Mobile object control system, mobile object, control method and storage medium

Abstract

The present invention provides a mobile control system, a mobile body, a control method, and a storage medium that enable the mobile body to move with greater consideration for surrounding conditions. The mobile control system includes: an acquisition unit that acquires an image of a road surface surrounding the mobile body; a recognition unit that recognizes support information obtained from the road surface reflected in the image to support the walking of a specific traffic participant having a predetermined attribute, i.e., a traffic participant reflected in the image; a prediction unit that predicts the behavior of the traffic participant recognized by the recognition unit based on the support information; and a control unit that controls the behavior of the mobile body based on the support information and the prediction result of the prediction unit.

Description

Technical Field

[0001] The present invention relates to a mobile body control system, a mobile body, a control method and a storage medium. Background Art

[0002] Conventionally, an automatic driving system that controls driving based on an image of a braille block has been disclosed (Japanese Patent Application Laid-Open No. 2017-102601). Summary of the Invention

[0003] However, in the above-mentioned technology, the surroundings may not be sufficiently taken into consideration.

[0004] The present invention has been made in consideration of such circumstances, and one of its objects is to provide a mobile body control system, a mobile body, a control method, and a storage medium that enable the mobile body to move with greater consideration for surrounding conditions.

[0005] Solutions to Problems

[0006] The mobile object control system, mobile object, control method, and storage medium of the present invention employ the following structures.

[0007] (1): A mobile body control system comprises: an acquisition unit that acquires an image obtained by photographing a road surface around a mobile body; a recognition unit that recognizes support information for supporting the movement of a traffic participant having specified attributes, i.e., a specific traffic participant, obtained from the road surface reflected in the image, and the traffic participant reflected in the image; a prediction unit that predicts the behavior of the traffic participant recognized by the recognition unit based on the support information; and a control unit that controls the behavior of the mobile body based on the support information and the prediction result of the prediction unit.

[0008] (2): Based on the solution of (1) above, the traffic participant is a pedestrian, and the support information is a blind brick installed on the sidewalk.

[0009] (3): In the above-mentioned configuration of (1) or (2), the prediction unit predicts the behavior of the traffic participant based on the type of the support information.

[0010] (4): Based on the above-mentioned solution (3), the support information is guidance information that shows the direction of travel of the specific traffic participant and guides the movement of the specific traffic participant, and warning information that warns the specific traffic participant.

[0011] (5): Based on any one of the above schemes (1) to (4), the recognition unit recognizes the attributes of the traffic participant, and the control unit controls the behavior of the mobile body based on the support information, the prediction result of the prediction unit and the attributes of the traffic participant, or based on the support information and the behavior of the traffic participant predicted by the prediction unit using the support information and the attributes of the traffic participant.

[0012] (6): Based on any one of the above schemes (1) to (5), the identification unit identifies the attributes of the traffic participant, and the prediction unit predicts the behavior of the traffic participant based on the support information and the attributes of the traffic participant. When the attribute of the traffic participant is a specific traffic participant, the prediction unit predicts the predicted degree of behavior of the traffic participant who is the specific traffic participant according to the support information to a first degree. When the attribute of the traffic participant is not a specific traffic participant, the prediction unit predicts the predicted degree of behavior of the traffic participant who is not the specific traffic participant according to the support information to a second degree which is smaller than the first degree.

[0013] (7): Based on any one of the above schemes (1) to (6), the support information is a tactile paving brick set on the sidewalk, the recognition unit recognizes the attributes of the traffic participant, the control unit controls the moving body to move along the tactile paving brick, and determines the distance between the moving body and the tactile paving brick based on the attributes of the traffic participant.

[0014] (8): Based on any one of the above schemes (1) to (7), the support information is guidance information for guiding the movement of the specific traffic participant by showing the direction of travel of the specific traffic participant, and warning information for warning the specific traffic participant. When the traffic participant in front of the mobile body reaches a specified position associated with the warning information while the mobile body is moving along the travel direction, the control unit decelerates or stops the mobile body, and thereafter, after the traffic participant passes the specified position or crosses in front of the mobile body, the control unit accelerates the mobile body or starts the mobile body.

[0015] (9): Based on any one of the above schemes (1) to (8), the support information is a blind brick, and the support information is a guide brick that shows the direction of travel of the specific traffic participant and guides the movement of the specific traffic participant, and a warning brick that warns the specific traffic participant. When a first guide brick is connected to the warning brick, and a second guide brick is connected to the warning brick in a direction intersecting the first guide brick, and the second guide brick exists in front of the moving body, when the moving body moves along the direction of travel indicated by the first guide brick and the traffic participant in front of the moving body reaches a specified position associated with the warning information, the control unit decelerates or stops the moving body, and then, after the traffic participant passes the specified position or crosses in front of the moving body, the control unit accelerates the moving body or starts the moving body.

[0016] (10): Based on the above scheme (8) or (9), the control unit delays the timing of accelerating the moving body or starting the moving body when the moving body is a specific moving body of the specified attribute, compared to the timing of accelerating the moving body or starting the moving body when the moving body is a moving body of a different attribute from the moving body of the specified attribute.

[0017] (11): A mobile body equipped with the mobile body control system according to any one of the above-mentioned schemes (1) to (10).

[0018] (12): A control method according to one embodiment of the present invention, wherein the control method causes a computer to perform the following processing: obtaining an image obtained by photographing a road surface surrounding a moving body; identifying support information for supporting the movement of a traffic participant having specified attributes, i.e., a specific traffic participant, obtained from the road surface reflected in the image, and the traffic participant reflected in the image; predicting the behavior of the identified traffic participant based on the support information; and controlling the behavior of the moving body based on the support information and the prediction result.

[0019] (13): A storage medium of one embodiment of the present invention stores a program, wherein the program causes a computer to perform the following processing: obtain an image obtained by photographing a road surface around a moving body; identify support information for supporting the movement of a traffic participant with specified attributes, i.e., a specific traffic participant, obtained from the road surface reflected in the image, and the traffic participant reflected in the image; predict the behavior of the identified traffic participant based on the support information; and control the behavior of the moving body based on the support information and the prediction result.

[0020] Effects of the Invention

[0021] According to (1)-(13), the mobile body control system controls the movement of the mobile body based on support information for supporting the movement of traffic participants with specified attributes, i.e., specific traffic participants, and the behavior of traffic participants predicted using the support information, thereby enabling the mobile body to move in a more conscious manner of the surrounding conditions.

[0022] According to (5), the mobile body control system takes the attributes of the traffic participants into consideration, and thus can realize the control of the mobile body taking the surrounding traffic participants into consideration.

