Artificial Intelligence based Safety Management System for Tram Stations

Abstract

The present invention relates to a safety management system for a tram station, and more specifically, to a safety management system for a tram station using artificial intelligence that divides the station into a danger zone and a caution zone, recognizes objects within each zone, and takes appropriate action. To this end, (i) a station monitoring device (100) having (i-1) at least one camera installed on the side of a tram (10) to photograph the side of the tram (10) and the station (20); (i-2) an artificial intelligence object detection unit (140) that detects an object (30) based on the image from the camera and infers the distance between the object (30) and the tram (10); and (i-3) a collision risk judgment unit (130) that determines the possibility of a collision between the object (30) and the tram (10) based on the object (30) and the distance detected by the artificial intelligence object detection unit (140); A safety management device for a tram station using artificial intelligence is provided, characterized by including: (ii) a vehicle control device (200) that controls the operation of the tram (10) based on the output of the station monitoring device (100).

Description

Technology Field

[0001] The present invention relates to a safety management system for a tram station, and more specifically, to a safety management system for a tram station using artificial intelligence that divides the station into danger zones and caution zones, recognizes objects within each zone, and takes appropriate countermeasures. Background Technology

[0002] Generally, infrared sensors have been utilized to detect potential hazards (pedestrians, obstacles, etc.) that may occur on the sides of a tram while it is driving or stopped. This conventional technology is configured to place low-power infrared sensors on the sides of the tram to detect the presence of objects in close proximity and transmit the detection signal to a control unit to determine whether a dangerous situation has occurred. Through this, the aim is to ensure safety on the sides of the tram using a method that consumes less power than cameras or LiDAR.

[0003] However, such conventional technology has been limited to proximity detection methods based on infrared sensors. Consequently, it can only determine the simple presence of an object, making it difficult to precisely distinguish the type of object (person, stroller, obstacle, etc.) or its behavior (boarding / alighting, approaching, etc.).

[0004] Furthermore, infrared sensors have limited recognition performance depending on the environment (illumination, weather, obstacle materials, etc.), and the lack of AI-based image analysis and object recognition capabilities made stable safety management difficult in various situations.

[0005] Furthermore, conventional technology has failed to provide a multi-layered safety management system linked with tram door control, driver notifications, and station signaling devices because it utilizes risk detection results solely as simple control signals. Prior art literature

[0006] 1. Korean Patent Publication No. 10-2001-0005883 (Occupant type and location detection system), 2. Korean Patent Registration No. 10-1692809 (Vehicle camera device and obstacle distance measurement method using the same), 3. Korean Patent Registration No. 10-2639022 (Operation using drivable area detection). The problem to be solved

[0007] Accordingly, the present invention has been devised to solve the aforementioned problems, and the objective of the present invention is to provide a safety management system for a tram station using artificial intelligence that can ensure boarding and alighting safety by accurately detecting whether passengers or obstacles are present near the doors using a side camera and AI-based object recognition technology during the process of a tram stopping or departing from a station, and intelligently controlling the opening and closing of the doors and the departure of the tram based on this.

[0008] The second objective of the present invention is to prevent accidents and enhance service reliability in various station scenarios, such as sudden passenger behavior, access by mobility aids like wheelchairs and strollers, and slow boarding and alighting situations involving children and the elderly, by introducing an artificial intelligence (AI)-based object detection and vehicle control process.

[0009] However, the technical problems to be solved by the present invention are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which the present invention belongs from the description below. means of solving the problem

[0010] To achieve the above technical objectives, a safety management device for a tram station using artificial intelligence is provided, comprising: (i) a station monitoring device (100) having (i-1) at least one camera installed on the side of a tram (10) to photograph the side of the tram (10) and a station (20); (i-2) an artificial intelligence object detection unit (140) that detects an object (30) based on the image of the camera and infers the distance between the object (30) and the tram (10); and (i-3) a collision risk judgment unit (130) that determines the possibility of a collision between the object (30) and the tram (10) based on the object (30) and the distance detected by the artificial intelligence object detection unit (140); and (ii) a vehicle control device (200) that controls the operation of the tram (10) based on the output of the station monitoring device (100).

[0011] Optionally, the camera may include a first camera (110) having a first field of view to photograph the side of the tram (10) and part of the station (20); and a second camera (120) having a second field of view larger than the first field of view to photograph a background including the side of the tram (10) and the station (20).

