Protective body control device, protective body control method, and program

JPWO2024201673A5Pending Publication Date: 2025-12-09
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
JP2025509299
Authority / Receiving Office
JP · JP
Patent Type
Applications
Filing Date
2025-09-18
Publication Date
2025-12-09

AI Technical Summary

Technical Problem

Existing vehicle accident prevention systems are ineffective in preventing collisions with pedestrians, as they often require manual operation and cannot guarantee avoidance of accidents even with warnings.

Method used

A protective body control device and method that predicts potential vehicle-pedestrian collisions and automatically adjusts a protective body's state between a protected and non-protected position using a prediction unit and control unit, integrated with a computer-readable medium to execute the protective body control method.

Benefits of technology

The system reliably prevents vehicle-pedestrian collisions by automatically changing the protective body's state to impede the vehicle's progress when a collision is predicted, reducing the risk of accidents and minimizing manual intervention.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024201673000001
    Figure 2024201673000001
Patent Text Reader

Abstract

A protective body control device (2000) predicts whether or not a vehicle (20) will come into contact with a person (30), and controls the state of a protective body (40) on the basis of the prediction result. The protective body (40) can take: a protective state in which the vehicle (20) is prevented from traveling; and a non-protective state in which the vehicle (20) is not prevented from traveling.
Need to check novelty before this filing date? Find Prior Art

Description

Protection control device, protection control method, and non-transitory computer-readable medium

[0001] The present disclosure relates to a protection control device, a protection control method, and a non-transitory computer-readable medium.

[0002] Systems for preventing vehicle accidents have been developed. Patent Document 1 discloses a safety fence installed on train station platforms. Patent Document 2 discloses an accident prevention system for preventing accidents involving vehicles traveling on roads. This accident prevention system takes into account the driving characteristics of the vehicle and generates an accident probability map that represents the spatial distribution of the probability of an accident occurring around the vehicle, and presents a warning to the driver regarding locations where the probability of an accident occurring is high.

[0003] JP 2002-348815 A JP 2015-225366 A

[0004] The safety measures in Patent Document 1 must be operated manually. Patent Document 2 cannot prevent accidents when controlling the vehicle cannot avoid a collision with another vehicle, etc. This disclosure has been made in light of this problem, and one of its purposes is to provide a new technology for preventing vehicle accidents.

[0005] The protective body control device of the present disclosure has a prediction means for predicting whether a vehicle will come into contact with a person, and a control means for controlling the state of the protective body, which can be a protected state in which the vehicle's progress is hindered, or a non-protected state in which the vehicle's progress is not hindered, based on the results of prediction by the prediction means.

[0006] A protective body control method according to the present disclosure is executed by a computer and includes a prediction step of predicting whether a vehicle will come into contact with a person, and a control step of controlling the state of the protective body, which can be in a protected state that prevents the vehicle from moving forward, or in a non-protected state that does not prevent the vehicle from moving forward, based on the result of the prediction by the prediction means.

[0007] The non-transitory computer-readable medium of the present disclosure stores a program that causes a computer to execute the protective body control method of the present disclosure.

[0008] According to the present disclosure, a new technology for preventing vehicle accidents is provided.

[0009] FIG. 1 is a diagram illustrating an overview of the operation of a protection body control device of embodiment 1. FIG. 2 is a first diagram illustrating a protection state and a non-protection state of a protection body. FIG. 3 is a second diagram illustrating a protection state and a non-protection state of a protection body. FIG. 4 is a block diagram illustrating a functional configuration of a protection body control device of embodiment 1. FIG. 5 is a block diagram illustrating a hardware configuration of a computer that realizes the protection body control device. FIG. 6 is a block diagram illustrating a configuration of a protection body. FIG. 7 is a flowchart illustrating a processing flow executed by the protection body control device of embodiment 1. FIG. 8 is a flowchart illustrating a processing flow executed by the protection body control device in a case where control information and warning information are used.

[0010] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are designated by the same reference numerals, and duplicate explanations will be omitted as necessary for clarity. Furthermore, unless otherwise specified, predetermined values ​​such as predetermined values ​​and threshold values ​​are stored in advance in a storage device accessible from a device that uses the values. Furthermore, unless otherwise specified, the storage unit is composed of one or any number of storage devices.

[0011] [Embodiment 1] <Overview> Fig. 1 is a diagram illustrating an example of an overview of the operation of the protective body control device 2000 of embodiment 1. Here, Fig. 1 is a diagram for facilitating understanding of the overview of the protective body control device 2000, and the operation of the protective body control device 2000 is not limited to that shown in Fig. 1.

[0012] The protection body control device 2000 controls the state of the protection body to prevent the vehicle from coming into contact with a person. In Fig. 1, the vehicle, person, and protection body are denoted by the reference numerals 20, 30, and 40, respectively.

[0013] The vehicle 20 is any vehicle that travels on a road, such as a car, a motorcycle, or a moped. The person 30 is any person using a sidewalk. For example, the person 30 is a person walking or running. Another example is a person riding a bicycle, a tricycle, or a unicycle. Another example is a person using a wheelchair. The person 30 may be moving or stationary.