[0023] According to (6), the mobile body control system can predict the behavior of traffic participants with higher accuracy based on the support information and the attributes of traffic participants.

[0024] According to (7), the moving body control system can more appropriately determine the distance between the moving body and the tactile paving bricks based on the attributes of the traffic participants.

[0025] According to (8) or (9), the mobile body control system can make the mobile body move in consideration of the behavior even in a situation where the behavior of traffic participants changes significantly. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a diagram showing an example of a mobile object including a control device according to an embodiment.

[0027] Figure 2 This is a diagram showing an example of other functional configurations included in a mobile object.

[0028] Figure 3 This is a diagram showing an example of the behavior of a moving object.

[0029] Figure 4 This is a diagram showing an example of a guide brick.

[0030] Figure 5 This is a diagram showing another example of a warning brick.

[0031] Figure 6 This is a diagram for explaining the behavior of a moving object (Part 1).

[0032] Figure 7 This is a diagram for explaining the behavior of a moving object (part 2).

[0033] Figure 8 This is a diagram for explaining the behavior of a moving object (part 3).

[0034] Figure 9 This is a diagram for explaining the behavior of a moving object (part 4).

[0035] Figure 10 This is a diagram for explaining the behavior of a moving object (part 5).

[0036] Figure 11 This is a diagram for explaining the behavior of a moving object (part 6).

[0037] Figure 12 This is a diagram for explaining the behavior of a moving object (part 7).

[0038] Figure 13 This is a diagram used to illustrate a specific pedestrian.

[0039] Figure 14 This is a diagram showing an example of the position of the moving object when a specific pedestrian exists and the position of the moving object when a pedestrian different from the specific pedestrian exists.

[0040] Figure 15 This is a diagram showing an example of the position of the moving object when a specific pedestrian exists and the position of the moving object when a pedestrian different from the specific pedestrian exists.

[0041] Figure 16 It is a diagram for explaining the third behavior and the fourth behavior.

[0042] Figure 17 This is a flowchart (part 1) showing an example of the flow of processing executed by the control device.

[0043] Figure 18 This is a flowchart (part 2) showing an example of the flow of processing executed by the control device. DETAILED DESCRIPTION

[0044] Hereinafter, a mobile object control system, a mobile object, a control method, and a storage medium according to embodiments of the present invention will be described with reference to the accompanying drawings.

[0045] <Implementation Method>

[0046] [Overall structure]

[0047] Figure 1: This is a diagram showing an example of a mobile body M equipped with a control device of an embodiment. The mobile body M is an autonomous mobile robot. The mobile body M supports the user's actions. For example, the mobile body M stops at a location specified by the user, and allows the user to ride and transport the user to the destination. In this embodiment, a case where the mobile body M allows the user to ride and move is described, but instead of (or in addition to) this, the mobile body M may transport items, or guide the user and move together with the user, or chase the user and support the user's actions. In addition, the mobile body M may not be a device that the user can ride. In the following description, the case where the mobile body M is traveling is described, but when the mobile body M does not travel but moves on foot or in other ways, the following words "travel" and "travelable area" can be read as "move" and "movable area".

[0048] The mobile object M includes a main body 2, one or more wheels 4 (4A and 4B in the figure), and a camera 10. The main body 2 is provided with an entrance, such as a door (not shown), through which a user can enter and exit the main body 2. The user can enter the main body 2 through the entrance and board the mobile object M. For example, the mobile object M drives the wheels 4 based on an image captured by the camera 10 to transport the user M.

[0049] In this embodiment, the case where the user rides in the main body 2 is described, but instead of (or in addition to) the user moving together with the moving body M, a seat portion on which the user can sit without riding in the main body 2, a footrest for the user to place his feet in order to move, etc. may be provided.

[0050] Figure 2 1 is a diagram showing an example of other functional configurations included in the mobile object M. The mobile object M includes, for example, a camera 10 , a communication device 20 , an HMI 30 , a mobile object sensor 40 , a position determination device 50 , a driving operation element 80 , a control device 100 , a driving force output device 200 , a braking device 210 , and a steering device 220 .

[0051] The camera 10 captures the surroundings of the moving object M. The camera 10 is, for example, a fisheye camera capable of capturing a wide-angle (e.g., 360-degree) image of the surroundings of the moving object M. The camera 10 is, for example, mounted on the upper portion of the moving object M, capturing a wide-angle image of the surroundings of the moving object M in the horizontal direction. The camera 10 may also be implemented by combining multiple cameras (e.g., multiple cameras capable of capturing images in a 120-degree or 60-degree horizontal range). The moving object M may also be equipped with a radar device or LIDAR for detecting objects in addition to the camera 10.

[0052] The communication device 20 is a communication interface for communicating with other devices using a cellular network, a Wi-Fi network, Bluetooth (registered trademark), DSRC (Dedicated Short Range Communication), or the like.

[0053] The HMI 30 presents various information to the user of the mobile object M and receives input operations from the user. The HMI 30 includes various display devices, speakers, buzzers, touch panels, switches, buttons, and the like.

[0054] The moving object sensor 40 includes a vehicle speed sensor for detecting the speed of the moving object M, an acceleration sensor for detecting acceleration, a yaw rate sensor for detecting angular velocity about a vertical axis, an azimuth sensor for detecting the orientation of the moving object M, and the like.

[0055] The position determination device 50 determines the position of the moving object M based on signals received from GNSS satellites. The position of the moving object M may be determined or supplemented by an INS (Inertial Navigation System) using the output of the moving object sensor 40 .

[0056] The driving operating elements 80 include, for example, an accelerator pedal, a brake pedal, a shift lever, a steering wheel, a special-shaped steering gear, a joystick, and other operating elements. Sensors are mounted on the driving operating elements 80 to detect the amount of operation or the presence or absence of an operation. These detection results are output to the control device 100, or to some or all of the driving force output device 200, the braking device 210, and the steering device 220. If the mobile object M is controlled solely by automated driving, the driving operating elements 80 may be omitted.

