Information processing device, information processing method, route searching device, route searching method and program

Abstract

To provide an information processing device capable of searching for an appropriate route based on information on the collective entity of objects to be detected.SOLUTION: An information processing device 1 includes: object detecting means 15-1-2 for detecting a first object and a second object; collective entity determining means 15-1-3 for determining whether the first object and the second object are the collective entity in the same group based on pieces of object detection information on the first object and the second object detected by the object detecting means; calculating means 15-1-4 for calculating spatial information on an occupied region that is occupied by at least one of the first object, the second object, and the collective entity; and transmitting means 15-4 for transmitting at least one of the object detection information, the information on the collective entity, and the spatial information.SELECTED DRAWING: Figure 12

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, a route search device, a route search method, and a program that perform a route search using information about a collection of detected objects. [Background technology]

[0002] Patent Document 1 discloses a method for notifying a moving vehicle of the presence of a moving group of multiple moving objects detected by a camera or radar installed near a road, in order to notify the moving vehicle of the presence of the moving group more quickly when a moving object such as a pedestrian or a bicycle suddenly appears. Patent Document 2 discloses a method for detecting suspicious individuals in a scene with many people captured on camera, in which people flow analysis is performed and individuals who are not following the flow of people are registered as suspicious individual candidates. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2020 / 116266 [Patent Document 2] Japanese Patent Application Publication No. 2019-50438 Summary of the Invention [Problem to be solved by the invention]

[0004] However, Patent Documents 1 and 2 do not disclose a method for providing suitable route information to an autonomously driving mobility vehicle using information related to a group of detected objects. Furthermore, Patent Documents 1 and 2 do not disclose a method for preventing an autonomously driving mobility vehicle from selecting a route that goes through a gap that occurs in a group of detected objects.

[0005] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide an information processing device that is capable of performing an appropriate route search based on information relating to a collection of detected objects. [Means for solving the problem]

[0006] An information processing device as one aspect of the present invention includes an object detection means for detecting a first object and a second object, an aggregate determination means for determining whether the first object and the second object are aggregates of the same group based on object detection information regarding the first object and the second object detected by the object detection means, a calculation means for calculating spatial information regarding an occupied area occupied by at least one of the first object, the second object, and the aggregate, and a transmission means for transmitting at least one of the object detection information, information regarding the aggregate, and the spatial information.

[0007] Other objects and features of the present invention will be described in the following embodiments. [Effects of the Invention]

[0008] According to the present invention, it is possible to provide an information processing device that is capable of performing an appropriate route search based on information relating to a collection of detected objects. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram illustrating the overall configuration of an autonomous mobile control system according to an embodiment of the present invention. [Figure 2] 1A is an image diagram showing a location information input screen in this embodiment, and FIG. 1B is an image diagram showing a selection screen for selecting an autonomous moving body. [Figure 3] 1A is an image diagram showing a screen for checking the current position of an autonomous moving body in this embodiment, and FIG. 1B is an image diagram showing a map display screen for checking the current position of an autonomous moving body. [Figure 4] 1 is a block diagram of an autonomous mobile object control system according to an embodiment of the present invention. [Figure 5] FIG. 1 is a perspective view showing a configuration of an autonomous moving body according to an embodiment of the present invention. [Figure 6] FIG. 2 is a block diagram of each control unit in the present embodiment. [Figure 7]FIG. 2 is a sequence diagram of a process executed by the autonomous mobile control system according to the present embodiment. [Figure 8] FIG. 1A is a diagram showing latitude / longitude information of the Earth, and FIG. 1B is a perspective view showing a predetermined space. [Figure 9] FIG. 2 is a schematic diagram of spatial information within a predetermined space. [Figure 10] (a) An image of route information using route information displayed on map information, (b) an image of route information using position point cloud data displayed on map information, and (c) an image of route information using a unique identifier displayed on map information. [Figure 11] (a) A diagram showing the spatial relationship between the autonomous mobile body and the pillar, and (b) an image of the three-dimensional map. [Figure 12] FIG. 2 is a block diagram of a sensor node according to the present embodiment. [Figure 13] (a) A diagram showing the state when various objects are present within the detection range of a sensor node, and (b) A diagram showing the data structure of the output result sent to the memory unit when the object detection unit detects an object present within the detection range. [Figure 14] 10 is a flowchart illustrating an example of a process for grouping aggregates in this embodiment. [Figure 15] 15(a) is a diagram showing an example in which a plurality of objects exist within the detection range of a sensor node in this embodiment, and FIG. 15(b) is a diagram showing the output result of the aggregate detection unit for the example in FIG. 15(a). [Figure 16] (a) A top view of the situation when the neighborhood of two different objects is a sphere, (b) a side view of the situation when the neighborhood of two different objects is a sphere. [Figure 17] (a) A top view of two different objects with ellipsoidal neighborhoods, (b) a side view of two different objects with ellipsoidal neighborhoods. [Figure 18]18(a) shows an example in which multiple objects exist within the detection range of a sensor node, and (b) shows the results when the aggregate detection unit performs grouping on the example in FIG. 18(a) in accordance with the flow in FIG. 14. [Figure 19] 10 is a flowchart illustrating an example of a process for grouping aggregates in this embodiment. [Figure 20] 20(a) shows a scene when multiple pedestrians are present within the detection range of the sensor node, and (b) shows the results when the cluster detection unit performs grouping on the scene in FIG. 20(a) in accordance with the flow in FIG. 19. [Figure 21] (a) A diagram showing a scene in which two pedestrians are walking side by side while three moving mobility vehicles are driving in a line, and (b) A diagram showing the results when the cluster detection unit performs grouping on the scene in Figure 21(a) in accordance with the flow in Figure 19. [Figure 22] 10 is a flowchart showing a method for calculating all inter-object occupied areas from within one of the aggregates in this embodiment. [Figure 23] (a) A top view of two circumscribing rectangles and the object-to-object neighborhood region formed by the circumscribing rectangles, and (b) a side view of two circumscribing rectangles and the object-to-object neighborhood region formed by the circumscribing rectangles. [Figure 24] FIG. 10 is a diagram showing a situation in which a straight route and a detour route are physically possible for an autonomous mobile body as it moves toward a goal in this embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0011] First, to facilitate understanding, an information processing device according to an embodiment of the present invention will be described using an autonomous mobile control system as an example.

[0012] (1. Overview of the Autonomous Mobile Control System Configuration) Fig. 1 is an overall configuration diagram of an autonomous mobile object control system (information processing device) 1. As shown in Fig. 1, the autonomous mobile object control system 1 includes a system control device 10, a user interface 11, an autonomous mobile object 12, a route determination device 13, a conversion device 14, and a sensor node 15. The devices that make up the autonomous mobile object control system 1 are connected via the Internet 16 by their respective network connection units, which will be described later.

[0013] In this embodiment, the Internet 16 is used, but the present invention is not limited to this, and other network systems such as a LAN (Local Area Network) may also be used. Furthermore, at least two of the system control device 10, the user interface 11, the route determination device 13, and the conversion device 14 may be configured as a single device.

[0014] The system control device 10, user interface 11, autonomous mobile body 12, route determination device 13, conversion device 14, and sensor node 15 are each configured as an information processing device (computer) including a CPU, ROM, RAM, HDD, etc. The function and internal configuration of each device will be described in detail later.

[0015] (2. Services provided by autonomous mobile control systems) Next, the services provided by the autonomous mobile object control system 1 will be described. In this description, first, a screen image (FIGS. 2(a) and (b)) displayed on the user interface 11 when the user inputs location information will be described. Next, a screen image (FIGS. 3(a) and (b)) displayed on the user interface 11 when the user views the current location of the autonomous mobile object 12 will be described. These descriptions will show how services are provided to the user in the autonomous mobile object control system 1. In this embodiment, for ease of understanding, the map display will be described on a two-dimensional plane. However, in this embodiment, the user can specify a three-dimensional position including "height", so "height" information can also be input.

[0016] FIG. 2(a) is an image diagram showing an input screen when a user inputs location information, and FIG. 2(b) is an image diagram showing a selection screen for selecting an autonomous mobile body to use. When a user accesses the Internet 16 on the display screen of the user interface 11 and selects a service of the autonomous mobile body control system 1, a web page of the system control device 10 is displayed. The first thing displayed on the web page is an input screen 40 for inputting departure points, intermediate points, and destinations when moving the autonomous mobile body 12. The input screen 40 has a list display button 48 for displaying a list for selecting an autonomous mobile body to use, and when the user presses this button, a list display screen 47 shown in FIG. 2(b) is displayed.

[0017] First, the user selects the autonomous moving body used on the list display screen 47. Upon selection, the screen automatically transitions to the input screen 40. The user then inputs the location to be set as the departure point into the “Departure Point” input field 41. The user also inputs the location to be set as the intermediate point into the “Intermediate Point 1” input field 42. Intermediate points can be added; by pressing the “Add Intermediate Point” button 44, an input field 46 for “Intermediate Point 2” is additionally displayed, allowing the user to input the additional intermediate point. The user also inputs the location to be set as the arrival point into the “Arrival Point” input field 43. The user then requests the movement of the autonomous moving body 12 by pressing the OK button 45. (In the example of FIG. 2, “AAA” is set as the departure point, “BBB” as the intermediate point 1, and “CCC” as the arrival point.) The text to be input into the input fields is intended to be a text that can specify any location, such as an address. However, location information indicating a specific location, such as latitude / longitude information or a store name, can also be input.

