Control device of mobile object, control method of mobile object and storage medium

Abstract

Provided are a control device for a mobile body, a control method for a mobile body, and a storage medium that can identify or remove light source noise with better accuracy. The control device for the mobile body comprises: a recognition unit that identifies a point group corresponding to an object existing in the vicinity of the mobile body based on an image obtained by photographing the condition of the vicinity of the mobile body; and a control unit that determines a moving path of the mobile body based on the condition of the vicinity and controls the mobile body to move along the determined moving path, wherein the recognition unit performs a noise determination process, in which the distribution of the height direction of the point group identified as a candidate for the object is obtained in a specified area around the mobile body, and based on the distribution, it is determined whether the point group in the specified area contains light source noise.

Description

Technical Field

[0001] The present invention relates to a control device for a mobile object, a control method for a mobile object and a storage medium. Background Art

[0002] In the past, the following scheme has been proposed: points corresponding to candidate obstacles determined based on the output of a LIDAR device (hereinafter referred to as corresponding points) are projected onto a horizontal plane area and associated with a grid on the horizontal plane, and based on the association between the corresponding points and the grid, a first candidate obstacle setting corresponding to the noise is removed from the candidate obstacles (for example, refer to Patent Document 1).

[0003] [Prior technical literature]

[0004] [Patent Literature]

[0005] Patent Document 1: Japanese Patent Application No. 2023-517105 Summary of the invention

[0006] Problems to be solved by the invention

[0007] However, in the conventional technology, light source noise may not be properly identified from the obstacle candidates, and light source noise may not be properly removed.

[0008] The present invention has been made in consideration of such a situation, and one of its objects is to provide a control device for a moving object, a control method for a moving object, and a storage medium that can recognize or remove light source noise with higher accuracy.

[0009] Solutions to Solve Problems

[0010] The control device for a mobile object, the control method for a mobile object, and the storage medium according to the present invention employ the following configurations.

[0011] (1): One embodiment of the present invention relates to a control device for a mobile body, wherein the control device for the mobile body comprises: an identification unit, which identifies a point group corresponding to an object existing in the vicinity of the mobile body based on an image obtained by photographing the condition of the vicinity of the mobile body; and a control unit, which determines a moving path of the mobile body based on the condition of the vicinity and controls the mobile body to move along the determined moving path, wherein the identification unit performs a noise determination process, in which the height direction distribution of the point group identified as a candidate for the object is obtained in a specified area around the mobile body, and based on the distribution, it is determined whether the point group in the specified area contains light source noise.

[0012] (2): Based on the scheme of (1) above, the recognition unit obtains a curve representing the distribution in the noise determination process, and determines whether the point group in the specified area contains light source noise based on the number of maximum points of the curve.

[0013] (3) Based on the above scheme (2), when the recognition unit determines that the point group in the specified area contains light source noise based on the number of the maximum points, the recognition unit removes the light source noise from the point group in the specified area.

[0014] (4): Based on the scheme of (1) above, the recognition unit recognizes the periphery of the mobile body as a collection of unit areas of the same size, and manages the presence or absence of the object in the unit area according to the occupancy status of the unit area, and the recognition unit performs the noise determination processing for each unit area.

[0015] (5): Based on the scheme of (4) above, the recognition unit recognizes the candidate area of ​​the object based on the clustering of the point group recognized from the image, and recognizes the candidate area of ​​the candidate area that is smaller than a specified size as the candidate area of ​​the light source noise.

[0016] (6) In the above-mentioned aspect (5), the recognition unit executes the noise determination process for each unit area included in the candidate area of ​​the light source noise.

[0017] (7) In the above-mentioned embodiment (2), when the number of local points of the curve is 2, the identification unit determines that the point group in the predetermined area includes light source noise.

[0018] (8): Another scheme of the present invention relates to a control method for a mobile body, wherein the control method for a mobile body causes a computer to perform the following processing: recognition processing for identifying a point group corresponding to an object existing in the vicinity of the mobile body based on an image obtained by photographing the condition of the vicinity of the mobile body; and control processing for determining a moving path of the mobile body based on the condition of the vicinity, and controlling the mobile body to move along the determined moving path. In the recognition processing, the height direction distribution of the point group identified as a candidate for the object is obtained in a specified area around the mobile body, and based on the distribution, it is determined whether the point group in the specified area contains light source noise.

