the update unit 52 of the processor 44 of the server 3. Figure 7 The operation flow chart shown in FIG. 2 illustrates the update processing of the update unit 52 in step S204.

[0108] The updating unit 52 executes the updating process in a predetermined updating cycle. The updating unit 52 executes the loop process of step S402 (steps S401 to S403) for each registered road feature for which any of the first to third updating flags is set.

[0109] The updating unit 52 updates the map data 421 for the registered road feature for which the update flag is set (step S402). The updating unit 52 changes the position and attribute information of the registered road feature for which the update flag is set based on the position and attribute information of one or more detected road features associated with the registered road feature and stored in the memory 43 or the storage device 42.

[0110] When the first update flag is set for a registered road feature, the update unit 52 determines the average value of the positions of multiple detected road features associated with the registered road feature as the position of the updated registered road feature. In addition, the update unit 52 determines the largest number of attribute information among the multiple detected road features associated with the registered road feature as the attribute information of the updated registered road feature. The update unit 52 replaces the position and attribute information of the road feature registered in the map data 421 in association with the road section ID with the position and attribute information of the new road feature. In the case where the first update flag is set, the fact that the attribute information of the road feature has been changed is presumed to be the reason for the information to be updated. For example, as a specific example, the maximum speed road sign as an example of a road feature is changed from 40km to 50km.

[0111] When the second update flag is set for the registered road feature, the update unit 52 calculates the average value and variance of the positions of multiple detected road features associated with the registered road feature. And, when (1) the variance is smaller than the reference variance, the update unit 52 determines the average value of the positions of multiple detected road features associated with the registered road feature as the position of the updated registered road feature. The update unit 52 replaces the position of the road feature registered in the map data 421 in association with the road section ID with the position of the new road feature. The attribute information of the new road feature is the same as before the update. In the case (1) where the second update flag is set, the fact that the position of the road feature has been changed or the fact that the position of the road feature registered in the map data 421 has become incorrect is inferred as the reason for the information being updated. On the other hand, in the case (2) where the variance is greater than or equal to the reference variance, the updating unit 52 uses, for example, the k-means method with a cluster number of 2 to obtain two centroid positions (a first centroid position and a second centroid position) of a plurality of detected road features associated with the registered road feature. The updating unit 52 determines the first centroid position as the position of the first road feature and the second centroid position as the position of the second road feature. The attribute information of the first road feature and the attribute information of the second road feature are the same as before the update. The updating unit 52 deletes the position and attribute information of the road feature registered in the map data 421, and registers the new position and attribute information of the first road feature and the new position and attribute information of the second road feature in the map data 421 in association with the road section ID. In the case (2) where the second update flag is set, the fact that a new road feature is added on the road near the road feature registered in the map data 421 is estimated as the reason for updating the information.

[0112] When the third update flag is set for the registered road feature, the update unit 52 determines the average value of the positions of the multiple detected road features associated with the registered road feature as the position of the updated registered road feature. In addition, the update unit 52 determines the largest number of attribute information of the multiple detected road features associated with the registered road feature as the attribute information of the updated registered road feature. The update unit 52 registers the position and attribute information of the new road feature in the map data 421 in association with the road section ID. In the case where the third update flag is set, the fact that a new road feature is added to the road is presumed to be the reason for updating the information.

[0113] After executing the loop processing of step S402 described above with respect to the registered road feature for which the update flag is set, the updating unit 52 updates the registered road feature based on the update flag in step S313 described above (see Figure 6) is determined to be a new road feature, and the map data 421 is updated (step S404). The updating unit registers the position and attribute information of the detected road feature determined to be a new road feature notified from the determining unit 51 in the map data 421 in association with the road section ID.