[0018] FIG. 3(a) shows a confirmation screen 50 that appears when the current location of the autonomous mobile body 12 is displayed on the display screen of the web page of the user interface 11 after a request to move the autonomous mobile body 12 is made. The user can recognize the current location of the autonomous mobile body 12 from the position of the current location 56 on the screen. The user can also update the screen display information to display the latest status by pressing an update button 57. The user can also change the departure point, transit point, or arrival point by pressing a waypoint / arrival point change button 54. This can be changed by entering the desired location in the "Departure Point" input field 51, the "Transit Point 1" input field 52, and the "Arrival Point" input field 53, respectively.

[0019] 3(b) shows a map display screen 60 that is switched from the confirmation screen 50 when the map display button 55 in FIG. 3(a) is pressed. On this screen, the current location of the autonomous moving body 12 on the map display can be confirmed based on the position of a current location 62. The user can also return the display screen to the confirmation screen 50 by pressing a back button 61.

[0020] As described above, the user can move the autonomous moving body 12 from one predetermined location to another by operating the user interface 11. Possible examples of use of this service include taxi dispatch services and drone delivery services.

[0021] (3. Detailed explanation of the configuration and functions of each device (10-15)) Next, the configuration and function of each device (10 to 15) of the autonomous mobile object control system 1 will be described in detail with reference to Fig. 4. Fig. 4 is a block diagram showing the internal configuration of each device of the autonomous mobile object control system 1.

[0022] (3-1. User Interface 11) 4, the user interface 11 includes an operation unit 11-1, a control unit 11-2, a display unit 11-3, an information storage unit (memory / HD) 11-4, and a network connection unit 11-5. The operation unit 11-1 is configured with a touch panel, key buttons, etc., and is used for inputting data. The display unit 11-3 is, for example, an LCD screen, etc., and is used for displaying data.

[0023] The display screen of the user interface 11 shown in FIGS. 2(a), 2(b) and 3(a), 3(b) is displayed on the display unit 11-3. The user can select a service, input information, and confirm information via the menu displayed on the display unit 11-3. In other words, the operation unit 11-1 and the display unit 11-3 provide a user interface for the user to actually operate the device. Although the operation unit 11-1 and the display unit 11-3 are described separately here, they may be treated as a common display unit that can be operated if they are touch panels. The control unit 11-2 manages various services in the user interface 11, manages modes such as information input and information confirmation, and controls communication processing. It also controls processing in each control unit, such as the operation unit 11-1, the display unit 11-3, the information storage unit (memory / HD) 11-4, and the network connection unit 11-5. The information storage unit (memory / HD) 11-4 is a database for storing necessary information. The network connection unit 11-5 controls communication via the Internet, LAN, wireless LAN, etc.

[0024] As described above, the user interface 11 is a device such as a smartphone, and is configured to display information required by the user on the display unit 11-3 and to accept operations by the user from the operation unit 11-1.

[0025] With the above configuration, in this embodiment, the user interface 11 displays a departure point, intermediate point, and arrival point input screen 40 on the browser screen of the system control device 10, and accepts input of location information such as the departure point, intermediate point, and arrival point by the user. Also, by displaying a confirmation screen 50 and a map display screen 60 on the browser screen, the current location of the autonomous moving body 12 is displayed to the user.

[0026] (3-2. Route determination device 13) In FIG. 4, the route determination device (route information generating means, route search device) 13 includes a map information management unit 13-1, a control unit 13-2, a position / route information management unit 13-3, an information storage unit (memory / HD) 13-4, and a network connection unit 13-5. The map information management unit 13-1 holds map information of the earth, searches for route information indicating a route on the map based on specified location information, and transmits the searched route information to the position / route information management unit 13-3. The map information not only manages information such as topography, latitude, longitude, and altitude, but also manages information related to road traffic laws, such as roadways, sidewalks, direction of travel, and traffic regulations. The sidewalk control unit 13-2 controls the route information search function of the route determination device 13 and controls the processing of each control unit, such as the map information management unit 13-1, the position / route information management unit 13-3, the information storage unit (memory / HD) 13-4, and the network connection unit 13-5. The position / route information management unit 13-3 manages the position information acquired through the network connection unit 13-5, transmits the position information to the map information management unit 13-2, and manages the route information of the search results acquired from the map information management unit 13-2. In accordance with a request from an external system, the control unit 13-2 converts the route information managed by the position / route information management unit 13-3 into a predetermined data format and transmits it to the external system.

[0027] As described above, the route determination device 13 is configured to search for a route that complies with the Road Traffic Act based on the specified predetermined position information, and to output the route in a predetermined data format.

[0028] With the above configuration, the route determination device 13 of this embodiment searches for route information based on position information specified by the system control device 10, and provides the route information in a predetermined data format to the system control device 10. The route determination device 13 generates route information for the autonomous moving body (12) using, for example, a map relating to the positions of multiple objects (multiple objects including a first object and a second object) generated based on spatial information.

[0029] (3-3. Conversion device 14) 4, the conversion device 14 includes a location / route information management unit 14-1, a unique identifier management unit 14-2, a control unit 14-3, a format database 14-4, an information storage unit (memory / HD) 14-5, and a network connection unit 14-6. The location / route information management unit 14-1 manages predetermined location information acquired through the network connection unit 14-5, and transmits the location information to the control unit 14-3 in response to a request from the control unit 14-3. The control unit 14-3 controls the unique identifier conversion function of the conversion device 14. The control unit 14-3 controls the processing of each control unit, such as the location / route information management unit 14-1, the unique identifier management unit 14-2, the format database 14-4, the information storage unit (memory / HD) 14-5, and the network connection unit 14-6. The control unit 14-3 converts the location information obtained from the location / route information management unit 14-1 into a unique identifier based on the format information managed in the format database 14-4, and transmits it to the unique identifier management unit 14-2.

[0030] The format will be explained in detail later. The format assigns an identifier (hereinafter, "unique identifier") to a space starting from a predetermined position, and manages the space using the unique identifier. Based on predetermined position information, the corresponding unique identifier and information within the space can be obtained. The unique identifier management unit 14-2 manages the unique identifier converted by the control unit 14-3 and transmits it via the network connection unit 14-6. The format database 14-4 manages format information and transmits the format information to the control unit 14-3 in response to a request from the control unit 14-3. The format database 14-4 also manages information within the space obtained via the network connection unit 14-6 using the format. Details of the management of information within the obtained space will be described later. The conversion device 14 manages information about the space obtained by external devices, apparatuses, and networks connected to it, linking it to the unique identifier. The conversion device 14 also provides the unique identifier and information about the space linked to it to external devices, apparatuses, and networks connected to it.

[0031] As described above, the conversion device 14 collects unique identifiers and information within the space based on specified location information, and manages and provides this information in a state that can be shared by external devices, equipment, and networks connected to it.

[0032] With the above configuration, in this embodiment, the conversion device 14 converts the location information specified by the system control device 10 into a unique identifier and provides it to the system control device 10.

[0033] (3-4. System control device 10) 4, the system control device 10 includes a unique identifier management unit 10-1, a control unit 10-2, a position / route information management unit 10-3, an information storage unit (memory / HD) 10-4, and a network connection unit 14-5. The position / route information management unit 10-3 holds simple map information that matches topographical information with latitude / longitude information, and manages predetermined position information and route information acquired through the network connection unit 10-5. The position / route information management unit 10-3 can also divide the route information at predetermined intervals and generate position information such as the latitude / longitude of the divided locations. The unique identifier management unit 10-1 manages information obtained by converting the position information and route information into unique identifiers.

[0034] The control unit 10-2 controls the communication functions of the system control device 10 for the position information, route information, and unique identifier. The control unit 10-2 controls the processing of each control unit, such as the unique identifier management unit 10-1, the position / route information management unit 10-3, the information storage unit (memory / HD) 10-4, and the network connection unit 14-5. The control unit 10-2 provides a web page to the user interface 11, transmits predetermined position information acquired from the web page to the route determination device 13, acquires predetermined route information from the route determination device 13, and transmits each position information piece of the route information to the conversion device 14. The control unit 10-2 then transmits the route information converted into the unique identifier acquired from the conversion device 14 to the autonomous moving body 12.

[0035] As described above, the system control device 10 is configured to be able to obtain predetermined location information specified by the user, send and receive location information and route information, generate location information, and send and receive route information using a unique identifier.

[0036] With the above configuration, the system control device 10 collects route information necessary for the autonomous moving body 12 to move autonomously based on the location information input to the user interface 11, and provides the route information to the autonomous moving body 12 using a unique identifier.

[0037] (3-5. Autonomous Mobile Unit 12) In FIG. 4, the autonomous mobile object 12 includes a detection unit 12-1, a control unit 12-2, a direction control unit 12-3, an information storage unit (memory / HD) 12-4, a network connection unit 12-5, and a drive unit 12-6. The detection unit 12-1 has an imaging unit such as an image sensor and a distance measurement function such as distance measurement based on the phase difference of light using multiple image sensors. The detection unit 12-1 acquires detection information (hereinafter, "detection information") such as the surrounding terrain and obstacles such as building walls, and has a self-location estimation function that estimates its own location from the detection information. The detection unit 12-1 also has a self-location detection function such as a GPS (Global Positioning System) and a direction detection function such as a geomagnetic sensor. Furthermore, the control unit 12-2 can create a three-dimensional map in cyberspace based on the acquired detection information, self-location estimation information, and direction detection information.

[0038] Here, a three-dimensional map of cyberspace is a map that can represent spatial information equivalent to the positions of features in the real world as digital data. This three-dimensional map of cyberspace stores information about autonomous mobile bodies 12 that exist in the real world and their surrounding features as spatially equivalent digital data, enabling efficient movement based on this digital data. The three-dimensional map of cyberspace used in this embodiment will be described below using Figures 11(a) and 11(b) as examples.

