Railway vehicle control apparatus and method

Abstract

The present invention relates to a railway vehicle control apparatus and method for controlling a railway vehicle, which receive sensing information through a sensor of the railway vehicle in an autonomous driving situation, determine the presence of a torpedo ladle car (TLC) by using a TLC detection algorithm based on the sensing information, calculate the distance to the TLC by using a distance measurement algorithm based on the sensing information, determine a fastening state of a TLC fastener by using a fastener recognition algorithm based on the sensing information, and control the speed of the railway vehicle by using the three factors of whether the TLC is present, the distance to the TLC, and the fastening state of the TLC fastener.

Description

Railway vehicle control device and method

[0001] The present embodiments relate to a railway vehicle control device and method for automatic TLC engagement during autonomous driving.

[0002] The braking distance of autonomous railway vehicles reaches 100 meters. Therefore, autonomous railway vehicles must be able to detect obstacles ahead, both close and far, and be controlled to stop when they detect an obstacle. To achieve this, sensors are attached to railway vehicles, and obstacle detection is performed using various sensors to encompass both close and far-range detection.

[0003] For the transport of chartered TLCs using autonomous rail vehicles, the fastening process, which connects the rail vehicle to the TLC, is essential. Chartered TLCs typically weigh between 300 and 600 tons, making them heavy. If the rail vehicle fails to perform the fastening process at the proper speed, a collision could result in serious safety issues.

[0004] Therefore, according to the conventional technology, there is a limit to controlling the speed of the process of fastening a railway vehicle and a chartered TLC, and a control technology for an autonomous railway vehicle is required to ensure smooth fastening of a railway vehicle and a chartered TLC.

[0005] The present embodiments can provide a railway vehicle control device for automatic TLC engagement during autonomous driving.

[0006] Additionally, the present embodiments can provide a railway vehicle control method for automatic TLC engagement during autonomous driving.

[0007] In one aspect, the present embodiments can provide a railway vehicle control device including a receiving unit that receives sensing information through a sensor of a railway vehicle in an autonomous driving situation, a TLC (Torpedo Ladle Car) presence determination unit that determines whether a TLC exists using a TLC detection algorithm based on the sensing information, a TLC distance calculation unit that calculates a distance to a TLC using a distance measurement algorithm based on the sensing information, and a fastener recognition unit that determines a TLC fastener fastening state using a fastener recognition algorithm based on the sensing information. The present embodiments can provide a railway vehicle control device including a speed control unit that controls the speed of the railway vehicle using three factors of the presence of a TLC, the distance to the TLC, and the TLC fastener fastening state.

[0008] In another aspect, the present embodiments can provide a railway vehicle control method including a receiving step of receiving sensing information through a sensor of a railway vehicle in an autonomous driving situation, a TLC (Torpedo Ladle Car) presence determination step of determining whether a TLC exists using a TLC detection algorithm based on the sensing information, a TLC distance calculation step of calculating a distance to a TLC using a distance measurement algorithm based on the sensing information, a fastening recognition step of determining a TLC fastener fastening status using a fastener recognition algorithm based on the sensing information, and a speed control step of controlling the speed of the railway vehicle using three factors of whether a TLC exists, the distance to the TLC, and the TLC fastener fastening status.

[0009] According to the present embodiments, a railway vehicle control device and method for automatic TLC engagement during autonomous driving can be provided.

[0010] FIG. 1 is a drawing for explaining a railway vehicle control device according to one embodiment.

[0011] FIG. 2 is a drawing for explaining a sensor equipped in a railway vehicle according to one embodiment.

[0012] Figure 3 is a flowchart for explaining the operation of a TLC presence determination unit according to one embodiment.

[0013] Figure 4 is a flowchart for explaining the operation of a TLC distance calculation unit according to one embodiment.

[0014] Fig. 5 is a flowchart for explaining the operation of a fastening recognition unit according to one embodiment.

[0015] Fig. 6 is a flowchart for explaining the speed control operation of the speed control unit according to one embodiment.

[0016] Fig. 7 is a flowchart for explaining a railway vehicle control method according to one embodiment.

[0017] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to exemplary drawings. When adding reference numerals to components in each drawing, identical components may have the same numerals as much as possible even if they are shown in different drawings. In addition, when describing the present embodiments, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the technical idea of ​​the present invention, the detailed description may be omitted. When "includes," "has," "consists of," etc. are used in this specification, other parts may be added unless "only" is used. When a component is expressed in the singular, it may include a case in which the plural is included unless specifically stated otherwise.

[0018] Additionally, terms such as first, second, A, B, (a), (b), etc. may be used to describe components of the present disclosure. These terms are only intended to distinguish the components from other components, and the nature, order, sequence, or number of the components are not limited by the terms.

[0019] In a description of the positional relationship of components, when it is described that two or more components are "connected," "combined," or "connected," it should be understood that the two or more components may be directly "connected," "combined," or "connected," but that the two or more components may also be further "interposed" with another component to be "connected," "combined," or "connected." Here, the other component may be included in one or more of the two or more components that are "connected," "combined," or "connected" to each other.

[0020] In the description of the temporal flow relationship related to components, operation methods, or manufacturing methods, for example, when the temporal or flow relationship is described as “after”, “following”, “next to”, “before”, etc., it may also include cases where it is not continuous, unless “immediately” or “directly” is used.

[0021] Meanwhile, when numerical values ​​or corresponding information (e.g., levels, etc.) for components are mentioned, even without separate explicit description, the numerical values ​​or corresponding information may be interpreted as including an error range that may occur due to various factors (e.g., process factors, internal or external impact, noise, etc.).

