Data generation device, data generation method, and program

Abstract

A data generation device comprises a measurement data acquisition means, an estimation means, and a superimposed data generation means. The measurement data acquisition means acquires measurement data, including shape data of objects existing in the periphery of a vehicle traveling on a road corresponding to predetermined map data. The estimation means detects, based on the difference between the map data and the measurement data, objects not included in the map data, and estimates the time period during which such objects exist. The superimposed data generation means generates, in a manner enabling output, superimposed data by superimposing object data representing the shape of the object and period data concerning the period of the object onto the map data.

Description

Data generation device, data generation method and program

[0001] The present invention relates to a data generation device, a data generation method, and a program.

[0002] BACKGROUND ART Various technologies have been developed to assist the movement of mobile objects such as automobiles.

[0003] For example, the environmental map data described in Patent Document 1 includes position information indicating a plurality of positions in a space, and state quantity variability and state quantity representative values ​​that indicate the ease with which the state quantity at each position changes over time.

[0004] Japanese Patent Application Laid-Open No. 2017-194527

[0005] However, when the above-mentioned technology is used for driving a car, it is difficult to properly grasp the positions and periods of surrounding objects that change periodically.

[0006] In view of the above-described problems, the present disclosure aims to provide a data generating device and the like that generates usable data related to objects that periodically exist around a vehicle.

[0007] A data generation device according to one embodiment of the present disclosure includes a measurement data acquisition means, an estimation means, and a superposition data generation means. The measurement data acquisition means acquires measurement data including shape data of objects present around a vehicle traveling on a road corresponding to predetermined map data. The estimation means detects objects not included in the map data based on differences between the map data and the measurement data, and estimates the time period in which the objects exist. The superposition data generation means generates outputtable superposition data in which object data representing the object's shape and period data relating to the object's period are superimposed on the map data.

[0008] In a data generation method according to an embodiment of the present disclosure, a computer executes the following processes: the computer acquires measurement data including shape data of objects present around a vehicle traveling on a road corresponding to predetermined map data; the computer detects differences between the map data and the measurement data and estimates a period of the differences; and the computer generates superimposed data in such a manner that the superimposed data is outputtable, in which object data representing the shapes of the objects and periodic data relating to the period of the objects are superimposed on the map data.

[0009] A program according to one embodiment of the present disclosure causes a computer to execute the following steps: the computer acquires measurement data including shape data of objects present around a vehicle traveling on a road corresponding to predetermined map data; the computer detects differences between the map data and the measurement data and estimates a period of the differences; and the computer generates superimposed data in such a manner that the superimposed data is outputtable, the superimposed data being obtained by superimposing object data representing the shapes of the objects and periodic data relating to the period of the objects on the map data.

[0010] According to the present disclosure, it is possible to provide a data generation device, a data generation method, and a program that generate usable data related to objects that periodically exist around a vehicle.

[0011] FIG. 1 is a block diagram showing the configuration of a data generating device according to an embodiment; FIG. 2 is a first flowchart showing a data generating method; FIG. 3 is a first block diagram showing the configuration of an automobile system; FIG. 4 is a second flowchart showing a data generating method; FIG. 5 is a first diagram showing superimposed data; FIG. 6 is a flowchart showing a method of managing superimposed data; FIG. 7 is a second block diagram showing the configuration of an automobile system; FIG. 8 is a second diagram showing superimposed data; and FIG. 9 is a block diagram illustrating the hardware configuration of a computer.

[0012] The present invention will be described below through embodiments of the invention, but the invention according to the claims is not limited to the following embodiments. Furthermore, not all of the configurations described in the embodiments are necessarily essential means for solving the problems. For clarity of explanation, the following description and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are assigned the same reference numerals, and duplicate explanations are omitted as necessary.

[0013] <First Embodiment> A data generating device 10 according to this embodiment will be described with reference to FIG. 1. FIG. 1 is a block diagram showing the configuration of the data generating device 10. The data generating device 10 generates data used by vehicles traveling on roads corresponding to predetermined map data. Vehicles traveling on roads include passenger cars, taxis, buses, trucks, etc. Vehicles traveling on roads may also be two-wheeled vehicles such as motorcycles and bicycles. These vehicles may also be driven by humans or may be semi-automatically or fully automatically driven.

