Map generation device and map generation method

Abstract

A map generation device includes: an information acquisition unit that acquires positional information of a specific vehicle and positional information of a peripheral vehicle from in-vehicle devices disposed in the specific vehicle and the peripheral vehicle located in the periphery of the specific vehicle; a reliability determination unit that determines the reliability of each of the in-vehicle devices on the basis of the degree of coincidence between the position information of the specific vehicle detected by the in-vehicle device mounted on the specific vehicle and the position information of the specific vehicle detected by the in-vehicle device mounted on the surrounding vehicle; and a map integration unit that integrates, into a map, the position information of the surrounding object acquired from the in-vehicle device determined on the basis of the degree of reliability among the plurality of in-vehicle devices.

Description

Technical Field

[0001] The present invention relates to a map generating device and a map generating method. Background Art

[0002] There is known a technique for generating a map based on images captured by an imaging device mounted on a vehicle. Patent Document 1 discloses a technique for generating a map by integrating data transmitted from an imaging device and weighting the data according to deviations.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Publication No. 2020-197708 Summary of the invention

[0006] In the technology of Patent Document 1, the reliability of data is evaluated based on information related to landmarks, and the priority of data used in map generation is set based on the reliability. Therefore, in the technology of Patent Document 1, if there is no object that can be recognized as a landmark, it may not be possible to appropriately generate a map.

[0007] An object of the present invention is to provide a map generation device and a map generation method that can generate a high-precision map even when there is no object that can be recognized as a landmark.

[0008] The map generating device of the present invention includes: an information acquiring unit, which acquires the position information of the specific vehicle and the position information of the surrounding vehicles located around the specific vehicle from the vehicle-mounted devices respectively configured on the specific vehicle and the surrounding vehicles; a reliability determining unit, which determines the reliability of each of the vehicle-mounted devices based on the degree of consistency between the position information of the specific vehicle detected by the vehicle-mounted device mounted on the specific vehicle and the position information of the specific vehicle detected by the vehicle-mounted device mounted on the surrounding vehicles; and a map integration unit, which integrates the position information of the surrounding objects acquired from the vehicle-mounted devices determined based on the reliability among the plurality of the vehicle-mounted devices into the map.

[0009] The map generation method of the present invention includes: a step of acquiring position information of a specific vehicle and position information of surrounding vehicles located around the specific vehicle from vehicle-mounted devices respectively configured on the specific vehicle and the surrounding vehicles; a step of determining the reliability of each of the vehicle-mounted devices based on the degree of consistency between the position information of the specific vehicle detected by the vehicle-mounted device mounted on the specific vehicle and the position information of the specific vehicle detected by the vehicle-mounted device mounted on the surrounding vehicles; and a step of integrating the position information of surrounding objects acquired from the vehicle-mounted devices determined based on the reliability among the plurality of vehicle-mounted devices into the map.

[0010] According to the present invention, a high-precision map can be generated even when there is no object that can be recognized as a landmark. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A diagram for explaining a configuration example of a map generation system in an embodiment.

[0012] Figure 2 It is a block diagram showing a configuration example of a vehicle-mounted device in the embodiment.

[0013] Figure 3 It is a diagram showing a configuration example of a map generating device in an embodiment.

[0014] Figure 4 This is a flowchart showing the flow of map generation processing in the embodiment.

[0015] Figure 5 It is a diagram for explaining a method of acquiring vehicle information in an embodiment.

[0016] Figure 6 It is a diagram for explaining a method of calculating a deviation of position information in an embodiment.

[0017] Figure 7 It is a diagram for explaining a method of calculating a deviation of position information in an embodiment.

[0018] Figure 8 It is a diagram for explaining a method of calculating a deviation of position information in an embodiment.

[0019] Fig. 9 This is a diagram for explaining a method of arranging surrounding objects on a map in an embodiment.

[0020] Fig.10 This is a diagram for explaining a method of arranging surrounding objects on a map in a modified example of the embodiment. DETAILED DESCRIPTION

[0021] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. However, the present invention is not limited to the embodiment, and in the following embodiments, the same parts are denoted by the same reference numerals to omit repeated descriptions.

[0022] [Implementation Method]

[0023] (Map generation system)

[0024] use Figure 1 The map generation system in the embodiment will be described. Figure 1 An example configuration of a map generation system in the embodiment will be described.

[0025] like Figure 1 As shown, the map generation system 1 includes a plurality of vehicle-mounted devices 10 and a map generation device 12. The plurality of vehicle-mounted devices 10 and the map generation device 12 are connected in a communicative manner via a network N. The map generation system 1 is a system that generates a dynamic map by giving priority to high-precision position information based on position information of a specific vehicle detected by the vehicle-mounted device 10 and position information of other vehicles, through the map generation device 12.