[0022] It will be understood by those skilled in the art that the terms “learning,” “learning,” and “algorithm” appearing throughout the detailed description and claims of the present disclosure are terms that refer to algorithms that perform or can perform machine learning or deep learning through procedural computing, and are not intended to refer to mental operations such as human educational activities or models to which mental operations are applied.

[0023] In the present disclosure, a railway vehicle refers to a moving vehicle that travels on a railway. For example, a railway vehicle may refer to a locomotive. A railway vehicle refers to a moving vehicle that travels along a railway using power, and there are no restrictions on the method of power supply. For example, a railway vehicle according to the present disclosure may be powered not only by an internal combustion engine but also by electricity.

[0024] FIG. 1 is a drawing for explaining a railway vehicle control device according to one embodiment.

[0025] According to FIG. 1, a railway vehicle control device (100) may include a receiving unit (110) that receives sensing information through a sensor of a railway vehicle in an autonomous driving situation, a TLC (Torpedo Ladle Car) presence determination unit (120) that determines whether a TLC exists using a TLC detection algorithm based on the sensing information, a TLC distance calculation unit (130) that calculates a distance to a TLC using a distance measurement algorithm based on the sensing information, a fastener recognition unit (140) that determines a TLC fastener fastening state using a fastener recognition algorithm based on the sensing information, and a speed control unit (150) that controls the speed of the railway vehicle using three factors of whether a TLC exists, the distance to the TLC, and the TLC fastener fastening state.

[0026] The railway vehicle control device (100) may include a receiving unit (110) that receives sensing information through a sensor of the railway vehicle in an autonomous driving situation.

[0027] The sensors described in this embodiment refer to various types of sensors, and there is no limitation on the number of sensors. For example, the sensors may include cameras, radar, lidar, ultrasonic, infrared, and ultraviolet sensors. Alternatively, the sensors may include sensors that generate sensing information about the operation of a railway vehicle, such as speed sensors, motion detection sensors, acceleration sensors, and position detection sensors. Furthermore, an embodiment regarding the arrangement of sensors installed in a railway vehicle will be described later with reference to FIG. 2.

[0028] In addition, as an example, the sensing information may include video information or image information received from a camera sensor. As another example, the sensing information may include point information received from a position detection sensor. As another example, the sensing information may include point information received from a lidar sensor, which is a position detection sensor. As another example, the sensing information may include driving direction information of a railway vehicle received from GPS, navigation, etc. In addition, the sensing information may include various information received from sensors configured in the railway vehicle, such as side information, rear information, structure information, railway vehicle position information, and railway vehicle acceleration information.

[0029] Additionally, the receiver (110) can receive additional railway control information transmitted from the railway control. For example, the railway control information may include information on the railway vehicle's travel path and track information. When determining the presence of a TLC, the presence of a TLC in front of the railway vehicle can be used to determine this. Since railway vehicles can travel in both directions, determining the direction in which the front of the railway vehicle is set is important. Therefore, because the direction of the front of the railway vehicle may change depending on the travel path, information on the railway vehicle's travel path may be required.

[0030] The railway vehicle control device (100) may include a TLC (Torpedo Ladle Car) presence determination unit (120) that determines whether a TLC exists using a TLC detection algorithm based on sensing information.

[0031] Torpedo Ladle Cars (TLCs) are railway vehicles used to transport molten iron produced in steel mills, transporting it to the steel mill. In conventional railway vehicles, the driver manually controls the TLC locking mechanism. However, autonomous railway vehicles may operate without a driver, requiring automatic locking of the TLC and the rail vehicle. Therefore, the first step in automatically locking the TLC and rail vehicle locking mechanism is to determine whether a TLC is present at the front of the rail vehicle. The following example describes the process of determining whether a TLC is present at the front of the rail vehicle.

[0032] For example, a TLC detection algorithm can be set to preprocess image information included in sensing information to extract image feature information, input the image feature information as an input value of a pre-learned artificial intelligence algorithm, and obtain the presence or absence of the TLC as an output value.

[0033] For example, Backbone can be used to preprocess image information. Image feature information applied with Backbone can include high-dimensional information for recognizing object shape, size, color, and location. As another example, the pre-trained AI algorithm can be a CNN-based AI algorithm. Examples include Yolox and Yolov7. As another example, the presence of a TLC can include two-dimensional location information. The TLC detection algorithm is described in detail below using Figure 3.

[0034] The railway vehicle control device (100) may include a TLC distance calculation unit (130) that calculates a distance to a TLC using a distance measurement algorithm based on sensing information.

[0035] For example, if the TLC presence determination unit (120) determines that a TLC does not exist, the TLC distance calculation unit (130) may not perform an operation of calculating a distance to the TLC. In addition, if the TLC presence determination unit (120) determines that a TLC exists, the TLC distance calculation unit (130) may perform an operation of calculating a distance to the TLC. For convenience of explanation, the operation of the TLC distance calculation unit (130) is described under the assumption that a TLC exists.

[0036] For example, the TLC distance calculation unit (130) can calculate the distance to a TLC existing ahead based on sensing information. As described above, the direction of the railway vehicle can be determined based on the direction of travel of the railway vehicle, and the same direction as the direction of travel of the railway vehicle can be set as the front.

[0037] For example, a distance measurement algorithm can set a point detection area based on point information included in sensing information, and calculate a distance to a TLC based on point information included in the point detection area.

