Control device for moving body, control method for moving body, and program

Abstract

To provide a control device for a moving body, a control method for a moving body, and a program, capable of more accurately recognizing or removing a light source noise.SOLUTION: The control device for a moving body includes a recognition part for recognizing a point group corresponding to an object existing around the moving body on the basis of an image in which a situation around the moving body is captured and a control part for deciding the moving path of the moving body on the basis of the peripheral situation and controlling the moving body so that it moves along the decided moving path. The recognition part obtains the distribution in the height direction of the point group recognized as a candidate for the object, in a predetermined area around the moving body and executes noise determination processing for determining whether the light source noise is included in the point group in the predetermined area on the basis of the distribution.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to a control device for a moving object, a control method for a moving object, and a program. [Background technology]

[0002] Conventionally, it has been proposed to project points (hereinafter, corresponding points) corresponding to candidate obstacles determined based on the output of a LIDAR device onto a horizontal plane area and associate them with a grid on the horizontal plane, and to remove a first set of candidate obstacles corresponding to noise from the candidate obstacles based on the association status between the corresponding points and the grid (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2023-517105 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, there are cases where light source noise cannot be properly recognized from candidate obstacles, and light source noise cannot be properly removed.

[0005] The present invention has been made in consideration of these circumstances, and one of its objects is to provide a moving body control device, a moving body control method, and a program that can more accurately recognize or remove light source noise. [Means for solving the problem]

[0006] The control device for a moving object, the control method for a moving object, and the program according to the present invention employ the following configuration. (1): A control device for a moving body according to one embodiment of the present invention includes a recognition unit that recognizes a point cloud corresponding to objects present in the vicinity of the moving body based on an image capturing the situation around the moving body, and a control unit that determines a movement path for the moving body based on the surrounding situation and controls the moving body to move along the determined movement path, wherein the recognition unit determines a height distribution of the point cloud recognized as candidates for the object in a specified area around the moving body, and executes a noise determination process that determines whether or not the point cloud in the specified area contains light source noise based on the distribution.

[0007] (2): In the aspect (1) above, in the noise determination process, the recognition unit obtains a curve representing the distribution, and determines whether or not the point cloud in the specified area contains light source noise based on the number of maximum points that the curve has.

[0008] (3): In the aspect (2) above, when the recognition unit determines that the point cloud in the specified region contains light source noise based on the number of the maximum points, the recognition unit removes the light source noise from the point cloud in the specified region.

[0009] (4): In the above aspect (1), the recognition unit recognizes the surroundings of the moving body as a collection of unit areas of the same size, manages the presence or absence of the moving body in the unit areas based on the occupancy state of the unit areas, and executes the noise determination process for each unit area.

[0010] (5): In the aspect of (4) above, the recognition unit recognizes candidate regions of the moving object by clustering a cloud of points recognized from the image, and recognizes those candidate regions that are equal to or smaller than a predetermined size as candidate regions of the light source noise.

[0011] (6) In the aspect of (5) above, the recognition unit executes the noise determination process for each unit area included in the candidate area for light source noise.

[0012] (7) In the above aspect (2), the recognition unit determines that the point cloud in the predetermined region contains light source noise when the number of maximum points in the curve is two.

[0013] (8): Another aspect of the present invention relates to a method for controlling a moving body, in which a computer executes a recognition process for recognizing a point cloud corresponding to an object present in the vicinity of the moving body based on an image capturing the situation around the moving body, and a control process for determining a movement path for the moving body based on the surrounding situation and controlling the moving body to move along the determined movement path, in which the recognition process determines a height distribution of the point cloud recognized as a candidate for the object in a specified area around the moving body, and determines whether or not the point cloud in the specified area contains light source noise based on the distribution.

[0014] (9): A program relating to another aspect of the present invention, which causes a computer to execute a recognition process for recognizing a point cloud corresponding to objects present around a moving body based on an image capturing the situation around the moving body, and a control process for determining a movement path of the moving body based on the situation around the moving body and controlling the moving body to move along the determined movement path, wherein the recognition process determines a height distribution of the point cloud recognized as candidates for the object in a specified area around the moving body, and determines whether or not the point cloud in the specified area contains light source noise based on the distribution. Effect of the Invention

[0015] According to the above aspects (1) to (9), light source noise can be removed with higher accuracy. [Brief description of the drawings]