[0014] The protective body 40 is provided at the boundary between the roadway and the sidewalk. Here, the boundary between the roadway and the sidewalk where the protective body 40 is provided may be the edge of the roadway, the edge of the sidewalk, or the area between the roadway and the sidewalk (in other words, an area that is not classified as either the roadway or the sidewalk).

[0015] The protective body 40 can be in at least two states: a protective state in which it hinders the progress of the vehicle 20, and a non-protective state in which it does not hinder the progress of the vehicle 20. In the protective state, the protective body 40 can prevent contact between the vehicle 20 and the person 30 by hindering the progress of the vehicle 20.

[0016] FIG. 2 is a first diagram illustrating the protected state and the unprotected state of the protective body 40. In FIG. 2, the protective body 40 is configured using a wall that can be raised and lowered. The unprotected protective body 40 is housed in the ground. On the other hand, the protected protective body 40 protrudes above the ground. When the protective body 40 is in the unprotected state, the protective body 40 can be changed to the protected state by raising the protective body 40. On the other hand, when the protective body 40 is in the protected state, the protective body 40 can be changed to the unprotected state by lowering the protective body 40.

[0017] Here, when the protective body 40 is configured to be able to rise and fall in this way, the protective body 40 in the unprotected state may be in a state where the vehicle 20 can pass over the protective body 40, and a part of the protective body 40 may be above the ground. In other words, there may be some difference in level between the unprotected protective body 40 and the surrounding ground.

[0018] Furthermore, the protective body 40 that can be raised and lowered may be configured using something other than a wall. For example, the protective body 40 may be configured using a fence, a pole, a cushion, or the like.

[0019] FIG. 3 is a second diagram illustrating the protective state and the non-protective state of the protective body 40. In FIG. 3, the protective body 40 is configured using an openable wall. The protective body 40 in the non-protective state is in an open state. On the other hand, the protective body 40 in the protected state is in a closed state. When the protective body 40 is in the non-protective state, the protective body 40 can be changed to the protective state by closing the protective body 40. On the other hand, when the protective body 40 is in the protected state, the protective body 40 can be changed to the non-protective state by opening the protective body 40. Note that the protective body 40 may be configured using something other than a wall. For example, the protective body 40 may be configured using a fence, a pole, a cushion, or the like.

[0020] The protective body control device 2000 operates, for example, as follows: The protective body control device 2000 acquires the captured image 12 generated by the camera 10. Furthermore, the protective body control device 2000 uses the captured image 12 to predict whether the vehicle 20 will come into contact with the person 30. The protective body control device 2000 controls the state of the protective body 40 based on the prediction result.

[0021] Here, the protective body 40 under normal circumstances may be in a non-protected state or a protected state. When the protective body 40 is under normal circumstances in a non-protected state, the protective body control device 2000 changes the state of the protective body 40 to a protected state when it predicts that the vehicle 20 will come into contact with the person 30. Because the state of the protective body 40 is automatically controlled by the protective body control device 2000, it is possible to more reliably prevent the vehicle 20 from coming into contact with the person 30 compared to a case in which the state of the protective body 40 must be controlled manually.

[0022] Furthermore, according to the protection body control device 2000, when it is predicted that the vehicle 20 will come into contact with the person 30, the protection body 40 can be used to prevent contact between the vehicle 20 and the person 30. Therefore, unlike the case where a warning is only given to the vehicle 20, even if the vehicle 20 cannot avoid contact with the person 30 despite being warned, the protection body 40 can prevent contact between the vehicle 20 and the person 30. Therefore, it is possible to more reliably prevent the vehicle 20 from coming into contact with the person 30.

[0023] When the protective body 40 is in a protective state under normal circumstances, for example, if the protective body 40 is installed in a location that the vehicle 20 must pass through when entering a parking lot of a house or store, the vehicle 20 will not be able to enter the parking lot.

[0024] Therefore, for example, the protection body control device 2000 predicts whether the vehicle 20 will come into contact with the protection body 40. If it is predicted that the vehicle 20 will come into contact with the protection body 40, the protection body control device 2000 further predicts whether the vehicle 20 will come into contact with the person 30. If it is predicted that the vehicle 20 will not come into contact with the person 30, the protection body control device 2000 changes the protection body 40 to a non-protection state. In this way, it is possible to prevent contact between the vehicle 20 and the person 30, while allowing the vehicle 20 to pass through a location where the protection body 40 is installed, if necessary.

[0025] The protective body control device 2000 of this embodiment will be described in more detail below.

[0026] 4 is a block diagram illustrating the functional configuration of the protective body control device 2000 of embodiment 1. The protective body control device 2000 has a prediction unit 2020 and a control unit 2040. The prediction unit 2020 acquires the captured image 12 and determines whether or not the vehicle 20 will come into contact with the person 30 using the captured image 12. The control unit 2040 controls the state of the protective body 40 based on the result of the prediction by the prediction unit 2020.

[0027] <Example of Hardware Configuration> Each functional component of the protective body control device 2000 may be realized by hardware that realizes the functional component (e.g., a hardwired electronic circuit, etc.), or may be realized by a combination of hardware and software (e.g., a combination of an electronic circuit and a program that controls it, etc.). Below, a case where each functional component of the protective body control device 2000 is realized by a combination of hardware and software will be further described.