[0038] For example, point information included in the sensing information may include information about a point cloud received via a lidar sensor. Furthermore, the point information may include information including a three-dimensional coordinate system. Thus, when the position of the TLC is calculated in a three-dimensional coordinate system, the distance to the TLC relative to the position of the railway vehicle can be calculated. As another example, the point detection area may be preset, multiple points may be set, or may be set based on the operating speed of the railway vehicle. The area size may be set in various ways, and there are no restrictions on the setting method. A more detailed description of the distance measurement algorithm will be described later with reference to FIG. 4.

[0039] The railway vehicle control device (100) may include a fastener recognition unit (140) that determines the TLC fastener fastening status using a fastener recognition algorithm based on sensing information.

[0040] For example, a fastener recognition algorithm can determine a TLC fastener fastening state by setting a fastener area based on image information included in sensing information and classifying the fastening state of the fastener based on image information converted from the image information existing in the fastener area.

[0041] For example, the fastener recognition algorithm can set the fastener area based on image information. Furthermore, the fastener area can be preset in the direction illuminated by the camera sensor that senses the image information. Furthermore, the size of the fastener area can be preset or varied depending on weather conditions and external circumstances. This embodiment is not limited thereto. A more detailed description of the fastener recognition algorithm will be provided below with reference to FIG. 5.

[0042] As another example, the fastening recognition unit (140) can classify the fastening state of the fastener and determine the fastening state of the TLC fastener. The fastening state of the fastener can be determined based on image information as being fastened or released. If the fastener is safely fastened, the TLC can be safely transported. However, if the fastener is released, the railway vehicle control device (100) can additionally perform a speed control operation, which will be described later, to fasten the fastener. Therefore, it is necessary to determine the fastening state of the fastener for railway vehicle speed control.

[0043] The railway vehicle control device (100) may include a speed control unit (150) that controls the speed of the railway vehicle by using three factors: the presence of a TLC, the distance to the TLC, and the TLC fastener fastening status.

[0044] The reason for using the presence of a TLC to control the speed of a railway vehicle is that if there is no TLC ahead, the TLC fastener of the railway vehicle does not need to engage. In addition, the reason for using the distance to the TLC is because the distance to the TLC must be calculated so that the relative and absolute speeds of the railway vehicle with respect to the TLC can be calculated, and the speed of the railway vehicle can be controlled to engage the TLC. In addition, the reason for using the TLC fastener engagement status is to control the speed of the railway vehicle to be as low as possible and to engage the fastener if the fastener is in the disengaged state.

[0045] For example, the speed control unit (150) can control the speed of the railway vehicle to the first speed if it is determined that the TLC does not exist in front of the railway vehicle based on the presence or absence of the TLC.

[0046] For example, if the speed control unit (150) determines that a TLC exists in front of the railway vehicle based on the presence or absence of a TLC, it can control the speed of the railway vehicle by comparing the distance to the TLC with a safe distance.

[0047] For example, the speed control unit (150) can control the speed of the railway vehicle to a second speed when the distance to the TLC is greater than the safe distance.

[0048] As another example, the speed control unit (150) can control the speed of the railway vehicle to a third speed if it is determined that the front TLC is not engaged based on the TLC fastener engagement status when the distance to the TLC is less than a safe distance.

[0049] As another example, the speed control unit (150) can control the speed of the railway vehicle to a fourth speed if it is determined that the TLC in front has been engaged based on the TLC fastener engagement status when the distance to the TLC is less than a safe distance.

[0050] The aforementioned first, second, third, and fourth speeds can be preset to decrease in sequence. Furthermore, the first speed can be preset to the speed of the railway vehicle when there is no TLC ahead, and the fourth speed can be preset to 0 km / h, which corresponds to a stationary state. However, speeds can be preset without being limited to the aforementioned speeds. A more detailed explanation will be provided later with reference to Fig. 6.

[0051] The embodiments are described in detail with reference to the drawings below.

[0052] FIG. 2 is a drawing for explaining a sensor equipped in a railway vehicle according to one embodiment.

[0053] Referring to FIG. 2, a railway vehicle may include one or more image sensors (210, 230, 240, 260) and one or more position detection sensors (220, 250). The reason why one or more image sensors (210, 230, 240, 260) and one or more position detection sensors (220, 250) are attached to one side of the railway vehicle and the opposite side of the one side is that the forward position can be set according to the direction of travel of the railway vehicle. Therefore, sensing information can be collected and received by a receiving unit using the image sensor and the position detection sensor in the direction set to the forward direction.

[0054] For example, one or more image sensors (210, 230, 240, 260) may include a camera sensor. The image sensors (210, 240) are positioned facing forward to determine whether a TLC is present in front, and the image sensors (210, 240) can receive image information collected from the front to a receiving unit. The image sensors (230, 250) are required to determine the fastening status of the fastener, and the image sensors (230, 260) may be positioned in the direction of the fastener.

[0055] For example, the position detection sensor (220, 250) may include a lidar sensor, a radar sensor, an ultraviolet sensor, an infrared sensor, or an ultrasonic sensor. The position detection sensor (220, 250) is required to calculate the distance between the TLC and the railway vehicle, and may be placed on one side and the opposite side of the railway vehicle. In addition, the position detection sensor (220, 250) may receive point information in the form of a point cloud.

[0056] The arrangement and function of one or more image sensors (210, 230, 240, 260) and position detection sensors (220, 250) are not limited to the present embodiment and can be set in various ways.

[0057] Figure 3 is a flowchart for explaining the operation of a TLC presence determination unit according to one embodiment.

[0058] Referring to FIG. 3, the TLC presence determination unit can calculate the distance to the TLC using a distance measurement algorithm based on the sensing information. In this case, the TLC detection algorithm can be configured to preprocess the image information included in the sensing information to extract image feature information, input the image feature information as an input value to a pre-trained artificial intelligence algorithm, and obtain the presence or absence of the TLC as an output value.