[0014] The data generating device 10 is, for example, a computer or a dedicated device mounted on a vehicle. The data generating device 10 is also a computer or a server with a communication function. The data generating device 10 mainly includes a measurement data acquiring unit 111, an estimation unit 112, and a superposition data generating unit 113.

[0015] The measurement data acquisition unit 111 acquires measurement data including shape data of objects present around a vehicle traveling on a road corresponding to predetermined map data. For example, the measurement data acquisition unit 111 acquires data measured by a distance measurement sensor mounted on the vehicle as shape data. The object is, for example, an object that is temporarily stationary. The object may be, for example, a vehicle that is periodically parked. The object may be, for example, an opening / closing part of an object that is periodically opened and closed. The opening / closing part includes, for example, a shutter or door of a building. The type of object is arbitrary.

[0016] The shape data acquired by the measurement data acquisition unit 111 is measured by a distance measurement sensor at predetermined intervals. The vehicle is moving while the distance measurement sensor is measuring the distance to the object. This allows the measurement data acquisition unit 111 to acquire three-dimensional point cloud data of the object. Furthermore, by having the distance measurement sensor acquire the shape data at predetermined intervals, the measurement data acquisition unit 111 can determine whether the object being measured is moving.

[0017] The measurement data acquisition unit 111 may acquire image data captured by a visible light camera or an infrared camera in addition to the distance measurement sensor. In this case, the measurement data acquisition unit 111 can recognize an object using the image data.

[0018] The estimation unit 112 detects objects not included in the map data based on the differences between the map data and the measurement data. The map data is, for example, three-dimensional space data configured as a virtual three-dimensional space. The estimation unit 112 detects objects not included in the map data by comparing the map data with the measurement data.

[0019] The estimation unit 112 also estimates the period of time during which the detected object is present. To estimate this period, the estimation unit 112 uses measurement data collected at multiple different times when the vehicle traveled along the road in the area where the object was detected. For example, the estimation unit 112 obtains measurement data from the past month to estimate the period of time during which the object is present in the corresponding area.

[0020] The period estimated by the estimation unit 112 may be, for example, a period of several hours, several days, or several weeks. The period may also include a period during which an object is present. For example, the period estimated by the estimation unit 112 may be that an object is present at a certain location from 8:00 AM to 9:00 AM every day.

[0021] The period estimated by the estimation unit 112 here includes a case where an object is always present, and also a case where an object is irregularly present.

[0022] The superimposition data generation unit 113 generates outputtable superimposition data in which shape data and periodic data of an object are superimposed on map data based on the difference between the map data and the measurement data and the period at which the object exists. The shape data is, for example, point cloud data measured by a distance measuring sensor set so as to be superimposable on map data. More specifically, for example, the shape data is data rendered so that the point cloud data can be superimposed on a predetermined virtual three-dimensional space.

[0023] The periodic data of an object is data relating to the period in which the object exists. The periodic data includes information relating to the period estimated by the estimation unit 112. By including the periodic data in the superimposed data, for example, when the vehicle is traveling near the object at the location and time when the object exists, the vehicle can use the shape data of the object.

[0024] 2 is a flowchart showing a data generation method executed by the data generation device 10. In the data generation method of this embodiment, the data generation device 10 executes the following processes.

[0025] First, the measurement data acquisition unit 111 acquires shape data of objects present around a vehicle traveling on a road corresponding to predetermined map data (step S11). The measurement data acquisition unit 111 supplies the acquired measurement data to the estimation unit 112.

[0026] Next, the estimation unit 112 detects a difference between the map data and the shape data, and estimates a period for the difference (step S12). The estimation unit 112 may acquire the map data from an external database. Alternatively, the estimation unit 112 may acquire map data that is pre-stored in the data generating device 10. The estimation unit 112 supplies information about the estimated period to the superposition data generating unit 113.

[0027] Next, the superimposition data generation unit 113 generates shape data and periodic data of the object from the difference between the map data and the shape data and the period estimated by the estimation unit 112. Furthermore, the superimposition data generation unit 113 superimposes the generated shape data and periodic data on the map data to generate outputtable superimposition data (step S13).

[0028] This concludes the description of the data generation method executed by the data generation device 10. By using the above-described method, the data generation device 10 generates superimposed data including data relating to periodically occurring objects.