[0028] 5 is a block diagram illustrating an example of the hardware configuration of a computer 1000 that realizes the protective body control device 2000. The computer 1000 is any computer. For example, the computer 1000 is a stationary computer such as a PC (Personal Computer) or a server machine. Alternatively, the computer 1000 may be a portable computer such as a smartphone or a tablet terminal. The computer 1000 may be a dedicated computer designed to realize the protective body control device 2000, or may be a general-purpose computer.

[0029] For example, by installing a predetermined application on the computer 1000, each function of the protective body control device 2000 is realized on the computer 1000. The application is configured as a program for realizing each functional component of the protective body control device 2000. The method for acquiring the program is arbitrary. For example, the program can be acquired from a storage medium (such as a DVD disk or USB memory) on which the program is stored. Alternatively, the program can be acquired by downloading the program from a server device that manages the storage device on which the program is stored.

[0030] The computer 1000 has a bus 1020, a processor 1040, a memory 1060, a storage device 1080, an input / output interface 1100, and a network interface 1120. The bus 1020 is a data transmission path for the processor 1040, the memory 1060, the storage device 1080, the input / output interface 1100, and the network interface 1120 to transmit and receive data to and from each other. However, the method of connecting the processor 1040 and the like to each other is not limited to bus connection.

[0031] The processor 1040 is a processor such as a central processing unit (CPU), a graphics processing unit (GPU), or a field-programmable gate array (FPGA). The memory 1060 is a main storage device realized using a random access memory (RAM) or the like. The storage device 1080 is an auxiliary storage device realized using a hard disk, a solid state drive (SSD), a memory card, a read only memory (ROM), or the like.

[0032] The input / output interface 1100 is an interface for connecting the computer 1000 to an input / output device. For example, the input / output interface 1100 is connected to an input device such as a keyboard and an output device such as a display device.

[0033] The network interface 1120 is an interface for connecting the computer 1000 to a network. This network may be a LAN (Local Area Network) or a WAN (Wide Area Network).

[0034] The storage device 1080 stores a program (a program that realizes the above-mentioned application) that realizes each functional component of the protective body control device 2000. The processor 1040 reads this program into the memory 1060 and executes it, thereby realizing each functional component of the protective body control device 2000.

[0035] The protective body control device 2000 may be realized by one computer 1000, or may be realized by multiple computers 1000. In the latter case, the configuration of each computer 1000 does not need to be the same, and can be different from each other.

[0036] For example, it is preferable that the protection device control device 2000 is installed near the location to be monitored. For example, the protection device control device 2000 is realized by an edge device installed in a street light on the side of the road. Alternatively, for example, the protection device control device 2000 may be built into the camera 10. However, the protection device control device 2000 does not necessarily have to be installed near the location to be monitored, and may be installed in a data center or the like.

[0037] <Configuration of Protective Body 40> Fig. 6 is a block diagram illustrating the configuration of the protective body 40. In Fig. 6, the protective body 40 is connected to an actuator 100. The actuator 100 physically changes the state of the protective body 40. For example, if the protective body 40 is a wall that can be raised and lowered, the actuator 100 raises and lowers the protective body 40.

[0038] The actuator 100 is connected to a computer 200. The computer 200 is realized by, for example, a semiconductor chip (for example, a SoC (System on Chip)). The configuration of the computer 200 is similar to that of the computer 1000, for example.

[0039] The computer 200 is connected to the protection body control device 2000 (to the computer 1000) via a network. The computer 200 receives control information from the protection body control device 2000 and controls the actuator 100 in accordance with the received control information. As a result, the state of the protection body 40 is changed in accordance with the control information from the protection body control device 2000.

[0040] <Processing Flow> Figure 7 is a flowchart illustrating the flow of processing executed by the protective body control device 2000 of embodiment 1. The protective body control device 2000 controls the protective body 40 at the location to be monitored (the location imaged by the camera 10) by repeatedly executing the processing of Figure 7. The prediction unit 2020 acquires the captured image 12 (S102). The prediction unit 2020 predicts whether the vehicle 20 will come into contact with the person 30 (S104). The control unit 2040 controls the state of the protective body 40 based on the prediction result (S106).

[0041] <Acquisition of Captured Image 12: S102> The protective body control device 2000 acquires the captured image 12 (S102). There are various methods for acquiring the captured image generated by the camera. For example, the camera 10 is configured to transmit the generated captured image 12 to the protective body control device 2000. In this case, the protective body control device 2000 acquires the captured image 12 by receiving the captured image 12 transmitted by the camera 10.

[0042] Alternatively, for example, the camera 10 stores the generated captured image 12 in a storage unit accessible from the protective body control device 2000. In this case, the protective body control device 2000 acquires the captured image 12 by accessing this storage unit.

[0043] Here, a plurality of cameras 10 may be provided. In this case, the protective body control device 2000 acquires the captured images 12 generated by each of the plurality of cameras 10.

[0044] <Prediction of Contact: S104> The prediction unit 2020 uses the captured image 12 to predict whether the vehicle 20 will come into contact with the person 30 (S104). For example, the prediction unit 2020 executes a process for detecting the vehicle 20 and a process for detecting the person 30 on the captured image 12. Here, various existing processes can be used for the process for detecting a predetermined type of object from the captured image. Note that if multiple cameras 10 are installed at the location to be monitored, the prediction unit 2020 detects the vehicle 20 and the person 30 using the captured images 12 obtained from each of the multiple cameras 10.