[0059] The receiving unit can receive sensing information. (S310) The TLC presence determination unit can extract image feature information by preprocessing the image information included in the received sensing information using a TLC detection algorithm. (S320) For example, the process of preprocessing the image information and extracting image feature information is as follows. The image information extracted from the image information is converted into a two-dimensional coordinate system, the converted image information is expressed as a pixel value, the size is adjusted, and normalization is performed. Through this process, the image information can be preprocessed and extracted as image feature information. In addition, Backbone can be used to preprocess the image information. The image feature information to which Backbone is applied can include high-dimensional information for recognizing the shape, size, color, position, etc. of an object. Networks that can be used as Backbone include ResNet, Darknet, and CSPDarknet networks set based on CNN (Convolutional Neural Networks). However, various networks can be used in addition to the network described in this embodiment.

[0060] The TLC presence determination unit can determine whether a TLC exists by inputting image feature information as input values ​​of a pre-learned artificial intelligence algorithm using a TLC detection algorithm and obtaining the presence of the TLC as an output value. (S330)

[0061] The pre-trained artificial intelligence algorithm can be configured to obtain the presence or absence of a TLC as an output value by calculating a probability value using an FPN (Feature Pyramid Network) and a PANet (Path Aggregation Network) network based on image feature information. In addition, the presence or absence of a TLC can include two-dimensional location information. The two-dimensional location information can include coordinates of the horizontal axis, vertical axis, height, and width. However, the information included in the presence or absence of a TLC is not limited to this embodiment and can include various types of information.

[0062] Additionally, the TLC detection algorithm can be generated based on Yolox, a CNN-based artificial intelligence algorithm, as well as a combination of the aforementioned networks. However, this is not limited to the present embodiment and various algorithms can be used.

[0063] Figure 4 is a flowchart for explaining the operation of a TLC distance calculation unit according to one embodiment.

[0064] According to FIG. 4, the TLC distance calculation unit can set a point detection area based on point information included in sensing information, and calculate a distance to the TLC based on the point information included in the point detection area.

[0065] The receiving unit can receive sensing information. (S410) For example, the sensing information can include information received from a lidar sensor, a laser sensor, etc. In addition, the point information included in the sensing information can include information about a point cloud. In addition, the point information can include information including a three-dimensional coordinate system. Through this, when the position of the TLC is calculated in a three-dimensional coordinate system, the distance to the TLC can be calculated in comparison with the position of the railway vehicle.

[0066] The TLC distance calculation unit can set a point detection area based on point information included in the received sensing information using a distance measurement algorithm. (S420)

[0067] For example, point detection areas can be preset, multiple areas can be set, and areas can be set based on the operating speed of the railway vehicle. Area sizes can also be varied. Furthermore, a minimum area ratio for the point detection area can be preset to filter out obstacles other than TLCs. However, this is not limited to the present embodiment, and point detection areas can be varied.

[0068] The TLC distance calculation unit can calculate the distance to the TLC based on point information included in the point detection area using a distance measurement algorithm. (S430)

[0069] For example, point information included in a point detection area may include information including a coordinate system in dimensional format. Accordingly, based on point information including a coordinate system, the position information of the TLC can be calculated in a coordinate system, and the distance to the TLC can be calculated using the position coordinates of the railway vehicle.

[0070] Fig. 5 is a flowchart for explaining the operation of a fastening recognition unit according to one embodiment.

[0071] The fastener recognition unit can determine the TLC fastener fastening status using a fastener recognition algorithm based on sensing information.

[0072] The receiver can receive sensing information (S510). The sensing information may include image information. For example, fasteners may be positioned on one side and the other side of the railway vehicle. Furthermore, the fasteners may be selected based on the direction of travel of the railway vehicle. Furthermore, the image information may include information received through a camera sensor positioned toward the corresponding fastener.

[0073] The fastener recognition unit can set the fastener area based on the image information included in the sensing information using a fastener recognition algorithm (S520). The fastener area can be set with a certain offset based on the image information. The fastener area can also be set in advance. The fastener area is not limited to the present embodiment and can be set in various ways.

[0074] The fastener recognition unit can classify the fastening state of the fastener based on image information converted from image information existing in the fastener area using a fastener recognition algorithm. (S530) A pre-trained artificial intelligence algorithm can be used to classify the fastening state of the fastener. There is no limitation on the pre-trained artificial intelligence algorithm as long as it is an algorithm that classifies and recognizes specific information based on given image information. For example, it can be a CNN-based artificial intelligence algorithm. In addition, AlexNet, ResNet34, GoogLeNet, VGG, etc. can be used as examples.

[0075] The fastening recognition unit can determine the TLC fastener state using the classified result values ​​of the fastening state of the fastener. (S540) The TLC fastener state can be determined as one of the fastening state and the releasing state. However, the TLC fastener state is not limited to the present embodiment and can be determined in various ways.

[0076] Fig. 6 is a flowchart for explaining the speed control operation of the speed control unit according to one embodiment.

[0077] The speed controller can control the speed of a railway vehicle using three factors: the presence of a TLC, the distance to the TLC, and the TLC fastener engagement status. All three factors can be used to control the speed of a railway vehicle, but they can also be used independently. For convenience, the control operation of the speed controller, in which all three factors are linked, is described.