[0019] (9): Another embodiment of the present invention relates to a storage medium storing a program, wherein the program is used to cause a computer to execute the following processing: recognition processing for identifying a point group corresponding to an object existing in the vicinity of the moving body based on an image obtained by photographing the condition of the vicinity of the moving body; and control processing for determining a moving path of the moving body based on the condition of the vicinity and controlling the moving body to move along the determined moving path, wherein the recognition processing obtains the height direction distribution of the point group identified as a candidate for the object in a specified area around the moving body, and determines whether the point group in the specified area contains light source noise based on the distribution.

[0020] Effects of the Invention

[0021] According to the above-mentioned aspects (1) to (9), light source noise can be removed with higher accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 1 is a diagram showing an example of a configuration of a moving body system 1 including a moving body 100 .

[0023] Figure 2 This is a diagram for explaining an example of the use form of the moving object 100.

[0024] Figure 3 It is a perspective view showing the moving object 100 .

[0025] Figure 4 1 is a diagram showing an example of a functional configuration of the mobile object 100 .

[0026] Figure 5 : is a diagram showing an example of light source noise that may be included in the recognition result of the recognition unit 206 .

[0027] Figure 6 This is a flowchart showing an example of the flow of processing performed by the recognition unit 206 to recognize objects around the moving body 100 while removing light source noise.

[0028] Figure 7 FIG. 1 is a diagram showing an example of the recognition result of the object candidate region.

[0029] Figure 8 This is a diagram showing an example of an object candidate region extracted as a light source noise candidate region.

[0030] Fig. 9 This is a diagram for explaining a method of removing a point group corresponding to light source noise from the light source noise candidate region C2.

[0031] Description of reference numerals:

[0032] 1 Mobile system

[0033] 2Terminal device

[0034] 10 Management Device

[0035] 20Information providing device

[0036] 100 moving bodies

[0037] 110 base

[0038] 112 Door Department

[0039] 120 First Wheel

[0040] 122 First Motor

[0041] 130 Second Wheel

[0042] 132 Second Motor

[0043] 134 Battery

[0044] 136 Braking device

[0045] 138 Steering device

[0046] 140 Third Wheel

[0047] 150 Support

[0048] 180 Camera

[0049] 190 Ministry of Communications

[0050] 200 control devices

[0051] 202 Position determination unit

[0052] 204 Information Processing Department

[0053] 206 Identification Department

[0054] 208 Path Generation Unit

[0055] 210 Track Generation Unit

[0056] 212 First Control Unit

[0057] 214 Second Control Unit

[0058] 220 Storage Department

[0059] 222 Control Information

[0060] 224 map information. DETAILED DESCRIPTION

[0061] Hereinafter, embodiments of a control device for a moving object, a control method for a moving object, and a storage medium according to the present invention will be described with reference to the accompanying drawings.

[0062] Figure 1 1 is a diagram showing an example of a structure of a mobile system 1 including a mobile body 100. The mobile system 1 includes, for example, one or more terminal devices 2, a management device 10, an information providing device 20, and one or more mobile bodies 100. These communicate via, for example, a network NW. The network NW is, for example, any network such as a LAN, a WAN, or an Internet line.

[0063] [Terminal device]

[0064] The terminal device 2 is a computer device such as a smartphone or a tablet terminal. The terminal device 2 requests the management device 10 to provide permission to use the mobile object 100 or obtains information indicating that the use is permitted from the management device 10 based on the operation of the user.

[0065] [Management Device]

[0066] The management device 10 grants the user of the terminal device 2 the right to use the mobile body 100 or manages the reservation for use of the mobile body 100 in response to the request of the terminal device 2. For example, the management device 10 generates and manages schedule information that associates the identification information of the pre-registered user with the date and time of the reservation for use of the mobile body 100.

[0067] [Information providing device]

[0068] The information providing device 20 provides the location of the mobile body 100, the area where the mobile body 100 moves, and map information of the surrounding area to the mobile body 100. The information providing device 20 may also generate a route to the destination of the mobile body 100 in response to a request from the mobile body 100, and provide the generated route to the mobile body 100.