[0045] If either the vehicle 20 or the person 30 is not detected in the captured image 12, or if neither the vehicle 20 nor the person 30 is detected in the captured image 12, the prediction unit 2020 predicts that the vehicle 20 will not come into contact with the person 30. On the other hand, if one or more vehicles 20 and one or more people 30 are detected in the captured image 12, the prediction unit 2020 predicts whether or not the vehicle 20 will come into contact with the person 30 for each pair of the vehicle 20 and the person 30, based on the time series data of the captured images 12 acquired so far (for example, using the time series data of the captured images 12 generated within a predetermined time in the past).

[0046] There are various methods for predicting whether two captured objects will come into contact using a time series of captured images. For example, the prediction unit 2020 identifies the position, speed, acceleration, and movement direction of each vehicle 20 and each person 30 by analyzing the time series data of the captured images 12. The prediction unit 2020 predicts changes in the position of each vehicle 20 and each person 30 based on the position, speed, acceleration, and movement direction. Then, for each pair of a vehicle 20 and a person 30, the prediction unit 2020 determines whether the distance between the predicted position of the vehicle 20 and the predicted position of the person 30 is sufficiently small (for example, equal to or less than a predetermined threshold).

[0047] When the distance between the predicted position of the vehicle 20 and the predicted position of the person 30 becomes sufficiently small, the prediction unit 2020 predicts that the vehicle 20 and the person 30 will come into contact. On the other hand, when the distance between the predicted position of the vehicle 20 and the predicted position of the person 30 does not become sufficiently small (for example, does not become equal to or smaller than a predetermined threshold), the prediction unit 2020 predicts that the vehicle 20 and the person 30 will not come into contact.

[0048] In addition, the prediction unit 2020 may use the captured image 12 to identify auxiliary information such as the status of traffic lights, the status of the vehicle 20's turn signals, or the status of the vehicle 20's brake lights, and use this auxiliary information to predict whether or not the vehicle 20 and the person 30 will come into contact.

[0049] <Regarding Control of Protective Body 40> Below, examples of control of the protective body 40 by the control unit 2040 will be described for both a case where the protective body 40 is in a non-protective state under normal circumstances and a case where the protective body 40 is in a protected state under normal circumstances.

[0050] <<Case in which the protective body 40 is in a non-protected state under normal circumstances>> In this case, when it is predicted that the vehicle 20 will come into contact with the person 30, the protective body control device 2000 changes the state of the protective body 40 that can prevent contact between the vehicle 20 and the person 30 to a protected state. For example, the control unit 2040 selects, from among a plurality of protective bodies 40, a protective body 40 that can prevent contact between the vehicle 20 and the person 30 as the protective body 40 to be controlled. The control unit 2040 then changes the state of the protective body 40 selected as the control object to the protected state. Specifically, the control unit 2040 transmits control information to the protective body 40 selected as the control object, instructing it to change the state of the protective body 40 to the protected state. Here, transmitting control information to the protective body 40 means, for example, transmitting control information to the computer 200 described in FIG. 6 .

[0051] According to this method of controlling only the protective body 40 that can prevent contact between the vehicle 20 and the person 30, the impact on the surrounding area caused by changing the protective body 40 to a protective state can be reduced compared to when all protective bodies 40 are controlled.

[0052] It is assumed that the protective body control device 2000 can grasp the position of each protective body 40 and address information for transmitting control information to that protective body 40. For example, this information is stored in advance in a storage unit accessible from the protective body control device 2000.

[0053] The protective bodies 40 that can prevent contact between the vehicle 20 and the person 30 are identified based on, for example, the position of the vehicle 20, the position of the person 30, and the position of each protective body 40. For example, the control unit 2040 selects the protective bodies 40 that exist on a line connecting the position of the vehicle 20 and the position of the person 30 as the protective bodies 40 to be controlled. Alternatively, for example, the control unit 2040 selects the protective bodies 40 whose distance from the line connecting the position of the vehicle 20 and the position of the person 30 is equal to or less than a predetermined threshold as the protective bodies 40 to be controlled. Furthermore, the control unit 2040 may further select, as the protective bodies 40 to be controlled, protective bodies 40 that are located in the vicinity (e.g., adjacent to) the protective body 40 selected as the control subject by the above-described method.

[0054] Alternatively, for example, the protection object control device 2000 may monitor contact between a vehicle 20 and a person 30 at each of a plurality of monitoring locations. In this case, the protection objects 40 to be controlled at each monitoring location may be predetermined in association with each monitoring location. In this case, when the control unit 2040 predicts that the vehicle 20 will come into contact with a person 30 at a certain monitoring location, it may set all protection objects 40 corresponding to that monitoring location to the protection state. In this way, according to a method in which all protection objects 40 related to a monitoring location are set to the control target, the protection objects 40 to be controlled can be easily selected, and the state of the protection objects 40 can be changed to the protection state in a shorter time.