[0026] (In-vehicle device)

[0027] use Figure 2 , a structural example of the vehicle-mounted device in the implementation mode is described. Figure 2 It is a block diagram showing a configuration example of a vehicle-mounted device in the embodiment.

[0028] like Figure 2 As shown, the vehicle-mounted device 10 includes a camera 20, a communication unit 22, a storage unit 24, a GNSS (Global Navigation Satellite System) receiving unit 26, a sensor unit 28, and a control unit 30. The vehicle-mounted device 10 is mounted on a vehicle. The vehicle-mounted device 10 detects the position information of the vehicle and the position information of the surrounding objects of the vehicle, and the position information of the surrounding objects includes the position information of the surrounding vehicles around the vehicle. The vehicle-mounted device 10 sends the detection results of the position information of the vehicle and the position information of the surrounding objects around the vehicle to the map generation device 12.

[0029] The camera 20 is a camera that captures the surroundings of the vehicle. The camera 20 is, for example, a camera that captures dynamic images at a predetermined frame rate. The camera 20 may be a single-lens camera or a stereo camera. The camera 20 may be a single camera or a plurality of camera groups. The camera 20 includes a front camera that captures the front of the vehicle, a right side camera that captures the right side of the vehicle, a left side camera that captures the left side of the vehicle, and a rear camera that captures the rear of the vehicle. For example, the camera 20 captures the surroundings of the vehicle all the time while the vehicle is in motion.

[0030] The communication unit 22 performs communication between the vehicle-mounted device 10 and an external device. For example, the communication unit 22 performs communication with the map generating device 12. The communication unit 22 is implemented by a communication module that performs communication in accordance with communication standards such as 4G (fourth generation) and 5G (fifth generation).

[0031] The storage unit 24 stores various information. The storage unit 24 stores information such as the calculation contents and programs of the control unit 30. The storage unit 24 includes, for example, at least one of a main storage device such as a RAM (Random Access Memory) or a ROM (Read Only Memory), and an external storage device such as a HDD (Hard Disk Drive).

[0032] The GNSS receiving unit 26 is composed of a GNSS receiver that receives GNSS signals from GNSS satellites, etc. The GNSS receiving unit 26 outputs the received GNSS signals to the vehicle position detecting unit 44 of the control unit 30 .

[0033] The sensor unit 28 includes various sensors. The sensor unit 28 detects sensor information that can identify the state of the vehicle equipped with the vehicle-mounted device 10. The sensor unit 28 can use sensors such as position sensors, gyro sensors, and acceleration sensors. As the position sensor, for example, a laser radar (for example, LIDAR: Laser Imaging Detection and Ranging) that detects the distance to the surrounding objects, an infrared sensor including an infrared irradiation unit and a light receiving sensor, and a ToF (Time of Flight) sensor can be exemplified. The position sensor can be implemented by combining any multiple of a gyro sensor, an acceleration sensor, a laser radar, an infrared sensor, and a ToF sensor, or by combining all of them together.

[0034] The control unit 30 controls each unit of the vehicle-mounted device 10. The control unit 30 includes, for example, an information processing device such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) and a storage device such as a RAM or a ROM. The control unit 30 may also be implemented by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 30 may also be implemented by a combination of hardware and software.

[0035] The control unit 30 includes an imaging control unit 40 , a sensor control unit 42 , a vehicle position detection unit 44 , an object position detection unit 46 , and a communication control unit 48 .

[0036] The imaging control unit 40 controls the camera 20 to capture images of the surroundings of the host vehicle. The imaging control unit 40 acquires image data captured by the camera 20 .

[0037] The sensor control unit 42 controls the sensor unit 28 to detect the state of the host vehicle. The sensor control unit 42 acquires sensor information indicating the state of the host vehicle detected by the sensor unit 28.

[0038] The vehicle position detection unit 44 detects the position of the vehicle equipped with the vehicle-mounted device 10 (the position of the vehicle-mounted device 10). The vehicle position detection unit 44 detects the position of the vehicle equipped with the vehicle-mounted device 10 based on the GNSS signal received by the GNSS receiving unit 26. The vehicle position detection unit 44 may detect the position of the vehicle based not only on the GNSS signal but also on the sensor information acquired by the sensor control unit 42. For example, the vehicle position detection unit 44 detects the position of the vehicle based on the GNSS signal received by the GNSS receiving unit 26, the information of the gyro sensor acquired by the sensor control unit 42, and the information of the acceleration sensor. The vehicle position detection unit 44 calculates the global coordinates of the vehicle based on the GNSS signal, for example.