[0078] The speed control unit can control the speed of the railway vehicle to the first speed if it is determined that the TLC does not exist in front of the railway vehicle. (S610)

[0079] For example, the need to slow down a railway vehicle may be reduced because it may be determined that there is no fastener that the railway vehicle needs to engage. Therefore, the first speed may be preset to the average speed of the railway vehicle in situations where there is no TLC ahead. However, the first speed is not limited to this embodiment and may be set to various speeds.

[0080] The speed control unit, if it determines that a tracked traction control (TLC) exists ahead of the railway vehicle, can control the speed of the railway vehicle by comparing the distance to the TLC with the safe distance. If the distance to the TLC is greater than the safe distance, the speed control unit can control the speed of the railway vehicle to a second speed. Furthermore, if the distance to the TLC is less than the safe distance, the speed control unit can determine the TLC fastener engagement status. (S620)

[0081] For example, if a TLC exists ahead but the distance to the TLC is greater than the safe distance, the second speed can be controlled to a speed lower than the first speed. The speed can be reduced or maintained at the same speed to reduce the distance between the rail vehicle and the TLC to a point where they can engage. However, the second speed is not limited to this embodiment and can be set to various speeds.

[0082] For example, if a TLC exists ahead but the distance to the TLC is less than the safe distance, the TLC fastener engagement status can be determined. If the distance to the TLC is determined to be less than the safe distance, it can be determined that a safe distance has been secured for the TLC to be engaged with the railway vehicle. Therefore, the TLC fastener engagement status can be determined to determine whether the fastener is engaged or disengaged, allowing for additional speed control.

[0083] The speed control unit may control the speed of the railway vehicle to a third speed if it determines that a TLC exists in front of the railway vehicle, that the distance to the TLC is less than a safe distance, and that the front TLC is not engaged. (S630)

[0084] For example, if it is determined that the forward TLC has not been engaged, the third speed may be set to a speed lower than the second speed. In this case, the forward TLC and the railway vehicle may be in close proximity, but the fastener may not be engaged. Therefore, the third speed may be set to a speed lower than the second speed to ensure that the fastener is engaged. Furthermore, the third speed may be set to a speed that exceeds the fourth speed described below, but is not significantly different from the fourth speed.

[0085] The speed control unit (150) can control the speed of the railway vehicle to a fourth speed if it is determined that a TLC exists in front of the railway vehicle, and if it is determined that the distance to the TLC is less than a safe distance and that the railway vehicle is engaged with the TLC in front. (S640)

[0086] For example, the fourth speed may be set to 0 km / h and considered stationary. In this case, the fastener may be considered engaged. Furthermore, the TLC and the railway vehicle may remain stationary to perform the next operation.

[0087] For example, the first to fourth speeds may be set as relative speeds of the TLC and the railway vehicle rather than as absolute speeds as described above.

[0088] The first to fourth speeds described above are not limited to the present embodiment and can be set.

[0089] Fig. 7 is a flowchart for explaining a railway vehicle control method according to one embodiment.

[0090] According to FIG. 7, a railway vehicle control method may include a receiving step for receiving sensing information through a sensor of a railway vehicle in an autonomous driving situation, a TLC presence determination step for determining whether a TLC (Torpedo Ladle Car) exists using a TLC detection algorithm based on the sensing information, a TLC distance calculation step for calculating a distance to a TLC using a distance measurement algorithm based on the sensing information, a fastening recognition step for determining a TLC fastener fastening status using a fastener recognition algorithm based on the sensing information, and a speed control step for controlling the speed of the railway vehicle using three factors of whether a TLC exists, the distance to the TLC, and the TLC fastener fastening status.

[0091] The railway vehicle control method may include a receiving step for receiving sensing information through a sensor of the railway vehicle in an autonomous driving situation. (S710)

[0092] The sensors described in this embodiment refer to various types of sensors, and their number is not limited. For example, the sensors may include cameras, radar, lidar, ultrasonic, infrared, and ultraviolet sensors. Alternatively, the sensors may include sensors that generate sensing information about the operation of a railway vehicle, such as speed sensors, motion detection sensors, acceleration sensors, and position detection sensors.

[0093] In addition, as an example, the sensing information may include video information or image information received from a camera sensor. As another example, the sensing information may include point information received from a position detection sensor. As another example, the sensing information may include point information received from a lidar sensor, which is a position detection sensor. As another example, the sensing information may include driving direction information of a railway vehicle received from GPS, navigation, etc. In addition, the sensing information may include various information received from sensors configured in the railway vehicle, such as side information, rear information, structure information, railway vehicle position information, and railway vehicle acceleration information.

[0094] Additionally, the receiving stage can receive additional railway control information transmitted from the railway control center. For example, railway control information may include information on the railway vehicle's travel path and track information. When determining the presence of a TLC, the presence of a TLC in front of the railway vehicle can be used as a basis. Since railway vehicles can travel in both directions, determining the direction in which the front of the vehicle is set is crucial. Therefore, because the direction of the front of a railway vehicle can change depending on the travel path, information on the railway vehicle's travel path may be necessary.

[0095] The railway vehicle control method may include a TLC presence determination step for determining the presence of a TLC using a TLC detection algorithm based on sensing information. (S720)

[0096] Torpedo Ladle Cars (TLCs) are railway vehicles used to transport molten iron produced in steel mills, transporting it to the steel mill. In conventional railway vehicles, the driver manually controls the TLC locking mechanism. However, autonomous railway vehicles may operate without a driver, requiring automatic locking of the TLC and the rail vehicle. Therefore, the first step in automatically locking the TLC and rail vehicle locking mechanism is to determine whether a TLC is present at the front of the rail vehicle. The following example describes the process of determining whether a TLC is present at the front of the rail vehicle.