[0055] Here, the time required for changing each protective body 40 from the non-protected state to the protected state may be measured in advance. In this case, the control unit 2040 may select, as the control target, only protective bodies 40 that can be changed to the protected state before the vehicle 20 comes into contact with the person 30, from among the protective bodies 40 that can prevent contact between the vehicle 20 and the person 30. Whether or not the protective body 40 can be changed to the protected state before the vehicle 20 comes into contact with the person 30 can be determined based on the time required to change the protective body 40 to the protected state and the time that the vehicle 20 and the person 30 are predicted to come into contact.

[0056] Furthermore, it may be known in advance whether or not each protective body 40 is malfunctioning. In this case, the control unit 2040 selects only those protective bodies 40 that are not malfunctioning as control targets among the protective bodies 40 that can prevent contact between the vehicle 20 and the person 30.

[0057] Furthermore, the control unit 2040 may exclude from the control targets those protective bodies 40 that can prevent contact between the vehicle 20 and the person 30 and that are predicted to come into contact with the person 30 during the process of changing to a protective state. For example, if the protective body 40 is configured to be liftable and lowerable, and the person 30 is standing on the protective body 40 housed on the ground, there is a possibility that the protective body 40 will come into contact with the person 30 if the protective body 40 is raised. Therefore, the control unit 2040 excludes from the control targets those protective bodies 40 that are located under the person 30's feet (in other words, does not select them as control targets). Similarly, if the protective body 40 is configured to be openable and closable, and the person 30 is on the path of travel of the protective body 40, there is a possibility that the person 30 will be trapped by the protective body 40. Therefore, such protective bodies 40 are excluded from the control targets.

[0058] <<<<Avoidance of Contact by Vehicle 20>>> When it is predicted that the vehicle 20 will come into contact with the person 30, the protective body control device 2000 may transmit to the vehicle 20 avoidance information requesting control to avoid contact with the person 30. In this case, for example, the vehicle 20 has a function to control the traveling of the vehicle without the driver's operation (for example, automatically apply the brakes to slow down the vehicle 20). The vehicle 20 also has a function to receive avoidance information from the protective body control device 2000.

[0059] The vehicle 20 performs processing to control the traveling of the vehicle in response to receiving the avoidance information from the protection body control device 2000. For example, the vehicle 20 may decelerate until it stops or change its direction of travel to a direction in which it can avoid contact with the person 30. Here, the avoidance information may indicate the position of the person 30 so that the vehicle 20 can determine the direction in which it can avoid contact with the person 30. Note that there may be other people 30 around the vehicle 20 in addition to the person 30 predicted to be contacted by the vehicle 20. Therefore, it is preferable that the avoidance information indicate the position of each person 30 located around the vehicle 20.

[0060] Alternatively, for example, the protective body control device 2000 may transmit warning information notifying the driver of the vehicle 20 of a danger when it is predicted that the vehicle 20 will come into contact with the person 30. In this case, the vehicle 20 has a function of receiving warning information from the protective body control device 2000 and a function of presenting the received warning information to the driver. The process of presenting the warning information is, for example, a process of displaying a screen showing the content of the warning information on an arbitrary display device, or a process of outputting a sound showing the content of the warning information from a speaker. Note that the display device that displays the warning information is, for example, a display device of a car navigation system, a head-up display, or a display device of the driver's mobile terminal.

[0061] The content of the warning information may be any information that can notify the driver of the vehicle 20 of a danger. For example, the content of the warning information may be a message such as "There is a person ahead" or "Please apply the brakes."

[0062] The protection body control device 2000 may be configured to transmit only either the avoidance information or the warning information to the vehicle 20, or may be configured to transmit both the avoidance information and the warning information.

[0063] When the protection body control device 2000 transmits avoidance information or warning information to the vehicle 20, there is a possibility that the vehicle 20 will not come into contact with the person 30 due to, for example, deceleration of the vehicle 20. Therefore, the prediction unit 2020 may predict again whether the vehicle 20 will come into contact with the person 30 after the avoidance information or warning information is transmitted to the vehicle 20. If it is predicted that the vehicle 20 will come into contact with the person 30, the protection body 40 is changed to the protection state. On the other hand, if it is predicted that the vehicle 20 will not come into contact with the person 30, the protection body 40 is not changed to the protection state.

[0064] For this reason, even if it is predicted that the vehicle 20 will come into contact with the person 30, if the vehicle 20 can subsequently be controlled to avoid contact between the vehicle 20 and the person 30, the state of the protective body 40 will not be changed. This makes it possible to reduce the frequency with which the state of the protective body 40 is changed. As a result, for example, it is possible to reduce the frequency with which the protective body 40 breaks down.

[0065] 8 is a flowchart illustrating the flow of processing executed by the protective body control device 2000 in a case where control information or warning information is used. The prediction unit 2020 acquires the captured image 12 (S202). The prediction unit 2020 uses the captured image 12 to predict whether the vehicle 20 will come into contact with the person 30 (S204).

[0066] If it is predicted that the vehicle 20 will not come into contact with the person 30 (S204: NO), the protective body control device 2000 ends the processing of Fig. 8. If it is predicted that the vehicle 20 will come into contact with the person 30 (S204: YES), the control unit 2040 transmits warning information or avoidance information to the vehicle 20 (S206). The prediction unit 2020 acquires the captured image 12 generated after execution of S204 (S208). The prediction unit 2020 further uses the captured image 12 acquired in S208 to predict whether the vehicle 20 will come into contact with the person 30 (S210).