[0016] [Figure 1] 1 is a diagram showing an example of the configuration of a mobile object system 1 including a mobile object 100. FIG. [Diagram 2] FIG. 2 is a diagram for explaining an example of a usage mode of a moving object 100. [Diagram 3] FIG. 1 is a perspective view showing a moving body 100. [Figure 4] 2 is a diagram illustrating an example of a functional configuration of a moving object 100. FIG. [Diagram 5] 13 is a diagram showing an example of light source noise that may be included in the recognition result of a recognition unit 206. FIG. [Figure 6] 13 is a flowchart showing an example of a processing flow in which the recognition unit 206 recognizes a moving object around the moving object 100 while removing light source noise. [Figure 7] FIG. 11 is a diagram showing an example of a recognition result of an object candidate region. [Figure 8] FIG. 13 is a diagram showing an example of an object candidate region extracted as a light source noise candidate region. [Figure 9] 13A and 13B are diagrams illustrating a method for removing a point group corresponding to light source noise from a light source noise candidate region C2. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, with reference to the drawings, embodiments of a control device for a moving object, a control method for a moving object, and a program according to the present invention will be described.

[0018] 1 is a diagram showing an example of the configuration of a mobile body system 1 including a mobile body 100. The mobile body 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 with each other, for example, via a network NW. The network NW is any network, such as a LAN, a WAN, or an Internet line.

[0019] [Terminal Device] The terminal device 2 is, for example, a computer device such as a smartphone, a tablet terminal, etc. The terminal device 2 requests the provision of authority to use the mobile object 100 from the management device 10 based on, for example, an operation by a user, and obtains information indicating that the use has been permitted.

[0020] [Management device] In response to a request from the terminal device 2, the management device 10 grants the user of the terminal device 2 the authority to use the mobile object 100 and manages reservations for the use of the mobile object 100. The management device 10 generates and manages schedule information that associates, for example, preregistered user identification information with the date and time of reservations for the use of the mobile object 100.

[0021] [Information providing device] The information providing device 20 provides the mobile body 100 with the location of the mobile body 100, the area in which the mobile body 100 moves, and map information about the surrounding area. In response to a request from the mobile body 100, the information providing device 20 may generate a route to the destination of the mobile body 100 and provide the generated route to the mobile body 100.

[0022] [Mobile object] The mobile body 100 is used by a user in the following manner of use. FIG. 2 is a diagram for explaining an example of the manner of use of the mobile body 100. The mobile body 100 is placed, for example, at a predetermined position in a facility or a town. When a user wants to use the mobile body 100, the user can start using the mobile body 100 by operating an operation unit (not shown) of the mobile body 100, or can start using the mobile body 100 by operating the terminal device 2. For example, when a user goes shopping and has a lot of luggage, the user starts using the mobile body 100 and puts the luggage in a storage unit of the mobile body 100. Then, the mobile body 100 moves together with the user so as to autonomously follow the user. The user can continue shopping or move to the next destination with the luggage stored in the mobile body 100. For example, the mobile body 100 moves together with the user while moving on a sidewalk or a crosswalk on a roadway. The mobile body 100 can move in an area where pedestrians can pass, such as a roadway and a sidewalk. For example, the vehicle 100 may be used in indoor or outdoor facilities or private grounds, such as shopping centers, airports, parks, and theme parks, and is capable of moving through areas where pedestrians can pass through.

[0023] The moving body 100 may be capable of moving autonomously 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 body 100 follows the user as described above.

[0024] 3 is a perspective view showing the moving body 100. In the following explanation, the forward direction of the moving body 100 is the plus x-direction, the rearward direction of the moving body 100 is the minus x-direction, the width direction of the moving body 100, which is the left direction based on the plus x-direction, the right direction is the minus y-direction, and the height direction of the moving body 100, which is a direction perpendicular to the x-direction and y-direction, is the plus z-direction.

[0025] The moving body 100 includes, for example, a base body 110, a door section 112 provided on the base body 110, and wheels (first wheel 120, second wheel 130, and third wheel 140) attached to the base body 110. For example, a user can open the door section 112 to put luggage into a storage section provided on the base body 110 or take luggage out of the storage section. The first wheel 120 and the second wheel 130 are driving wheels, and the third wheel 140 is an auxiliary wheel (driven wheel). The moving body 100 may be movable using a configuration other than wheels, such as caterpillars.

[0026] A cylindrical support 150 extending in the positive z direction is provided on the surface of the base 110 in the positive z direction. A camera 180 that captures an image of the surroundings of the moving body 100 is provided on the end of the support 150 in the positive z direction. The position at which the camera 180 is provided may be any position different from the above.