[0097] For example, a TLC detection algorithm can be set to preprocess image information included in sensing information to extract image feature information, input the image feature information as an input value of a pre-learned artificial intelligence algorithm, and obtain the presence or absence of the TLC as an output value.

[0098] For example, Backbone can be used to preprocess image information. Image feature information applied with Backbone can include high-dimensional information for recognizing object shape, size, color, and location. As another example, the pre-trained AI algorithm can be a CNN-based AI algorithm. Examples include Yolox and Yolov7. As another example, determining the presence of a TLC can include two-dimensional location information.

[0099] The railway vehicle control method may include a TLC distance calculation step of calculating a distance to a TLC using a distance measurement algorithm based on sensing information. (S730)

[0100] For example, if the TLC presence determination step determines that the TLC does not exist, the TLC distance calculation step may not perform the operation of calculating the distance to the TLC. Furthermore, if the TLC presence determination step determines that the TLC exists, the TLC distance calculation step may perform the operation of calculating the distance to the TLC. For convenience of explanation, the TLC distance calculation step is described under the assumption that the TLC exists.

[0101] For example, the TLC distance calculation step can calculate the distance to a TLC ahead based on sensing information. As described above, the direction of the railway vehicle can be determined based on the direction of travel of the railway vehicle, and the direction identical to the direction of travel of the railway vehicle can be set as the forward direction.

[0102] For example, a distance measurement algorithm can set a point detection area based on point information included in sensing information, and calculate a distance to a TLC based on point information included in the point detection area.

[0103] For example, point information included in the sensing information may include information about a point cloud received via a lidar sensor. Furthermore, the point information may include information including a three-dimensional coordinate system. Thus, when the position of the TLC is calculated in a three-dimensional coordinate system, the distance to the TLC relative to the position of the railway vehicle can be calculated. As another example, the point detection area may be preset, multiple points may be set, or may be set based on the operating speed of the railway vehicle. The area size may be set in various ways, and there are no restrictions on the setting method.

[0104] The railway vehicle control method may include a fastening recognition step for determining the fastening status of a TLC fastener using a fastener recognition algorithm based on sensing information. (S740)

[0105] For example, a fastener recognition algorithm can determine a TLC fastener fastening state by setting a fastener area based on image information included in sensing information and classifying the fastening state of the fastener based on image information converted from the image information existing in the fastener area.

[0106] For example, a fastener recognition algorithm can set a fastener area based on image information. Furthermore, the fastener area can be preset in the direction illuminated by a camera sensor that senses the image information. Furthermore, the size of the fastener area can be preset or varied depending on weather conditions and external circumstances. This embodiment is not limited thereto.

[0107] As another example, the fastening recognition step can classify the fastening state of the fastener to determine the fastening state of the TLC fastener. The fastening state of the fastener can be determined based on image information, whether it is fastened or released. If the fastener is securely fastened, the TLC can be safely transported. However, if the fastener is released, the railway vehicle control method may additionally perform a speed control operation, described later, to fasten the fastener. Therefore, determining the fastening state of the fastener is necessary for railway vehicle speed control.

[0108] The railway vehicle control method may include a speed control step for controlling the speed of the railway vehicle using three factors: the presence of a TLC, the distance to the TLC, and the TLC fastener fastening status. (S750)

[0109] The reason for using the presence of a TLC to control the speed of a railway vehicle is that if there is no TLC ahead, the TLC fastener of the railway vehicle does not need to engage. In addition, the reason for using the distance to the TLC is because the distance to the TLC must be calculated so that the relative and absolute speeds of the railway vehicle with respect to the TLC can be calculated, and the speed of the railway vehicle can be controlled to engage the TLC. In addition, the reason for using the TLC fastener engagement status is to control the speed of the railway vehicle to be as low as possible and to engage the fastener if the fastener is in the disengaged state.

[0110] For example, the speed control step may control the speed of the railway vehicle to a first speed if it is determined that no TLC exists in front of the railway vehicle based on the presence or absence of a TLC.

[0111] For example, the speed control step can control the speed of the railway vehicle by comparing the distance to the TLC with the safety distance when it is determined that a TLC exists in front of the railway vehicle based on the presence or absence of a TLC.

[0112] For example, the speed control step can control the speed of the railway vehicle to a second speed if the distance to the TLC is greater than the safe distance.

[0113] As another example, the speed control step may control the speed of the railway vehicle to a third speed if it is determined that the front TLC is not engaged based on the TLC fastener engagement status when the distance to the TLC is less than a safe distance.

[0114] As another example, the speed control step may control the speed of the railway vehicle to a fourth speed if it is determined that the railway vehicle has been engaged with the TLC in front based on the engagement status of the TLC fastener when the distance to the TLC is less than a safe distance.

[0115] The first, second, third, and fourth speeds described above may be preset to decrease in sequence. Furthermore, the first speed may be preset to the speed of the railway vehicle when there is no TLC ahead, and the fourth speed may be preset to 0 km / h, which corresponds to a stationary state. However, speeds may be preset without being limited to the aforementioned speeds.

[0116] As described above, the railway vehicle control device and method according to the present disclosure can provide a function capable of controlling automatic engagement of a forward TLC with an autonomously running railway vehicle.

[0117] The algorithms described above can be used in various ways depending on the operator's choice, in addition to the above-described model.

[0118] The railway vehicle control device (100) may be configured as a computing system or as a GPU server equipped with a GPU processor and general memory, but the present embodiments are not limited thereto.