[0067] If it is predicted that the vehicle 20 will come into contact with the person 30 (S210: YES), the control unit 2040 changes the state of the protective body 40 to the protected state (S212). On the other hand, if it is predicted that the vehicle 20 will not come into contact with the person 30 (S210: NO), the protective body control device 2000 ends the processing of FIG.

[0068] Here, the vehicle 20 that has received the avoidance information from the protection body control device 2000 may transmit response information to the protection body control device 2000 that represents information related to the automatic control of the vehicle 20. The response information includes, for example, information such as the predicted stopping position of the vehicle 20 and the braking distance of the vehicle 20. The prediction unit 2020 may use the information on the predicted stopping position and braking distance indicated in the response information when predicting whether or not the vehicle 20 and the person 30 will come into contact after the avoidance information is transmitted.

[0069] For example, suppose that the predicted stopping position of the vehicle 20 is in front of the position of the person 30 when viewed from the current position of the vehicle 20. In this case, the prediction unit 2020 predicts that the vehicle 20 will not come into contact with the person 30. On the other hand, suppose that the predicted stopping position of the vehicle 20 is not in front of the position of the person 30 when viewed from the current position of the vehicle 20. In this case, the prediction unit 2020 predicts that the vehicle 20 will come into contact with the person 30.

[0070] <<Case in which the protective body 40 is in a protective state under normal circumstances>> In this case, the protective body control device 2000 changes the protective body 40 to a non-protective state when it is predicted that the vehicle 20 will come into contact with the protective body 40, but when it is predicted that the vehicle 20 will not come into contact with the person 30. This makes it possible, for example, for the vehicle 20 to pass through the sidewalk and enter a parking lot in a case in which the boundary between the roadway and the sidewalk is normally blocked by the protective body 40.

[0071] Therefore, first, the prediction unit 2020 predicts whether or not the vehicle 20 will come into contact with the protective body 40. For example, the prediction unit 2020 predicts the movement path of the vehicle 20 by identifying the position and movement direction of the vehicle 20 using time-series data of the captured images 12. Then, if the protective body 40 is present on the movement path of the vehicle 20, the prediction unit 2020 predicts that the vehicle 20 will come into contact with the protective body 40. On the other hand, if the protective body 40 is not present on the movement path of the vehicle 20, the prediction unit 2020 predicts that the vehicle 20 will not come into contact with the protective body 40.

[0072] When it is predicted that the vehicle 20 will come into contact with the protective body 40, the prediction unit 2020 predicts whether or not the vehicle 20 will come into contact with the person 30 if the protective body 40 is put into a non-protected state (for example, if it is assumed that the protective body 40 does not exist). Here, the method for predicting whether or not the vehicle 20 and the person 30 will come into contact is as described above.

[0073] If it is predicted that the vehicle 20 will come into contact with the person 30, the prediction unit 2020 does not change the protective body 40 to the non-protected state. On the other hand, if it is predicted that the vehicle 20 will not come into contact with the person 30, the prediction unit 2020 changes the protective body 40 to the non-protected state.

[0074] After changing the protective body 40 to the non-protected state, the prediction unit 2020 preferably changes the protective body 40 back to the protected state at a timing when there are no vehicles 20 that will come into contact with the protective body 40. In this way, the time that the protective body 40 is in the non-protected state can be minimized.

[0075] <Operation Test of Protective Body 40> The protective body control device 2000 may perform an operation test of the protective body 40 during a period when the probability of the vehicle 20 coming into contact with the person 30 is low. The period when the probability of the vehicle 20 coming into contact with the person 30 is low is, for example, a time period when traffic volume (i.e., the number of vehicles 20 traveling on the road) is low at the location to be monitored. The time period when traffic volume is low at the location to be monitored is, for example, manually set by an administrator of the protective body control device 2000. Alternatively, for example, the time period when traffic volume is low at the location to be monitored may be identified by the protective body control device 2000 based on the result of detecting the vehicle 20 from the captured image 12.

[0076] For example, when the current time is a time period with low traffic volume at the location to be monitored, the protection body control device 2000 detects the vehicle 20 from the time-series data of the captured images 12. While the vehicle 20 is detected in the captured images 12, the protection body control device 2000 does not perform an operation test of the protection body 40. On the other hand, when the vehicle 20 is no longer detected in the captured images 12, the protection body control device 2000 performs an operation test of the protection body 40. Note that the operation test of the protection body 40 may be performed immediately when the vehicle 20 is no longer detected in the captured images 12, or the operation test of the protection body 40 may be performed when a situation in which the vehicle 20 is not detected in the captured images 12 continues for a certain period of time (for example, when a predetermined length of time or more has continued).

[0077] The operational test of the protective body 40 may include various tests. For example, the protective body control device 2000 measures the time from when a control signal for a state change is sent to the protective body 40 until the state change of the protective body 40 is completed (i.e., the time required for the state change), for each protective body 40, and stores the time in the memory unit. The required time is measured for each of the time required to change from a protected state to a non-protected state and the time required to change from a non-protected state to a protected state.