[0039] FIG. 11(a) is a diagram showing the spatial positional relationship between an autonomous mobile body 12 in the real world and a pillar 99 that exists as feature information about the surrounding area. The position of the autonomous mobile body 12 is identified as the same position α0 within the autonomous mobile body 12 from latitude and longitude position information acquired by a GPS (not shown) or the like of the autonomous mobile body 12. The orientation of the autonomous mobile body 12 is identified by the difference between the orientation αY acquired by an electronic compass (not shown) or the like and the moving direction 12Y of the autonomous mobile body 12. The position of the pillar 99 is identified as the position of a vertex 99-1 from position information measured in advance. The distance from α0 of the autonomous mobile body 12 to the vertex 99-1 can be acquired by the ranging function of the autonomous mobile body 12. In FIG. 11(a), the coordinates of the vertex 99-1 are shown as (Wx, Wy, Wz) when the 12Y direction is the axis of an XYZ coordinate system and α0 is the origin.

[0040] In a three-dimensional map of cyberspace, the information acquired in this manner is managed as digital data and can be reconstructed as spatial information such as that shown in Figure 11(b). Figure 11(b) shows the autonomous mobile unit 12 and the pillar 99 mapped onto an arbitrary XYZ coordinate system space with P0 as the origin. By setting P0 to a specific latitude and longitude in the real world and taking the north direction in the real world as the Y-axis direction, the autonomous mobile unit 12 can be represented as P1 and the pillar 99 as P2 in this arbitrary XYZ coordinate system space. Specifically, from the latitude and longitude of α0 and the latitude and longitude of P0, the position P1 of α0 in this space can be managed, and similarly, the pillar 99 can be managed as P2. In this example, the autonomous mobile unit 12 and the pillar 99 are represented on a three-dimensional map of cyberspace, but of course, multiple autonomous mobile units and pillars can be handled in the same way.

[0041] As described above, a three-dimensional map is a mapping of the user's own position and objects in the real world onto a three-dimensional space.

[0042] Furthermore, the autonomous moving body 12 stores, for example, learning result data obtained through machine learning in the information storage unit 12-4, and can detect objects from captured images. Detection information can also be acquired from an external system via the network connection unit 12-5 and reflected in a three-dimensional map. The control unit 12-2 controls the movement, direction changes, and autonomous driving functions of the autonomous moving body 12, and controls the processing of each control unit, such as the detection unit 12-1, direction control unit 12-3, information storage unit (memory / HD) 12-4, network connection unit 12-5, and drive unit 12-6. The direction control unit 12-3 changes the direction of movement of the autonomous moving body 12 by changing the direction of the drive unit 12-6. The drive unit 12-6 is composed of a drive device such as a motor, and generates propulsive force for the autonomous moving body 12.

[0043] The autonomous mobile body 12 can perform autonomous driving by reflecting its own position, detection information, and object detection information (sensors) in a three-dimensional map, generating a route that maintains a certain distance from surrounding terrain, buildings, obstacles, and objects. The difference between this and the route generation performed by the route determination device 13 is as follows: The route determination device 13 generates a route that mainly takes into account regulatory information related to the Road Traffic Act. On the other hand, the autonomous mobile body 12 generates a route by more accurately detecting its own size and the positions of surrounding obstacles on the route determined by the route determination device 13, and moving in a way that avoids contact with them.

[0044] Here, the main body configuration of the autonomous moving body 12 in this embodiment will be described with reference to Fig. 5. Fig. 5 is a perspective view showing the mechanical configuration of the autonomous moving body 12. Note that although this embodiment describes the autonomous moving body 12 as a running body having wheels, this is not limitative, and the autonomous moving body 12 can also be an air vehicle such as a drone.

[0045] 5, a detection unit 12-1, a control unit 12-2, a direction control unit 12-3, an information storage unit (memory / HD) 12-4, a network connection unit 12-5, and a drive unit 12-6 are electrically connected to the autonomous moving body 12. At least two drive units 12-6 and two direction control units 12-3 are provided in the autonomous moving body 12. The direction control unit 12-3 changes the direction of movement of the autonomous moving body 12 by driving the rotation of the shaft to change the direction of the drive unit 12-6. The drive unit 12-6 moves the autonomous moving body 12 forward and backward by rotating the shaft. Note that the configuration described with reference to FIG. 5 is one example and is not limited to this. Any structure that can achieve the same effect, such as the adoption of an omniwheel in a movement direction change structure, may be used.

[0046] As described above, the autonomous moving body 12 is a moving body equipped with, for example, SLAM technology, and is configured to be able to autonomously move along a specified route based on detection information detected by the detection unit 12-1 and detection information from an external system obtained via the Internet 16.

[0047] The autonomous moving body 12 can perform tracing movement, tracing precisely specified points, or it can pass through roughly set points and generate its own route information in the space between them to move.

[0048] With the above configuration, in this embodiment, the autonomous moving body 12 moves autonomously based on route information using the unique identifier provided by the system control device 10.

[0049] (3-6. Sensor Node 15) In FIG. 4, the sensor node 15 is an external system, such as a roadside unit or other video surveillance system. It includes a detector 15-1, a controller 15-2, an information storage unit (memory / HD) 15-3, and a network connection unit (transmitter) 15-4. The detector 15-1 detects obstacles, such as terrain and building walls, around the area detectable by the detector, such as a camera, as well as objects such as pedestrians, dogs, and mailboxes. The detector 15-1 also has a cluster detection function that detects groups of objects and a function that calculates the area occupied by the objects and clusters. The detector 15-1 also has a distance measurement function that identifies the three-dimensional structure of obstacles or objects. Details of the processing performed by the detector 15-1 are described later in "6. Registering the Presence of Detected Objects and Clusters by the Sensor Node."

[0050] The control unit 15-2 controls the detection, data storage, and data transmission functions of the sensor node 15, and controls the processing of each unit of the sensor node 15, such as the detection unit 15-1, information storage unit (memory / HD) 15-3, and network connection unit 15-4. The control unit 15-2 also stores the detection information acquired by the detection unit 15-1 in the information storage unit (memory / HD) 15-3, and controls the function of transmitting the information to the conversion device 14 via the network connection unit 15-4.

[0051] As described above, the sensor node 15 is configured to store and communicate information such as image information, obstacle detection information, object detection information, cluster detection information, and occupied area information in the information storage unit 15-3. The object detection information includes, for example, information about the feature points, position, orientation, and movement of an object.

[0052] With the above configuration, in this embodiment, the sensor node 15 provides the conversion device 14 with detection information of the area that the sensor node 15 can detect.

[0053] (4. Hardware configuration of each control unit) Next, a specific configuration of each control unit in Fig. 4 will be described. Fig. 6 is a block diagram showing a specific example configuration of control unit 10-2, control unit 11-2, control unit 12-2, control unit 13-2, control unit 14-3, and control unit 15-2.

[0054] In FIG. 6, 21 denotes a central processing unit (hereinafter referred to as CPU) that controls the calculations and control of the information processing device. 22 denotes random access memory (hereinafter referred to as RAM), which functions as the main memory of the CPU 21, as well as an area for executing programs, an execution area for the programs, and a data area. 23 denotes read-only memory (hereinafter referred to as ROM) that stores the operation and processing procedures of the CPU 21. ROM 23 includes a program ROM that stores the operating system (OS), which is a system program that controls the equipment of the information processing device, and a data ROM that stores information necessary for operating the system. Note that a hard disk drive (HDD) 29, described below, may be used instead of ROM 23. 24 denotes a network interface (NETIF), which controls data transfer between information processing devices via the Internet 16 and diagnoses connection status. 25 denotes video RAM (VRAM), which develops images to be displayed on the screen of a CRT 26 and controls the display. 26 denotes a display device such as a display (hereinafter referred to as CRT).

[0055] Reference numeral 27 denotes a controller (hereinafter referred to as KBC) for controlling input signals from an external input device 28. Reference numeral 28 denotes an external input device (hereinafter referred to as KB) for receiving operations performed by a user, and may be, for example, a keyboard or a pointing device such as a mouse. Reference numeral 29 denotes a hard disk drive (hereinafter referred to as HDD), which is used for storing application programs and various data. The application program in this embodiment is a software program or the like that executes various processing functions in this embodiment.

[0056] An external input / output device (hereinafter referred to as FDD) 30 is used to input and output data from removable data recording devices (removable media), such as floppy disk drives and CD-ROM drives. The FDD 30 is used when reading the above-mentioned application programs from removable media, etc.

[0057] Reference numeral 31 denotes removable media such as magnetic recording media (e.g., floppy disks or external hard disks) or optical recording media (e.g., CD-ROMs) read by the FDD 30. Removable media such as magneto-optical recording media (e.g., MOs) or semiconductor recording media (e.g., memory cards) may also be used. Application programs and data stored in the HDD 29 can also be stored in the FDD 30 and used. Reference numeral 20 denotes transmission buses (address bus, data bus, input / output bus, and control bus) for connecting the above-mentioned units.

[0058] (5. Processing flow in the autonomous mobile control system) Next, details of the control operations in the autonomous mobile object control system 1 for realizing the services described with reference to Figures 2(a) and 2(b) and Figures 3(a) and 3(b) will be described with reference to Figure 7. Figure 7 is a sequence diagram showing the processing executed by each unit of the autonomous mobile object control system 1 from when the user inputs location information into the user interface 11 until when the current location information of the autonomous mobile object 12 is received.