[0012] Optionally, the camera has a first field of view of the first camera (110) in the range of 20° to 40°, and a second field of view of the second camera (120) in the range of 100° to 130°.

[0013] Optionally, the artificial intelligence object detection unit (140) further infers the speed of the object (30).

[0014] Optionally, the collision risk judgment unit (130) may define a first distance from the side of the tram (10) as a danger area (40), and define an area outside the danger area (40) as a caution area (50).

[0015] Optionally, the first distance is in the range of 1 to 2 m.

[0016] Optionally, the collision risk judgment unit (130) may determine that there is a possibility of collision if an object (30) is detected within the danger area (40) or if the object (30) is moving toward the tram (10) at a speed greater than the reference speed.

[0017] Optionally, the vehicle control unit (200) includes (ii-1) a door control unit (220) that controls a door control switch (230); (ii-2) a driving control unit (240) that controls a driving control unit (250); and (iii-3) a driver alarm device (210) that warns the driver of a potential collision.

[0018] Optionally, it further includes (iii) a station signaling device (300) that wirelessly receives status information of the vehicle control device (200) and displays a signal regarding the operation of the tram (10) at the station (20).

[0019] Optionally, the station signal device (300) comprises: (iii-1) a driving control judgment data receiving unit (330) that wirelessly receives status information of a vehicle control device (200); (iii-2) a door control unit data receiving unit (320) that receives door control unit data from a door control judgment unit (220) of a vehicle control device (200); and (iii-3) a station signal device control unit (310) that controls a station signal device located in front of the tram (10) based on data received by the driving control judgment data receiving unit (330) and the door control unit data receiving unit (320).

[0020] The objective of the present invention as described above is, as another category, a safety management method using the safety management device of the tram station described above, comprising: a step (S100) in which an artificial intelligence object detection unit (140) detects an object (30) within the station (20) based on an image captured by a camera; a step (S120) in which a collision risk judgment unit (130) determines whether the object (30) is located within a predefined danger area (40) and a caution area (50) of the station (20); and a step (S130) in which the collision risk judgment unit (130) determines the possibility of a collision between the object (30) and the tram (10) based on the location and speed of the object (30) and the distance from the tram (10).

[0021] In the case of a dangerous situation where a collision is possible, the method comprises: (i-1) a step in which the door control judgment unit (220) determines whether the door is closed (S140); (i-2) a step in which, if the door is not closed, there is a door closing command (S150); (i-3) a step in which, if there is a door closing command, the door closing command is blocked (S160); (i-4) a step in which, if the door closing command is blocked, or if the door is closed, or if there is no door closing command, the driving control judgment unit (240) blocks the driving command of the tram (10) (S170); (i-5) a step in which the driver alarm device (210) notifies the driver of the dangerous situation (S180); and (i-6) a step in which the vehicle control device (200) transmits a stop signal to the station signal device (300) (S190);

[0022] In the case where there is no dangerous situation, (ii-1) a step (S132) in which the door control judgment unit (220) determines whether the door is closed; (ii-2) if the door is not closed, return to the step (S100) of detecting an object (30); and (ii-3) if the door is closed, the vehicle control device (200) transmits a driving signal to the station signal device (300) (S134). This can also be achieved by a method for managing safety of a tram station using artificial intelligence.

[0023] Optionally, even if the object (30) is located within the attention area (50), if the speed of the object (30) is greater than a threshold value in the direction toward the tram (10), the collision risk judgment unit (130) determines that there is a possibility of collision. Effects of the invention

[0024] According to one embodiment of the present invention, the results of object detection are provided to the train driver in real-time as a warning, thereby reducing the driver's cognitive burden and enabling an immediate response in the event of a dangerous situation. For example, even if the driver issues a command to close the door while it is open, the door is automatically blocked from closing if a passenger is located near the door. Additionally, when the door is closed, a warning notification can be used to induce additional verification before departure. This has the effect of minimizing the possibility of accidents caused by errors in judgment by the driver.

[0025] In addition, according to the present invention, by linking a signal device installed outside the tram and the station to output a non-departure signal based on the presence of an object, dangerous situations are clearly indicated even in the environment outside the tram. This allows not only the driver but also station management personnel to quickly recognize dangerous situations, thereby significantly improving overall safety during operation.