[0057] The control device 100 includes, for example, an acquisition unit 110, an identification unit 120, a prediction unit 130, a trajectory generation unit 140, a travel control unit 150, an information processing unit 160, and a storage unit 180. The acquisition unit 110, the identification unit 120, the prediction unit 130, the trajectory generation unit 140, the travel control unit 150, and the information processing unit 160 are each 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 also be implemented 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 through a combination of software and hardware. The program can be stored in a storage unit 180 such as an HDD 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 a CD-ROM, and installed in a drive device by assembling the storage medium (non-temporary storage medium) to the HDD or flash memory. Some of the functional units mentioned above can also be included in other devices. For example, the recognition unit 120 can also be included in other devices, and analyze the images captured by a camera installed on the lane or sidewalk to recognize the conditions of the lane or sidewalk, and the conditions of objects existing on the lane or sidewalk. In this case, the control device 100 can also obtain the above-mentioned recognition results from other devices and perform various processing based on the obtained recognition results. For example, a functional structure including one or both of the trajectory generation unit 140 and the driving control unit 150, the acquisition unit 110, the recognition unit 120, and the prediction unit 130 is an example of a "mobile body control system."

[0058] The acquisition unit 110 acquires an image captured by the camera 10. The acquisition unit 110 acquires an image of a road surface around the moving object M.

[0059] The recognition unit 120 utilizes, for example, functions based on AI (Artificial Intelligence) or functions based on a pre-given model, or utilizes them in parallel to recognize the conditions around objects and the mobile body M. For example, the function of "the mobile body M recognizes the drivable area" can be achieved by "parallel execution of recognition of roads, sidewalks, curbs, etc. based on deep learning, and recognition based on pre-given conditions (signals that can match patterns), and scoring both for comprehensive evaluation." The recognition unit 120 can also perform semantic segmentation processing to classify each pixel in the image frame into levels (for example, objects, drivable areas, non-drivable areas, etc.), and identify the drivable area of ​​the mobile body M based on the classification results. In this way, the reliability of the movement of the mobile body M is ensured.

[0060] The recognition unit 120 recognizes the position, speed, acceleration and other states of objects in the vicinity of the mobile body M based on the image captured by the camera 10. The position of the object is, for example, recognized as a position on an absolute coordinate with a representative point (center of gravity, center of drive shaft, etc.) of the mobile body M as the origin, and is used for control. The position of the object can also be represented by a representative point such as the center of gravity or a corner of the object, or by a displayed area. The "state" of the object can also include the acceleration, jerk, or "action state" of the object (for example, whether a lane change is in progress or about to be made). The recognition unit 120 recognizes, for example, road dividing lines, shoulders, curbs, central median strips, guardrails, temporary stop lines, obstacles, signals, and other road phenomena. The recognition unit 120 recognizes the position and posture of the mobile body M.

[0061] The trajectory generator 140 determines one or both of a stopping position of the mobile body M and a driving position of the mobile body M based on a user instruction, a travelable area of ​​the mobile body M, and a travel-inhibited area of ​​the mobile body M.

[0062] The trajectory generation unit 140 generates a target trajectory for the mobile body M to automatically (independent of the driver's operation) travel in the future in a manner that can cope with the surrounding conditions of the mobile body M. The target trajectory includes, for example, a speed element. For example, the target trajectory is expressed as a trajectory obtained by arranging the places (track points) that the mobile body M should reach in sequence. Track points are places that the mobile body M should reach at every specified driving distance (for example, a few meters) along the way. Different from this, the target speed and target acceleration at every specified sampling time (for example, a few tenths of a second) are generated as part of the target trajectory. The track point can also be the position that the vehicle M should reach at the sampling moment at every specified sampling time. In this case, the information of the target speed and target acceleration is expressed by the interval between the track points.

[0063] The trajectory generation unit 140 generates a trajectory for the moving object M and calculates the risk of the generated trajectory. Risk is an indicator value indicating the likelihood that the moving object M will approach an obstacle. The risk tends to increase as the distance of the obstacle from the trajectory (or a point on the trajectory) decreases, and decreases as the distance from the obstacle to the trajectory (or a point on the trajectory) increases.

[0064] When the total risk value and the risk of each track point meet a predetermined benchmark (for example, when the total value is below the threshold Th1 and the risk of each track point is below the threshold Th2), the track generation unit 140 adopts the track that meets the benchmark as the track for the moving body to move.

[0065] The travel control unit 150 causes the vehicle M to travel along a track that satisfies a predetermined reference. The travel control unit 150 outputs a command value for causing the vehicle M to travel along the track to the travel driving force output device 200 .

[0066] The information processing unit 160 controls various devices and equipment included in the mobile object M. The information processing unit 160 controls, for example, the HMI 30. The information processing unit 160 acquires data of voice input to a microphone, or recognizes an operation performed on an operation unit.

[0067] The driving force output device 200 outputs driving force (torque) to the drive wheels for driving the vehicle M. The driving force output device 200 includes, for example, an electric motor and an ECU (Electronic Control Unit) that controls them. The ECU controls the aforementioned configuration based on information input from the driving control unit 150 or from the driving operating element 80.

[0068] The brake system 210 includes, for example, a brake caliper, a hydraulic cylinder that transmits hydraulic pressure to the brake caliper, an electric motor that generates hydraulic pressure in the hydraulic cylinder, and a brake ECU. The brake ECU controls the electric motor based on information input from the driving control unit 150 or information input from the driving operating element 80 to output a braking torque to each wheel in response to the braking operation.

[0069] The steering system 220 includes, for example, a steering ECU and an electric motor. The electric motor applies force to, for example, a rack-and-pinion mechanism to change the direction of the steering wheel. The steering ECU drives the electric motor based on information input from the driving control unit 150 or from the driving operating element 80 to change the direction of the steering wheel.

[0070] [Overview of Control of Moving Objects]

[0071] Figure 3This diagram illustrates an example of the behavior of a mobile object M. Mobile object M, for example, is carrying a user to a destination. In this case, mobile object M travels on sidewalk Sw (times t and t+1), exits sidewalk Sw onto lane Rw, and then travels on lane Rw (times t+2 and t+3). Mobile object M travels on sidewalk Sw at a speed similar to a pedestrian's walking speed (e.g., 4 km / h or 6 km / h), or travels on lane Rw at a speed faster than the aforementioned walking speed.

[0072] The recognition unit 120 of the control device 100 recognizes support information obtained from the road surface reflected in the image, which is used to support the walking of a specific pedestrian with specified attributes (e.g., a visually impaired person), and the pedestrian reflected in the image. The prediction unit 130 predicts the behavior of the pedestrian recognized by the recognition unit 120 based on the support information, or based on the support information and the attributes of the traffic participant. Furthermore, the control device 100 controls the behavior of the moving object M based on the support information and the prediction result of the prediction unit 130. For example, this control involves the trajectory generation unit 140 generating a trajectory for the moving object M to travel, and the travel control unit 150 controlling the travel drive force output device 200, the braking device 210, and the steering device 220 to move the moving object M along the generated trajectory.