[0069] [Mobile body]

[0070] The mobile object 100 is used by the user in the following usage forms. Figure 2It is a diagram for explaining an example of the use form of the mobile body 100. The mobile body 100 is configured, for example, at a specified position of a facility or a street. When a user wants to use the mobile body 100, he can operate the operation unit (not shown) of the mobile body 100 to start the use, or operate the terminal device 2 to start the use of the mobile body 100. For example, when the user goes out to buy things and has a lot of goods, he starts to use the mobile body 100 and puts the goods into the storage unit of the mobile body 100. And the mobile body 100 moves with the user in a manner of autonomously following the user. The user can continue shopping or go to the next destination while storing the goods in the mobile body 100. For example, the mobile body 100 moves with the user on the sidewalk or the crosswalk of the road. The mobile body 100 can move in areas where pedestrians can pass, such as roads and sidewalks. For example, the mobile body 100 can be used in indoor or outdoor facilities, private land, such as shopping malls, airports, parks, theme parks, etc., and can also move in areas where pedestrians can pass.

[0071] The moving object 100 may be capable of autonomously moving in a mode such as a guidance mode or an emergency mode in addition to (or instead of) the following mode in which the moving object 100 follows the user as described above.

[0072] Figure 3 : is a perspective view showing the moving body 100. In the following description, the front direction of the moving body 100 is set as the positive x direction, the rear direction of the moving body 100 is set as the negative x direction, the width direction of the moving body 100 and the left direction based on the positive x direction is set as the positive y direction, the width direction of the moving body 100 and the right direction based on the positive x direction is set as the negative y direction, and the direction perpendicular to the x direction and the y direction and the height direction of the moving body 100 is set as the positive z direction.

[0073] The mobile body 100 includes, for example, a base 110, a door 112 provided on the base 110, and wheels (a first wheel 120, a second wheel 130, and a third wheel 140) assembled on the base 110. For example, a user can open the door 112 to put goods into or take goods out of the storage portion provided on the base 110. The first wheel 120 and the second wheel 130 are driving wheels, and the third wheel 140 is an auxiliary wheel (driven wheel). The mobile body 100 may also be able to move using a structure other than wheels, such as tracks.

[0074] A cylindrical support body 150 extending in the positive z direction is provided on the surface of the base body 110 in the positive z direction. A camera 180 for photographing the surroundings of the moving body 100 is provided at the end of the support body 150 in the positive z direction. The position where the camera 180 is provided may be any position different from the above.

[0075] The camera 180 is, for example, a camera capable of capturing images of the surroundings of the moving object 100 at a wide angle (eg, 360 degrees). The camera 180 may include a plurality of cameras. The camera 180 may be realized by combining a plurality of 120-degree cameras or a plurality of 60-degree cameras, for example.

[0076] Figure 4 FIG. 1 is a diagram showing an example of a functional configuration of the mobile object 100. The mobile object 100 includes Figure 3 In addition to the functional structure shown, the first motor 122, the second motor 132, the battery 134, the brake device 136, the steering device 138, the communication unit 190 and the control device 200 are further provided. The first motor 122 and the second motor 132 are operated by the power supplied by the battery 134. The first motor 122 drives the first wheel 120, and the second motor 132 drives the second wheel 130. The first motor 122 may be an in-wheel motor provided in the wheel portion of the first wheel 120, and the second motor 132 may be an in-wheel motor provided in the wheel portion of the second wheel 130.

[0077] The brake device 136 outputs a braking torque to each wheel based on an instruction from the control device 200. The steering device 138 includes an electric motor. The electric motor, for example, applies a force to a rack-and-pinion mechanism based on an instruction from the control device 200 to change the direction of the first wheel 120 or the second wheel 130, thereby changing the forward path of the moving body 100.

[0078] The communication unit 190 is a communication interface for communicating with the terminal device 2 , the management device 10 , or the information providing device 20 .

[0079] [Control device]

[0080] The control device 200 includes, for example, a position determination unit 202, an information processing unit 204, an identification unit 206, a path generation unit 208, a track generation unit 210, a first control unit 212, a second control unit 214, and a storage unit 220. The position determination unit 202, the information processing unit 204, the identification unit 206, the path generation unit 208, the track generation unit 210, the first control unit 212, and the second control unit 214 are implemented by, for example, a hardware processor such as a CPU (Central Processing Unit) executing a program (software). Some or all of these components may be implemented by hardware (including circuitry) such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), GPU (Graphics Processing Unit), or by the coordinated cooperation of software and hardware. The program can be pre-stored in a storage device such as an HDD (Hard Disk Drive) or a flash memory (a storage device having a non-temporary storage medium), or can be stored in a removable storage medium such as a DVD or CD-ROM (a non-temporary storage medium), and installed by mounting the storage medium in a drive device.