[0029] The data generating device 10 may include a processor and a storage device (not shown). In this case, the storage device may include a nonvolatile memory such as a flash memory or a solid-state drive (SSD). In this case, the storage device may store a computer program (hereinafter simply referred to as a program) for executing the above-described method. The processor loads the computer program from the storage device into a buffer memory such as a dynamic random access memory (DRAM) and executes the program.

[0030] Each component of the data generation device 10 may be realized by dedicated hardware. Furthermore, some or all of the components may be realized by general-purpose or dedicated circuits, processors, etc., or a combination thereof. These may be configured by a single chip, or by multiple chips connected via a bus. Some or all of the components may be realized by a combination of the above-mentioned circuits, etc., and a program. Furthermore, a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), etc. may be used as the processor. Furthermore, at least some of the functions of this embodiment may be provided in the form of infrastructure as a service (IaaS), platform as a service (PaaS), software as a service (SaaS), etc.

[0031] As described above, according to the present embodiment, it is possible to provide a data generating device, a data generating method, and a program that generate usable data relating to objects that periodically exist around a vehicle.

[0032] <Second Embodiment> Next, a second embodiment will be described. Fig. 3 is a block diagram showing the configuration of an automobile system 1. The automobile system 1 is used, for example, for driving a vehicle. The automobile system 1 mainly comprises a data generating device 20, an information management device 200, a distance measuring sensor 301, and a positioning sensor 302. These components in the vehicle are communicably connected via a network N1. The network N1 is, for example, an in-vehicle LAN (Local Area Network).

[0033] The information management device 200 manages information related to vehicle operation. The information management device 200 is, for example, a navigation system. The information management device 200 may also be an ECU (Electronic Control Unit) for controlling at least some of the functions of the vehicle.

[0034] The ranging sensor 301 measures the distance to and shape of a measurement target. The ranging sensor 301 is, for example, a light detection and ranging (LiDAR) sensor. The ranging sensor 301 may include object recognition technology using a visible light camera or an infrared light camera. The positioning sensor 302 includes, for example, an antenna that receives positioning signals from satellites of the Global Navigation Satellite System (GNSS).

[0035] The data generating device 20 mainly comprises a measurement data acquiring unit 111 , an estimating unit 112 , a superimposed data generating unit 113 , a trained model 114 , an output unit 115 , and a memory unit 120 .

[0036] The measurement data acquisition unit 111 acquires shape data of objects around the vehicle from the distance measurement sensor 301 via the network N1. The data generation device 20 also acquires positioning data related to the vehicle's position from the positioning sensor 302 via the network N1. That is, the measurement data acquisition unit 111 acquires vehicle position data and time data acquired via a satellite positioning antenna provided on the vehicle as measurement data. The measurement data acquisition unit 111 stores the acquired measurement data in the storage unit 120.

[0037] The estimation unit 112 estimates the period using measurement data acquired from a period going back a predetermined set period. The predetermined set period is a period required for the estimation unit 112 to estimate the period. The predetermined set period is, for example, one week. The predetermined set period may also be one month or several months. The estimation unit 112 reads past data from the measurement data stored in the memory unit 120.

[0038] The estimation unit 112 according to this embodiment supplies map data and measurement data to the trained model 114 and receives an estimation result from the trained model 114. The estimation unit 112 receives the estimation result from the trained model 114, thereby estimating the period of the object.

[0039] Furthermore, if there are multiple objects, the estimation unit 112 estimates the period for each object. This allows the data generation device 20 to generate usable data for each of the multiple objects that exist periodically around the vehicle. The trained model 114 is a trained model that has learned to estimate the period in which objects exist using sample map data and sample measurement data as training data.

[0040] The superimposition data generation unit 113 generates superimposition data by using the map data, measurement data, and period data, which is data related to the period estimated by the estimation unit 112, stored in the storage unit 120. The superimposition data generation unit 113 stores the generated superimposition data in the storage unit 120.

[0041] The output unit 115 supplies the generated superimposition data to the information management device 200 via the network N1, for example, in response to a request from the information management device 200. The output unit 115 outputs superimposition data on which an object corresponding to the position and time at which the vehicle is located is superimposed, based on the period of the object. This allows the data generation device 20 to suitably provide superimposition data to the information management device 200 during vehicle operation.