[0039] The object position detection unit 46 detects the position information of the objects located around the vehicle, that is, the position information of the surrounding objects. The object position detection unit 46 identifies the objects around the vehicle based on the image data acquired by the shooting control unit 40, and measures the distance from the identified objects to detect the position information of the surrounding objects of the vehicle. For example, when the camera 20 is a single-lens camera, the object position detection unit 46 detects the position information of the surrounding objects of the vehicle by using the SfM (Structure from Motion) method or the like. For example, the object position detection unit 46 can also analyze the behavior of the objects around the vehicle by the SfM method and calculate the position of the objects after a predetermined time. When the camera 20 is a stereo camera, the object position detection unit 46 detects the position information of the surrounding objects of the vehicle using the principle of triangulation. The object position detection unit 46 can also detect the position information of the surrounding objects of the vehicle based not only on the image data but also on the sensor information acquired by the sensor control unit 42. For example, the object position detection unit 46 detects position information of objects around the host vehicle based on the image data acquired by the imaging control unit 40 and the information of the gyro sensor and the acceleration sensor acquired by the sensor control unit 42 .

[0040] The object position detection unit 46 detects, for example, the position information of a moving object moving around the vehicle. The object position detection unit 46 detects, for example, the position information of surrounding vehicles traveling around the vehicle. The object position detection unit 46 detects, for example, the position information of a person moving around the vehicle. The object position detection unit 46 detects, for example, the position information of a bicycle or wheelchair moving around the vehicle.

[0041] The communication control unit 48 controls the communication unit 22 to control the communication between the vehicle-mounted device 10 and the external device. The communication control unit 48 controls the communication unit 22 to control the communication between the vehicle-mounted device 10 and the map generating device 12. The communication control unit 48, for example, sends the position information of the vehicle detected by the vehicle position detecting unit 44 to the map generating device 12. The communication control unit 48, for example, sends the position information of the surrounding objects detected by the object position detecting unit 46 to the map generating device 12.

[0042] (Map generation device)

[0043] use Figure 3 An example configuration of a map generating device in the embodiment will be described. Figure 3 It is a diagram showing a configuration example of a map generating device in an embodiment.

[0044] like Figure 3 As shown, the map generating device 12 includes a communication unit 50, a storage unit 52, and a control unit 54. The map generating device 12 is implemented by, for example, a server device arranged in a management center or the like that manages the map generating system 1. The map generating device 12 generates a dynamic map based on information obtained from the vehicle-mounted device 10.

[0045] The communication unit 50 performs communication between the map generating device 12 and an external device. For example, the communication unit 50 performs communication with the map generating device 12. The communication unit 50 is implemented by a communication module that performs communication in a manner such as 4G (4th Generation), 5G (5th Generation), wireless LAN, and wired LAN.

[0046] The storage unit 52 stores various information. The storage unit 52 stores information such as the calculation contents and programs of the control unit 54. The storage unit 52 includes at least one of a main storage device such as a RAM and a ROM, and an external storage device such as a HDD.

[0047] The storage unit 52 stores basic map information 52a as a basis for generating a dynamic map. A dynamic map generally refers to a map obtained by mapping dynamic object data such as pedestrians, cars, and traffic conditions to static map data. The basic map information 52a is high-precision static map data. The map data includes road information, building information, etc.

[0048] The control unit 54 controls each unit of the map generating device 12. The control unit 54 includes, for example, an information processing device such as a CPU or an MPU and a storage device such as a RAM or a ROM. The control unit 54 may be implemented by, for example, an integrated circuit such as an ASIC or an FPGA. The control unit 54 may also be implemented by a combination of hardware and software.

[0049] The control section 54 includes an information acquisition section 60 , a reliability determination section 62 , a map integration section 64 , and a communication control section 66 .

[0050] The information acquisition unit 60 acquires various information from the vehicle-mounted device 10 via the communication unit 50. The information acquisition unit 60 acquires the position information of the vehicle detected by the vehicle position detection unit 44 of each of the plurality of vehicle-mounted devices 10 as the position information of the specific vehicle via the communication unit 50. The information acquisition unit 60 acquires the position information of the surrounding objects via the communication unit 50, and the position information of the surrounding objects includes the position information of the surrounding vehicles located around the specific vehicle on which the vehicle-mounted device 10 is mounted, detected by the object position detection unit 46 of each of the plurality of vehicle-mounted devices 10.