[0119] The railway vehicle control device (100) may be implemented by a computing device including at least some of a processor, a memory, a user input device, and a presentation device. The memory is a medium that stores computer-readable software, applications, program modules, routines, instructions, and / or data, etc., which are coded to perform a specific task when executed by the processor. The processor can read and execute the computer-readable software, applications, program modules, routines, instructions, and / or data stored in the memory. The user input device may be a means for allowing a user to input a command to cause the processor to perform a specific task or to input data necessary for the execution of a specific task. The user input device may include a physical or virtual keyboard or keypad, key buttons, a mouse, a joystick, a trackball, a touch-sensitive input device, or a microphone. The presentation device may include a display, a printer, a speaker, or a vibration device.

[0120] Computing devices can include a variety of devices, including smartphones, tablets, laptops, desktops, servers, and clients. A computing device may be a single, standalone device, or it may include multiple computing devices operating in a distributed environment, each of which collaborates with another through a communications network.

[0121] In addition, the aforementioned railway vehicle control device (100) can be executed by a computing device having a processor and a memory storing computer-readable software, applications, program modules, routines, instructions, and / or data structures coded to perform an image classification method utilizing a deep learning model when executed by the processor.

[0122] The artificial intelligence model described in these embodiments may be a current or future machine learning model, such as a model that performs algorithm-based machine learning operating on the aforementioned computing device or a model that performs artificial neural network-based learning.

[0123] Models that perform algorithm-based machine learning can be classical machine learning models such as tree-based models, k-Nearest Neighbors, k-Means Clustering, Principal Component Analysis (PCA), and support vector machines (SVM).

[0124] A tree-based model can be, for example, a decision tree model, a regression model, or a random tree model.

[0125] Meanwhile, an artificial intelligence model can be an ensemble model that solves problems by training and combining multiple models rather than using just one trained model.

[0126] Ensemble models combine multiple individually trained models to prevent overfitting and improve generalization performance. Ensemble models can be helpful in improving performance when the performance of individual models is not sufficient.

[0127] Ensemble models can be broadly divided into voting and boosting methods.

[0128] Voting methods derive a final result through voting on the results generated by multiple models. Examples include bagging, which combines algorithms of the same type but trains them on different data sets, and voting, which combines different types of algorithms.

[0129] Boosting is a method of combining weak machine learning models to create a more accurate and powerful model. Boosting involves sequentially performing tasks on each weak machine learning model, with subsequent models exploring additional areas missed by the previous models. Examples of boosting methods include random forests, gradient boosting, and XGBoost (eXtra Gradient Boost).

[0130] An artificial neural network (ANN) is a machine learning algorithm that analyzes and learns complex data based on a large number of interconnected artificial neurons, mimicking the operating principles of the human brain. An ANN can be any type of ANN, including the multilayer perceptron (MLP), the most basic ANN structure consisting of an input layer, a hidden layer, and an output layer; a convolutional neural network (CNN), which performs convolution operations to extract image features and reduces dimensionality through pooling operations; and a recurrent neural network (RNN), an ANN structure used to process ordered data. These ANNs can be modified in various ways depending on the complexity and diversity of the data.

[0131] A model that has undergone learning based on an artificial neural network can also be an ensemble model that solves problems by learning multiple models and combining them rather than learning just one model.

[0132] Meanwhile, algorithm-based machine learning models and models trained using artificial neural networks can be used complementarily. For example, an algorithm-based machine learning model can use the results of an artificial neural network-based model, and vice versa. An ensemble model combining algorithm-based machine learning models and artificial neural network-based models can also be used.

[0133] The embodiments described above may be implemented through various means. For example, the embodiments may be implemented through hardware, firmware, software, or a combination thereof.

[0134] In the case of hardware implementation, the railway vehicle control method according to the present embodiments may be implemented by one or more ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), DSPDs (Digital Signal Processing Devices), PLDs (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), processors, controllers, microcontrollers, or microprocessors.

[0135] For example, the railway vehicle control method according to the embodiments can be implemented using an artificial intelligence semiconductor device in which neurons and synapses of a deep neural network are implemented using semiconductor devices. In this case, the semiconductor devices may be currently used semiconductor devices, such as SRAM, DRAM, NAND, etc., or may be next-generation semiconductor devices, such as RRAM, STT MRAM, PRAM, etc., or may be a combination thereof.

[0136] When implementing a railway vehicle control method according to embodiments using an artificial intelligence semiconductor device, the results (weights) of learning a deep learning model using software may be transferred to synapse-mimetic elements arranged in an array, or learning may be performed in the artificial intelligence semiconductor device.

[0137] When implemented using firmware or software, the railway vehicle control method according to the present embodiments may be implemented in the form of a device, procedure, or function that performs the functions or operations described above. The software code may be stored in a memory unit and executed by a processor. The memory unit may be located within or outside the processor and may exchange data with the processor using various known means.

[0138] Additionally, terms such as "system," "processor," "controller," "component," "module," "interface," "model," or "unit" as described above may generally refer to a computer-related entity, such as hardware, a combination of hardware and software, software, or software in execution. For example, the aforementioned components may be, but are not limited to, a process driven by a processor, a processor, a controller, a control processor, an object, a thread of execution, a program, and / or a computer. For example, both an application running on a controller or a processor and the controller or the processor may be components. One or more components may be within a process and / or thread of execution, and the components may be located on a single device (e.g., a system, a computing device, etc.) or distributed across two or more devices.

[0139] The above description is merely an illustrative example of the technical idea of ​​the present disclosure, and those skilled in the art to which the present disclosure pertains will appreciate that various modifications and variations can be made without departing from the essential characteristics of the technical idea of ​​the present disclosure. In addition, the present embodiments are not intended to limit the technical idea of ​​the present disclosure but rather to explain it, and therefore the scope of the technical idea of ​​the present disclosure is not limited by these embodiments. The scope of protection of the present disclosure should be interpreted by the claims below, and all technical ideas within a scope equivalent thereto should be interpreted as being included within the scope of the rights of the present disclosure.