[0027] Camera 180 is, for example, a camera capable of capturing images of the periphery of moving body 100 at a wide angle (for example, 360 degrees). Camera 180 may include multiple cameras. Camera 180 may be realized by combining, for example, multiple 120-degree cameras or multiple 60-degree cameras.

[0028] 4 is a diagram showing an example of a functional configuration of the moving body 100. In addition to the functional configuration shown in FIG. 3, the moving body 100 further includes a first motor 122, a second motor 132, a battery 134, a brake device 136, a steering device 138, a communication unit 190, and a control device 200. The first motor 122 and the second motor 132 are operated by power supplied to 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 of the first wheel 120, and the second motor 132 may be an in-wheel motor provided in the wheel of the second wheel 130.

[0029] The brake device 136 outputs a brake torque to each wheel based on an instruction from the control device 200. The steering device 138 includes an electric motor. The electric motor 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 course of the moving body 100.

[0030] 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 .

[0031] [Control device] The control device 200 includes, for example, a position identification unit 202, an information processing unit 204, a recognition unit 206, a path generation unit 208, a trajectory generation unit 210, a first control unit 212, a second control unit 214, and a storage unit 220. The position identification unit 202, the information processing unit 204, the recognition unit 206, the path generation unit 208, the trajectory generation unit 210, the first control unit 212, and the second control unit 214 are realized 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 realized by hardware (including circuitry) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a GPU (Graphics Processing Unit), or may be realized by cooperation between software and hardware. The program may be stored in advance in a storage device (a storage device with a non-transient storage medium) such as an HDD (Hard Disk Drive) or flash memory, or may be stored in a removable storage medium (non-transient storage medium) such as a DVD or CD-ROM and installed by inserting the storage medium into a drive device.

[0032] The storage unit 220 is realized by a storage device such as a HDD, a flash memory, or a RAM (Random Access Memory). The storage unit 220 stores map information 224 and control information 222, which is a control program for controlling the behavior of the moving object 100 referred to by the first control unit 212 and the second control unit 214. The map information 224 is, for example, map information on the location of the moving object 100 provided by the information providing device 20, the area in which the moving object 100 moves, and the surroundings of the area. The map information may include areas in which the moving object 100 can move and areas in which the moving object 100 cannot move (statically placed obstacles, no-entry areas, etc.).

[0033] Some or all of the path generating unit 208, the trajectory generating unit 210, the first control unit 212, and the second control unit 214 are examples of a "control unit." Some or all of the functional configuration included in the control device 200 may be included in another device. For example, the other device and the moving body 100 may communicate with each other and cooperate to control the moving body 100.

[0034] The position identifying unit 202 identifies the position of the mobile object 100. The position identifying unit 202 acquires position information of the mobile object 100 by a GPS (Global Positioning System) device (not shown) built into the mobile object 100. The position information may be, for example, two-dimensional map coordinates or latitude and longitude information.

[0035] The information processing unit 204 manages information acquired from the terminal device 2, the management device 10, or the information providing device 20, for example.

[0036] The recognition unit 206 recognizes the position (distance from the mobile body 100 and direction relative to the mobile body 100) of objects around the mobile body 100, and the state of the objects such as speed and acceleration, based on, for example, an image captured by the camera 180. The objects include traffic participants and obstacles present in facilities and on roads. The obstacles include static obstacles included in map information and dynamic obstacles not included in 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 (e.g., a face image of the user) captured by the user registered when the user uses the mobile body 100, or a face image of the user (or a feature amount obtained from the user face image) provided by the terminal device 2 or the management device 10. The recognition unit 206 recognizes a gesture made by the user. The mobile body 100 may be provided with a detection unit other than a camera, such as a radar device or LIDAR. In this case, the recognition unit 206 recognizes the situation around the moving object M using the detection results of a radar device or LIDAR instead of (or in addition to) an image.

[0037] The route generation unit 208 generates a route to a destination specified by the user. The destination may be the location of a product or a facility. In this case, the user specifies the product or facility, and the mobile body 100 sets the location of the specified product or facility as the destination. The route is a route that can reach the destination reasonably. For example, the distance to the destination, the time required to reach the destination, the ease of travel of the route, etc. are scored, and a route is derived in which each score and the combined score of the scores are equal to or greater than a threshold value.