[0059] (5-1. User input of information) First, the user accesses a web page provided by the system control device 10 through the user interface 11 (S201). The system control device 10 displays a location input screen, such as that described in FIG. 2, on the display screen of the web page (S202). As described in FIG. 2, the user selects an autonomous moving body and inputs location information (hereinafter, location information) indicating the departure / transit / arrival points (S203). The location information may be a word specifying a specific location (hereinafter, location word), such as a building name, station name, or address, or a method of specifying a specific location on a map displayed on the web page as a point (hereinafter, point). The system control device 10 saves information about the selected autonomous moving body (autonomous moving body 12 in this example) and the input location information (S204). At this time, if the location information is a location word, the location word is saved. If the location information is a point, the system control device searches for the latitude / longitude corresponding to the point based on the simplified map information saved in the location / route information management unit 10-3, and saves the latitude / longitude.

[0060] (5-2. Obtaining route information) Next, the system control device 10 specifies the type of route that the autonomous mobile body 12 can travel (hereinafter referred to as the route type) based on the mobility type specified by the user (S205), and transmits this to the route determination device 13 together with the location information (S206). The mobility type refers to the legally identified type of mobile body, such as an automobile, bicycle, or drone. The route type refers to, for example, a general road or expressway for an automobile, or a designated sidewalk, shoulder strip on a general road, or bicycle lane for a bicycle. The route determination device 13 inputs the received location information into its map information as the departure / intermediate / arrival points. If the location information is a location word, the location word is searched in the map information (S207), and the corresponding latitude / longitude information is used. If the location information is latitude / longitude information, the location information is directly entered into the map information and used. Next, the route determination device 13 searches for a route from the departure point to the arrival point via the intermediate points (S208). At this time, the route to be searched conforms to the route type. Then, as a result of the search, the route determination device 13 outputs a route from the departure point to the destination point via the waypoints (hereinafter referred to as route information) in GPX format (GPS eXchange Format) and transmits it to the system control device 10 (S209). GPX format files are mainly composed of three types of data: waypoints (point information with no sequential order), routes (point information with sequential order to which time information is added), and tracks (a collection of multiple point information: a trajectory). Attribute values for each point information include latitude and longitude, and subelements include altitude, geoid height, GPS reception status, and accuracy. The minimum element required for a GPX file is the latitude and longitude information for a single point, and other information can be described arbitrarily. The route information output is a route, which is a collection of point information consisting of sequential latitude and longitude. Note that the route information may be in other formats as long as it satisfies the above requirements.

[0061] (5-3. Format structure) Next, the configuration of the format managed by the format database 14-4 of the conversion device 14 will be described in detail with reference to Figures 8(a), (b), and 9. Figure 8(a) is a diagram showing latitude / longitude information of the Earth, and Figure 8(b) is a perspective view showing a predetermined space 100 in Figure 8(a). In Figure 8(b), the center of the predetermined space 100 is defined as center 101. Figure 9 is a schematic diagram of spatial information within space 100.

[0062] In Figures 8(a) and (b), the format divides the Earth's space into partitions determined by ranges starting from latitude / longitude / height, and assigns a unique identifier to each space for management purposes. For example, space 100 is shown here as a specific space. Space 100 is a partition defined with its center 101 at 20 degrees north latitude, 140 degrees east longitude, and height H, and is defined as a width D in the latitude direction, a width W in the longitude direction, and a width T in the height direction. It is one of the partitions of the Earth's space determined by ranges starting from latitude / longitude / height. While only space 100 is shown in Figure 8(a) for clarity, the format defines spaces defined similarly to space 100, arranged side by side in the latitude / longitude / height directions, as described above. Each partition has its horizontal position defined by latitude / longitude, and overlaps vertically, with its vertical position defined by its height. In addition, in FIG. 8(b), the center of the divided space is set as the starting point of the latitude / longitude / height, but this is not limited to this, and the starting point may be, for example, a corner of the space or the center of the bottom surface.

[0063] The shape also needs to be roughly rectangular, and when considering the case of laying them out on the surface of a sphere like the Earth, it is better to make the top of the rectangular prism slightly wider than the bottom so that they can be placed more tightly without gaps.

[0064] 9, taking space 100 as an example, format database 14-4 stores information (spatial information) relating to the state and time of objects existing within the range of space 100 in a time series from the past to the future. The spatial information is updated by information input from an external system (e.g., sensor node 15) communicatively connected to conversion device 14, and the information is shared with other external systems communicatively connected to conversion device 14.

[0065] The above is a format that enables space-time management by associating information about the state and time of objects in a space determined by a range starting from latitude / longitude / altitude (hereinafter referred to as spatial information) with a unique identifier.

[0066] (5-4. Create location point cloud data from route information) Returning to FIG. 7, the rest of the processing executed by the autonomous mobile object control system 1 will be explained again. The system control device 10 checks the intervals between each piece of point information in the received route information, and creates position point cloud data (hereinafter referred to as position point cloud data) that matches the intervals between the point information and the intervals between the origin positions of the divided space defined by the format (S210). At this time, if the intervals between the point information are smaller than the intervals between the origin positions of the divided space, the system control device 10 thins out the point information in the route information to match the intervals between the origin positions of the divided space, and creates the position point cloud data. On the other hand, if the intervals between the point information are larger than the intervals between the origin positions of the divided space, the system control device 10 interpolates the point information within a range that does not deviate from the route information, and creates the position point cloud data.

[0067] (5-5. Converting position point cloud data into format route information) Next, the system control device 10 transmits the latitude / longitude information of each point information of the position point cloud data to the conversion device 14 in the order of the route (S211). The conversion device 14 searches for a unique identifier corresponding to the received latitude / longitude information (S212) and transmits it to the system control device 10 (S213). The system control device 10 arranges the received unique identifiers in the same order as the original position point cloud data and stores them as route information using the unique identifiers (hereinafter, formatted route information) (S214).

[0068] Here, the process of generating position point cloud data from route information and converting it into route information using unique identifiers will be described in detail with reference to Figures 10(a) to 10(c). Figures 10(a), 10(b), and 10(c) are conceptual diagrams showing route information, position point cloud data, and route information using unique identifiers, respectively, displayed as map information.

[0069] 10(a), 120 is route information, 121 is a non-movable area that the autonomous moving body 12 cannot pass through, and 122 is a movable area of the autonomous moving body 12. The route information 120 generated by the route determination device 13 based on the position information of the departure point, intermediate point, and arrival point specified by the user is generated as a route that passes through the departure point, intermediate point, and arrival point and passes through the movable area 122 on the map information.

[0070] In Figure 10(b), 123 is position information on the route information. The system control device 10, which has acquired the route information 120, generates position information 123 arranged at predetermined intervals on the route information 120. The position information 123 can be expressed as latitude / longitude / altitude, and this position information 123 is collectively referred to as position point cloud data. The system control device 10 then transmits the latitude / longitude / altitude of each point of this position information 123 one by one to the conversion device 14, which converts it into a unique identifier.

[0071] In Figure 10(c), 124 is position-spatial information obtained by converting each piece of position information 123 into a unique identifier and expressing the spatial range defined by the unique identifier in a rectangular frame. By converting the position information into a unique identifier, the position-spatial information 124 is obtained. As a result, the route expressed by the route information 120 is expressed by the continuous position-spatial information 124, and data is created in which intra-space information is linked to each piece of position-spatial information 124. This continuous position-spatial information 124 is collectively referred to as formatted route information.

[0072] (5-6. Conversion of unique identifier to cost map) Returning to FIG. 7, the rest of the processing executed by the autonomous mobile object control system 1 will be explained again. The system control device 10 downloads spatial information linked to each unique identifier of the formatted route information from the conversion device 14 (S215). Then, the system control device (map generation means) 10 converts the spatial information into a format that can be reflected in a three-dimensional map of the cyberspace of the autonomous mobile object 12, and creates (generates) information indicating the positions of multiple objects in a predetermined space (hereinafter referred to as a cost map) (S216). The cost map may be created initially for all routes in the formatted route information, or may be created in a form divided into certain regions and then updated sequentially.

[0073] (5-7. Load formatted route information and cost map to the autonomous vehicle) Next, the system control device 10 stores the formatted route information and the cost map by linking them to the unique identification number assigned to the autonomous moving body 12 (S217). The autonomous moving body 12 monitors (hereinafter referred to as "polling") its own unique identification number via the network at predetermined intervals and downloads the linked data (S218). Based on the latitude / longitude information of each unique identifier in the formatted route information, the autonomous moving body 12 reflects the information as route information in the three-dimensional map of cyberspace that it has created (S219).

[0074] (5-8. Updating the cost map) Next, the autonomous mobile body 12 reflects the cost map as obstacle information on the route in a three-dimensional map of cyberspace (S220). If the cost map is created in a form divided into regular intervals, after moving through the area for which the cost map is created, the autonomous mobile body 12 downloads the cost map for the next area and updates the cost map. The autonomous mobile body 12 moves along the route information while avoiding objects input in the cost map (S221). At this time, the autonomous mobile body 12 moves while detecting objects, and if there is a difference with the cost map, updates the cost map using the object detection information (S222), and moves. In addition, the autonomous mobile body 12 transmits difference information with the cost map together with the corresponding unique identifier to the system control device 10 (S223). The system control device 10, which has acquired the difference information between the unique identifier and the cost map, transmits spatial information to the conversion device 14 (S224), and the conversion device 14 updates the spatial information of the corresponding unique identifier (S225). The content of the spatial information updated here does not directly reflect the difference information with the cost map, but is abstracted by the system control device 10 and transmitted to the conversion device 14. Details of the abstraction will be described later in (5-11. Updating information within the divided space by sensor nodes).