[0051] Since the information of each of the plurality of vehicle-mounted devices 10 is different according to the performance of the camera, sensor, etc. of each of the vehicle-mounted devices 10, the reliability determination unit 62 determines the reliability indicating the degree of detection accuracy of the surrounding objects of each of the plurality of vehicle-mounted devices 10. The reliability determination unit 62 determines the reliability of the detection accuracy of the surrounding objects of the vehicle-mounted devices 10 mounted on the surrounding vehicles, for example, based on the degree of consistency between the position information of the vehicle detected by the vehicle-mounted device 10 mounted on the vehicle and the position information of the vehicle detected by the vehicle-mounted devices 10 mounted on the surrounding vehicles. For example, the higher the degree of consistency between the position information of a specific vehicle detected by the vehicle-mounted device 10 mounted on the surrounding vehicles and the position information of the specific vehicle detected by the vehicle-mounted device 10 mounted on the specific vehicle, the higher the reliability determination unit 62 determines the detection accuracy of the surrounding objects of the vehicle-mounted device 10 mounted on the surrounding vehicles. This is because the detection accuracy of the position of the specific vehicle by the vehicle-mounted device 10 based on the GNSS signal is higher than the detection accuracy of the position of the surrounding vehicles based on the image data.

[0052] The reliability of the vehicle-mounted device 10 depends not only on the performance of the device, but may also change dynamically depending on the direction of sunlight, surrounding brightness, vehicle speed, weather, and lens contamination of the camera 20 when the vehicle is traveling. Therefore, the reliability determination unit 62 preferably determines the reliability every time it obtains position information from the vehicle-mounted device 10. In other words, the reliability determination unit 62 preferably always keeps determining the reliability of the vehicle-mounted device 10.

[0053] The reliability determination unit 62 may determine the reliability of the vehicle-mounted device 10 at a predetermined timing, for example, when the reliability determination processing load is heavy. The reliability determination unit 62 may determine the reliability of the vehicle-mounted device 10, for example, when the vehicle stops due to a red light or traffic congestion. By determining the reliability of the vehicle-mounted device 10 at a predetermined timing, the processing load can be reduced.

[0054] The map integration unit 64 integrates the position information of the specific vehicle and the position information of the surrounding objects obtained from the vehicle-mounted device 10 into the basic map information 52a stored in the storage unit 52 to generate a dynamic map. The map integration unit 64 integrates the position information of the surrounding objects obtained from the vehicle-mounted device 10 determined based on the reliability among the multiple vehicle-mounted devices 10 into the basic map information 52a to generate a dynamic map. The map integration unit 64 integrates the position information of the surrounding objects obtained from the vehicle-mounted device 10 with the highest reliability among the multiple vehicle-mounted devices 10 into the basic map information 52a to generate a dynamic map. The map integration unit 64 may also integrate the position information of the surrounding objects obtained from the vehicle-mounted device 10 with a reliability higher than a predetermined threshold among the multiple vehicle-mounted devices 10 into the basic map information 52a to generate a dynamic map.

[0055] The communication control unit 66 controls the communication unit 50 to control the communication between the map generating device 12 and the external device. The communication control unit 66 controls the communication unit 50 to control the communication between the map generating device 12 and the vehicle-mounted device 10.

[0056] (Map generation process)

[0057] use Figure 4 The map generation process in the embodiment will be described. Figure 4 This is a flowchart showing the flow of map generation processing in the embodiment.

[0058] Figure 4 The flow of processing in which the map generating device 12 generates a dynamic map based on information acquired from the vehicle-mounted device 10 is shown.

[0059] The information acquisition unit 60 acquires the position information of the specific vehicle (step S10 ). Figure 5 FIG. 1 is a diagram for explaining a method for acquiring vehicle information in an embodiment. Figure 5 In the diagram, the direction written with "forward" indicates the direction of travel of the vehicle, and the direction written with "rearward" indicates the opposite direction of the direction of travel of the vehicle. Figure 5As shown, for example, it is assumed that vehicles 100A, 100B, and 100C are traveling on a road. Vehicle 100A is equipped with a vehicle-mounted device 10A. Vehicle 100B is equipped with a vehicle-mounted device 10B. Vehicle 100C is equipped with a vehicle-mounted device 10C. The vehicle-mounted devices 10A, 10B, and 10C have the same Figure 2 The vehicle-mounted device 10 shown in the figure has the same structure. The detection accuracy of the position of the specific vehicle and the detection accuracy of the positions of the surrounding vehicles of the vehicle-mounted device 10A, the vehicle-mounted device 10B and the vehicle-mounted device 10C may be different. In this case, the information acquisition unit 60 acquires the position information of the vehicle 100A detected by the vehicle-mounted device 10A from the vehicle-mounted device 10A. The information acquisition unit 60 acquires the position information of the vehicle 100B detected by the vehicle-mounted device 10B from the vehicle-mounted device 10B. The information acquisition unit 60 acquires the position information of the vehicle 100C detected by the vehicle-mounted device 10C from the vehicle-mounted device 10C. Then, enter step S12.