[0042] The output unit 115 may also output superimposed data of the position and time according to the vehicle's travel schedule to a route generation device that generates a travel route for the vehicle. This allows the data generation device 20 to preferably provide information about periodically occurring objects to the information management device 200.

[0043] The storage unit 120 is a storage device including a non-volatile memory such as a solid-state drive (SSD) or flash memory. The storage unit 120 stores map data, measurement data, and superimposition data. The map data is, for example, virtual three-dimensional space data of the area in which the vehicle travels. The measurement data is measurement data from a predetermined period back.

[0044] Next, the processing executed by the data generating device 20 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the data generating method executed by the data generating device 20.

[0045] First, the measurement data acquisition unit 111 acquires shape data of objects present around the vehicle from the distance measurement sensor 301 (step S101). The measurement data acquisition unit 111 supplies the acquired measurement data to the estimation unit 112.

[0046] Next, the estimation unit 112 detects an object based on the difference between the map data and the shape data (step S102). Furthermore, the estimation unit 112 causes the trained model 114 to estimate the period of the object using measurement data for a preset period (step S103).

[0047] Next, the superimposition data generation unit 113 generates superimposition data from the map data, the shape data of the object, and the period data related to the period estimated by the estimation unit 112 (step S104). The superimposition data generation unit 113 supplies the generated superimposition data to the storage unit 120.

[0048] Next, the storage unit 120 adds the superimposition data received from the superimposition data generation unit 113 to the superimposition data stored in the storage unit 120 to update the data (step S105).

[0049] The above describes the data generation method executed by the data generating device 20. By using the above-described method, the data generating device 20 generates superimposition data including data related to objects that exist periodically during a preset period.

[0050] Next, an example of superimposition data will be described with reference to FIG. 5 . FIG. 5 is a diagram showing superimposition data generated by the data generating device 20. The superimposition data has a data structure that can be displayed on a display of a vehicle, for example. The superimposition data has a configuration in which multiple layers are superimposed. The superimposition data shown in FIG. 5 has layer 1, layer 2, and layer 3.

[0051] Layer 1 is map data. Layer 2 is object data. Object data is data that represents the shape of an object. Object data is three-dimensional shape data that is generated so that it can be superimposed on the virtual space of the map data. Layer 3 is periodic data. Periodic data is data linked to object data and includes information about the period in which the object exists.

[0052] With the above-described data structure, the information management device 200 using the superimposition data can, for example, display an image in which an object is superimposed on a virtual space on a navigation system screen. Furthermore, the information management device 200 can display a virtual space including an object on the navigation system screen when the object is present. In other words, the information management device 200 can display a virtual space in which no object is present on the navigation system screen when the object is not present. The format of the superimposition data is not limited to the example of FIG. 5 . The format of the superimposition data may be, for example, one in which map data, object data, and periodic data are associated in a format different from that of layers.

[0053] Next, a method for using the superimposed data will be described with reference to Fig. 6. Fig. 6 is a flowchart showing a method for using the superimposed data by the automobile system 1. In the example shown in Fig. 6, the automobile system 1 measures data relating to the distance to objects present around the vehicle and the shape of those objects in order to estimate its own position.

[0054] First, the automobile system 1 acquires positioning data and time data from the positioning sensor 302 (step S201). The automobile system 1 supplies the acquired positioning data and time data to the data generating device 20.

[0055] Next, the data generating device 20 of the automobile system 1 outputs superimposition data corresponding to the vehicle position and time from the acquired positioning data and time data (step S202). The superimposition data output by the data generating device 20 here has been generated in advance by the process shown in FIG.

[0056] Next, the automobile system 1 uses the object associated with the superimposed data output by the data generating device 20 for self-location estimation (step S203). More specifically, the automobile system 1 measures the distance to the object in real space corresponding to the three-dimensional shape data of the object included in the superimposed data, and uses the measurement data for self-location estimation.

[0057] Next, the automobile system 1 determines whether or not to end the series of processes (step S204). The series of processes may be ended, for example, when the vehicle stops traveling or when the operation of the automobile system 1 itself stops. If the automobile system 1 does not determine that the series of processes should be ended (step S204: NO), the automobile system 1 returns to step S201. If the automobile system 1 determines that the series of processes should be ended (step S204: YES), the automobile system 1 ends the processes.