[0075] (5-9. Location information notification) The autonomous moving body 12, moving based on the formatted route information, transmits the unique identifier corresponding to the space in which it currently resides to the system control device 10 each time it passes through a divided space associated with a unique identifier (S226). Alternatively, the autonomous moving body 12 may be associated with a unique identification number during polling. The system control device 10 determines the current location of the autonomous moving body 12 in the formatted route information based on the unique identifier information received from the autonomous moving body 12. By repeating step 226, the system control device 10 can determine the current location of the autonomous moving body 12 in the formatted route information. The system control device 10 may stop retaining the unique identifiers that the autonomous moving body 12 has passed through, thereby reducing the data volume retained in the formatted route information.

[0076] (5-10. Status notification to users) 2 and 3 based on the current location information of the autonomous moving body 12 that has been grasped, and displays them on the display screen of the web page (S227). Every time the autonomous moving body 12 transmits a unique identifier indicating its current location to the system control device 10, the system control device 10 updates the confirmation screen 50 and the map display screen 60.

[0077] (5-11. Updating information within the partitioned space by sensor nodes) The sensor node 15 saves the detection information of the detection range (S228), abstracts the detection information (S229), and transmits it as spatial information to the conversion device 14 (S230). The abstraction refers to information such as whether an object exists or whether there has been a change in the existence state of the object, rather than detailed information about the object. Detailed information about the object is stored in the memory of the sensor node. The conversion device 14 then associates the spatial information with the unique identifier of the location to which the spatial information corresponds and stores it (S231). At this point, the spatial information is stored in one unique identifier in the format database.

[0078] Furthermore, when an external system different from the sensor node 15 utilizes spatial information, the external system acquires and utilizes the detection information in the sensor node 15 via the conversion device 14 based on the spatial information in the conversion device 14. In this case, the conversion device 14 also has the function of connecting the communication standards of the external system and the sensor node 15.

[0079] By storing the spatial information as described above among multiple devices, not just the sensor node 15, the conversion device 14 can function as a format that connects data from multiple devices with a relatively light data volume. In (5-6. Conversion from unique identifier to cost map), if the system control device 10 needs detailed object information when creating the cost map, it downloads and uses the detailed information from an external system that stores detailed detection information of the spatial information.

[0080] (5-12. Reflecting spatial information updates to autonomous mobile units) Here, it is assumed that the sensor node 15 updates spatial information on the route of the format route information of the autonomous mobile body 12. At this time, the sensor node 15 acquires detection information (S232), generates spatial information (S233), and transmits it to the conversion device 14 (S234). The conversion device 14 stores the spatial information in the format database 14-4 (S235). The system control device 10 checks for changes in the spatial information in the format route information it manages at predetermined time intervals. If there is a change in the spatial information, the system control device 10 downloads the spatial information (S236) and updates the cost map, and also updates the cost map linked to the unique identification number assigned to the autonomous mobile body 12 (S237). The autonomous mobile body 12 recognizes the update to the cost map by polling and reflects it in the three-dimensional map of cyberspace that it created (S238).

[0081] As described above, by utilizing spatial information shared by multiple devices, the autonomous moving body 12 can recognize in advance changes on the route that it cannot recognize itself, and can respond to those changes.

[0082] After carrying out the above series of processes, the system control device 10 recognizes that the autonomous moving body 12 has arrived at the destination point (S239) through the transmitted unique identifier (S240), and displays an arrival indication on the user interface 11 (S241), and the service ends.

[0083] (6. Sensor node detection information acquisition method and data structure) As explained in (5-11. Updating of information in divided space by sensor node), the sensor node 15 saves the detection information of the detection range (S228). Here, we will explain the process of acquiring the detection information, as well as the data structure of the saved detection information.

[0084] 12 is a block diagram of the sensor node 15. The detection unit 15-1 includes an obstacle detection unit 15-1-1, an object detection unit (object detection means) 15-1-2, an aggregation detection unit (aggregation determination means) 15-1-3, and an occupied area calculation unit (calculation means) 15-1-4. The obstacle detection unit 15-1-1 detects obstacles such as terrain and building walls included in the detection range of the sensor node 15.

[0085] The object detection unit 15-1-2 detects objects such as people, dogs, mailboxes, and mobility items that are included in the detection range of the sensor node 15. That is, the object detection unit 15-1-2 detects a plurality of objects including a first object and a second object using signals from the sensor.

[0086] The assembly detection unit 15-1-3 detects an assembly (hereinafter referred to as an assembly) of objects (detected objects) detected by the object detection unit 15-1-2. That is, the assembly detection unit 15-1-3 is an assembly determination means that determines whether or not a plurality of objects are an assembly of the same group based on object detection information about the plurality of objects including the first object and the second object detected by the object detection unit 15-1-2. For example, when the assembly detection unit 15-1-3 determines that the first object and the second object are an assembly of the same group, the assembly detection unit 15-1-3 groups the first object and the second object.

[0087] Occupied area calculation unit 15-1-4 calculates spatial information regarding the range of space occupied in the real world by the detected objects detected by object detection unit 15-1-2 (hereinafter referred to as object occupied area). Occupied area calculation unit 15-1-4 also calculates the range of space occupied in the real world by the aggregate detected by aggregate detection unit 15-1-3 (hereinafter referred to as aggregate occupied area). Occupied area calculation unit 15-1-4 is a calculation unit that calculates spatial information regarding the occupied area (object occupied area) occupied by at least one of the first object, the second object, and the aggregate. Occupied area calculation unit 15-1-4 also calculates occupied areas in three-dimensional space and calculates areas existing between the calculated occupied areas.

[0088] All output results of each block are stored in an information storage unit (memory / HD) 15-3. A network connection unit (transmission unit) 15-4 transmits at least one of the object detection information, information related to the aggregate, and spatial information.

[0089] The details of the processing performed by the obstacle detection unit 15-1-1, the object detection unit 15-1-2, the aggregate detection unit 15-1-3, and the occupied area calculation unit 15-1-4 will be described later.

[0090] (6-1. Obstacle detection by the obstacle detection unit) The obstacle detection unit 15-1-1 detects obstacles such as terrain and building walls that exist within the detection range of the sensor node 15. The obstacle detection unit 15-1-1 detects obstacles and stores the detection results in the information storage unit 15-3.

[0091] If the sensor node 15 is equipped with a camera, a deep learning model whose tasks are image area segmentation and monocular depth estimation is used to calculate the image area and depth information of each obstacle such as the floor, ground, wall, etc. from the image information acquired from the camera. Then, based on the calculated image area and depth information and the camera parameters acquired in advance by calibration, the position information of the obstacle in the three-dimensional map is calculated.

[0092] When a camera is mounted on the sensor node 15 and the camera's angle of view is fixed, depth information corresponding to the image area may be extracted from a depth map previously stored in the information storage unit 15-3, and the position information of the obstacle in the three-dimensional map may be calculated.

[0093] If the sensor node 15 is equipped with a lidar, it extracts point cloud information of each obstacle, such as the floor, ground, or wall, by plane detection from the point cloud information acquired from the lidar. Then, it calculates the position information of the obstacle on the three-dimensional map based on the attitude information of the lidar acquired in advance and the extracted point cloud information.

[0094] If the sensor node 15 is equipped with both a camera and a lidar, the position information of the obstacle is calculated using either or both of the image information and the point cloud information.

[0095] (6-2. Object detection by the object detection unit) The object detection unit 15-1-2 detects objects such as pedestrians, dogs, and mailboxes that exist within the detection range of the sensor node 15. If the sensor node 15 is equipped with a camera, a detector that inputs image information is used, but a deep learning algorithm, a support vector machine, or the like may be selected as the detection algorithm. Below, an example in which the sensor node 15 detects an object that exists within the detection range will be described using FIGS. 13(a) and (b) as examples. Below, the object detector 15-1-2 used in this embodiment will be described using FIGS. 13(a) and (b) as examples.

[0096] 13(a) shows the situation when various objects are present within the detection range of the sensor node 15. 131 indicates the camera mounted on the sensor node 15, 132 indicates the detection range of the sensor node 15, and 132 indicates the objects present within the detection range of the sensor node 15.

[0097] 13(b) shows the data structure of the output result sent to storage unit 15-3 when object detection unit 15-1-2 detects object 132 existing in detection range 131. The detection result includes object ID 133, category (attribute) 134, detected position 135, vertices of a circumscribed rectangle 136, orientation vector (direction vector) 137, and motion vector 138.

[0098] The object ID 133 is an identifier of the object detected up to now, and is also an identifier used to determine whether the object detected from the image information is the same as an object detected in the past. The category 134 indicates the attribute of the detected object.

[0099] The detected position 135 indicates the representative position of the object detected from the image information within the 3D map, and the vertices 136 of the circumscribing rectangle indicate the vertices of a rectangular parallelepiped that surrounds the detected object (there are eight of them in total). The vertices 136 of the circumscribing rectangle are expressed by coordinate values within the 3D map.

[0100] 13(c) will be described as an example of the detected position 135 and the vertices 136 of the circumscribing rectangle. Reference numeral 1301 denotes a pedestrian present within the detection range of the sensor node 15, 1302 denotes the detected position of the pedestrian 1301, and 1303 to 1310 denote the vertices that make up the circumscribing rectangle surrounding the pedestrian 1029. The coordinate values of the detected position 135 in each direction may be the average of the coordinate values of the vertices of the circumscribing rectangle.

[0101] The orientation vector 137 and the motion vector 138 respectively indicate the direction and movement of an object detected from image information within the three-dimensional map. The motion vector 138 is calculated based on the detected position 135 of the object obtained from the image information and the previous detected positions of the object read from the information storage unit (memory / HD) 15-3. The orientation vector 137 may be obtained by converting the magnitude of the motion vector 138 to 1.