[0073] The support information for supporting the walking of a specific pedestrian with a predetermined attribute is, for example, a tactile paving brick. The tactile paving brick includes, for example, a guide brick and a warning brick. Figure 4 This figure shows an example of a guide brick Bg. The guide brick Bg has a plurality of linear protrusions. These protrusions are provided on the surface of the brick, and the longitudinal direction of the protrusions indicates the direction in which a specific pedestrian moves.

[0074] Figure 5 This figure shows another example of a warning brick Bw. Warning brick Bw has multiple dot-shaped protrusions. These protrusions are located on the brick's surface. These dot-shaped protrusions serve to draw attention and provide warnings to specific pedestrians. For example, warning bricks Bw can be placed before steps, before crosswalks, at junctions where guide bricks Bg intersect, before guide plates, before obstacles, and at the ends of stations.

[0075] In this embodiment, the support information is described as a blind brick. However, instead of (or in addition to) this, the support information may be information for supporting the walking of a specific pedestrian or other pedestrians, or information indicated by an object.

[0076] An example will be given of the behavior of the mobile object M. The behavior of the mobile object M described below is executed, for example, based on the control of the control device 100. The processing described below may be executed in an overlapping manner.

[0077] [Behavior of Moving Objects (Part 1)]

[0078] The mobile body M recognizes the guide brick Bg, and when the travel direction indicated by the guide brick Bg matches the travel direction of the mobile body M (the direction of the path to the destination), the mobile body M generates a track parallel to the travel direction of the guide brick Bg (a substantially parallel track) and travels along the generated track. Matching means that the deviation between the vector corresponding to the travel direction of the guide brick Bg and the vector corresponding to the travel direction of the mobile body M is within a specified angle (e.g., 30 degrees, 45 degrees).

[0079] Figure 6 This figure illustrates the behavior of a moving object M (Part 1). At time t, the moving object M is traveling in a predetermined direction. At time t+1, the moving object M recognizes the guide brick Bg and arrives near it. It is then determined whether the angle θ formed between the moving direction of the moving object M and the moving direction of the guide brick Bg is equal to or smaller than a predetermined angle. At time t+2, if the angle θ is equal to or smaller than the predetermined angle, the moving object M continues traveling in the direction of the guide brick Bg.

[0080] As described above, the moving body M travels based on the guide blocks Bg, thereby enabling control of the moving body that is more considerate of surrounding pedestrians. For example, pedestrians tend to move along the direction of travel of the guide blocks Bg, so travel is performed with greater consideration for surrounding pedestrians.

[0081] [Behavior of Moving Objects (Part 2)]

[0082] When the moving body M recognizes the warning block Bw while moving along the traveling direction of the guide block Bg, it decelerates or stops in front of (near) the warning block Bw.

[0083] Figure 7 This diagram illustrates the behavior of a moving object M (Part 2). At time t, the moving object M is traveling in the direction of travel of a guide brick Bg. At time t+1, when the moving object M arrives near a warning brick Bw, it decelerates and checks the surrounding conditions. If, based on the results of the surrounding conditions check, the moving object M determines that there are no pedestrians or other objects nearby, it continues traveling in the direction of travel.

[0084] As described above, the mobile object M travels based on the warning bricks Bw, thereby enabling control of the mobile object M that is considerate of surrounding pedestrians. For example, near the warning brick B2, pedestrian behavior tends to vary significantly compared to other areas. By performing control that allows the mobile object M to further identify unexpected pedestrians, it is possible to be more considerate of surrounding pedestrians. Even when the mobile object M is not moving in the direction of travel of the guide brick Bg, upon recognizing the warning brick Bw, it can decelerate or stop in front of (near) the warning brick Bw.

[0085] [Behavior of Moving Objects (Part 3)]

[0086] When the moving body M is moving along the direction of travel of the guide brick Bg, if it recognizes the warning brick Bw and the new guide brick Bg connected to the warning brick Bw, it decelerates or stops in front of (near) the warning brick Bw and further moves along the direction of travel of the new guide brick Bg.

[0087] Figure 8 This diagram illustrates the behavior of a moving object M (part 3). At time t, the moving object M is traveling in the direction of travel of the guide brick Bg1. At time t+1, the moving object M arrives near the warning brick Bw and decelerates. At time t+2, with no pedestrians or other objects nearby, the moving object M turns toward the direction of travel of the guide brick Bg2 and travels in the direction of travel of the guide brick Bg2. The guide brick Bg2 is an example of a new guide brick Bg connected to the warning brick Bw. The direction of travel of the guide brick Bg2 intersects the direction of travel of the guide brick Bg1. This direction of travel is, for example, the direction of the moving object M's destination.

[0088] As described above, the moving object M travels based on the guide bricks Bg1, warning bricks, and guide bricks Bg2, thereby enabling control of the moving object M that is more considerate of surrounding pedestrians. For example, pedestrians tend to move along the guide bricks Bg1, warning bricks, and guide bricks Bg2, so the moving object M is controlled with greater consideration for surrounding pedestrians.

[0089] The above-mentioned [Mobile Object Behavior (Part 1)]-[Mobile Object Behavior (Part 3)] are examples of the process of "predicting the behavior of the pedestrian based on the type of support information." In [Mobile Object Behavior (Part 1)]-[Mobile Object Behavior (Part 3)], the actual pedestrian of interest is not determined, but the behavior of hypothetical nearby pedestrians is predicted based on the support information.

[0090] [Behavior of Moving Objects (Part 4)]

[0091] In [Behavior of Moving Object (Part 1)]-[Behavior of Moving Object (Part 3)], an example was described in which no pedestrian was present. However, in the following example, an example in which a pedestrian was present is described. The moving object M moves so as not to interfere with the movement of the pedestrian. Figure 9 This figure is used to illustrate the behavior (Part 4) of a moving object M. The moving object M is traveling behind a pedestrian P. When the direction of travel of the pedestrian P coincides with the direction of travel of the moving object M, the moving object M maintains a position at a predetermined distance from the pedestrian P and travels behind the pedestrian P.

[0092] For example, when the moving body M changes its path toward a pedestrian P (e.g. Figure 9In the case of turning right in the middle, the moving body M decelerates and changes the forward path after the pedestrian P moves to the front by a predetermined distance.

[0093] As described above, the mobile body M can travel in the same direction as pedestrians while maintaining a predetermined distance from them. This allows the mobile body M to travel without interfering with pedestrians' walking. As a result, the mobile body M can travel with greater consideration for surrounding pedestrians.