[0140]

[0141] CROSS-REFERENCE TO RELATED APPLICATION

[0142] This patent application claims priority under 35 USC § 119(a) to Korean Patent Application No. 10-2023-0183733, filed December 15, 2023, the entire contents of which are incorporated herein by reference. Furthermore, this patent application claims priority in countries other than the United States for the same reasons, the entire contents of which are incorporated herein by reference.

Claims

1. A receiving unit that receives sensing information through a sensor of a railway vehicle in an autonomous driving situation; A TLC presence determination unit that determines whether a TLC (Torpedo Ladle Car) exists using a TLC detection algorithm based on the above sensing information; A TLC distance calculation unit that calculates the distance to the TLC using a distance measurement algorithm based on the above sensing information; A fastener recognition unit that determines the TLC fastener fastening status using a fastener recognition algorithm based on the above sensing information; and A speed control unit that controls the speed of the railway vehicle by using three factors: presence or absence of the TLC, distance to the TLC, and TLC fastener fastening status; A railway vehicle control device including a .

2. In paragraph 1, The above TLC detection algorithm is, A railway vehicle control device configured to preprocess image information included in the above sensing information to extract image feature information, input the image feature information as an input value of a pre-learned artificial intelligence algorithm, and obtain the presence or absence of the TLC as an output value.

3. In paragraph 1, The above distance measurement algorithm is, A railway vehicle control device that sets a point detection area based on point information included in the above sensing information, and calculates a distance to the TLC based on the point information included in the point detection area.

4. In paragraph 1, The above-mentioned fastener recognition algorithm is, A railway vehicle control device that sets a fastener area based on image information included in the sensing information, classifies the fastening state of the fastener based on image information converted from the image information existing in the fastener area, and determines the fastening state of the TLC fastener.

5. In paragraph 1, The above speed control unit, A railway vehicle control device that controls the speed of the railway vehicle to a first speed when it is determined that the TLC does not exist in front of the railway vehicle based on the presence or absence of the TLC.

6. In paragraph 1, The above speed control unit, A railway vehicle control device that controls the speed of the railway vehicle by comparing the distance to the TLC with a safe distance when it is determined that the TLC exists in front of the railway vehicle based on the presence or absence of the TLC.

7. In paragraph 6, The above speed control unit, A railway vehicle control device that controls the speed of the railway vehicle to a second speed when the distance to the above TLC is greater than the above safety distance.

8. In paragraph 6, The above speed control unit, A railway vehicle control device that controls the speed of the railway vehicle to a third speed when it is determined that the front TLC is not engaged based on the engagement status of the TLC fastener when the distance to the TLC is less than the safe distance.

9. In paragraph 6, The above speed control unit, A railway vehicle control device that controls the speed of the railway vehicle to a fourth speed when it is determined that the TLC in front has been fastened based on the fastening status of the TLC fastener when the distance to the TLC is less than the safe distance.

10. A receiving step for receiving sensing information through a sensor of a railway vehicle in an autonomous driving situation; A TLC presence determination step for determining whether a TLC (Torpedo Ladle Car) exists using a TLC detection algorithm based on the above sensing information; A TLC distance calculation step for calculating a distance to a TLC using a distance measurement algorithm based on the above sensing information; A fastening recognition step for determining the TLC fastener fastening status using a fastener recognition algorithm based on the above sensing information; and A speed control step for controlling the speed of the railway vehicle by using three factors: presence or absence of the TLC, distance to the TLC, and TLC fastener fastening status; A railway vehicle control method comprising:

11. In Article 10, The above TLC detection algorithm is, A railway vehicle control method configured to preprocess image information included in the above sensing information to extract image feature information, input the image feature information as an input value of a pre-learned artificial intelligence algorithm, and obtain the presence or absence of the TLC as an output value.

12. In paragraph 10, The above distance measurement algorithm is, A railway vehicle control method for setting a point detection area based on point information included in the above sensing information, and calculating a distance to the TLC based on the point information included in the point detection area.

13. In paragraph 10, The above-mentioned fastener recognition algorithm is, A railway vehicle control method for determining a fastening state of a TLC fastener by setting a fastening area based on image information included in the sensing information, and classifying the fastening state of the fastener based on image information converted from the image information existing in the fastening area.

14. In paragraph 10, The above speed control step is, A railway vehicle control method for controlling the speed of the railway vehicle to a first speed when it is determined that the TLC does not exist in front of the railway vehicle based on the presence or absence of the TLC.

15. In paragraph 10, The above speed control step is, A railway vehicle control method for controlling the speed of the railway vehicle by comparing the distance to the TLC and a safe distance when it is determined that the TLC exists in front of the railway vehicle based on the presence or absence of the TLC.

16. In paragraph 15, The above speed control step is, A railway vehicle control method for controlling the speed of the railway vehicle to a second speed when the distance to the above TLC is greater than the above safe distance.

17. In paragraph 15, The above speed control step is, A railway vehicle control method for controlling the speed of the railway vehicle to a third speed when it is determined that the front TLC is not engaged based on the engagement status of the TLC fastener when the distance to the TLC is less than the safe distance.

18. In paragraph 15, The above speed control step is, A railway vehicle control method for controlling the speed of the railway vehicle to a fourth speed when it is determined that the TLC in front has been fastened based on the fastening status of the TLC fastener when the distance to the TLC is less than the safe distance.

Images