[0026] However, the effects obtainable from the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description below. Brief explanation of the drawing

[0027] The following drawings attached to this specification illustrate preferred embodiments of the present invention and serve to further enhance understanding of the technical concept of the present invention together with the detailed description of the invention provided below; therefore, the present invention should not be interpreted as being limited only to the matters described in such drawings. FIG. 1 is a schematic block diagram of a safety management device for a tram station using artificial intelligence according to an embodiment of the present invention. FIG. 2 is a state diagram of a tram (10) and a station (20) equipped with a safety management device according to the present invention. FIGS. 3a to 3d are photographs illustrating the process of a safety management device according to the present invention recognizing an object (30) within a danger area (40). FIG. 4 is a flowchart schematically illustrating a method for managing the safety of a tram station using artificial intelligence according to an embodiment of the present invention. Specific details for implementing the invention

[0028] Below, with reference to the attached drawings, embodiments of the present invention are described in detail so that those skilled in the art can easily implement the invention. However, since the description of the present invention is merely an example for structural or functional explanation, the scope of the present invention should not be interpreted as being limited by the embodiments described in the text. That is, since the embodiments are subject to various modifications and may take various forms, the scope of the present invention should be understood to include equivalents capable of realizing the technical concept. Furthermore, the objectives or effects presented in the present invention do not imply that a specific embodiment must include all of them or only such effects; therefore, the scope of the present invention should not be understood as being limited by them.

[0029] The meaning of the terms described in this invention should be understood as follows.

[0030] Terms such as "first" and "second" are intended to distinguish one component from another, and the scope of rights shall not be limited by these terms. For example, the first component may be named the second component, and similarly, the second component may be named the first component. When a component is referred to as being "connected" to another component, it should be understood that it may be directly connected to that other component, or that there may be other components in between. Conversely, when a component is referred to as being "directly connected" to another component, it should be understood that there are no other components in between. Meanwhile, other expressions describing the relationship between components, such as "between" and "exactly between," or "adjacent to" and "directly adjacent to," shall be interpreted in the same manner.

[0031] A singular expression should be understood to include a plural expression unless the context clearly indicates otherwise, and terms such as "include" or "have" are intended to specify the existence of the set-up features, numbers, steps, actions, components, parts, or combinations thereof, and should be understood not to preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0032] Unless otherwise defined, all terms used herein have the same meaning as generally understood by those skilled in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having meanings consistent with the context of the relevant technology and should not be interpreted as having an ideal or overly formal meaning unless explicitly defined in this invention.

[0033] Composition of the embodiment

[0034] Hereinafter, the configuration of a preferred embodiment will be described in detail with reference to the attached drawings. FIG. 1 is a schematic block diagram of a safety management device for a tram station using artificial intelligence according to an embodiment of the present invention, and FIG. 2 is a state diagram of a tram (10) and a station (20) equipped with a safety management device according to the present invention.

[0035] As illustrated in FIGS. 1 and 2, a camera is installed on the upper side of the tram (10) to photograph the side of the tram (10) and the station (20). The first camera (110) photographs the side of the tram (10) and part of the station (20), and the first field of view is in the range of 20° to 40° and preferably about 30°.

[0036] The second camera (120) is installed next to the first camera (110) and captures the entire background including the side of the tram (10) and the station (20). To this end, the second field of view of the second camera (120) is a wide angle in the range of 100° to 130°, preferably about 120°. Video from the first and second cameras (110, 120) is transmitted to the camera data receiver (150).

[0037] The station monitoring device (100) includes a collision risk judgment unit (130), an artificial intelligence object detection unit (140), and a camera data receiving unit (150), and can be realized by a computer and application software.

[0038] The camera data receiving unit (150) receives and stores video from the first and second cameras (110, 120).

[0039] The artificial intelligence object detection unit (140) detects an object (30) based on the image from the camera and infers the type of the detected object (30) (e.g., passenger, child, elderly person, stroller, wheelchair, obstacle, cargo, carrier, pet, etc.), size, speed (including speed and direction of movement), and distance between the object (30) and the tram (10). To this end, the artificial intelligence object detection unit (140) is trained in advance using a plurality of training datasets. The artificial intelligence object detection unit (140) is composed of artificial intelligence models such as a neural network and a convolutional neural network (CNN).

[0040] Specifically, the artificial intelligence object detection unit (140) may adopt an R-CNN, Fast R-CNN, Faster R-CNN: Region Proposal, YOLO (You Only Look Once), or RetinaNet: Focal Loss model for object detection (30). Additionally, the artificial intelligence object detection unit (140) may adopt an SSD (Single Shot MultiBox Detector) model to infer the speed of the object (30).