[0094] [Behavior of Moving Objects (Part 5)]

[0095] When the moving body M moves along the travel direction of the guide brick Bg and there is a pedestrian P moving along the travel direction of the guide brick Bg near the guide brick Bg, the moving body M travels at a position farther away than when there is no pedestrian P moving along the travel direction of the guide brick Bg near the guide brick Bg. Figure 10 This is a diagram for explaining the behavior of the moving object M (part 5).

[0096] For example, when a pedestrian is present, the reference position of the mobile object M (the position at which the mobile object M is traveling) is set at a first predetermined distance from the predetermined position. When a pedestrian is not present, the reference position of the mobile object M is set at a second predetermined distance from the predetermined position. The first predetermined distance is longer than the second predetermined distance. The predetermined position may be set with reference to the guide brick Bg or the pedestrian P. Figure 10 In the example of FIG, the pedestrian P walking on the guide brick Bg is targeted, but the pedestrian at a position a predetermined distance away from the guide brick Bg may be targeted.

[0097] As described above, when a pedestrian P is present, the mobile object M travels in a position more responsive to the pedestrian, thereby driving with greater consideration for the surrounding pedestrians. In other words, the mobile object M predicts that the pedestrian P will travel along the guide bricks Bg and drives based on this prediction. This process is another example of "predicting the pedestrian's behavior based on the type of support information."

[0098] [Behavior of Moving Objects (Part 6)]

[0099] Assume that a moving object M moves along the direction of travel of a guide block Bg1 and arrives near a warning block Bw. At this point, a pedestrian P is also near the warning block Bw. In this case, the moving object M decelerates or stops, and after the pedestrian P leaves the warning block Bw, the moving object M moves in the desired direction.

[0100] Figure 11This figure illustrates the behavior of a moving object M (part 6). At time t, the moving object M is traveling in the direction of travel of the guide brick Bg. At time t+1, the moving object M and the pedestrian P arrive near the warning brick Bw. At this point, the moving object M decelerates. At time t+2, the pedestrian P passes the warning brick Bw. After the pedestrian P passes the warning brick Bw, the moving object M moves in the desired direction (e.g., the same direction of travel of the pedestrian P or the direction of travel of the guide brick Bg2).

[0101] As described above, the mobile object M controls itself, taking into account the possibility of a pedestrian interfering with the mobile object near the warning brick Bg. In other words, the mobile object M predicts that a pedestrian will move in the direction of travel of the mobile object M and controls its travel based on the prediction. As a result, the mobile object M drives with greater consideration for surrounding pedestrians. This process is another example of "predicting the pedestrian's behavior based on the type of support information."

[0102] [Behavior of Moving Objects (Part 7)]

[0103] The explanation will focus on the differences from [Behavior of Moving Object (Part 6)]. Figure 12 This figure illustrates the behavior of a moving object M (part 7). At time t+1, the moving object M and a pedestrian P arrive near a warning brick Bw. At this point, the moving object M decelerates. At time t+2, pedestrian P begins walking along guide brick Bg2. At time t+3, pedestrian P crosses in front of the moving object M, and pedestrian P is a predetermined distance away from the moving object M. After pedestrian P has sufficiently cleared the moving object M, the moving object M moves in the desired direction (e.g., the same direction as pedestrian P, or a direction to cross and proceed straight through guide brick Bg2).

[0104] As described above, the mobile body M controls itself, taking into account the possibility of a pedestrian interfering with the mobile body M near the warning brick Bg. In other words, the mobile body M predicts that a pedestrian will move in the direction of its travel and controls its travel based on the prediction. As a result, the vehicle M is driven with greater consideration for surrounding pedestrians. This process is another example of "predicting the pedestrian's behavior based on the type of support information."

[0105] [Relationship between pedestrian attributes and mobile object behavior]

[0106] The mobile object M may also modify its behavior based on the estimated attributes of the pedestrian in addition to the aforementioned support information and the predicted pedestrian behavior. The mobile object M may also predict the pedestrian's behavior by taking the pedestrian's attributes into account and modify its behavior based on the predicted result and the support information. For example, the control device 100 of the mobile object M may predict the pedestrian's behavior without considering the pedestrian's attributes when determining the mobile object M's behavior, and then modify the predicted pedestrian's behavior based on the pedestrian's attributes. Alternatively, the control device 100 may predict the pedestrian's behavior by taking the pedestrian's attributes into account and use the predicted result.

[0107] The attributes of pedestrians include, for example, pedestrians estimated to be walking using tactile paving bricks (specific pedestrians) and pedestrians estimated to be walking without using tactile paving bricks. Figure 13 is a diagram for explaining a specific pedestrian. Figure 13 A user who uses a predetermined stick (for example, a stick used by a visually impaired person to sense the road ahead by touch when walking) as shown in A, or Figure 13 A user walking with a guide dog as shown in B.

[0108] The recognition unit 120 identifies the presence and location of a specific pedestrian in the captured image. For example, the recognition unit 120 uses a pattern matching process and a learned model to identify the specific pedestrian. The pattern matching process compares a pre-prepared template with features obtained from the image to identify the specific pedestrian. The learned model is a model that has been learned so that, when an image containing the specific pedestrian is input, it outputs information indicating the presence and location of the specific pedestrian in the image.

[0109] [Behavior of a Moving Object When a Specific Pedestrian is Recognized (Part 1)]

[0110] When the mobile object M recognizes the presence of a specific pedestrian near the guide brick Bg, it moves while maintaining a first distance from the pedestrian. When the mobile object M recognizes the presence of a pedestrian (not the specific pedestrian) near the guide brick Bg, it moves while maintaining a second distance from the pedestrian. The first distance is longer than the second distance. In other words, when the specific pedestrian is present, the mobile object M moves while maintaining a greater distance from the specific pedestrian than when the specific pedestrian is present.

[0111] Figure 14 : is a diagram showing an example of the position of the moving body M when a specific pedestrian exists and the position of the moving body M when a pedestrian different from the specific pedestrian exists. Figure 14As shown, the position of the moving object M is set at a first distance L1, a second distance L2, and a third distance L3 from the guide brick Bg. The third distance L3 is shorter than the first distance L1 and the second distance L2 and is the position of the moving object M set when no pedestrians are present.

[0112] As described above, by controlling the position of the mobile object M in consideration of the attributes of pedestrians, the mobile object M can be driven with greater consideration for surrounding pedestrians. For example, it is predicted that a specific pedestrian may have difficulty recognizing the presence of the mobile object M and may be more likely to approach the mobile object M than a pedestrian who is not a specific pedestrian, and this situation can be appropriately addressed.

