Rail locomotive control method and system and electronic equipment

Abstract

The invention relates to the technical field of rail locomotive control scheme design, in particular to a rail locomotive control method and system and electronic equipment. Comprising the steps of shooting a visual image of a target area by using a visual camera arranged in front of the rail locomotive; collecting point cloud information of the target area by using a laser radar arranged in front of the rail locomotive; the visual image and the point cloud information of the target area are processed, the opening and closing state of a turnout of the target area is recognized, and the state information of traffic lights is obtained; if the opening and closing state of the turnout and the state information of the traffic light meet the passing conditions, controlling the rail locomotive to pass through the turnout; and if the opening and closing state of the turnout or the state information of the traffic light does not conform to the passing condition, outputting alarm information about that the opening and closing state of the turnout or the state information of the traffic light does not conform to the passing condition. And a deep learning model for visual and laser radar feature extraction is combined, so that turnout identification with higher precision is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of rail locomotive control scheme design, and in particular to a rail locomotive control method and system, and electronic equipment. Background Art

[0002] In the rail transportation industry, the locomotive needs to confirm when passing through the switch, and sometimes two drivers need to confirm at the same time. That is, the driver is located in the driver's cab at the front and rear ends of the locomotive to manually control the acceleration, deceleration, parking, switch switching, damper opening and other actions of the rail locomotive, which leads to a large number of workers in the auxiliary transportation system, high labor intensity for the drivers, and the possibility of unsafe accidents during transportation and driving.

[0003] Therefore, the prior art needs to be further developed. Summary of the invention

[0004] The purpose of the present invention is to overcome the above technical deficiencies and provide a rail vehicle control method and system, and electronic equipment to solve the problems existing in the prior art.

[0005] To achieve the above technical objectives, according to a first aspect of the present invention, the present invention provides a railway locomotive control method, comprising: S100, using a visual camera disposed in front of the rail vehicle to capture a visual image of the target area; The laser radar installed in front of the rail vehicle is used to collect point cloud information of the target area; S200, respectively processing the visual image and point cloud information of the target area, identifying the opening and closing status of the turnout in the target area, and obtaining the status information of the traffic light; S300. If the opening and closing status of the turnout and the status information of the traffic light meet the conditions for passage, control the rail locomotive to pass the turnout; if the opening and closing status of the turnout or the status information of the traffic light do not meet the conditions for passage, output an alarm message indicating that the opening and closing status of the turnout or the status information of the traffic light do not meet the conditions for passage.

[0006] Specifically, the processing of the image and point cloud information of the target area respectively to identify the opening and closing state of the turnout and the traffic light state of the target area includes: Apply a 3×3 convolution kernel K to perform a convolution operation on the visual image: Xconv =Conv(I,K); Among them, the convolution kernel K is a weight matrix, and the local features of the turnout in the image are extracted through multi-layer convolution. Xconv represents the result of convolution, Conv represents the convolution function, and I represents the visual image; Residual connections are used to solve the gradient vanishing problem and optimize network training: Yrcs=Xconv+F(Xconv,W); Where F represents the combination of convolution operation and activation function, W is the weight matrix; Xconv represents the result of convolution, and Yrcs represents the result of residual operation; The high-level features of the turnout image are extracted through multiple convolutional layers, and the feature map F is finally output. image , represents the spatial and structural information of the turnout in the image: F image =ResNet(I); Among them, ResNet represents the ResNet network, and I represents the visual image.

[0007] Specifically, the processing of the image and point cloud information of the target area respectively to identify the opening and closing state of the turnout and the traffic light state of the target area includes: Input point cloud data P={p1,p2,…,p n}∈R n×3 , where n is the number of points in the point cloud, p i =(C i ,y i ,z i ) is the three-dimensional coordinate of the i-th point in the point cloud; Each point in the point cloud is converted into a high-dimensional feature vector through a multi-layer perceptron network: f i =MLP(p i ,W); Among them, MLP is a multi-layer perceptron, and W is a weight matrix; PointNet uses the maximum pooling operation to aggregate the features of all points to obtain a global feature representation: F pointcloud =max(f i ); This operation performs maximum pooling on the features of all points to obtain the global descriptor F pointcloud , representing the characteristics of the turnout structure in the point cloud.

[0008] Specifically, the method further includes: Using the weighted fusion method, the features and feature maps of the turnout structure in the point cloud are learned by machine learning. image The fusion weights of the turnout features in the algorithm are used to automatically adjust their respective influences.