[0060] The information acquisition unit 60 acquires the position information of the surrounding vehicles of the specific vehicle (step S12). Figure 5 The information acquisition unit 60 acquires the position information of the vehicle 100B and the vehicle 100C acquired by the vehicle-mounted device 10A from the vehicle-mounted device 10A. The information acquisition unit 60 acquires the position information of the vehicle 100A and the vehicle 100C acquired by the vehicle-mounted device 10B from the vehicle-mounted device 10B. The information acquisition unit 60 acquires the position information of the vehicle 100A and the vehicle 100B acquired by the vehicle-mounted device 10C from the vehicle-mounted device 10C. Then, the process proceeds to step S14.

[0061] exist Figure 4 In the illustrated flow, the information acquisition unit 60 may not necessarily acquire the position information of the specific vehicle and the position information of the surrounding vehicles of the specific vehicle from the plurality of vehicle-mounted devices 10 in steps S10 and S12 .

[0062] The reliability determination unit 62 determines whether the position information of the specific vehicle has been acquired from the vehicle-mounted devices installed in a plurality of surrounding vehicles (step S14). Figure 5. Regarding vehicle 100A, the reliability determination unit 62 determines whether the location information of vehicle 100A has been obtained from both the vehicle-mounted device 10B and the vehicle-mounted device 10C. Regarding vehicle 100B, the reliability determination unit 62 determines whether the location information of vehicle 100B has been obtained from both the vehicle-mounted device 10A and the vehicle-mounted device 10C. Regarding vehicle 100C, the reliability determination unit 62 determines whether the location information of vehicle 100C has been obtained from both the vehicle-mounted device 10A and the vehicle-mounted device 10B. In a case where it is determined that the location information of a specific vehicle has been obtained from vehicle-mounted devices installed in multiple surrounding vehicles (step S14: Yes), the process proceeds to step S16. In a case where it is not determined that the location information of a specific vehicle has been obtained from vehicle-mounted devices installed in multiple surrounding vehicles (step S14: No), the process proceeds to step S10.

[0063] If it is determined to be yes in step S14, the reliability determination unit 62 determines whether the time when the position information of the specific vehicle is detected is consistent with the time when the surrounding vehicles of the specific vehicle detect the position information of the specific vehicle within a specified range (step S16). The specified range refers to a specified time range. Specifically, the reliability determination unit 62 determines whether the time when the vehicle-mounted device 10A detects the vehicle 100A is consistent with the time when the vehicle-mounted device 10B and the vehicle-mounted device 10C each detect the vehicle 100A within a specified range. The reliability determination unit 62 determines whether the time when the vehicle-mounted device 10B detects the vehicle 100B is consistent with the time when the vehicle-mounted device 10A and the vehicle-mounted device 10C each detect the vehicle 100B within a specified range. The reliability determination unit 62 determines whether the time when the vehicle-mounted device 10C detects the vehicle 100C is consistent with the time when the vehicle-mounted device 10A and the vehicle-mounted device 10B each detect the vehicle 100C within a specified range. Here, the specified range can also be changed according to the driving state of the vehicle. For example, when all vehicles 100A to 100C are stopped, the specified range is expanded, for example, set to a few seconds. For example, when any of the vehicles 100A to 100C is traveling at high speed, the prescribed range may be set narrower, for example, to a few milliseconds. If it is determined that the time when the position information of the specific vehicle is detected coincides with the time when the position information of the specific vehicle is detected by the surrounding vehicles of the specific vehicle (step S16: Yes), the process proceeds to step S18. If it is determined that the time when the position information of the specific vehicle is detected coincides with the time when the position information of the specific vehicle is detected by the surrounding vehicles of the specific vehicle (step S16: No), the process proceeds to step S10.

[0064] However, when it is determined that the time when the position information of the specific vehicle is detected is inconsistent with the time when the position information of the specific vehicle is detected by the surrounding vehicles of the specific vehicle (step S16: No), when processing is performed to predict the position of the specific vehicle and the positions of the surrounding vehicles based on the vehicle's driving speed, etc., it is also possible to enter step S18 instead of step S10.

[0065] If the determination result in step S16 is yes, the reliability determination unit 62 determines the reliability of the vehicle-mounted device (step S18). The reliability determination unit 62 determines the reliability of each vehicle-mounted device based on the degree of consistency between the position information of the specific vehicle detected by the vehicle-mounted device mounted on the specific vehicle and the position information of the specific vehicle detected by the vehicle-mounted devices mounted on the surrounding vehicles. Figure 6 , Figure 7 , Figure 8 It is a diagram for explaining a method of calculating a deviation of position information in an embodiment.