[0081] The storage unit 220 is implemented by a storage device such as an HDD, a flash memory, or a RAM (Random Access Memory). The storage unit 220 stores control information 222, which is a control program for controlling the behavior of the mobile body 100, and map information 224 for reference by the first control unit 212 and the second control unit 214. The map information 224 is, for example, map information such as the location of the mobile body 100, the area where the mobile body 100 moves, and the surrounding area of ​​the area provided by the information providing device 20. The map information may include an area where the mobile body 100 can move, and an area where the mobile body 100 cannot move (statically arranged obstacles, prohibited entry areas, etc.).

[0082] Part or all of the path generation unit 208, the track generation unit 210, the first control unit 212, and the second control unit 214 are examples of a "control unit". Part or all of the functional structure included in the control device 200 may also be included in other devices. For example, other devices may communicate with the mobile body 100 and cooperate to control the mobile body 100.

[0083] The position determination unit 202 determines the position of the moving object 100. The position determination unit 202 obtains the position information of the moving object 100 from a GPS (Global Positioning System) device (not shown) built in the moving object 100. The position information may be, for example, two-dimensional map coordinates or longitude and latitude information.

[0084] The information processing unit 204 manages information acquired from, for example, the terminal device 2 , the management device 10 , or the information providing device 20 .

[0085] The recognition unit 206 recognizes the position (distance from the mobile body 100 and direction relative to the mobile body 100), speed, acceleration and other states of objects in the vicinity of the mobile body 100 based on the image captured by the camera 180. The so-called objects include traffic participants, obstacles existing in facilities and roads, etc. In addition, the so-called obstacles include static obstacles included in the map information and dynamic obstacles not included in the map information. The recognition unit 206 recognizes and tracks the user of the mobile body 100. For example, the recognition unit 206 tracks the user based on an image captured of the user registered when the user uses the mobile body 100 (for example, a facial image of the user) and a facial image of the user provided by the terminal device 2 or the management device 10 (or a feature value obtained from the facial image of the user). The recognition unit 206 recognizes gestures made by the user. It should be noted that a detection unit different from the camera, such as a radar device or LIDAR, may also be provided in the mobile body 100. In this case, the recognition unit 206 recognizes the surrounding conditions of the moving object M using the detection results of the radar device or LIDAR instead of (or in addition to) the image.

[0086] The route generation unit 208 generates a route to the destination specified by the user. The so-called destination may also be a place where goods are sold or a place where facilities are sold. In this case, the user specifies goods or facilities, and the mobile body 100 sets the place where the goods or facilities are specified as the destination. The route is a route that can reasonably reach the destination. For example, the distance to the destination, the time to reach the destination, the ease of travel of the route, etc. are scored, and each score and a route having a score above a threshold value obtained by combining the scores are derived.

[0087] The track generation unit 210 generates a track that the moving body 100 should travel in the future, for example, based on the user's gesture, the destination set by the user, the surrounding objects, the user's position, etc. The track generation unit 210 generates a track that allows the moving body 100 to move smoothly to the target location. The track generation unit 210 generates a track corresponding to the movement of the moving body 100, for example, based on the correspondence between the preset gesture and the action, or generates a track for going to the destination while avoiding the surrounding objects. In addition, the track generation unit 210 generates a track for following the user being tracked or a track for guiding the user. The track generation unit 210 generates a track corresponding to the action obtained based on a preset pattern, for example. The track generation unit 210 generates a plurality of tracks corresponding to the movement of the moving body 100, and obtains the risk of each track. When the total value of the obtained risk and the risk of each track point meet the preset reference (for example, the total value is less than the threshold value Th1, and the risk of each track point is less than the threshold value Th2), the track that meets the reference is adopted as the track for the moving body 100. For example, the risk tends to be higher as the distance between the obstacle and the track (track point of the track) is smaller, and the risk tends to be lower as the distance between the obstacle and the track is larger.

[0088] The first control unit 212 controls the motors (the first motor 122 and the second motor 132 ), the brake device 136 , and the steering device 138 so that the moving body 100 travels along a track that satisfies a preset reference.