[0041] The artificial intelligence object detection unit (140) may adopt U-Net, Mask R-CNN: Faster R-CNN, DeepLab (v3, v3+) models to segment objects (30) detected within the image.

[0042] The artificial intelligence object detection unit (140) may adopt SORT, DeepSORT, I3D, SlowFast Network, and TimeSformer models to recognize tracking or behavior of an object (30) detected in an image.

[0043] The collision risk determination unit (130) determines the possibility of a collision between the object (30) and the tram (10) based on the object (30) detected by the artificial intelligence object detection unit (140) and the size, distance, and speed (including speed and direction of movement) of the object (30).

[0044] As shown in FIG. 3c, the collision risk judgment unit (130) defines a danger zone (40) within 1 to 2 m from the side of the tram (10) and defines a caution zone (50) outside the danger zone (40). In FIG. 3c, the danger zone (40) is indicated in red. The collision risk judgment unit (130) determines that there is a possibility of collision if an object (30) is detected within the danger zone (40) or if the object (30) is moving toward the tram (10) at a speed greater than a reference speed.

[0045] The vehicle control unit (200) includes a door control unit (220), a driving control unit (240), and a driver alarm device (210) to control the operation of the tram (10) based on the output of the station monitoring unit (100).

[0046] The door control unit (220) controls the door control switch (230), and the driving control unit (240) controls the driving control device (250) of the tram (10). The door control unit (220) and the driving control unit (240) can be implemented using a CPU, a microcomputer, a PLC (programmable logic controller), etc.

[0047] The driver alarm device (210) outputs the judgment status and control status of the door control panel (220) and the driving control panel (240) to the driver. To this end, the driver alarm device (210) may be a monitor, a speaker, etc.

[0048] The station signal device (300) is installed at a station outside the tram (10) and is configured to wirelessly receive a signal regarding the operation of the tram (10) and display it at the station (20).

[0049] The station signal device (300) is composed of a driving control judgment data receiving unit (330), a door control unit data receiving unit (320), and a station signal device control unit (310).

[0050] The driving control judgment data receiving unit (330) wirelessly receives status information of the vehicle control device (200) of the tram (10). To this end, the driving control judgment data receiving unit (330) includes a wireless Wi-Fi module, a Bluetooth module, a wireless LAN module, an internet module, and a 4G or 5G communication network module.

[0051] The door control unit data receiving unit (320) receives door control unit data from the door control judgment unit (220) of the vehicle control device (200). To this end, the door control unit data receiving unit (320) includes a wireless Wi-Fi module, a Bluetooth module, a wireless LAN module, an internet module, and a 4G or 5G communication network module.

[0052] The station signal device control unit (310) controls the station signal device located in front of the tram (10) based on data received by the driving control judgment data receiving unit (330) and the door control unit data receiving unit (320).

[0053] Operation of the example

[0054] Hereinafter, the operation of a preferred embodiment will be described in detail with reference to the attached drawings. FIG. 4 is a flowchart schematically showing a safety management method for a tram station using artificial intelligence according to an embodiment of the present invention, and FIGS. 3a to 3d are photographs illustrating the process of a safety management device according to the present invention recognizing an object (30) within a danger area (40).

[0055] As shown in FIG. 4, with the tram (10) stopped at the station (20), the first and second cameras (110, 120) photograph the side of the tram (10) and the station (20) (see FIG. 3a).

[0056] Next, the camera data receiving unit (150) receives the captured video, and the artificial intelligence object detection unit (140) detects an object (30) within the station (20) based on the video (S100). Specifically, the object (30) is detected in individual frames within the video (see FIG. 3b).

[0057] To detect the object (30), first, the top-left corner of the 2D box occupied by the object (30) ) and bottom right ( Get the pixel coordinates of ). The bottom-right pixel coordinates of the 2D box of the object (30) ( The straight-line distance between the side of the tram (10) and the object (30) is estimated using ). For the estimation, an extrinsic parameter matrix calculated by matching the camera pixel coordinate system and the actual coordinate system (metric) is utilized.

[0058] The homography matrix is ​​a 3×3 transformation matrix calculated based on the camera's external attitude (roll, pitch, yaw) and position, and is used to transform the image's pixel coordinate system (u,v,1) into the global coordinate system (x,y,1) (metric). Here y represents the distance value of the object (30) from the side of the tram (10).