[0114] As described above, the map data collection device is a map data collection device that collects the position and attribute information of the road features included in the map data used in the automatic driving control of the vehicle, inputs the position and attribute information of the second road feature detected by the sensor arranged on the vehicle, refers to the map data including the position and attribute information of one or more first road features, selects a first road feature that exists at a position closest to the position of the second road feature, and determines whether to update the map data based on the attribute information of the first road feature, the attribute information of the second road feature, and the distance between the first road feature and the second road feature. Thus, the map data collection device compares the position and attribute information of the first road feature that exists at a position closest to the position of the second road feature, and can determine whether to update the map data with a small amount of processing. Specifically, for each second road feature located in a road section inputted via the input unit, the map data collection device selects a first road feature located at a position closest to the position of the second road feature from the first road features associated with the road section in the map data, and determines whether to update the map data based on the attribute information of the selected first road feature, the attribute information of the second road feature, and the distance between the selected first road feature and the second road feature. Thus, the map data collection device can reduce the amount of processing for selecting a first road feature located at a position closest to the position of the second road feature.

[0115] Next, a modified example of the above-mentioned map data collection system is described below. In the map data collection system of modified example 1, the processor 44 of the server 3 may also have a data acquisition instruction unit (not shown), which selects a road section without an associated road feature or with fewer associated road features than a predetermined reference value, and sends a road section ID and a data acquisition instruction representing the road section to the vehicle 2. In this case, the detection unit 31 of the vehicle 2 detects the road feature only when traveling on the road section for which the data acquisition instruction is received from the server 3. When the camera image C is input from the camera 11, the detection unit 31 determines whether the road section where the vehicle 2 is traveling is consistent with the road section for which the data acquisition instruction is received from the server 3 based on the positioning information and the driving route input from the navigation device 14. When the road section where the vehicle 2 is traveling is consistent with the road section for which the data acquisition instruction is received from the server 3, the detection unit 31 performs detection of the road feature in the camera image C.

[0116] In the map data collection system of variant example 2, a road feature may also be registered in map data 421 in association with a lane included in a road section. A road feature is associated with a lane that is closest to the position of the road feature. A lane is identified based on lane identification information (lane ID). A lane is associated with a road section including the lane. In the case where a certain road section has multiple lanes, multiple lanes are associated with the certain road section. In this way, each registered road feature in map data 421 is associated with a road section via a lane.

[0117] In the map data collection system of Modification 3, the determination unit 51 of the processor 44 of the server 3 may also delete the position and attribute information of the detected road feature stored in the memory 43 or the storage device 42 in association with the registered road feature for which the update flag is set, from the memory 43 or the storage device 42, when a predetermined period has passed since it was determined that the update flag was set. For example, a road feature may be erroneously detected by a sensor such as the camera 11 of the vehicle 2. Such a road feature is not repeatedly detected, and therefore, it is preferably deleted.

[0118] In the map data collection system of the modification 4, the detection unit 31 of the processor 23 of the map data acquisition device 15 of the vehicle 2 may also detect the height of the road feature. The detection unit 31 may also use the angle θ formed by the direction of the optical axis of the camera 11 and the vertical direction of the ground, the distance D between the vehicle 2 and the road feature, and the size Rc of the road surface development vector, and use the relationship of the height of the road feature = Rc / tanθ-D / tanθ to calculate the height of the road feature. Here, the road surface development vector means a vector obtained by connecting the foot of the perpendicular line from the viewpoint of the camera 11 to the ground and the following point, which is the point where the straight line connecting the viewpoint of the camera 11 and the vertex of the road feature intersects the ground. The data generation unit 32 of the processor 23 of the vehicle 2 sends the height of the road feature to the server 3 together with the road section ID, the position of the detected road feature, and the attribute information. The determination unit 51 of the processor 44 of the server 3 may also, during the update process, add a determination as to whether the height of the detected road feature is consistent with the height of the registered road feature when performing a comparison determination between the detected road feature and the registered road feature that is located closest to the detected road feature.