[0102] (6-3. Grouping of detected objects by aggregate detection unit) The aggregate detection unit 15-1-3 groups the detected objects based on the detection results obtained by the object detection unit 15-1-2. A list of object IDs is created for each group through grouping. Two patterns of processing by the aggregate detection unit 15-1-3 are introduced below. The first pattern is a basic flowchart and will be explained in 6-3-1. Processing flow for grouping detected objects. The second pattern is a derivative of the first pattern and will be explained in 6-3-2. Processing flow for grouping detected objects using a reference object.

[0103] (6-3-1. Processing flow for grouping detected objects) FIG. 14 is a flowchart showing the basic grouping process of detected objects in the sensor node 15.

[0104] In S101, control unit 15-2 reads the detection results of object detection unit 15-1-2 from information storage unit (memory / HD) 15-3 and checks the number of detected objects. If the number of detected objects is 0 in S101, the grouping process ends. If the number of detected objects is 1 or more in S101, control unit 15-2 assigns 0 to variable K to perform initialization in S102. Variable K is used as a group ID number, and in subsequent processing, the value of variable K is changed as appropriate to select which group to place the detected object into.

[0105] In S103, the control unit 15-2 searches for nearby objects (hereinafter, nearby objects) for each detected object, and creates a list of object IDs of the nearby objects (hereinafter, nearby list). The nearby list is stored in the information storage unit (memory / HD) 15-3. Here, a specific method for creating the nearby list will be described with reference to FIGS. 15(a) and 15(b).

[0106] FIG. 15(a) shows a scene in which multiple objects exist within the detection range of the sensor node 15. Objects 151 to 158 (i.e., multiple objects including a first object and a second object) exist within the detection range. Each object (first object) is assigned a range (hereinafter referred to as a neighborhood area) within which it searches for other objects (second objects) in the vicinity. If an object (second object) exists within the neighborhood area (first object), the object (second object) is determined to be a nearby object. Dotted lines 1501 to 1508 indicate the boundaries of the neighborhood areas of the objects 151 to 158, respectively.

[0107] As an example, a method for searching for nearby objects of object (first object) 151 will be described. First, it is confirmed whether an object (second object) other than object 151 exists inside boundary 1501 of the nearby area of object 151. Because object (second object) 152 exists inside boundary 1501, object 152 becomes a nearby object of object 151, and the object ID of object 152 is included in the nearby list of object 151. Nearby objects are searched for in the same way for objects 152 to 158, and the object IDs of the nearby objects (hereinafter referred to as nearby object IDs) are added to the respective nearby lists.

[0108] Fig. 15(b) is a table that aggregates the lists for the number of detected objects, created based on the scene in Fig. 15(a). The left side of Fig. 15(b) lists the object IDs of objects 151 to 158, and the right side lists the corresponding neighborhood lists.

[0109] 15(a) and 15(b), the shapes of the regions near the detected object are all spherical, but the shapes do not necessarily have to be spherical and can be ellipsoidal. Therefore, using Figures 16 and 17, we will explain what the conditional equation for one object being near the other of two objects present in the detection range will be when the shape of the region near the detected object is spherical or ellipsoidal.

[0110] Figures 16(a) and (b) show the state when the neighborhood regions of two different objects are spherical. Objects 161 and 162 are located at positions 163 and 164 on a three-dimensional map, and neighborhood regions 165 and 166 are developed around positions 163 and 164. Figure 16(a) shows the state as viewed from above, and Figure 16(b) shows the state as viewed from the side. The coordinate values of positions 163 and 164 are (x1, y1, z1) and (x2, y2, z2), respectively, and the radii of neighborhood regions 165 and 166 are r1 and r2. In this case, for example, if the following conditional expression (1) is satisfied, it is determined that object 162 is located near object 161.

[0111]

number

[0112] Furthermore, for example, if the following conditional expression (2) is satisfied, it is determined that the object 161 is present in the vicinity of the object 162.

[0113]

number

[0114] 17(a) and (b) show the state of two different objects when their respective neighborhood regions are ellipsoids. Objects 171 and 172 are located at positions 173 and 174 on the 3D map, and neighborhood regions 175 and 176 are centered at positions 173 and 174, respectively.

[0115] Because the neighborhood region 175 extends to match the orientation of the object 171, the radius on the X axis is larger than the radii on the other axes. By extending the neighborhood region to match the orientation of the object in this way, it becomes easier to create groups of objects facing the same direction.

[0116] Assume that object 172 is a drone, moving in the Y-axis direction. The neighborhood region 176 extends in the direction of movement of object 172, so its radius on the Y-axis is larger than its radius on any other axis. By extending the neighborhood region in this way in accordance with the movement of the object, it becomes easier to create a group of objects moving in a line.

[0117] The coordinate values of positions 173 and 174 are (x1, y1, z1) and (x2, y2, z2), respectively. The radii of neighborhood region 175 on the X-axis, Y-axis, and Z-axis are (a1, b1, c1), respectively, and the radii of neighborhood region 176 on the X-axis, Y-axis, and Z-axis are (a2, b2, c2), respectively. In this case, if the following conditional expression (3) is satisfied, for example, it is determined that object 172 exists near object 171.

[0118]

number

[0119] Furthermore, for example, if the following conditional expression (4) is satisfied, it is determined that the object 171 is present in the vicinity of the object 172.

[0120]

number

[0121] In S104, an empty processed object ID list is obtained. The processed object ID list stores the object IDs of detected objects for which grouping has been completed. In S105, an empty target object ID list is obtained. The target object ID list is a list for storing the object IDs of detected objects that will be grouped most recently. In S106, 1 is added to the variable K.

[0122] In S107, a new object ID list is created for group K. By inserting S106 and S107 into the loop process, the object ID lists required for grouping are increased for group 1, group 2, group 3, and so on.

[0123] In S108, if the target object ID list includes an object ID and the number of elements is 1 or more, the list is emptied and the number of elements is set to 0. In S109, the object IDs of objects detected by object detection unit 15-1-2 that are not included in the processed object ID list are added to the target object ID list. In S110, one object ID is selected from the target object ID list, and the object assigned the extracted object ID is set as the selected object.

[0124] In S111, the object ID of the selected object (hereinafter referred to as selected object ID) is added to the object list of group K. In S112, the selected object ID is added to the processed object ID list. In S113, the selected object ID is removed from the target object ID list. In S114, the neighbor list created in S13 is referenced to confirm neighboring objects of the selected object. In S115, if the number of neighboring objects confirmed in S114 is 0, the process proceeds to step S121, and if it is 1 or more, the process proceeds to step S116.

[0125] In S116, one of the nearby objects confirmed in S114 is focused on and set as the nearby object of interest. In S117, it is confirmed whether the object ID of the nearby object of interest (hereinafter referred to as nearby object of interest ID) is included in the processed object ID list. If it is included, the process proceeds to step S120, and if it is not included, the process proceeds to step S118. In S118, it is confirmed whether the nearby object ID is included in the target object ID list. If it is included, the process proceeds to step S120, and if it is not included, the process proceeds to step S119. In S119, the nearby object ID of interest is added to the target object ID list.

[0126] In S120, if all nearby objects have been focused on, the process proceeds to step S121. If not all objects have been focused on yet, the process returns to step S116. In S121, the number of elements in the object target list is checked to see if the number of elements is 0. If the number of elements is 1 or more, the process proceeds to step S110, and if the number of elements is 0, the process proceeds to step S122.

[0127] In S122, it is confirmed whether all the object IDs of the objects detected by the object detection unit 15-1-2 are included in the processed object ID list. If all are included, the process proceeds to step S123, and if not, the process returns to step S16.

[0128] In S123, the object ID lists created for each group are aggregated to generate a grouping result, which is then stored in the information storage unit (memory / HD) 15-3.

[0129] In this way, the aggregate detection unit (aggregate determination unit) 15-1-3 determines that, for example, if a second object exists in an area centered on the position in three-dimensional space of the first object detected by the object detection unit 15-1-2, the first object and the second object are aggregates of the same group.

[0130] 18(a) and 18(b) show the data structure of the results generated in step S123 when the aggregate detection unit 15-1-3 performs grouping according to the flowchart explained in Fig. 14. Fig. 18(a) shows a scene in which multiple objects exist within the detection range, and Fig. 18(b) shows the results of grouping the detected objects for the scene shown in Fig. 18(a). In Fig. 18(a), objects 181 to 188 exist, but the grouping process separates them into a group made up of people surrounded by dotted line 1801 and a group made up of people surrounded by dotted line 1802.

[0131] (6-3-2. Processing flow for grouping detected objects using a reference object) When the aggregate detection unit 15-1-3 performs grouping processing according to the flowchart explained in Fig. 14, the group to which the detected objects are assigned depends on the position of the detected objects and the neighborhood area assigned to the detected objects. Therefore, the grouping processing cannot create groups of detected objects of the same category (attribute) or detected objects that move in a similar manner.

[0132] In this embodiment, a derivative grouping process (variant example) for overcoming the issues with grouping process will be described with reference to Fig. 19. Fig. 19 is a flowchart showing an example of grouping process for aggregates. In the derivative grouping, a reference object (hereinafter referred to as reference object) is designated for each group, and when a new object is to be added to a group, the detection information of the object to be added is compared with the detection information of the reference object, and a decision is made on whether to add the object based on the comparison result.

[0133] In S301, control unit 15-2 reads the detection results of object detection unit 15-1-2 from information storage unit (memory / HD) 15-3 and checks the number of detected objects. In S302, if the number of detections is 0, the grouping process ends. If the number of detections is 1 or more, 0 is assigned to variable K for initialization. Variable K is used as a group ID number, and in subsequent processing, the value of variable K is changed appropriately to select which group a detected object should be placed in. In S303, a neighborhood list is created for each detected object and saved in information storage unit (memory / HD) 15-3.