[0059]

[0060] Next, the collision risk determination unit (130) determines whether the object (30) is located within the danger area (40) and the caution area (50) of the station (20) (S120) (see FIG. 3c). More specifically, the collision risk determination unit (130) determines that the object (30), who is a passenger, is within the danger area (40) in an image such as FIG. 3c.

[0061] Next, the collision risk judgment unit (130) determines the possibility of a collision between the object (30) and the tram (10) based on the location, size, speed, and distance from the object (30) (S130) (see FIG. 3d). Even if the object (30) is located within the caution area (50), if the object (30) moves rapidly toward the tram (10), the collision risk judgment unit (130) determines that there is a possibility of a collision. Additionally, the collision risk judgment unit (130) determines that it is a dangerous situation if the object (30) stays within the danger area (40) for a certain period of time (e.g., 10 seconds).

[0062] If there is a dangerous situation where a collision is possible, the door control judgment unit (220) determines whether the door is closed (S140). If the door is not closed, it determines whether there is a door closing command (S150), and if there is a door closing command, it blocks the door closing command (S160). This is to prevent accidents where a passenger gets caught in the door or bumps into the door while the door is closing.

[0063] Then, if the door closing command is blocked, or if the door is closed, or if there is no door closing command, the driving control judgment unit (240) blocks the driving command of the tram (10) (S170). This is to prevent the tram (10) from starting in a dangerous situation. Then, the driver alarm device (210) notifies the driver of the dangerous situation (S180). The vehicle control unit (200) transmits a stop signal to the station signal device (300) (S190). Through this, the driver hears the alarm inside the driver's seat of the tram (10) and can easily check the signal device in front of the tram (10) with the naked eye.

[0064] If there is no dangerous situation, the door control judgment unit (220) determines whether the door is closed (S132), and if the door is not closed, returns to the step of detecting the object (30) (S100). And if the door is closed, the vehicle control device (200) transmits a driving signal to the station signal device (300) to operate the tram (10) (S134).

[0065] Modified Examples

[0066] One embodiment of the present invention is intended for a tram (10), but it may also be intended for a train running on a railway, a high-speed train, a subway, a tourist train, a monorail, etc.

[0067] The camera of the present invention can be replaced with an ultrasonic sensor, lidar, proximity sensor, momentum sensor, etc.

[0068] In the present invention, the station is defined as a risk area and a caution area, but depending on the choice of the implementer, it may be subdivided into 3 to 5 areas and then assigned different risk weights to each subdivided area.

[0069] As described above, the detailed description of the preferred embodiments of the present invention disclosed is provided to enable those skilled in the art to implement and practice the present invention. Although the present invention has been described with reference to preferred embodiments, those skilled in the art will understand that various modifications and changes can be made to the present invention without departing from the scope of the invention. For example, those skilled in the art may utilize each configuration described in the embodiments described above in combination with one another. Accordingly, the present invention is not intended to be limited to the embodiments shown herein, but to be given the broadest scope consistent with the principles and novel features disclosed herein.

[0070] The present invention may be embodied in other specific forms without departing from the spirit and essential features of the invention. Accordingly, the above detailed description should not be interpreted restrictively in all respects but should be considered exemplary. The scope of the invention shall be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the invention are included within the scope of the invention. The invention is not intended to be limited to the embodiments shown herein, but to be given the broadest possible scope consistent with the principles and novel features disclosed herein. Furthermore, embodiments may be constructed by combining claims that are not explicitly related in the claims, or by including them as new claims through amendments made after filing. Explanation of the symbols

[0071] 10 : Tram, 20 : Station, 30 : Object, 40 : Risk area, 50 : Area of ​​caution, 100 : Fixed price monitoring device, 110: 1st Camera, 120 : 2nd camera, 130 : Collision risk judgment unit, 140 : Artificial intelligence object detection unit, 150 : Camera data receiver, 200 : Vehicle control unit, 210 : Engineer's alarm device, 220 : Door control judgment unit, 230 : Door control switch, 240 : Driving control judgment unit, 250 : Driving control unit, 300 : Station signaling device, 310 : Fixed signal device control unit, 320 : Door control panel data receiver, 330 : Driving control judgment data receiving unit.