[0119] In the present invention, the map data collection device and the non-transitory storage medium storing the map data collection computer program of the above-mentioned embodiments can be appropriately changed as long as they do not deviate from the purpose of the present invention. In addition, the technical scope of the present invention is not limited to those embodiments, but can be extended to the invention described in the claims and their equivalents.

[0120] For example, in the above-described embodiment, map data is used for automatic driving control of a vehicle as an example of a moving object, but map data may also be used for automatic driving control of a moving object other than a vehicle.

[0121] Furthermore, in the above-described embodiment, the server has the function of the map data collection device, but the map data collection device may be disposed in a vehicle.

Claims

1. A map data collection device for collecting position and attribute information of road features contained in map data used in automatic driving control of a moving object, comprising: a storage unit storing map data including position and attribute information of one or more first road features; an input unit that inputs the position and attribute information of the second road feature detected by a sensor disposed on the mobile object; and a determination unit that refers to the map data stored in the storage unit, selects one of the first road features that is located closest to the second road feature, and determines whether to update the map data based on attribute information of the first road feature, attribute information of the second road feature, and a distance between the first road feature and the second road feature. The determination unit determines to update the map data when a distance between the selected one of the first road features and the second road feature is greater than a predetermined threshold and attribute information of the selected one of the first road features is the same as attribute information of the second road feature.

2. The map data collection device according to claim 1, The determination unit determines to update the map data when the distance between the selected one of the first road features and the second road feature is less than a predetermined threshold and the attribute information of the selected one of the first road features is different from the attribute information of the second road feature.

3. The map data collection device according to claim 2, The determination unit determines to update the map data when the distance between the selected one of the first road features and the second road feature is greater than the predetermined threshold and the attribute information of the selected one of the first road features is different from the attribute information of the second road feature.

4. The map data collection device according to claim 2 or 3, The determination unit determines not to update the map data when the distance between the selected one of the first road features and the second road feature is less than a predetermined threshold and the attribute information of the selected one of the first road features is the same as the attribute information of the second road feature.

5. The map data collection device according to any one of claims 1 to 3, The present invention further includes an updating unit that updates the map data stored in the storage unit based on the position and attribute information of the second road feature when determining that the update is to be performed.

6. The map data collection device according to claim 5, The determination unit counts the number of times the map data is determined to be updated, each time the determination unit determines that the map data is to be updated for the selected one of the first road features. When the updating unit determines that the number of times the map data has been updated has reached a predetermined number for the selected one of the first road features, the updating unit updates the map data based on the positions and attribute information of the predetermined number of the second road features used in determining the one of the first road features.

7. The map data collection device according to any one of claims 1 to 3 and 6, The storage unit stores, for each of a plurality of road sections, the map data including the position and attribute information of one or more first road features associated with the road section. The determination unit selects, for each of the second road features located in the road section input via the input unit, one of the first road features associated with the road section in the map data, which is located at a position closest to the position of the second road feature, and determines whether to update the map data based on attribute information of the selected first road feature, attribute information of the second road feature, and a distance between the selected first road feature and the second road feature, and determines the second road feature that is not an object of determination as a new road feature.

8. A non-transitory storage medium, the computer-readable storage medium storing a computer program for collecting map data, the computer program for collecting map data collecting collecting positions and attribute information of road features included in map data used in automatic driving control of a mobile object, the computer program for collecting map data causing a computer to execute: inputting, via the input unit, the position and attribute information of the second road feature detected by the sensor disposed on the mobile object; Referring to map data containing positions and attribute information of one or more first road features stored in a storage unit, selecting one of the first road features that is located closest to the position of the second road feature, and determining whether to update the map data based on the attribute information of the first road feature, the attribute information of the second road feature, and the distance between the first road feature and the second road feature; When the distance between the selected one of the first road features and the second road feature is greater than a predetermined threshold and the attribute information of the selected one of the first road features is the same as the attribute information of the second road feature, it is determined that the map data is to be updated.

Images