[0134] In S304, an empty processed object ID list is obtained. In S305, an empty target object ID list is obtained. In S306, 1 is added to the variable K. In S307, a new object ID list for group K is created. In S308, if the number of elements in the target object ID list is 1 or more, the list is emptied and the number of elements is set to 0.

[0135] In S309, among the objects detected by object detection unit 15-1-2, an object whose object ID is not included in the processed object ID list is set as a reference object. In S310, the object ID of the reference object (hereinafter referred to as reference object ID) is added to the target object ID list. In S311, one object ID is selected from the target object ID list, and the corresponding object is set as the selected object.

[0136] In S312, the selected object ID is added to the object ID list of group K. In S313, the selected object ID is added to the processed object ID list. In S314, the selected object ID is removed from the target object ID list. In S315, the neighbor list is referenced to check the neighboring objects of the selected object. In S316, if the number of neighboring objects is 0, the process moves to step S323. Also, if the number of neighboring objects is 1 or more, the process moves to step S317.

[0137] In S317, one of the nearby objects is selected and set as the nearby object of interest. In S318, it is confirmed whether the nearby object of interest ID is included in the processed object ID list. If it is included, the process proceeds to step S322; if it is not included, the process proceeds to step S319.

[0138] In S319, it is confirmed whether the target nearby object ID is included in the target ID list, and if it is included, the process proceeds to step S322, and if it is not included, the process proceeds to step S320.

[0139] In S320, the detection information of the target nearby object is compared with the detection information of the reference object, and if it is determined that the two objects are similar, the process proceeds to step S322, and if it is not determined that they are similar, the process proceeds to step S321. The criterion for determining whether the two objects are similar may be how similar the orientation vectors 137 or motion vectors 138 of the detection information are, or whether the categories (attributes) 134 match.

[0140] In S321, the ID of the nearby object of interest is added to the target object ID list. In S322, it is confirmed whether all nearby objects have been focused on, and if so, the process proceeds to step S323. If not all nearby objects have been focused on yet, the process returns to step S317.

[0141] In S323, the number of elements in the object target list is checked to see if it is 0. If the number of elements is 1 or more, the process proceeds to step S311; if the number of elements is 0, the process proceeds to step S324. In S324, the process checks whether the object IDs of all objects detected by object detection unit 15-1-2 are included in the processed object ID list. If all are included, the process proceeds to step S325; if not, the process returns to step S36.

[0142] In S325, the object ID lists created for each group are aggregated to generate the grouping processing results, which are then stored in the information storage unit (memory / HD) 15-3.

[0143] The effect obtained when the aggregate detection unit 15-1-3 performs the grouping process according to the flowchart shown in FIG. 19 will be described with reference to FIGS. 20(a), (b) and 21(a), (b).

[0144] 20(a) is a diagram showing a scene when multiple pedestrians are present within the detection range. 201 to 205 are pedestrians, and 206 to 210 are their motion vectors. Pedestrians 201, 202, and 203 are walking in the positive direction of the Y axis, while pedestrians 204 and 205 are walking in the negative direction of the Y axis.

[0145] Figure 20(b) shows the results of grouping the scene in Figure 20(a). In grouping step S320, the condition for determining whether the target nearby object and the reference object are similar is that the motion vectors 138 of the target nearby object and the reference object are normalized and the solid angle formed by the two normalized vectors is equal to or less than a predetermined value.

[0146] In the results shown in Figure 20(b), not all pedestrians are grouped together in one group, but instead pedestrians walking in the positive direction of the Y axis are grouped as group 2001, and pedestrians walking in the negative direction of the Y axis are grouped as group 2002. In this way, by following the flowchart shown in Figure 19, grouping can be performed taking into account the movement of detected objects.

[0147] Figure 21(a) shows a scene in which two pedestrians are walking side by side while three moving mobilities are driving in a line. 211 and 212 are pedestrians, and 213, 214, and 215 are moving mobilities.

[0148] Fig. 21(b) shows the result of grouping the scene in Fig. 21(a). In the grouping step S320, the condition for determining whether the target nearby object and the reference object are similar is that the categories 134 of the target nearby object and the reference object match.

[0149] In the results shown in Figure 21(b), pedestrians and moving mobilities are not all grouped together, but rather pedestrians 211 and 212 form one group 2101, and moving mobilities 213, 214, and 215 form another group 2102. In this way, by following the flowchart in Figure 19, it is also possible to perform grouping taking into account the category (attributes) of detected objects.

[0150] When a second object exists in an area centered on the position of a first object in three-dimensional space detected by object detection unit 15-1-2 and the first object and the second object are similar objects, aggregate detection unit 15-1-3 determines that the first object and the second object are aggregates of the same group. Preferably, aggregate detection unit 15-1-3 determines that the first object and the second object are similar objects when the attributes of the first object and the second object match. Also preferably, aggregate detection unit 15-1-3 determines that the first object and the second object are similar objects when the angle formed between a first direction vector of the first object and a second direction vector of the second object is equal to or smaller than a predetermined first angle. Also preferably, aggregate detection unit 15-1-3 determines that the first object and the second object are similar objects when the angle formed between a first motion vector of the first object and a second motion vector of the second object is equal to or smaller than a predetermined second angle. Also preferably, the shape of the region changes in accordance with at least one of the orientation and the movement of the first object.

[0151] (6-4. Calculation of the area occupied by detected objects and aggregates) Occupied area calculation unit 15-1-4 calculates the occupied area of the object detected by object detection unit 15-1-2, and calculates the occupied area of the assembly detected by assembly detection unit 15-1-3. Here, the methods for calculating the object occupied area and the assembly occupied area will be described.

[0152] (6-4-1. How to calculate the area occupied by an object) 13(b), the coordinate values of vertices 1026 of the circumscribing rectangle included in the information about the object detected by object detection unit 15-1-2 can be used as they are as the coordinate values of the vertices of the area occupied by the object. Therefore, the calculation of the object occupation area is completed by storing the coordinate values of vertices 1026 of the circumscribing rectangle output by object detection unit 15-1-2 again in information storage unit (memory / HD) 15-3 as the coordinate values of the vertices of the area occupied by the detected object.

[0153] If it is desired to provide some margin in the object's occupied area, the detection position 1025 is obtained from the information storage unit (memory / HD) 15-3 along with the vertices 1026 of the circumscribing rectangle. Then, the circumscribing rectangle is enlarged with the detection position as the center, and the coordinates of the vertices of the enlarged circumscribing rectangle are saved in the information storage unit (memory / HD) 15-3 as the coordinate values of the object's occupied area.

[0154] (6-4-2. Calculation method for the area occupied by an aggregate) The aggregate occupied area is the combined area of the object occupied area and the occupied area that occurs between the objects that make up the aggregate (hereinafter referred to as the inter-object occupied area). Therefore, to calculate the aggregate occupied area, it is sufficient to calculate the object occupied area and the inter-object occupied area, and then combine the calculated object occupied area. Since the calculation method for the object occupied area was explained in the previous section, only the calculation method for the inter-object occupied area will be explained below.

[0155] 22 is a flowchart showing a method for calculating all inter-object occupied areas within a single cluster. By performing the process shown in the flowchart for all groups acquired by the cluster detection unit 15-1-3, all inter-object occupied areas within the detection range can be calculated.

[0156] In S401, all objects in the group are acquired. In S402, a neighbor list is acquired from the information storage unit (memory / HD) 15-3. In S403, the neighbor list is used to create pairs of objects (first object, second object) that are close to each other from the objects in the group. In S404, one pair of objects created in S403 is selected. In S405, a circumscribing rectangle is acquired from each of the selected object pairs. In S406, four vertices are selected from each of the two circumscribing rectangles acquired in S405. In S407, the eight vertices selected in S406 are set as vertices of the occupied areas of the first object and the second object, and their coordinate values are saved in the information storage unit (memory / HD) 15-3.

[0157] 23(a) and (b) show an image of the circumscribing rectangles of paired objects and the object-to-object neighborhood region calculated from the circumscribing rectangles in step S407. Fig. 23(a) is a top view of the paired circumscribing rectangles and the object-to-object neighborhood region that have been set, and Fig. 23(b) is a side view.

[0158] Reference numerals 231 and 232 denote paired objects, and 233 and 234 denote circumscribing rectangles of 231 and 232, respectively. Reference numeral 235 denotes an inter-object occupied area (area between the first object and the second object), and the position and shape of the inter-object occupied area are determined by the vertices of the opposing faces of the circumscribing rectangles 233 and 234.

[0159] In S408, it is confirmed whether all of the object pairs created in S403 have been selected, and if so, the process ends.

[0160] 7. Path Planning for Autonomous Vehicles Considering Detected Objects and Clusters The object occupied area and the aggregate occupied area calculated by the occupied area calculation unit 15-1-4 are abstracted and transmitted to the conversion device 14 as spatial information.

[0161] As explained in (5-12. Reflecting Spatial Information Updates in Autonomous Mobile Bodies), the transmitted spatial information is stored in the format database 14-4. The system control device 10 checks for changes in the spatial information in the format route information that it manages at predetermined time intervals. If there is a change in the spatial information, the system control device 10 downloads the spatial information and updates the cost map, and also updates the cost map linked to the unique identification number assigned to the autonomous mobile body 12. The autonomous mobile body 12 recognizes the update to the cost map by polling and reflects it in the three-dimensional map of cyberspace that it created.

[0162] FIG. 24 is a diagram showing a situation in which the autonomous mobile body 12 is physically able to take a straight route and a detour route as it heads toward a goal.