[0066] Figure 6 10A is a diagram showing the detection result of the position information of the surrounding vehicles by the vehicle-mounted device 10A. The detected vehicle 110B shows the position of the vehicle 100B detected by the vehicle-mounted device 10A. The detected vehicle 110C shows the position of the vehicle 100C detected by the vehicle-mounted device 10A.

[0067] Figure 7 1 is a diagram showing the detection result of the position information of the periphery of the vehicle by the vehicle-mounted device 10B. The detected vehicle 120A shows the position of the vehicle 100A detected by the vehicle-mounted device 10B. The detected vehicle 120C shows the position of the vehicle 100C detected by the vehicle-mounted device 10B.

[0068] Figure 8 1 is a diagram showing the detection result of the position information of the periphery of the vehicle by the vehicle-mounted device 10C. The detected vehicle 130A shows the position of the vehicle 100A detected by the vehicle-mounted device 10C. The detected vehicle 130B shows the position of the vehicle 100B detected by the vehicle-mounted device 10C.

[0069] Reference Figures 6 to 8 ,like Figure 6 As shown, the positions of the detection vehicle 110B and the detection vehicle 110C detected by the vehicle-mounted device 10A are greatly different from the positions of the vehicle 100B detected by the vehicle-mounted device 10B and the vehicle 100C detected by the vehicle-mounted device 10C, respectively. In this case, the reliability determination unit 62 determines that the reliability of the vehicle-mounted device 10A is low. Specifically, when the distance between the position information of the specific vehicle detected by the vehicle-mounted device mounted on the specific vehicle and the position information of the specific vehicle detected by the vehicle-mounted devices mounted on the surrounding vehicles is greater than 1m, it is determined that the reliability of the vehicle-mounted device A is low.

[0070] Reference Figures 6 to 8 ,like Figure 7 As shown, the positions of the detection vehicle 120A and the detection vehicle 120C detected by the vehicle-mounted device 10B are less different from the positions of the vehicle 100A and the vehicle 100C detected by the vehicle-mounted device 10A and the vehicle 100C detected by the vehicle-mounted device 10C, respectively. In this case, the reliability determination unit 62 determines that the reliability of the vehicle-mounted device 10B is high. Specifically, when the distance between the position information of the specific vehicle detected by the vehicle-mounted device mounted on the specific vehicle and the position information of the specific vehicle detected by the vehicle-mounted devices mounted on the surrounding vehicles is less than 1m, the reliability of the vehicle-mounted device A is determined to be high.

[0071] Reference Figures 6 to 8 ,like Figure 8 As shown, the position of the detection vehicle 130A detected by the vehicle-mounted device 10C is consistent with the position of the vehicle 100A detected by the vehicle-mounted device 10A. In addition, the position of the detection vehicle 130B detected by the vehicle-mounted device 10C is significantly different from the position of the vehicle 100B detected by the vehicle-mounted device 10B. In this case, the reliability determination unit 62 may also determine the reliability of the vehicle-mounted device 10C in each direction. Figure 8 In the example shown, if the right hand side is regarded as the right side when viewed from the traveling direction described as the front, the reliability determination unit 62 determines that the reliability of the front of the vehicle-mounted device 10C is the highest among the vehicle-mounted device 10A, the vehicle-mounted device 10B, and the vehicle-mounted device 10C, and the reliability of the right side is relatively low among the vehicle-mounted device 10A, the vehicle-mounted device 10B, and the vehicle-mounted device 10C. The reliability determination unit 62 may determine the reliability of each of the front, the rear, the left side, and the right side, for example. The reliability determination unit 62 may also determine the reliability of only a specific direction.

[0072] exist Figures 6 to 8 In the illustrated example, the reliability determination unit 62 determines that the reliability of the onboard device 10B is the highest among the onboard device 10A, the onboard device 10B, and the onboard device 10C.

[0073] So far, the reliability of the vehicle-mounted device 10 has been described as two values, high and low, but the expression of reliability is not limited to this. Reliability can also be expressed as a score in the range of 0 to 10, for example. In this case, the lower the score, the lower the reliability, and the higher the score, the higher the reliability. When the reliability determination unit 62 expresses the reliability as a score, it can also use a well-known technique of matching feature points to determine the reliability.

[0074] The map integration unit 64 places the position of the specific vehicle on the map (step S20). Figure 5. The map integration unit 64 integrates the position information of the vehicle 100A detected by the vehicle-mounted device 10A into the basic map information 52a. The map integration unit 64 integrates the position information of the vehicle 100B detected by the vehicle-mounted device 10B into the basic map information 52a. The map integration unit 64 integrates the position information of the vehicle 100C detected by the vehicle-mounted device 10C into the basic map information 52a. That is, since the reliability of the vehicle position information detected based on the GNSS signal is high, the map integration unit 64 directly integrates the detected position into the basic map information 52a. Specifically, since the vehicle is a continuously moving object, the map integration unit 64 integrates the position information of the vehicles 100A to 100C into the basic map information 52a as dynamic information of a dynamic map associated with the time. Proceed to step S22.