Claims

Claim 1 (i-1) at least one camera installed on the side of the tram (10) to photograph the side of the tram (10) and the station (20); (i-2) an artificial intelligence object detection unit (140) that detects an object (30) based on the image of the camera and infers the distance between the object (30) and the tram (10); and (i-3) a collision risk judgment unit (130) that determines the possibility of a collision between the object (30) and the tram (10) based on the object (30) and the distance detected by the artificial intelligence object detection unit (140); (i) a station monitoring device (100); A safety management method using a safety management device for a tram station using artificial intelligence, comprising: (ii) a vehicle control device (200) that controls the operation of the tram (10) based on the output of the station monitoring device (100); wherein, based on an image captured by a camera, an artificial intelligence object detection unit (140) detects an object (30) within the station (20) (S100); a collision risk judgment unit (130) determines whether the object (30) is located within a predefined danger area (40) and caution area (50) of the station (20) (S120); wherein the collision risk judgment unit (130) determines the possibility of a collision between the object (30) and the tram (10) based on the location and speed of the object (30) and the distance from the tram (10) (S130); and, in the case of a dangerous situation with a possibility of collision, (iii-1) a door control judgment unit (220) determines whether the door is closed A step of determining (S140); (iii-2) a step of determining whether there is a closing command for the door if the door is not closed (S150); (iii-3) a step of blocking the closing command for the door if there is a closing command (S160); (iii-4) a step in which the driving control judgment unit (240) blocks the driving command of the tram (10) if the closing command for the door is blocked, or if the door is closed, or if there is no closing command for the door (S170);(iii-5) a step in which the driver alarm device (210) notifies the driver of the dangerous situation (S180); and (iii-6) a step in which the vehicle control device (200) transmits a stop signal to the station signal device (300) (S190); wherein, if the dangerous situation is not, (iv-1) a step in which the door control judgment unit (220) determines whether the door is closed (S132); (iv-2) if the door is not closed, return to the step of detecting the object (30) (S100); and (iv-3) if the door is closed, a step in which the vehicle control device (200) transmits a driving signal to the station signal device (300) (S134); characterized by a method for safety management of a tram station using artificial intelligence. Claim 2 A method for safety management of a tram station using artificial intelligence according to claim 1, wherein the camera comprises: a first camera (110) having a first field of view to photograph the side of the tram (10) and a part of the station (20); and a second camera (120) having a second field of view larger than the first field of view to photograph a background including the side of the tram (10) and the station (20). Claim 3 A method for managing safety of a tram station using artificial intelligence, characterized in that, in claim 2, the first field of view of the first camera (110) is in the range of 20° to 40°, and the second field of view of the second camera (120) is in the range of 100° to 130°. Claim 4 delete Claim 5 A method for managing safety of a tram station using artificial intelligence, characterized in that, in claim 1, the collision risk judgment unit (130) defines a danger area (40) within a first distance from the side of the tram (10) and defines an area outside the danger area (40) as a caution area (50). Claim 6 A method for safety management of a tram station using artificial intelligence, characterized in that, in claim 5, the first distance is in the range of 1 to 2 m. Claim 7 A method for managing safety of a tram station using artificial intelligence, characterized in that, in claim 5, the collision risk determination unit (130) determines that there is a possibility of collision when the object (30) is detected within the risk area (40) or when the object (30) is moving toward the tram (10) at a speed greater than a reference speed. Claim 8 A method for managing safety of a tram station using artificial intelligence, wherein, in claim 1, the vehicle control device (200) comprises: (ii-1) a door control unit (220) that controls a door control switch (230); (ii-2) a driving control unit (240) that controls a driving control device (250); and (iii-3) a driver alarm device (210) that warns the driver of the possibility of a collision. Claim 9 A method for managing safety of a tram station using artificial intelligence, characterized in that, in claim 1, it further includes (iii) a station signaling device (300) that wirelessly receives status information of the vehicle control device (200) and displays a signal regarding the operation of the tram (10) at the station (20). Claim 10 In claim 9, the station signal device (300) comprises: (iii-1) a driving control judgment data receiving unit (330) that wirelessly receives status information of the vehicle control device (200); (iii-2) a door control unit data receiving unit (320) that receives door control unit data from the door control judgment unit (220) of the vehicle control device (200); and (iii-3) a station signal device control unit (310) that controls a station signal device located in front of the tram (10) based on the data received by the driving control judgment data receiving unit (330) and the door control unit data receiving unit (320). This characterizes a method for managing safety of a tram station using artificial intelligence. Claim 11 delete Claim 12 A method for managing safety of a tram station using artificial intelligence, characterized in that, in claim 1, even if the object (30) is located within the attention area (50), if the speed of the object (30) is greater than a reference value in the direction toward the tram (10), the collision risk judgment unit (130) determines that there is a possibility of collision.

Images