[0089] The second control unit 214 controls the mobile body 100 based on the recognition result of the recognition unit 206 so that the mobile body 100 does not come into contact with surrounding objects and the distance between the user and the mobile body 100 is within a predetermined distance range. The predetermined distance range refers to a distance range between a preset shortest distance Dmin and a preset longest distance Dmax. The shortest distance Dmin and the longest distance Dmax may be variable distances corresponding to the type of motion control (follow-up control, induction control, etc.), the surrounding conditions (shape of the moving path, degree of crowding), etc., or may be fixed distances.

[0090] [Light source noise]

[0091] As described above, the recognition unit 206 recognizes objects around the moving body 100 based on the image captured by the camera 180. However, when there are light sources such as lighting and windows around the moving body 100, the image captured by the camera 180 sometimes contains light source noise such as so-called overexposure depending on the position and orientation of the moving body 100. Figure 5is a diagram showing an example of light source noise that may be included in the recognition result of the recognition unit 206. The recognition unit 206 manages the surrounding area of ​​the moving object 100 as a set of grids of a predetermined size, and manages the presence or absence of an object according to the state of each grid. For example, Figure 5 The example represents the existence of an object according to the grid of the occupied state, and represents the non-existence of the object according to the grid of the unoccupied state. Figure 5 The grid plane (hereinafter referred to as “occupancy grid graph”) viewed from a height direction at a certain point in time when the surrounding area R1 of the moving object 100 is viewed is shown. Here, each grid of the occupation grid graph (or the area corresponding to each grid) is an example of a “unit area”.

[0092] It should be noted that in the management of the presence or absence of obstacles based on the occupied grid map, the road surface on which the mobile body 100 is traveling is not treated as an object that can influence the occupancy status of each grid. That is, the recognition unit 206 recognizes the road surface on which the mobile body 100 can travel around the mobile body 100 (hereinafter referred to as the "driving road surface") based on the image captured by the camera 180, the map information 224, etc., and recognizes the occupancy status of each grid by the presence or absence of objects other than the driving road surface. For example, the recognition unit 206 can three-dimensionally recognize the point group corresponding to the object existing in the surrounding area based on the image captured by the camera 180, the map information 224, etc., and recognize the point group corresponding to the driving road surface based on the height direction position of the point group.

[0093] Figure 5 The situation where obstacles B1, B2, and B3 are recognized in area R1 is shown. Among these obstacles, obstacles B1 and B3 are correctly recognized obstacles, and obstacle B2 is light source noise that is mistakenly recognized as an obstacle. When an obstacle is misidentified due to such light source noise, the area that should have been used as the driving path of the mobile body 100 becomes an inaccessible area, and an appropriate driving path cannot be set. For example, in Figure 5 In the example, if there is no erroneous recognition of the obstacle B2, the straight path RT1 can be set as the driving path. On the other hand, due to the erroneous recognition of the obstacle B2, the driving path is set as the roundabout path RT2. In this way, the light source noise may hinder the determination of an appropriate driving path for the moving body 100. Therefore, the recognition unit 206 of this embodiment is configured to perform filtering processing to remove the light source noise on the recognition results of the objects around the moving body 100.

[0094] [Filtering of light source noise]

[0095] Figure 6This is a flowchart showing an example of the process of the recognition unit 206 identifying objects around the moving body 100 while removing light source noise. First, the recognition unit 206 identifies each object candidate area by clustering the grids of the occupied state with respect to the occupied grid figure recognized based on the image (S101). The clustering method is arbitrary, and for example, the shortest distance method can be used. Figure 7 FIG. 1 is a diagram showing an example of the recognition result of the object candidate region. Figure 7 Indicates recognition of Figure 5 The obstacles B1, B2, B3 are arranged in the same manner as the object candidate areas C1, C2, C3.