[0058] The above describes a method for using superimposed data. By using the above method, the automobile system 1 can estimate its own location using objects having periodicity. However, the method for using superimposed data is not limited to the above. For example, the automobile system 1 can use the superimposed data when setting a driving route for the vehicle. In this case, the automobile system 1 can set an efficient route by using the superimposed data.

[0059] As described above, the data generating device 20 outputs usable data related to objects that have periodicity during vehicle travel. Note that in the automobile system 1, at least a portion of the data generating device 20 may be installed at a location remote from the vehicle. In this case, the data generating device 20 realizes the above-described functions by connecting to the vehicle via wireless communication.

[0060] As described above, according to the present embodiment, it is possible to provide a data generation device, a data generation method, and a program that generate usable data relating to objects that periodically exist around a vehicle.

[0061] Third Embodiment Next, a third embodiment will be described. Fig. 7 is a block diagram showing the configuration of an automobile system 2. The automobile system 2 differs from the above-described automobile system 1 in that it includes a data generating device 30. The data generating device 30 includes a determining unit 116.

[0062] The determination unit 116 determines whether an object detected by the estimation unit 112 can be used for vehicle self-localization estimation. More specifically, the determination unit 116 calculates the variance in the object's position at different times. If the variance in the object's position is within a predetermined range, the determination unit 116 determines that the object can be used for vehicle self-localization estimation. In this case, the determination unit 116 calculates the variance in the object's position by calculating a statistical value such as a variance or standard deviation. The object's position can be calculated, for example, by the distance from a predetermined reference position when the object is superimposed on map data as superimposition data. The determination unit 116 supplies the result of the determination on the object to the superimposition data generation unit 113.

[0063] The superimposition data generation unit 113 according to this embodiment adds the determination result received from the determination unit 116 to the superimposition data. That is, the superimposition data generation unit 113 generates superimposition data including information related to the determination.

[0064] 8 is a diagram showing the superimposition data generated by the superimposition data generating unit 113 according to this embodiment. The superimposition data shown in Fig. 8 differs from the superimposition data shown in Fig. 5 in that it includes layer 4.

[0065] Layer 4 is annotation data. The annotation data is data linked to the object data and includes data different from the periodic data. The annotation data includes, for example, information related to the determination made by the determination unit 116. That is, in the superimposed data, Layer 2 includes three-dimensional shape data of the object corresponding to the map data. Layer 3 includes periodic data linked to the object. And Layer 4 includes information related to the determination linked to the object. As a result, for example, the information management device 200 obtains information regarding the location of the object shown in the superimposed data, the time the object is present, and whether the object can be used for self-location estimation.

[0066] As described above, the data generating device 30 outputs information indicating that data measured on periodically existing objects can be used for self-location estimation, which enables the information management device 200 to suitably use the data on periodically existing objects for self-location estimation.

[0067] The annotation data may include information other than the information indicating that the data can be used for self-location estimation.

[0068] As described above, according to the present embodiment, it is possible to provide a data generation device, a data generation method, and a program that generate usable data relating to objects that periodically exist around a vehicle.

[0069] <Example of Hardware Configuration> Hereinafter, an example will be described in which each functional configuration of an information processing device according to the present disclosure is realized by a combination of hardware and software.

[0070] FIG. 10 is a block diagram illustrating an example of the hardware configuration of a computer. The information processing device of the present disclosure can realize the above-described functions by a computer 500 including the hardware configuration shown in the figure. The computer 500 may be a portable computer such as a smartphone or tablet terminal, or a stationary computer such as a PC. The computer 500 may be a dedicated computer designed to realize each device, or may be a general-purpose computer. The computer 500 can realize desired functions by installing a predetermined application.

[0071] The computer 500 has a bus 502, a processor 504, a memory 506, a storage device 508, an input / output interface (I / F) 510, and a network interface (I / F) 512. The bus 502 is a data transmission path for the processor 504, the memory 506, the storage device 508, the input / output interface 510, and the network interface 512 to transmit and receive data to and from each other. However, the method of connecting the processor 504 and the like to each other is not limited to bus connection.