[0163] Reference numeral 1132 denotes a goal point to which the autonomous mobile body 12 is heading. Reference numerals 1138 and 1139 respectively denote a straight route and a detour route that the autonomous mobile body 12 takes to the goal point 1132. Reference numerals 1133 to 1136 denote people (multiple objects including a first object and a second object) standing between the autonomous mobile body 12 and the goal point 1132. Reference numeral 1137 denotes an obstacle such as a wall.

[0164] When the system control device 10 updates the cost map, it takes into account not only the area occupied by the object but also the area occupied by the collection. Therefore, when planning the route of the autonomous moving body (autonomous mobility) 12 based on the updated cost map, it selects a detour route 1139 instead of a straight route 1138.

[0165] (8. Occupied Area Calculation Function of Autonomous Mobile Body 12) The detection unit 12-1 has functions equivalent to the object detection function of the object detection unit 15-1-2, the aggregation detection function of the aggregation detection unit 15-1-3, and the occupation area calculation function of the occupation area calculation unit 15-1-4. The autonomous moving body 12 detects the inter-object occupation area using the occupation area calculation function. Based on information about the inter-object occupation area, the autonomous moving body 12 may determine by itself whether or not to pass between objects.

[0166] For example, the autonomous mobile body control system 1 of this embodiment also functions as a route search device that searches for a route for the autonomous mobile body 12. The route search device has a recognition unit (recognition means, for example, sensor node 15) that recognizes a first object and a second object, and a route search unit (route search means, for example, route determination device 13). Based on the recognition result of the recognition unit, if the distance between the first object and the second object is longer than the width of the autonomous mobile body 12 and the distance is equal to or shorter than a predetermined distance, the route search unit searches for a route that prevents the autonomous mobile body 12 from passing between the first object and the second object.

[0167] The above description provides a digital architecture format and an autonomous mobile control system using the same.

[0168] (Other embodiments) The present invention can also be realized by supplying a program that realizes one or more functions of the above-described embodiments to a system or device via a network or a storage medium, and having one or more processors in the computer of the system or device read and execute the program. It can also be realized by a circuit (e.g., ASIC) that realizes one or more functions.

[0169] This embodiment can detect a collection of detected objects from detection information acquired by a sensor such as a camera, calculate the range of the space occupied by the collection, plan an optimal route, and provide the route information to autonomous mobility. Therefore, this embodiment can provide an information processing device, an information processing method, and a program that can perform an appropriate route search based on information about the collection of detected objects.

[0170] The disclosure of each embodiment includes the following configurations and methods. (Configuration 1) an object detection means for detecting a first object and a second object; an aggregate determination means for determining whether the first object and the second object are aggregates of the same group based on object detection information regarding the first object and the second object detected by the object detection means; a calculation means for calculating spatial information regarding an occupied area occupied by at least one of the first object, the second object, and the collection; and a transmitting means for transmitting at least one of the object detection information, the information about the aggregate, and the spatial information. (Configuration 2) a map generating means for generating a map relating to the positions of the first object and the second object based on the spatial information transmitted by the transmitting means; 2. The information processing device according to configuration 1, further comprising: route information generating means for generating route information for an autonomous moving body based on the map. (Configuration 3) The information processing device described in configuration 1 or 2, characterized in that when the second object is present in an area centered on the position in three-dimensional space of the first object detected by the object detection means, the aggregate determination means determines that the first object and the second object are aggregates of the same group. (Configuration 4) The information processing device described in configuration 1 or 2, characterized in that the aggregation determination means determines that the first object and the second object are aggregations of the same group when the second object is present in an area centered on the position in three-dimensional space of the first object detected by the object detection means and the first object and the second object are similar objects. (Configuration 5) The information processing device according to configuration 4, wherein the aggregate determination means determines that the first object and the second object are similar objects when the attributes of the first object and the second object match. (Configuration 6) The information processing device described in configuration 4, characterized in that the aggregate determination means determines that the first object and the second object are similar objects when the angle formed between the first direction vector of the first object and the second direction vector of the second object is less than or equal to a first angle. (Configuration 7) The information processing device described in configuration 4, characterized in that the aggregation determination means determines that the first object and the second object are similar objects when an angle formed between a first motion vector of the first object and a second motion vector of the second object is less than or equal to a second angle. (Configuration 8) 8. The information processing device according to any one of configurations 3 to 7, wherein the shape of the region changes depending on the orientation of the first object. (Configuration 9) 8. The information processing device according to any one of configurations 3 to 7, wherein the shape of the region changes in accordance with the movement of the first object. (Configuration 10) 10. The information processing device according to any one of configurations 1 to 9, wherein the calculation means calculates the occupied areas in a three-dimensional space, and calculates areas existing between the calculated occupied areas. (Configuration 11) the occupied regions are two circumscribing rectangles corresponding to the first object and the second object, respectively; 11. The information processing device according to configuration 10, wherein the calculation means acquires four vertices from each of the two circumscribed rectangles, and acquires an area formed by the acquired eight vertices in total. (Configuration 12) A route search device that searches for a route for a moving body, recognition means for recognizing a first object and a second object; and route searching means for searching for a route such that the moving body does not pass between the first object and the second object when, based on the recognition result of the recognition means, the distance between the first object and the second object is longer than the width of the moving body and the distance is equal to or less than a predetermined distance. (Method 1) a detection step of detecting a first object and a second object; a determination step of determining whether the first object and the second object are a group of the same object based on object detection information regarding the first object and the second object detected in the detection step; a calculation step of calculating spatial information regarding an occupied area occupied by at least one of the first object, the second object, and the collection; a transmitting step of transmitting at least one of the object detection information, the information about the collection, and the spatial information. (Method 2) A route search method for searching for a route for a moving body, comprising: a recognition step of recognizing a first object and a second object; and a search step of searching for a route such that the moving body does not pass between the first object and the second object when, based on the recognition result in the recognition step, the distance between the first object and the second object is longer than the width of the moving body and the distance is equal to or less than a predetermined distance. (Configuration 13) A program that causes a computer to execute the information processing method described in Method 1. (Configuration 14) A program that causes a computer to execute the route search method according to Method 2.

[0171] Although the preferred embodiments of the present invention have been described above, the present invention is not limited to these embodiments, and various modifications and changes are possible within the scope of the gist of the present invention. [Explanation of symbols]

[0172] 1 Autonomous mobile control system (information processing device) 15-1-2 Object detection unit (object detection means) 15-1-3 Aggregate detection unit (aggregate determination means) 15-1-4 Occupied area calculation unit (calculation means) 15-4 Network connection part (transmission means)

Claims

1. an object detection means for detecting a first object and a second object; an aggregate determination means for determining whether the first object and the second object are aggregates of the same group based on object detection information relating to the first object and the second object detected by the object detection means; a calculation means for calculating spatial information regarding an occupied area occupied by at least one of the first object, the second object, and the collection; and a transmitting means for transmitting at least one of the object detection information, the information about the aggregate, and the spatial information.

2. a map generating means for generating a map relating to the positions of the first object and the second object based on the spatial information transmitted by the transmitting means; 2. The information processing apparatus according to claim 1, further comprising: route information generating means for generating route information for an autonomous moving body based on the map.

3. The information processing device according to claim 1, characterized in that the aggregation determination means determines that the first object and the second object are aggregations of the same group when the second object is present in an area centered on the position in three-dimensional space of the first object detected by the object detection means.

4. The information processing device described in claim 1, characterized in that the aggregation determination means determines that the first object and the second object are aggregations of the same group if the second object is present in an area centered on the position in three-dimensional space of the first object detected by the object detection means and if the first object and the second object are similar objects.

5. 5. The information processing apparatus according to claim 4, wherein the aggregate determination means determines that the first object and the second object are similar objects when attributes of the first object and the second object match.

6. The information processing device according to claim 4, characterized in that the aggregate determination means determines that the first object and the second object are similar objects when the angle formed between the first direction vector of the first object and the second direction vector of the second object is less than or equal to a first angle.

7. The information processing device according to claim 4, characterized in that the aggregation determination means determines that the first object and the second object are similar objects when the angle formed between the first motion vector of the first object and the second motion vector of the second object is less than or equal to a second angle.

8. The information processing apparatus according to claim 3 , wherein the shape of the region changes depending on the orientation of the first object.

9. The information processing apparatus according to claim 3 , wherein the shape of the region changes in accordance with the movement of the first object.

10. 2. The information processing apparatus according to claim 1, wherein said calculation means calculates the occupied areas in a three-dimensional space, and calculates areas existing between the calculated occupied areas.

11. the occupied regions are two circumscribing rectangles corresponding to the first object and the second object, respectively; 11. The information processing apparatus according to claim 10, wherein the calculation means acquires four vertices from each of the two circumscribing rectangles, and acquires an area formed by a total of eight acquired vertices.

12. A route search device that searches for a route for a moving body, recognition means for recognizing a first object and a second object; and route searching means for searching for a route such that the moving body does not pass between the first object and the second object when, based on the recognition result of the recognition means, the distance between the first object and the second object is longer than the width of the moving body and the distance is equal to or less than a predetermined distance.

13. a detecting step of detecting a first object and a second object; a determination step of determining whether the first object and the second object are a group of the same object based on object detection information regarding the first object and the second object detected in the detection step; a calculation step of calculating spatial information regarding an occupied area occupied by at least one of the first object, the second object, and the collection; a transmitting step of transmitting at least one of the object detection information, the information about the collection, and the spatial information.

14. A route search method for searching for a route for a moving body, comprising: a recognition step of recognizing a first object and a second object; and a search step of searching for a route such that the moving body does not pass between the first object and the second object when, based on the recognition result in the recognition step, the distance between the first object and the second object is longer than the width of the moving body and the distance is equal to or less than a predetermined distance.

15. A program causing a computer to execute the information processing method according to claim 13.

16. A program causing a computer to execute the route search method according to claim 14.

Images