[0078] The time when the state change of the protective body 40 is completed may be identified using the captured image 12, or may be identified using a completion notification transmitted from the protective body 40 to the protective body control device 2000. The completion notification is a notification transmitted from the protective body 40 to the protective body control device 2000 in response to the completion of the state change of the protective body 40.

[0079] Here, it is possible that the state of the protective body 40 cannot be changed because the protective body 40 is malfunctioning. Therefore, if the state change of the protective body 40 is not completed within a predetermined length of time after transmitting a control signal for changing the state to the protective body 40, the protective body control device 2000 determines that the protective body 40 is malfunctioning. The protective body control device 2000 then stores identification information of the malfunctioning protective body 40 in the memory unit. This makes it possible to exclude the malfunctioning protective body 40 from being subject to control by the control unit 2040, or to identify protective bodies 40 that need repair.

[0080] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0081] In the above examples, the program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray (registered trademark) disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0082] Some or all of the above embodiments can be described as in the following supplementary notes, but are not limited to the following: (Supplementary Note 1) A protective body control device having: a prediction means for predicting whether a vehicle will come into contact with a person; and a control means for controlling the state of a protective body, which can be a protected state in which the vehicle's progress is hindered, or a non-protected state in which the vehicle's progress is not hindered, based on the result of the prediction by the prediction means. (Supplementary Note 2) A protective body control device according to Supplementary Note 1, wherein, when it is predicted that the vehicle will come into contact with a person, the control means identifies a protective body that can hinder the vehicle's progress from among a plurality of protective bodies based on the positions of the vehicle, the person, or both, and changes the state of the identified protective body to the protected state. (Supplementary Note 3) The protective body control device according to Supplementary Note 1 or 2, wherein the control means, when it is predicted that the vehicle will come into contact with a person, transmits to the vehicle avoidance information requesting control to avoid contact with a person, warning information notifying of a danger, or both, the prediction means predicts whether the vehicle will come into contact with a person after the avoidance information or the warning information is transmitted, and the control means, when it is predicted that the vehicle will come into contact with a person after the avoidance information or the warning information is transmitted, changes the state of the protective body to the protected state. (Supplementary Note 4) The protective body control device according to Supplementary Note 1 or 2, wherein a required time required for each of the protective bodies to change from the non-protected state to the protected state is stored in a memory unit, and the control means, based on the required time for each of the protective bodies, identifies from among the multiple protective bodies a protective body that can impede the progress of the vehicle predicted to come into contact with a person, and changes the state of the identified protective body to the protected state. (Supplementary Note 5) The protection body control device according to Supplementary Note 1, wherein the prediction means predicts whether or not a vehicle will come into contact with the protection body, predicts whether or not the vehicle will come into contact with a person when it is predicted that the vehicle will come into contact with the protection body, and changes the state of the protection body predicted to come into contact with the vehicle to the non-protection state when it is predicted that the vehicle will not come into contact with the person. (Supplementary Note 6) The protection body control device according to Supplementary Note 1, 2, or 5, wherein the protection body is provided between a road and a sidewalk.(Supplementary Note 7) A protective body control method executed by a computer, comprising: a prediction step of predicting whether a vehicle will come into contact with a person; and a control step of controlling the state of a protective body, which can be a protected state in which the vehicle's progress is hindered, or a non-protected state in which the vehicle's progress is not hindered, based on the result of the prediction by the prediction step. (Supplementary Note 8) The protective body control method described in Supplementary Note 7, wherein, when it is predicted that the vehicle will come into contact with a person in the control step, a protective body that can hinder the vehicle's progress is identified from among a plurality of protective bodies based on the positions of the vehicle, the person, or both, and the state of the identified protective body is changed to the protected state. (Supplementary Note 9) The protective body control method according to Supplementary Note 7 or 8, wherein, in the control step, when it is predicted that the vehicle will come into contact with a person, avoidance information requesting control to avoid contact with the person, warning information notifying of danger, or both, is transmitted to the vehicle, the prediction step predicts whether the vehicle will come into contact with a person after the avoidance information or the warning information is transmitted, and in the control step, when it is predicted that the vehicle will come into contact with a person after the avoidance information or the warning information is transmitted, the state of the protective body is changed to the protected state. (Supplementary Note 10) The protective body control method according to Supplementary Note 7 or 8, wherein, for each of the protective bodies, a required time required for the protective body to change from the non-protected state to the protected state is stored in a memory unit, and in the control step, a protective body that can impede the progress of the vehicle predicted to come into contact with a person is identified from among a plurality of protective bodies based on the required time for each of the protective bodies, and the state of the identified protective body is changed to the protected state. (Supplementary Note 11) The protective body control method according to Supplementary Note 7, wherein in the predicting step, predicting whether or not the vehicle will come into contact with the protective body, predicting whether or not the vehicle will come into contact with a person if it is predicted that the vehicle will come into contact with the protective body, and changing the state of the protective body predicted to come into contact with the vehicle to the non-protected state if it is predicted that the vehicle will not come into contact with the person. (Supplementary Note 12) The protective body control method according to Supplementary Note 7, 8, or 11, wherein the protective body is provided between a road and a sidewalk.(Supplementary Note 13) A non-transitory computer-readable medium storing a program that causes a computer to execute the following steps: a prediction step of predicting whether a vehicle will come into contact with a person; and a control step of controlling the state of a protective body, which can be a protected state that prevents the vehicle from traveling and a non-protected state that does not prevent the vehicle from traveling, based on the result of the prediction by the prediction step. (Supplementary Note 14) The readable medium according to Supplementary Note 13, wherein in the control step, when it is predicted that the vehicle will come into contact with a person, a protective body that can prevent the vehicle from traveling is identified from among a plurality of protective bodies based on the positions of the vehicle, the person, or both, and the state of the identified protective body is changed to the protected state. (Supplementary Note 15) The readable medium according to Supplementary Note 13 or 14, wherein in the control step, when it is predicted that the vehicle will come into contact with a person, avoidance information requesting control to avoid contact with the person, warning information notifying of danger, or both, is transmitted to the vehicle, the prediction step predicts whether the vehicle will come into contact with a person after the avoidance information or the warning information is transmitted, and in the control step, when it is predicted that the vehicle will come into contact with a person after the avoidance information or the warning information is transmitted, the state of the protective body is changed to the protected state. (Supplementary Note 16) The readable medium according to Supplementary Note 13 or 14, wherein, for each of the protective bodies, a required time required for it to change from the non-protected state to the protected state is stored in a storage unit, and in the control step, a protective body that can impede the progress of the vehicle predicted to come into contact with a person is identified from among a plurality of protective bodies based on the required time for each of the protective bodies, and the state of the identified protective body is changed to the protected state. (Supplementary Note 17) The readable medium according to Supplementary Note 13, wherein in the predicting step, predicting whether or not the vehicle will come into contact with the protective body, predicting whether or not the vehicle will come into contact with a person if it is predicted that the vehicle will come into contact with the protective body, and changing a state of the protective body predicted to come into contact with the vehicle to the non-protected state if it is predicted that the vehicle will not come into contact with the person. (Supplementary Note 18) The readable medium according to Supplementary Note 13, 14, or 17, wherein the protective body is provided between a road and a sidewalk.