[0038] The trajectory generating unit 210 generates a trajectory along which the moving body 100 should travel in the future based on, for example, a gesture of the user, a destination set by the user, surrounding objects, the position of the user, and the like. The trajectory generating unit 210 generates a trajectory that allows the moving body 100 to move smoothly to a target point. The trajectory generating unit 210 generates a trajectory according to the behavior of the moving body 100 based on, for example, a correspondence between a gesture and a behavior determined in advance, or generates a trajectory for moving toward a destination while avoiding surrounding objects. In addition, the trajectory generating unit 210 generates, for example, a trajectory for following a user being tracked or a trajectory for leading a user. The trajectory generating unit 210 generates, for example, a trajectory according to a behavior based on a preset mode. The trajectory generation unit 210 generates a plurality of trajectories according to the behavior of the moving body 100, calculates the risk for each trajectory, and when the total value of the calculated risks and the risk of each trajectory point meet a preset criterion (for example, when the total value is equal to or less than a threshold value Th1 and the risk of each trajectory point is equal to or less than a threshold value Th2), adopts the trajectory that satisfies the criterion as the trajectory for the moving body 100 to move along. For example, the risk tends to be higher the closer the distance between the trajectory (trajectory point of the trajectory) and an obstacle, and to be lower the closer the distance between the trajectory and an obstacle.

[0039] 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 trajectory that satisfies a preset standard.

[0040] The second control unit 214 controls the moving body 100 based on the recognition result of the recognition unit 206 so that the moving body 100 does not come into contact with surrounding objects and the distance between the user and the moving body 100 is within a predetermined distance range. The predetermined distance range is a distance range between a preset shortest distance Dmin and a maximum distance Dmax. The shortest distance Dmin and the maximum distance Dmax may be variable distances depending on, for example, the type of motion control (following control, guidance control, etc.) and surrounding conditions (shape of the moving path, degree of crowding), or may be fixed distances.

[0041] [Light source noise] 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 light sources such as lights and windows are present around the moving body 100, the image captured by the camera 180 may contain light source noise such as so-called blown-out highlights depending on the position and orientation of the moving body 100. FIG. 5 is 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 body 100 as a set of lattices of a predetermined size, and manages the presence or absence of an object based on the state of each lattice. For example, the example of FIG. 5 shows the presence of an object by an occupied lattice, and the absence of an object by an unoccupied lattice. FIG. 5 shows a lattice plane (hereinafter referred to as an "occupied lattice diagram") in which the surrounding area R1 of the moving body 100 at a certain time point is viewed from the height direction. Here, each lattice (or an area corresponding to each lattice) in the occupied lattice diagram is an example of a "unit area".

[0042] In addition, in managing the presence or absence of obstacles using the occupancy grid diagram, the road surface on which the mobile object 100 is traveling is not treated as an object that may affect the occupancy state of each grid. That is, the recognition unit 206 recognizes the road surface on which the mobile object 100 can travel (hereinafter referred to as the "traveling road surface") around the mobile object 100 based on the image captured by the camera 180, the map information 224, etc., and recognizes the occupancy state of each grid based on the presence or absence of objects other than the traveling road surface. For example, the recognition unit 206 can recognize a point cloud corresponding to objects existing in the vicinity in three dimensions based on the image captured by the camera 180, the map information 224, etc., and recognize the point cloud corresponding to the traveling road surface based on the height position of the point cloud.

[0043] FIG. 5 shows a situation where obstacles B1, B2, and B3 are recognized in the region R1. Among these obstacles, obstacles B1 and B3 represent correctly recognized obstacles, and obstacle B2 represents light source noise that is erroneously recognized as an obstacle. When such erroneous recognition of an obstacle occurs due to light source noise, an area that should be usable as a travel route of the moving body 100 becomes an impassable area, and an appropriate travel route cannot be set. For example, in the example of FIG. 5, if there was no erroneous recognition of obstacle B2, a straight line route RT1 could be set as the travel route, but because obstacle B2 is erroneously recognized, the travel route is set as a detour route RT2. In this way, light source noise may hinder the determination of an appropriate travel route for the moving body 100. For this reason, the recognition unit 206 of this embodiment is configured to perform a filtering process to remove light source noise from the recognition result of the object around the moving body 100.

[0044] [Light source noise filtering] FIG. 6 is a flowchart showing an example of a process flow in which the recognition unit 206 recognizes objects around the moving body 100 while removing light source noise. First, the recognition unit 206 recognizes each object candidate region by clustering the occupied grids in the occupied grid diagram recognized based on the image (S101). Any clustering method can be used, and for example, a shortest distance method can be used. FIG. 7 is a diagram showing an example of the recognition result of the object candidate region. FIG. 7 shows a case in which object candidate regions C1, C2, and C3 are recognized that are arranged similarly to the obstacles B1, B2, and B3 in FIG. 5.