[0009] Specifically, the method further includes: confidence calculation: mapping the fused feature vector to a probability distribution through a fully connected layer or a support vector machine SVM to represent the possibility of different turnout states: =Softmax(Wfc F fused + b); in, is the state probability distribution of the output, W fc and b are the weight and bias of the fully connected layer respectively; the probability of each switch state is obtained through the softmax function, and the switch state includes normal, abnormal, and alarm; By confidence ,Dynamically adjust the fusion weight α, the dynamic adjustment formula is as follows: a new =a old +β( max -0.5); in, max is the maximum confidence value, β is the adjustment step size, a old is the weight before adjustment, a new is the weight after adjustment.

[0010] Specifically, the weighted fusion method is used to learn the features and feature graphs of the turnout structure in the machine learning point cloud. image The fusion weights of the turnout features in the model are automatically adjusted to adjust their respective influences, including: Let the visual feature be F image And the point cloud feature is F pointcloud ; Concatenate these two feature vectors into a comprehensive feature vector F fused : F fused =αF image +(1-α)F pointcloud ; Among them, α∈[0,1] is the fusion weight, which indicates the contribution ratio of visual features and point cloud features; Based on the feature fusion vector F fused Make turnout status judgment and calculate the confidence of the recognition result; The rule engine makes the final switch status judgment based on the fused features and confidence levels; the decision rule formula is as follows: State=RuleEngine(F fused , ); The RuleEngine function outputs the turnout state according to the features and confidence. State represents the turnout state, and F fused represents the comprehensive feature vector, is the state probability distribution of the output.

[0011] Specifically, the method further includes: The support vector machine (SVM) is used to judge the turnout status. The feature vector F fused Mapped to the turnout state, the decision formula of SVM is: y=sign(w T F fused + b); Among them, W is the weight matrix, b is the bias, sign is the sign function, y represents the final state of the turnout, and T represents the transpose.

[0012] Specifically, the method further includes: During the operation of the system, as more turnout status data is collected, we can perform incremental learning; each time a new data point is obtained, the system will update the model parameters based on this new data point. The incremental update formula is as follows: θ new =θ old +η·∇L(θ old ,F fused ,y true ); Among them, θ old is the parameter of the model before updating, θ new is the parameter of the updated model, η is the learning rate, ∇L is the gradient of the loss function, L is the loss function of the model, and F fused represents the comprehensive feature vector, y true Indicates the calculated state of the turnout.

[0013] According to a second aspect of the present invention, there is provided a railway locomotive control system, comprising: The acquisition module includes a visual camera arranged in front of the rail vehicle, which is used to capture the visual image of the target area; and also includes a laser radar arranged in front of the rail vehicle, which is used to collect point cloud information of the target area; The control module is used to process the visual image and point cloud information of the target area respectively, identify the opening and closing status of the turnout in the target area, and obtain the status information of the traffic light; if the opening and closing status of the turnout and the status information of the traffic light both meet the traffic conditions, control the rail locomotive to pass the turnout; if the opening and closing status of the turnout or the status information of the traffic light do not meet the traffic conditions, output alarm information about the opening and closing status of the turnout or the status information of the traffic light not meeting the traffic conditions.

[0014] According to a third aspect of the present invention, there is provided an electronic device, comprising: a memory; and a processor, wherein the memory stores computer-readable instructions, and the computer-readable instructions implement the above-mentioned rail vehicle control method when executed by the processor.

[0015] Beneficial effects: 1. Save labor costs: Reduce the need for driver confirmation and reduce human resource consumption, especially when double confirmation is required.

[0016] 2. Improve operational efficiency: Speed ​​up the locomotive passing through the turnout and optimize the overall transportation process.

[0017] 3. Enhanced Security: Through automated judgment, the risk of human error is reduced and the safety of railway transportation is ensured.

[0018] 4. Support automated operations: It provides the basis for unmanned and higher-level automated train operations and improves the modernization level of the railway system.

[0019] 5. A deep learning model that combines vision and lidar feature extraction can achieve more accurate turnout recognition.

[0020] 6. Dynamically adjust the fusion strategy based on the confidence of the recognition results to improve the adaptability of the system.