[0096] Next, the recognition unit 206 extracts the object candidate area with a small number of grids (below the threshold) in the object candidate area as a light source noise candidate area (S102), and creates a density curve in the height direction (Z-axis direction) for the point group contained in the light source noise candidate area for each extracted light source noise candidate area (S103). The density curve is obtained by summing the number of point groups existing in the light source noise candidate area at each height. In this sense, the density curve can be called a histogram of the point group in the height direction. The recognition unit 206 performs a histogram review based on the created density curve to identify the maximum point (S104), and removes the light source noise contained in the grid of the object based on the distribution of the identified maximum point (S105). More specifically, the recognition unit 206 removes the second point group as light source noise when there is a first point group corresponding to the object and a second point group separated from the first point group into the air (in the height direction). For example, the recognition unit 206 may also regard the maximum point of the density curve that exists above a predetermined height as the cause of light source noise, and remove the point group located at the height of the maximum point as light source noise. This is because light source noise exists in the air. Hereinafter, the process of determining whether the identified point group is light source noise is referred to as noise determination processing.

[0097] Figure 8 : is a figure which shows an example of the object candidate region C2 extracted as the light source noise candidate region. Figure 8 About Figure 7 The object candidate regions C1, C2, and C3 in the example are set to a threshold value of 2 or more and 5 or less for the number of grids when extracting the light source noise candidate region. In this case, the number of grids of the object candidate regions C1, C2, and C3 is 9, 2, and 6, respectively, so when the threshold value is 2 or more and 5 or less, the object candidate region C2 is extracted as the light source noise candidate region. Hereinafter, the object candidate region C2 is sometimes referred to as the light source noise candidate region C2. Figure 8This indicates that in the light source noise candidate area C2, the point group P1 corresponding to the traveled road surface exists at a low altitude position (e.g., near Z=z1), and the point group P2 corresponding to the light source noise exists in the air near a specified altitude (e.g., near Z=z2).

[0098] Fig. 9 This is a diagram for explaining a method of removing a point group corresponding to light source noise from the light source noise candidate region C2. Fig. 9 It is a graph showing the density curve L1 produced for the light source noise candidate area C2. In this case, the maximum points of the density curve appear near Z=z1 and near Z=z2, so the light source noise in the light source noise candidate area C2 can be removed by filtering the point group above the height threshold zth, for example. The recognition unit 206 updates the occupied grid diagram (S106) based on the distribution of the point group after the light source noise is removed. As a result, the occupied state of the grid group constituting the light source noise candidate area C2 is changed from occupied to non-occupied, and the grid group is recognized as a drivable area.

[0099] It should be noted that the threshold of the number of grids used when extracting the candidate area for light source noise and the threshold of the height used when detecting the maximum point of the cause of light source noise can be appropriately adjusted according to the environment in which the mobile body 100 is traveling. In addition, in order to prevent the point group corresponding to the actual obstacle from being mistakenly removed as light source noise, in addition to the height threshold, filtering conditions can be added based on the distribution characteristics of the point group corresponding to the light source noise. For example, as described above, light source noise occurs in the air in a relatively small range, so it is also possible to add a judgment condition associated with the shape with respect to the peak value of the maximum point that forms the cause of light source noise. For example, the following judgment conditions can also be set.

[0100] The peak width is below the threshold (i.e. the peak is sharp and the distribution range is small)

[0101] The minimum points before and after the peak are near the frequency 0 (i.e. hollow)

[0102] It should be noted that, depending on the obstacle, sometimes a maximum point or a minimum point is formed according to its shape (e.g., convex or concave), so the density curve can also be discretized in a larger range (height direction). In this way, the density curve gradually approaches the histogram representing the frequency (number of points) of each specified width (height direction), so the fine peaks generated by the shape of the obstacle are flattened and can be less likely to be mistakenly identified as the cause of light source noise.

[0103] In addition, in the case of simple filtering, it is also possible to determine whether it is light source noise based on the number of maximum points. For example, in an area where there is no obstacle on the road surface, it is hollow in the height direction, and there is no light source noise, only the point group corresponding to the road surface is detected (that is, only the maximum point corresponding to the road surface is detected), so the number of detected maximum points becomes 1. In addition, in an area where there is an obstacle on the road surface, the area above the obstacle is hollow, and there is no light source noise, a point group corresponding to the road surface and the obstacle is also detected in a relatively close range, so in this case, the possibility that the number of detected maximum points is 1 is also high. Therefore, in the case where there is light source noise in the air, the possibility that the number of maximum points is 2 is high. Therefore, the recognition unit 206 can also be configured to count the number of maximum points of the density curve (which can also be a histogram), and when the number of maximum points is 2, it is determined that there is light source noise, and the point group corresponding to the maximum point on the higher side is filtered as light source noise.