[0075] The map integration unit 64 arranges the surrounding objects detected by the highly reliable vehicle-mounted device on the map (step S22 ). Fig. 9 FIG. 1 is a diagram for explaining a method of arranging surrounding objects on a map in an embodiment. Fig. 9 As shown, as surrounding objects, the characters U1 and U2 are located around the vehicle 100A, the vehicle 100B, and the vehicle 100C. In this case, the map integration unit 64 integrates the position information of the characters U1 and U2 detected by the vehicle-mounted device 10B, which is determined to be the most reliable, into the basic map information 52a. Specifically, since the characters U1 and U2 are continuously moving objects, the map integration unit 64 integrates the position information of the characters U1 and U2 into the basic map information 52a as dynamic information of a dynamic map associated with the moment. Here, the surrounding objects configured on the map by the map integration unit 64 are not only characters, but also all moving objects moving around a specific vehicle, including vehicles, bicycles, wheelchairs, etc. that are not equipped with the vehicle-mounted device 10.

[0076] The map integration unit 64 may also arrange not only the surrounding objects detected by the vehicle-mounted device 10 determined to have the highest reliability but also the surrounding objects detected by the vehicle-mounted device 10 having a reliability of at least an arbitrary threshold value on the map. For example, when the reliability is expressed as a score ranging from 0 to 10, the surrounding objects detected by the vehicle-mounted device 10 having a reliability of 8 or more are arranged on the map. In this case, sometimes the same surrounding object detected by multiple vehicle-mounted devices 10 is arranged on the map, so the location information of the object may be different in each vehicle-mounted device 10. For example, in Fig. 9In the above example, there may be a discrepancy between the position information of the person U1 detected by the vehicle-mounted device 10C and the position information of the person U1 detected by the vehicle-mounted device 10B. In this case, the map integration unit 64 integrates the intermediate position between the position information of the person U1 detected by the vehicle-mounted device 10C and the position information of the person U1 detected by the vehicle-mounted device 10B into the basic map information 52a as the position information of the person U1.

[0077] When the plurality of vehicle-mounted devices 10 set the reliability for each direction, the map integration unit 64 may arrange the surrounding objects on the map according to the reliability for each direction. Fig.10 FIG. 1 is a diagram for explaining a method of arranging surrounding objects on a map in a modified example of the embodiment. Fig.10 As shown, for example, the person U1 is located on the right side of the vehicle 100B and the vehicle 100C, and the person U3 is located in front of the vehicle 100C. In this case, the map integration unit 64 may also arrange the position information of the person U1 detected by the vehicle-mounted device 10B determined by the reliability determination unit 62 as having high reliability among the vehicle-mounted devices 10A to 10C on the map, and arrange the position information of the person U3 on the map detected by the vehicle-mounted device 10C determined by the reliability determination unit 62 as having the highest reliability in the forward direction among the vehicle-mounted devices 10A to 10C. In this way, the accuracy of the map can be further improved.

[0078] As described above, the present embodiment determines the reliability of the vehicle-mounted devices respectively mounted on the specific vehicle and the surrounding vehicles around the specific vehicle, and integrates the position information of the surrounding objects detected by the highly reliable vehicle-mounted devices into the map data as the dynamic information of the dynamic map. Thus, the present embodiment can generate a high-precision map as long as there are surrounding vehicles in the environment even if there are no objects that can be identified as landmarks in the surrounding area.

[0079] [Modification of the embodiment]

[0080] The following is a description of a modified example of the implementation. In the implementation, the position information of a specific vehicle equipped with a vehicle-mounted device is detected based on GNSS signals, so the accuracy is good. However, in the case of a short driving time or continuous straight driving, the reliability of the position of the specific vehicle will also decrease.

[0081] In a modified example of the embodiment, the control unit 30 of the vehicle-mounted device 10 may also determine whether the accuracy of the position of the specific vehicle detected by the vehicle position detection unit 44 exceeds a predetermined threshold. The control unit 30 of the vehicle-mounted device 10 determines that the accuracy of the position of the specific vehicle detected by the vehicle position detection unit 44 is less than the predetermined threshold when the driving time is less than a predetermined time, or when the vehicle continues to drive in a straight line for more than a predetermined time. In this case, when it is determined that the accuracy of the position of the specific vehicle is less than the threshold, the communication control unit 48 may not send the position information of the specific vehicle to the map generation device 12. As a result, position information with an accuracy less than the threshold is not used when generating a dynamic map, so that the accuracy of the dynamic map can be prevented from being deteriorated.