[0045] Next, the recognition unit 206 extracts object candidate regions with a small number of lattices (below a threshold) as light source noise candidate regions (S102), and creates a density curve in the height direction (Z-axis direction) for each extracted light source noise candidate region for the point clouds included in the light source noise candidate region (S103). This density curve is the sum of the number of point clouds present in the light source noise candidate region for each height. In this sense, the density curve can be said to be a histogram of the point clouds in the height direction. The recognition unit 206 performs a histogram test on the created density curve to recognize maximum points (S104), and removes light source noise included in the target lattices based on the distribution of the recognized maximum points (S105). More specifically, when a first point cloud corresponding to an object and a second point cloud are present at a distance in the air (height direction) from the first point cloud, the recognition unit 206 removes the second point cloud as light source noise. For example, the recognition unit 206 may determine that the maximum points of the density curve that exist at a predetermined altitude or higher are caused by light source noise, and remove the point group located at the altitude 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 recognized point group is light source noise or not is referred to as noise determination processing.

[0046] FIG. 8 is a diagram showing an example of an object candidate region C2 extracted as a light source noise candidate region. FIG. 8 shows an example in which the threshold value of the number of lattices when extracting the light source noise candidate region is set to 2 or more and 5 or less for the object candidate regions C1, C2, and C3 in FIG. 7. In this case, the number of lattices of the object candidate regions C1, C2, and C3 is 9, 2, and 6, respectively, so that 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 may be referred to as the light source noise candidate region C2. FIG. 8 shows a case in which, in the light source noise candidate region C2, a point group P1 corresponding to the road surface exists at a low position in the height direction (for example, near Z=z1) and a point group P2 corresponding to the light source noise exists in the air near a predetermined altitude (for example, near Z=z2).

[0047] FIG. 9 is a diagram for explaining a method for removing a point group corresponding to light source noise from the light source noise candidate region C2. FIG. 9 is a graph showing a density curve L1 created for the light source noise candidate region C2. In this case, the local maximum points of the density curve appear near Z=z1 and near Z=z2, so for example, the light source noise in the light source noise candidate region C2 can be removed by filtering the point group having a height threshold value zth or more. The recognition unit 206 updates the occupied grid diagram based on the distribution of the point group after removing the light source noise (S106). As a result, the occupied state of the grid group constituting the light source noise candidate region C2 is changed from occupied to unoccupied, and the grid group is recognized as a drivable region.

[0048] The threshold number of grids used when extracting light source noise candidate regions and the height threshold used when detecting local maxima caused by light source noise may be adjusted as appropriate according to the environment in which the moving body 100 travels. In addition to the height threshold, a filtering condition may be added based on the characteristics of the distribution of the point cloud corresponding to the light source noise in order to prevent the point cloud corresponding to an actual obstacle from being erroneously removed as light source noise. For example, as described above, since light source noise occurs in the air in a relatively small range, a judgment condition related to the shape of the peak that forms the local maxima caused by light source noise may be added. For example, the following judgment conditions may be set. The peak width is below the threshold (i.e. the peak is sharp and the distribution range is small) The minimum points before and after the peak are near 0 degrees (i.e. hollow)

[0049] Depending on the obstacle, local maximum and minimum points may be formed due to its shape (e.g., unevenness, etc.), so the density curve may be discretized (in the height direction) over a larger range. By doing so, the density curve becomes closer to a histogram that represents the frequency (number of points) for each predetermined width (in the height direction), so that small peaks caused by the shape of the obstacle are smoothed out, making it less likely that they will be erroneously recognized as being caused by light source noise.

[0050] Also, when performing simple filtering, the determination of whether or not there is light source noise may be performed based on the number of maximum points. For example, in an area where there is no obstacle on the road surface, the area is hollow in the height direction, and there is no light source noise, only the point cloud corresponding to the road surface is detected (i.e., only the maximum points corresponding to the road surface are detected), so the number of detected maximum points is 1. Also, 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, the point cloud corresponding to the road surface and the obstacle is detected in a relatively close range, so in this case, the number of detected maximum points is also likely to be 1. Therefore, when light source noise exists in the air, the number of maximum points is likely to be 2. Therefore, the recognition unit 206 may be configured to count the number of maximum points in a density curve (which may be a histogram), determine that there is light source noise when the number of maximum points is 2, and filter the point cloud corresponding to the higher maximum point as light source noise.