[0072] The processor 504 is a processor such as a CPU, a GPU, an FPGA, etc. The memory 506 is a main storage device realized using a RAM (Random Access Memory) or the like.

[0073] The storage device 508 is an auxiliary storage device realized using a hard disk, an SSD, a memory card, a ROM (Read Only Memory), etc. The storage device 508 stores programs for realizing desired functions. The processor 504 reads the programs into the memory 506 and executes them to realize the respective functional components of each device.

[0074] The input / output interface 510 is an interface for connecting the computer 500 to input / output devices. For example, an input device such as a keyboard and an output device such as a display device are connected to the input / output interface 510. The network interface 512 is an interface for connecting the computer 500 to a network.

[0075] The present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0076] Each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0077] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes. (Supplementary Note 1) A data generation device comprising: a measurement data acquisition means for acquiring measurement data including shape data of objects present in the vicinity of a vehicle traveling on a road corresponding to predetermined map data; an estimation means for detecting the object not included in the map data based on a difference between the map data and the measurement data and estimating a time period in which the object is present; and a superimposition data generation means for generating superimposition data in which object data representing the shape of the object and period data related to the period of the object are superimposed on the map data so as to be output. (Supplementary Note 2) The data generation device according to Supplementary Note 1, wherein the estimation means estimates the period using the measurement data acquired during a period after a predetermined set period. (Supplementary Note 3) The data generation device according to Supplementary Note 1 or 2, wherein the measurement data acquisition means acquires, as the measurement data, position data and time data of the vehicle acquired via a satellite positioning antenna provided on the vehicle. (Supplementary Note 4) The data generation device according to any one of Supplements 1 to 3, wherein the estimation means estimates the period of the object by supplying the map data and the measurement data to a trained model that has learned to estimate the period in which the object exists using sample map data and sample measurement data as training data, and receiving an estimation result from the trained model. (Supplementary Note 5) The data generation device according to any one of Supplements 1 to 4, wherein, if a plurality of the objects are present, the estimation means estimates the period for each of the objects. (Supplementary Note 6) The data generation device according to any one of Supplements 1 to 5, further comprising: determination means that determines that the object can be used for self-localization estimation of the vehicle when variation in the position of the object at different times is within a predetermined range, and the superimposed data generation means generates the superimposed data including information related to the determination. (Supplementary Note 7) The data generating device according to any one of Supplementary Notes 1 to 6, further comprising: an output unit configured to output the superimposed data in which the object corresponding to the position and time at which the vehicle is present is superimposed, based on the period of the object.(Supplementary Note 8) The data generation device according to any one of Supplementary Notes 1 to 6, further comprising an output means for outputting the superimposition data of positions and times according to the vehicle's planned travel to a route generation device that generates a travel route for the vehicle. (Supplementary Note 9) A data generation method in which a computer acquires measurement data including shape data of objects present in the vicinity of a vehicle traveling on a road corresponding to predetermined map data, detects a difference between the map data and the measurement data, estimates a period for the difference, and generates outputtable superimposition data in which object data representing the shape of the object and period data related to the period of the object are superimposed on the map data. (Supplementary Note 10) A program that causes a computer to execute a data generation method in which a computer acquires measurement data including shape data of objects present in the vicinity of a vehicle traveling on a road corresponding to predetermined map data, detects a difference between the map data and the measurement data, estimates a period for the difference, and generates outputtable superimposition data in which object data representing the shape of the object and period data related to the period of the object are superimposed on the map data.

[0078] Some or all of the elements (e.g., configurations and functions) described in Supplementary Notes 2 to 8 that are dependent on Supplementary Note 1 may also be dependent on Supplementary Notes 9 and 10 in the same dependency relationship as Supplementary Notes 2 to 8. Some or all of the elements described in any Supplementary Note may be applied to various hardware, software, recording means for recording software, systems, and methods.

[0079] REFERENCE SIGNS LIST 1 Automobile system 2 Automobile system 10 Data generating device 20 Data generating device 30 Data generating device 111 Measurement data acquisition unit 112 Estimation unit 113 Superimposition data generating unit 114 Trained model 115 Output unit 116 Determination unit 120 Storage unit 200 Information management device 301 Distance measuring sensor 302 Positioning sensor 500 Computer 502 Bus 504 Processor 506 Memory 508 Storage device 510 Input / output I / F 512 Network I / F N1 Network

Claims

1. A data generation device comprising: measurement data acquisition means for acquiring measurement data including shape data of objects present around a vehicle traveling on a road corresponding to predetermined map data; estimation means for detecting the object not included in the map data based on the difference between the map data and the measurement data, and estimating the time period of the object's existence; and superimposition data generation means for generating outputtable superimposition data in which object data representing the object's shape and period data relating to the object's period are superimposed on the map data.