[0083] REFERENCE SIGNS LIST 10 camera 12 captured image 20 vehicle 30 person 40 protective body 100 actuator 200 computer 1000 computer 1020 bus 1040 processor 1060 memory 1080 storage device 1100 input / output interface 1120 network interface 2000 protective body control device 2020 prediction unit 2040 control unit

Claims

1. a prediction means for predicting whether a vehicle will come into contact with a person; and a control means for controlling the state of the protective body, which can be in a protected state in which the vehicle's progress is hindered, or in a non-protected state in which the vehicle's progress is not hindered, based on the results of prediction by the prediction means.

2. 2. The protection body control device according to claim 1, wherein the control means, when it is predicted that the vehicle will come into contact with a person, identifies a protection body from among a plurality of protection bodies that can hinder the progress of the vehicle based on the positions of the vehicle, the person, or both, and changes the state of the identified protection body to the protection state.

3. The control means When it is predicted that the vehicle will come into contact with a person, transmitting to the vehicle avoidance information requesting control to avoid contact with the person, warning information notifying the vehicle of danger, or both of these; the prediction means predicts whether the vehicle will come into contact with a person after the avoidance information or the warning information is transmitted; 3. The protection body control device according to claim 1, wherein the control means changes the state of the protection body to the protection state when it is predicted that the vehicle will come into contact with a person after the avoidance information or the warning information is transmitted.

4. For each of the protective bodies, a required time required for the protective body to change from the non-protected state to the protected state is stored in a storage unit, 3. The protection body control device according to claim 1, wherein the control means identifies, from among the plurality of protection bodies, a protection body that can impede the progress of a vehicle predicted to come into contact with a person based on the required time for each protection body, and changes the state of the identified protection body to the protection state.

5. The prediction means predict whether the vehicle will come into contact with the protection; When it is predicted that the vehicle will come into contact with the protective body, predicting whether the vehicle will come into contact with a person; The protection body control device according to claim 1 , wherein, when it is predicted that the vehicle will not come into contact with a person, the state of the protection body predicted to come into contact with the vehicle is changed to the non-protection state.

6. The protection body control device according to claim 1 , 2 or 5 , wherein the protection body is provided between a road and a sidewalk.

7. a prediction step of predicting whether the vehicle will come into contact with a person; a control step of controlling the state of the protective body, which can be a protected state in which the vehicle's progress is hindered, and a non-protected state in which the vehicle's progress is not hindered, based on the results of the prediction by the prediction step.

8. 8. The protective body control method according to claim 7, wherein, in the control step, when it is predicted that the vehicle will come into contact with a person, a protective body that can hinder the progress of the vehicle is identified from among a plurality of protective bodies based on the positions of the vehicle, the person, or both, and the state of the identified protective body is changed to the protective state.

9. a prediction step of predicting whether the vehicle will come into contact with a person; a control step of controlling the state of the protective body, which can be in a protected state in which the vehicle's progress is hindered, or in a non-protected state in which the vehicle's progress is not hindered, based on the result of the prediction by the prediction step.

10. 10. The program according to claim 9, wherein, in the control step, when it is predicted that the vehicle will come into contact with a person, a protective body that can hinder the progress of the vehicle is identified from among the plurality of protective bodies based on the positions of the vehicle, the person, or both, and the state of the identified protective body is changed to the protective state.