[0113] In the above example, the distance set when a specific pedestrian is present can be set as the second distance L2, and the distance set when a pedestrian is present can be set as the first distance L1. For example, it is also possible to predict that the pedestrian is not walking using the guide brick Bg, the specific pedestrian is walking using the guide brick Bg, and there is a high probability that the pedestrian is moving in a direction different from the guidance direction of the guide brick Bg. This improves the accuracy of the prediction.

[0114] Alternatively, the prediction unit 130 analyzes the behavior of a pedestrian who is not a specific pedestrian and predicts whether the pedestrian is more likely than or equal to a predetermined level to move in a direction different from the guide direction of the guide bricks Bg. For example, the prediction unit 130 predicts the pedestrian's behavior by referring to one or more pieces of information, such as facial orientation, line of sight, and the pedestrian's behavioral history. For example, if the pedestrian's facial orientation or line of sight is toward a direction connecting the guide bricks Bg, or if the pedestrian has a tendency to move in the guide direction of the guide bricks Bg in past behavior, the prediction unit 130 determines that the pedestrian is less likely than or equal to a predetermined level to move in a direction different from the guide direction of the guide bricks Bg (determines that the pedestrian is moving in the guide direction). In other circumstances, the prediction unit 130 determines that the pedestrian is more likely than or equal to a predetermined level to move in a direction different from the guide direction of the guide bricks Bg. If the prediction unit 130 determines that the pedestrian is more likely than or equal to a predetermined level to move in a direction different from the guide direction of the guide bricks Bg, the control device 100 determines the position of the mobile object M relative to the guide bricks Bg based on the prediction result. For example, when it is determined that the probability that a pedestrian is moving in a direction different from the guide direction of the guide brick Bg is greater than or equal to a predetermined level, the control device 100 moves the mobile body M from a position at the second distance L2 to a position at a distance longer than the second distance L2 (e.g., the first distance L1). This allows the mobile body M to move while maintaining a sufficient distance from a pedestrian who is highly likely to be moving in a direction different from the guide direction.

[0115] The control device 100 may also predict the predicted degree of action of a specific traffic participant according to the support information to be a first degree if the traffic participant's attribute is a specific traffic participant. If the traffic participant's attribute is not a specific traffic participant, the control device 100 may predict the predicted degree of action of a non-specific traffic participant according to the support information to be a second degree, which is smaller than the first degree. Based on this prediction result, the control device 100 determines the position of the mobile object M relative to the guide bricks or pedestrians. In the case of the first degree, the mobile object M may be positioned farther from the guide bricks or pedestrians, or closer to them, compared to the case of the second degree. In the case of a non-specific pedestrian whose face or line of sight is directed toward the direction of the guide bricks Bg, or whose past behavior has shown a tendency to move in the direction guided by the guide bricks Bg, the predicted degree of action of the traffic participant according to the support information may be set to a third degree, which is higher than the second degree. The third degree may be higher than the second degree and lower than the first degree, the same as the first degree, or higher than the first degree. In the case of the third degree, the moving body M may be set at a position farther away from the guide brick or the pedestrian than in the other degrees, or may be set at a position closer.

[0116] In the above example, the process is described for the case where a specific pedestrian is recognized. However, in addition to (or instead of) recognizing a specific pedestrian, the mobile body M may travel at a position spaced apart from other pedestrians. The specific pedestrian may be a pedestrian pushing a stroller, a pedestrian pushing a wheelchair, or the like.

[0117] As described above, the control device 100 controls the moving body M to travel along the tactile paving bricks (e.g., guide bricks Bg) and determines the distance between the moving body M and the tactile paving bricks based on the attributes of the pedestrians, thereby enabling the moving body M to travel with greater consideration for the surrounding pedestrians.

[0118] [Behavior of a moving object when a specific pedestrian is recognized (Part 2)] - [Behavior of a moving object when a specific pedestrian is recognized (Part 4)] described below is another example of the process of "predicting the behavior of the pedestrian based on the type of the support information."

[0119] [Behavior of a Moving Object When a Specific Pedestrian is Recognized (Part 2)]

[0120] When the mobile body M recognizes the presence of a specific pedestrian near the warning brick Bw, it maintains an eleventh distance L11 from the warning brick Bw (or the specific pedestrian). When the mobile body M recognizes the presence of a pedestrian (not the specific pedestrian) near the warning brick Bw, it maintains a twelfth distance L12 from the pedestrian. The above-mentioned maintenance can be achieved by decelerating or stopping.

[0121] Figure 15 : is a diagram showing an example of the position of the moving body M when a specific pedestrian exists and the position of the moving body M when a pedestrian different from the specific pedestrian exists. Figure 15 As shown, the position of the mobile body M is set to a position that is, for example, an eleventh distance L11 and a twelfth distance L12 from an imaginary line IL obtained by extending the reference line of the warning brick Bw.

[0122] As described above, when a specific pedestrian is present, the moving body M maintains a greater distance than when a pedestrian other than the specific pedestrian is present, thereby enabling the moving body M to travel with greater consideration for surrounding pedestrians.

[0123] The [Behavior of the moving body when a specific pedestrian is identified (Part 3)] and [Behavior of the moving body when a specific pedestrian is identified (Part 4)] described below are an example of processing in which "when the pedestrian in front of the moving body reaches a specified position associated with a warning message while the moving body is moving along the travel direction, the control unit decelerates or stops the moving body, and thereafter, after the pedestrian passes the specified position or crosses in front of the moving body, the control unit accelerates the moving body or starts the moving body."

[0124] [Behavior of a Moving Object When a Specific Pedestrian is Recognized (Part 3)]

[0125] The moving body M performs a first action when a specific pedestrian passes the warning block Bw and goes straight, and performs a second action when the pedestrian passes the warning block Bw and goes straight. The first action is an action in which the moving body M approaches the guide block Bg at a later time than the second action.

[0126] The moving body M is Figure 15 When the specific pedestrian reaches the position at time t+3 (at the time of arrival), it approaches the warning brick Bw (or starts approaching). Approaching means that it approaches the warning brick Bw closer than the eleventh distance L11. Figure 15When the pedestrian shown (a pedestrian different from the specific pedestrian) reaches the position at time t+2, he approaches the warning brick Bw. Approaching means that he is closer to the warning brick Bw than the twelfth distance L12. The position of the pedestrian at time t+3 is a position farther away from the warning brick Bw than the position of the pedestrian at time t+2. The timing of performing the first behavior or the second behavior can also be based on the time from the specific pedestrian or pedestrians to the specified position instead of the position of the specific pedestrian or pedestrians. For example, the first behavior can be performed when a first time has passed since the arrival at the specified position (for example, when passing the warning brick), and the second behavior can be performed when a second time has passed since the arrival at the specified position. The first time is a longer time than the second time.