2. The data generating device according to claim 1, wherein the estimation means estimates the period using the measurement data acquired during a period going back a predetermined set period.

3. A data generating device according to claim 1 or 2, wherein the measurement data acquisition means acquires, as the measurement data, position data and time data of the vehicle acquired via a satellite positioning antenna provided on the vehicle.

4. A data generation device according to any one of claims 1 to 3, wherein the estimation means estimates the period of the object by supplying the map data and the measurement data to a trained model that has learned to estimate the period in which the object exists using sample map data and sample measurement data as training data, and receiving an estimation result from the trained model.

5. The data generating device according to any one of claims 1 to 4, wherein, when a plurality of objects are present, the estimation means estimates the period for each of the objects.

6. A data generation device according to any one of claims 1 to 5, further comprising a determination means for determining that the object can be used for estimating the vehicle's self-position when the variation in the object's position at different times is within a predetermined range, and wherein the superimposed data generation means generates the superimposed data including information relating to the determination.

7. The data generating device according to any one of claims 1 to 6, further comprising an output means for outputting the superimposed data in which the object corresponding to the position and time at which the vehicle is present is superimposed based on the period of the object.

8. The data generation device according to any one of claims 1 to 6, further comprising an output means for outputting the superimposed data of positions and times according to the vehicle's planned travel to a route generation device that generates a travel route for the vehicle.

9. A data generation method in which a computer acquires measurement data including shape data of objects present around a vehicle traveling on a road corresponding to predetermined map data, detects differences between the map data and the measurement data, estimates a period for the differences, and generates outputtable superimposed data in which object data representing the shape of the objects and period data relating to the period of the objects are superimposed on the map data.

10. The data generation method according to claim 9, wherein the computer further estimates the period using the measurement data acquired during a period going back a predetermined set period.

11. A data generation method according to claim 9 or 10, wherein the computer further acquires position data and time data of the vehicle obtained via a satellite positioning antenna provided on the vehicle as the measurement data.

12. A data generation method according to any one of claims 9 to 11, wherein the computer further estimates the period of the object by supplying the map data and the measurement data to a trained model that has learned to estimate the period in which the object exists using sample map data and sample measurement data as training data, and receiving an estimation result from the trained model.

13. The data generation method according to any one of claims 9 to 12, wherein, if there are multiple objects, the computer further estimates the period for each of the objects.

14. A data generation method according to any one of claims 9 to 13, wherein the computer further determines that the object can be used for estimating the vehicle's self-position when the variation in the object's position at different times is within a predetermined range, and generates the superimposed data including information related to the determination.

15. A data generation method according to any one of claims 9 to 14, wherein the computer further outputs the superimposed data in which the object corresponding to the position and time at which the vehicle is present is superimposed, based on the period of the object.

16. A data generation method according to any one of claims 9 to 14, wherein the computer further outputs the superimposed data of positions and times according to the vehicle's planned travel to a route generation device that generates a travel route for the vehicle.

17. A program causing a computer to execute a data generation method, which comprises acquiring measurement data including shape data of objects present around a vehicle traveling on a road corresponding to predetermined map data, detecting differences between said map data and said measurement data, estimating a period for said differences, and generating outputtable superimposed data in which object data representing the shape of said object and period data relating to said period of said object are superimposed on said map data.

18. The program according to claim 17, wherein the computer further estimates the period using the measurement data acquired during a period after a predetermined set period.

19. A program according to claim 17 or 18, wherein the computer further acquires position data and time data of the vehicle obtained via a satellite positioning antenna provided on the vehicle as the measurement data.

20. The program described in any one of claims 17 to 19, wherein the computer further estimates the period of the object by supplying the map data and the measurement data to a trained model that has learned to estimate the period in which the object exists using sample map data and sample measurement data as training data, and receiving an estimation result from the trained model.

Images