[0082] The control unit 30 of the vehicle-mounted device 10 may also determine whether the accuracy of the position of the specific vehicle detected by the vehicle position detection unit 44 exceeds a predetermined threshold value by the control unit 54 of the map generation device 12. In this case, if it is determined that the accuracy of the position information of the specific vehicle detected by the vehicle position detection unit 44 is less than the threshold value, the map integration unit 64 does not integrate the position information into the basic map information 52a. This can prevent the accuracy of the dynamic map from deteriorating.

[0083] The components of each device shown in the figure are conceptual functions and do not necessarily need to be physically configured as shown in the figure. That is, the specific method of distributing and integrating each device is not limited to the method shown in the figure, and all or part of them can be functionally or physically distributed or integrated in arbitrary units according to various loads, usage conditions, etc. In addition, the structure based on this distribution / integration can also be dynamically performed.

[0084] The embodiments of the present invention have been described above, but the present invention is not limited to the contents of these embodiments. In addition, the above-mentioned constituent elements include elements that can be easily thought of by those skilled in the art, substantially the same elements, and elements of so-called equal scope. Moreover, the above-mentioned constituent elements can be appropriately combined. Moreover, various omissions, substitutions or changes of constituent elements can be performed within the scope of the gist of the above-mentioned embodiments.

[0085] The present invention contributes to the realization of "laying the foundation for industrial and technological innovation" of SDGs (Sustainable Development Goals), and includes matters that contribute to value creation based on IoT solutions.

[0086] Industrial Applicability

[0087] The map generating device and the map generating method of the present invention can be applied to information processing devices such as computers, for example.

[0088] Description of Reference Numerals

[0089] 1Map Generation System

[0090] 10 Car-mounted device

[0091] 12Map Generator

[0092] 20 cameras

[0093] 22.50 Ministry of Communications

[0094] 24, 52 Storage

[0095] 26GNSS receiving unit

[0096] 28 Sensor unit

[0097] 30, 54 control unit

[0098] 40 Shooting control unit

[0099] 42Sensor control unit

[0100] 44 Vehicle position detection unit

[0101] 46 Object position detection unit

[0102] 48 Communication Control Unit

[0103] 52a basic map information

[0104] 60 Information Acquisition Department

[0105] 62Reliability determination unit

[0106] 64 Map Integration Department

[0107] 66 Communication Control Unit

Claims

1. A map generating device, comprising: an information acquisition unit that acquires position information of the specific vehicle and position information of the surrounding vehicles from vehicle-mounted devices respectively arranged on the specific vehicle and surrounding vehicles located around the specific vehicle; a reliability determination unit that determines the reliability of each of the vehicle-mounted devices based on the degree of consistency between the position information of the specific vehicle detected by the vehicle-mounted device mounted on the specific vehicle and the position information of the specific vehicle detected by the vehicle-mounted device mounted on the surrounding vehicles; as well as The map integration unit integrates the position information of the surrounding objects acquired from the vehicle-mounted device determined based on the reliability among the plurality of vehicle-mounted devices into a map.

2. The map generating device according to claim 1, wherein: The map integration unit integrates the position information of the surrounding objects acquired from the vehicle-mounted device with the highest reliability into a map.

3. The map generating device according to claim 1, wherein: The map integration unit integrates the position information of the surrounding objects acquired from the vehicle-mounted device whose reliability is higher than a predetermined threshold into a map.

4. The map generating device according to any one of claims 1 to 3, wherein: The reliability determination unit determines the reliability of each direction of the vehicle-mounted device based on the degree of consistency between the position information of the specific vehicle detected by the vehicle-mounted device mounted on the specific vehicle and the position information of the specific vehicle detected by the vehicle-mounted device mounted on the surrounding vehicles, The map integration unit integrates the position information of the surrounding objects into the map based on the reliability of each of the directions.

5. A map generation method comprising the following steps: acquiring position information of the specific vehicle and position information of the surrounding vehicles from vehicle-mounted devices respectively arranged on the specific vehicle and surrounding vehicles located around the specific vehicle; determining the reliability of each of the vehicle-mounted devices based on the degree of consistency between the position information of the specific vehicle detected by the vehicle-mounted device mounted on the specific vehicle and the position information of the specific vehicle detected by the vehicle-mounted devices mounted on the surrounding vehicles; as well as The position information of the surrounding objects acquired from the vehicle-mounted device determined based on the reliability among the plurality of vehicle-mounted devices is integrated into a map.

Images