[0127] As described above, by changing the control according to the attributes of the pedestrian, the mobile body M can travel in consideration of the attributes of the pedestrian and the surrounding conditions.

[0128] [Behavior of a Moving Object When a Specific Pedestrian is Recognized (Part 4)]

[0129] The moving body M performs a third behavior when a specific pedestrian moves along the front guide brick Bg and crosses in front of the moving body M. The moving body M performs a fourth behavior when a pedestrian moves along the front guide brick Bg and crosses in front of the moving body M. The third behavior is a behavior in which the timing at which the moving body M approaches the guide brick Bg is delayed compared to the fourth behavior.

[0130] Figure 16 1 is a diagram for explaining the third and fourth behaviors. Figure 16 When the specific pedestrian reaches the position at time t+4 (at the time of arrival), the moving body M approaches the warning brick Bw (or starts approaching). Figure 16 When the pedestrian (different from the specific pedestrian) reaches the position at time t+3, it approaches the warning brick Bw. The position of the pedestrian at time t+4 is farther from the warning brick Bw than the position of the pedestrian at time t+3.

[0131] As described above, the mobile body M changes its control according to the attributes of the pedestrian, thereby enabling it to travel in a manner that takes into account the attributes of the pedestrian and the surrounding conditions. Alternatively, if a specific pedestrian is present at or near the warning brick Bw, or if a pedestrian moves in a direction (a second direction) opposite to the direction in which the guide brick Bg2 is present, the mobile body M may release its deceleration or start from a stopped state.

[0132] In the above Figure 15 [Behavior of a moving object when a specific pedestrian is recognized (Part 3)] and Figure 16In [Behavior of a Moving Object When a Specific Pedestrian is Recognized (Part 4)], the case where a specific pedestrian or other pedestrians are present at or near warning brick Bw is described. However, instead of considering other pedestrians, the vehicle can decelerate or stop when a specific pedestrian is present at or near warning brick Bw. Pedestrians sometimes walk without considering the blind bricks. Therefore, focusing on the specific pedestrian using the blind bricks can improve the accuracy of prediction of specific pedestrians.

[0133] [Flowchart (1)]

[0134] Figure 17 This is a flowchart (part 1) showing an example of the process flow executed by the control device 100. Part of the process in the flowchart described below may be omitted ( Figure 18 First, the control device 100 determines whether there are any tactile paving bricks around the moving object M based on the captured image (step S100). If there are any tactile paving bricks, the control device 100 determines whether the tactile paving bricks are guide bricks (step S102).

[0135] In the case where the blind brick is not a guide brick (but a warning brick), the following steps are executed. Figure 18 When the tactile paving brick is a guide brick, the control device 100 determines whether there is a pedestrian around the guide brick (step S104).

[0136] When there are pedestrians around the guide bricks, the control device 100 estimates the attributes of the pedestrians and determines the behavior of the moving body M based on the estimated attributes (step S106). Figure 14 The position of the moving body M is determined as described in .

[0137] Next, the control device 100 determines whether the moving direction of the moving body M matches the moving direction of the guide brick (step S108). If the moving direction of the moving body M does not match the moving direction of the guide brick, the processing of one routine of this flowchart ends.

[0138] When the moving direction of the mobile object M matches the moving direction of the guide brick, the control device 100 drives along the guide brick's direction (step S110). Thus, the mobile object M maintains an appropriate distance from the pedestrian based on the pedestrian's attributes. The processing of one routine in this flowchart then ends.

[0139] Through the above-described processing, the moving body M can travel in consideration of the guide bricks Bg and pedestrians around the guide bricks Bg.

[0140] [Flowchart (Part 2)]

[0141] Figure 18 2 is a flowchart illustrating an example of a process flow executed by the control device 100. First, the control device 100 determines whether a warning tile exists in a predetermined area (step S200). The predetermined area is, for example, an area in front of the moving object M and within a predetermined distance from the moving object M. If a warning tile exists, the control device 100 determines whether a pedestrian exists near the warning tile (step S202). If no pedestrian exists near the warning tile, the control device 100 drives based on the behavior of other pedestrians, other surrounding conditions, and the like (step S208).

[0142] When there is a pedestrian around the warning brick, the control device 100 estimates the attributes of the pedestrian and determines the behavior of the moving body M based on the estimated attributes of the pedestrian (step S204). Figure 15 or Figure 16 The position of the moving body M is determined as described in . Next, the control device 100 drives based on the behavior of the pedestrian (step S206). For example, Figure 15 ,or Figure 16 As described in , based on the timing when the pedestrian reaches a predetermined position, the moving body M is controlled. Thus, the processing of one routine in this flowchart ends.

[0143] Through the above-described processing, the moving body M can travel in consideration of the warning brick Bw and pedestrians around the warning brick Bw.

[0144] As described above, the control device 100 controls the moving object M by executing each process, thereby taking into account the support information and the predicted behavior or attributes of the pedestrian, and can make the moving object M travel with greater consideration for the surrounding conditions.

[0145] Traffic participants can be participants on roads or pathways located indoors (e.g., roads or pathways within facilities such as airports) or outdoors. In the above example, pedestrians are used as examples of traffic participants, but instead of (or in addition to) this, traffic participants may include bicycles (light vehicles) or other types of traffic participants. In this case, the control device 100 also identifies support information obtained from the road surface reflected in the image to support the movement of traffic participants with specified attributes, i.e., specific traffic participants, and the traffic participants reflected in the image. Based on the support information, the control device 100 predicts the behavior of the identified traffic participants and controls the movement of the moving object based on the support information and the prediction results. "Support information" includes priority identification for traffic participants (e.g., bicycles), information indicating the direction of travel, stopping locations, information urging deceleration, information urging stopping, and so on. If the support information is a tactile paving brick, the control device 100 predicts that traffic participants other than pedestrians are likely to act without regard to the information indicated by the tactile paving brick. For example, the control device 100 predicts that a traffic participant such as a bicycle is traveling on a portion of the sidewalk different from the portion where the support bricks are installed.

[0146] As described above, the control device 100 predicts the behavior of the traffic participants based on the type of support information and the type of the traffic participants, and controls the behavior of the moving object based on the predicted behavior.

[0147] The above-described embodiment can be expressed as follows.