[0104] In addition, in the above description, a density curve is produced for the light source noise candidate area, and the light source noise in the light source noise candidate area is removed based on the produced density curve, but the production of the density curve and the removal of the light source noise can also be performed for each grid that constitutes the light source noise candidate area.

[0105] According to the above-described embodiment, it is possible to recognize or remove light source noise with higher accuracy for an occupied grid pattern recognized from an image obtained by capturing the periphery of the moving object 100 .

[0106] The above-described embodiment can be expressed as follows.

[0107] A mobile body, comprising:

[0108] a storage medium storing computer-readable instructions; and

[0109] a processor connected to the storage medium,

[0110] The processor executes the following processing by executing the instructions that can be read by the computer:

[0111] Recognition processing for recognizing a point group corresponding to an object existing in the vicinity of the moving body based on an image obtained by photographing the condition of the vicinity of the moving body;

[0112] A control process for determining a moving path of the moving body based on the surrounding conditions, and controlling the moving body to move along the determined moving path;

[0113] In the recognition process, a distribution in a height direction of a point group recognized as a candidate for the object is obtained in a predetermined area around the moving body, and based on the distribution, it is determined whether the point group in the predetermined area includes light source noise.

[0114] As mentioned above, although the specific embodiment of the present invention was described using the embodiment, the present invention is not limited to such embodiment at all, and various modifications and substitutions can be added within the scope not departing from the gist of the present invention.

Claims

1. A control device for a mobile object, wherein: The control device of the mobile body comprises: a recognition unit that recognizes a point group corresponding to an object existing in the vicinity of the moving body based on an image obtained by capturing a condition in the vicinity of the moving body; as well as a control unit that determines a moving path of the moving body based on the surrounding conditions and controls the moving body to move along the determined moving path, The recognition unit performs a noise determination process in which a distribution in a height direction of a point group recognized as a candidate for the object is obtained in a predetermined area around the moving body, and based on the distribution, it is determined whether the point group in the predetermined area contains light source noise.

2. The control device for a moving object according to claim 1, wherein: The identification unit obtains a curve representing the distribution in the noise determination process, and determines whether the point group in the predetermined area includes light source noise based on the number of local points of the curve.

3. The control device for a moving object according to claim 2, wherein: The recognition unit removes the light source noise from the point group in the predetermined area when determining based on the number of the local maximum points that the point group in the predetermined area includes light source noise.

4. The control device for a moving object according to claim 1, wherein: The recognition unit recognizes the periphery of the mobile body as a collection of unit areas of the same size, and manages the presence or absence of the object in the unit area according to the occupation status of the unit area. The recognition unit executes the noise determination process for each of the unit areas.

5. The control device for a moving object according to claim 4, wherein: The recognition unit recognizes a candidate region of the object based on clustering of a point group recognized from the image, and recognizes a candidate region having a size or less among the candidate regions as a candidate region of the light source noise.

6. The control device for a moving object according to claim 5, wherein: The recognition unit executes the noise determination process for each unit area included in the candidate area of ​​the light source noise.

7. The control device for a moving object according to claim 2, wherein: When the number of local points included in the curve is 2, the identification unit determines that the point group in the predetermined region includes light source noise.

8. A method for controlling a moving object, wherein: The control method of the mobile body causes the computer to execute the following processing: Recognition processing for recognizing a point group corresponding to an object existing in the vicinity of the moving body based on an image obtained by photographing the condition of the vicinity of the moving body; as well as control processing for determining a moving path of the moving body based on the surrounding conditions and controlling the moving body to move along the determined moving path, In the recognition process, a distribution in a height direction of a point group recognized as a candidate of the object is obtained in a predetermined area around the moving body, and based on the distribution, it is determined whether the point group in the predetermined area includes light source noise.

9. A storage medium storing a program, wherein: The program is used to cause the computer to execute the following processing: Recognition processing for recognizing a point group corresponding to an object existing in the vicinity of the moving body based on an image obtained by photographing the condition of the vicinity of the moving body; as well as control processing for determining a moving path of the moving body based on the surrounding conditions and controlling the moving body to move along the determined moving path, The recognition process is a process of obtaining a distribution in a height direction of a point group recognized as a candidate for the object in a predetermined area around the moving body, and determining whether the point group in the predetermined area includes light source noise based on the distribution.

Images