[0051] In addition, in the above explanation, a density curve is created for a light source noise candidate area, and light source noise within the light source noise candidate area is removed based on the created density curve, but the creation of a density curve and the removal of light source noise may also be performed for each grid that makes up the light source noise candidate area.

[0052] According to the embodiment described above, it is possible to more accurately recognize or remove light source noise from an occupancy grid map recognized from an image capturing the periphery of the moving object 100 .

[0053] The above-described embodiment can be expressed as follows. a storage medium for storing computer-readable instructions; a processor coupled to the storage medium; The processor executes the computer-readable instructions to: A recognition process for recognizing a group of points corresponding to objects present around the moving body based on an image of the surroundings of the moving body; A control process for determining a movement route of the moving object based on the surrounding situation and controlling the moving object to move along the determined movement route; Run In the recognition process, a distribution in a height direction of a point cloud recognized as a candidate for the object in a predetermined area around the moving object is obtained, and whether or not a light source noise is included in the point cloud in the predetermined area is determined based on the distribution. Mobile body.

[0054] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention. [Explanation of symbols]

[0055] 1 Mobile Systems 2 Terminal Equipment 10 Management device 20 Information provision device 100 Mobile 110 Base 112 Door section 120 1st wheel 122 First Motor 130 2nd wheel 132 Second Motor 134 Battery 136 Brake device 138 Steering device 140 3rd wheel 150 Support 180 Camera 190 Communications Department 200 Control device 202 Location identification part 204 Information Processing Section 206 Recognition part 208 Route Generation Unit 210 Trajectory generation part 212 First Control Section 214 Second Control Section 220 Storage section 222 Control Information 224 Map Information

Claims

1. a recognition unit that recognizes a group of points corresponding to objects present around a moving object based on an image of the surroundings of the moving object; a control unit that determines a movement route of the moving object based on the surrounding situation and controls the moving object to move along the determined movement route; the recognition unit executes a noise determination process to obtain a distribution in a height direction of a point cloud recognized as the object candidate in a predetermined area around the moving body, and to determine whether or not a light source noise is included in the point cloud in the predetermined area based on the distribution. A control device for a moving object.

2. the recognition unit obtains a curve representing the distribution in the noise determination process, and determines whether or not light source noise is included in the point cloud in the predetermined region based on the number of maximum points in the curve. The control device for a moving body according to claim 1 .

3. When the recognition unit determines that light source noise is included in the point cloud in the specified region based on the number of the maximum points, the recognition unit removes the light source noise from the point cloud in the specified region. The control device for a moving body according to claim 2.

4. the recognition unit recognizes the periphery of the moving object as a collection of unit areas of the same size, and manages the presence or absence of the object in the unit areas based on an occupancy state of the unit areas; performing the noise determination process for each of the unit regions; The control device for a moving body according to claim 1 .

5. the recognition unit recognizes candidate regions of the object by clustering a point cloud recognized from the image, and recognizes, among the candidate regions, those having a predetermined size or smaller as candidate regions of the light source noise; The control device for a moving body according to claim 4.

6. the recognition unit executes the noise determination process for each unit area included in the light source noise candidate area. The control device for a moving body according to claim 5.

7. the recognition unit determines that the point cloud in the predetermined region includes light source noise when the number of maximum points in the curve is two. The control device for a moving body according to claim 2.

8. The computer A recognition process for recognizing a group of points corresponding to objects present around the moving body based on an image of the surroundings of the moving body; A control process for determining a movement route of the moving object based on the surrounding situation and controlling the moving object to move along the determined movement route; A method for controlling a moving object, comprising: In the recognition process, a distribution in a height direction of a point cloud recognized as a candidate for the object in a predetermined area around the moving object is obtained, and whether or not a light source noise is included in the point cloud in the predetermined area is determined based on the distribution. A method for controlling a moving object.

9. On the computer, A recognition process for recognizing a group of points corresponding to objects present around the moving body based on an image of the surroundings of the moving body; A control process for determining a movement route of the moving object based on the surrounding situation and controlling the moving object to move along the determined movement route; A program for executing The recognition process obtains a distribution in a height direction of a point cloud recognized as a candidate for the object in a predetermined area around the moving body, and determines whether or not a light source noise is included in the point cloud in the predetermined area based on the distribution. program.

Images