[0148] A control device, wherein:

[0149] The control device comprises:

[0150] a storage device storing a program; and

[0151] Hardware processor,

[0152] The hardware processor executes the program stored in the storage device to perform the following processing:

[0153] Acquire an image of a road surface surrounding the moving object;

[0154] recognizing support information for supporting walking of a specific traffic participant having a predetermined attribute, obtained from a road surface reflected in the image, and the traffic participant reflected in the image;

[0155] predicting the behavior of the identified traffic participant based on the support information;

[0156] The behavior of the mobile object is controlled based on the support information and the predicted result.

[0157] While specific embodiments of the present invention have been described above, the present invention is not limited to these embodiments at all, and various modifications and substitutions can be made without departing from the spirit of the present invention.

Claims

1. A mobile control system, wherein: The mobile body control system comprises: an acquisition unit that acquires an image of a road surface surrounding the moving object; a recognition unit that recognizes support information for supporting movement of a specific traffic participant having a predetermined attribute obtained from a road surface reflected in the image, and the traffic participant reflected in the image; a prediction unit configured to predict, based on the support information, a behavior of the traffic participant identified by the identification unit; as well as a control unit configured to control the behavior of the mobile body based on the support information and the prediction result of the prediction unit, The recognition unit recognizes the attributes of the traffic participant, The prediction unit predicts the behavior of the traffic participant based on the support information and the attributes of the traffic participant. When the attribute of the traffic participant is a specific traffic participant, the prediction unit predicts that the prediction degree of the traffic participant's action according to the support information is a first degree, When the attribute of the traffic participant is not a specific traffic participant, the prediction unit predicts a predicted degree of action of the traffic participant who is not the specific traffic participant according to the support information to a second degree smaller than a first degree.

2. The mobile object control system according to claim 1, wherein: The traffic participants are pedestrians, The support information is the blind paving bricks set on the sidewalk.

3. The mobile object control system according to claim 1 or 2, wherein: The prediction unit predicts the behavior of the traffic participant based on the type of the support information.

4. The mobile object control system according to claim 3, wherein: The support information includes guidance information that indicates the direction in which the specific traffic participant is traveling and guides the movement of the specific traffic participant, and warning information that warns the specific traffic participant.

5. The mobile object control system according to claim 1 or 2, wherein: The control unit controls the behavior of the mobile object based on the support information, the prediction result of the prediction unit, and the attributes of the traffic participant, or based on the support information and the behavior of the traffic participant predicted by the prediction unit using the support information and the attributes of the traffic participant.

6. The mobile object control system according to claim 1 or 2, wherein: The support information is the blind bricks set on the sidewalk, The control unit controls the moving body to move along the tactile paving bricks, and determines a distance between the moving body and the tactile paving bricks based on the attributes of the traffic participant.

7. The mobile object control system according to claim 1 or 2, wherein: The support information includes guidance information indicating the direction in which the specific traffic participant is traveling and guiding the movement of the specific traffic participant, and warning information warning the specific traffic participant. When the traffic participant in front of the moving body reaches a predetermined position associated with warning information while the moving body is moving in the traveling direction, the control unit decelerates or stops the moving body. Thereafter, when the traffic participant passes the predetermined position or crosses in front of the moving body, the control unit accelerates the moving body or starts the moving body.

8. The mobile object control system according to claim 1 or 2, wherein: The support information is the blind bricks, The support information includes a guide tile that indicates the direction in which the specific traffic participant is traveling and guides the movement of the specific traffic participant, and a warning tile that warns the specific traffic participant. When a first guide brick is connected to the warning brick, a second guide brick is connected to the warning brick in a direction intersecting the first guide brick, and the second guide brick is present in front of the moving body, When the moving body moves in the direction of travel indicated by the first guide brick and the traffic participant in front of the moving body reaches a predetermined position associated with the warning information, the control unit decelerates or stops the moving body. Thereafter, when the traffic participant passes the predetermined position or crosses in front of the moving body, the control unit accelerates the moving body or starts the moving body.

9. The mobile object control system according to claim 7, wherein: The control unit delays the timing of accelerating or starting the mobile body when the mobile body is a specific traffic participant with the specified attributes, compared to the timing of accelerating or starting the mobile body when the traffic participant is a traffic participant with an attribute different from a traffic participant with the specified attributes.

10. The mobile object control system according to claim 1, wherein: The recognition unit sets the traveling position of the mobile body to a position at a first predetermined distance from a predetermined position when the presence of the traffic participant is recognized, and sets the traveling position of the mobile body to a position at a second predetermined distance from the predetermined position when the presence of the traffic participant is not recognized.

11. The mobile object control system according to claim 10, wherein: The predetermined position is set based on the position of the traffic participant or the support information.

12. The mobile object control system according to claim 10, wherein: The first predetermined distance is set to be longer than the second predetermined distance.

13. A mobile object, wherein: The moving object is equipped with the moving object control system according to any one of claims 1 to 12.

14. A control method, wherein: The control method enables the computer to perform the following processing: Acquire an image of a road surface surrounding the moving object; identifying support information for supporting movement of a specific traffic participant having a predetermined attribute, obtained from a road surface reflected in the image, and the traffic participant reflected in the image; predicting a movement of the identified traffic participant based on the support information; controlling the behavior of the mobile object based on the support information and the predicted result; identifying attributes of the traffic participant; predicting the behavior of the traffic participant based on the support information and the attributes of the traffic participant; When the attribute of the traffic participant is a specific traffic participant, predicting the prediction degree of the action of the traffic participant according to the support information to be the first degree; If the attribute of the traffic participant is not a specific traffic participant, the predicted degree of action of the traffic participant who is not the specific traffic participant according to the support information is predicted to be a second degree smaller than the first degree.

15. A storage medium storing a program, wherein: The program causes the computer to perform the following processing: Acquire an image of a road surface surrounding the moving object; identifying support information for supporting movement of a specific traffic participant having a predetermined attribute, obtained from a road surface reflected in the image, and the traffic participant reflected in the image; predicting a movement of the identified traffic participant based on the support information; controlling the behavior of the mobile object based on the support information and the predicted result; identifying attributes of the traffic participant; predicting the behavior of the traffic participant based on the support information and the attributes of the traffic participant; When the attribute of the traffic participant is a specific traffic participant, predicting the prediction degree of the action of the traffic participant according to the support information to be the first degree; If the attribute of the traffic participant is not a specific traffic participant, the predicted degree of action of the traffic participant who is not the specific traffic participant according to the support information is predicted to be a second degree smaller than the first degree.

Images