[0021] 7. Continuously optimize the model through real-time feedback and online learning to adapt to different environments and changing conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of a rail vehicle control method provided in a specific embodiment of the present invention; Figure 2 It is a schematic diagram of the system composition of a rail vehicle control system provided in a specific embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution of the present invention is clearly and completely described below in conjunction with the accompanying drawings of the present invention. Based on the embodiments in this application, other similar embodiments obtained by ordinary technicians in this field without making creative work should all fall within the scope of protection of this application. In addition, the directional words mentioned in the following embodiments, such as "up", "down", "left", "right", etc., are only reference to the directions of the accompanying drawings. Therefore, the directional words used are used to illustrate rather than limit the invention.

[0024] The present invention will be further described below in conjunction with the accompanying drawings and preferred embodiments.

[0025] See also Figure 1 The present invention provides a rail vehicle control method, comprising: S100: Using a visual camera disposed in front of a rail vehicle to capture a visual image of a target area.

[0026] The laser radar installed in front of the rail locomotive is used to collect point cloud information of the target area.

[0027] S200, respectively process the visual image and point cloud information of the target area, identify the opening and closing status of the turnout in the target area, and obtain the status information of the traffic light.

[0028] It is understandable that for visual feature extraction, the present invention uses a convolutional neural network (CNN) architecture, specifically using ResNet (residual network) as the basic network for feature extraction. ResNet performs well in deep networks and avoids the gradient vanishing problem, making it very suitable for extracting complex turnout structures.

[0029] Specifically, the processing of the image and point cloud information of the target area respectively to identify the opening and closing state of the turnout and the traffic light state of the target area includes: Input preprocessed image I∈R H×W×3 , where H and W are the height and width of the image, and 3 represents the RGB channels.

[0030] The image preprocessing comprises: Use mean filtering, Gaussian filtering, median filtering or bilateral filtering to reduce the noise of the image.

[0031] Apply a 3×3 convolution kernel K to perform a convolution operation on the visual image: Xconv =Conv(I,K); Among them, the convolution kernel K is a trainable weight matrix, and the local features of the turnout in the image are extracted through multi-layer convolution. The local features of the turnout include the track edge, the connection between the turnout and the track, the opening and closing connection point of the turnout, the track gap, and the geometric shape of the track. Xconv represents the result of convolution, Conv represents the convolution function, and I represents the visual image.

[0032] Preferably, the convolution kernel K .

[0033] Residual connections are used to solve the gradient vanishing problem and optimize network training: Yrcs=Xconv+F(Xconv,W); Where F represents the combination of convolution operation and activation function (such as Relu function), W is the weight matrix; Xconv represents the result of convolution, and Yrcs represents the result of residual operation; The high-level features of the turnout image are extracted through multiple convolutional layers, and the feature map F is finally output. image , represents the spatial and structural information of the turnout in the image: F image =ResNet(I); Among them, ResNet represents the ResNet network, and I represents the visual image.

[0034] It is understandable that for lidar point cloud data, PointNet is used because it can directly process the original point cloud and can effectively handle the disorder of the point cloud. PointNet processes point cloud data by using symmetric functions.

[0035] The processing flow is as follows: Specifically, the processing of the image and point cloud information of the target area respectively to identify the opening and closing state of the turnout and the traffic light state of the target area includes: Input point cloud data P={p1,p2,…,p n}∈R n×3 , where n is the number of points in the point cloud, p i =(C i ,y i ,z i ) is the three-dimensional coordinate of the i-th point in the point cloud; Each point in the point cloud is converted into a high-dimensional feature vector through a multi-layer perceptron network: f i =MLP(p i ,W); Among them, MLP is a multi-layer perceptron, and W is a weight matrix; PointNet uses the maximum pooling operation to aggregate the features of all points to obtain a global feature representation: F pointcloud =max(f i ); This operation performs maximum pooling on the features of all points to obtain the global descriptor F pointcloud , representing the characteristics of the turnout structure in the point cloud.

[0036] Specifically, the present invention recognizes the state of a traffic light through a visual image, including the following steps: Image capture: Use a camera or other device to capture images of traffic intersections including traffic lights in real time.

[0037] Preprocessing: Clean the captured images, such as denoising, grayscale processing, and histogram equalization, in order to improve the effect of subsequent processing.

[0038] Object detection: Apply deep learning models such as YOLO (You Only Look Once), SSD (Single Shot MultiBox Detector), or Faster R-CNN to locate the traffic light area in the image. These models can identify the location and size of the traffic light in the image.

[0039] Feature extraction: Use a convolutional neural network (CNN) to extract features such as color, shape, and texture from the detected traffic light areas.

[0040] State recognition: Based on the features, a classification model (such as SVM, decision tree, or again using CNN) is trained to recognize the specific color state of the traffic light (red, green, yellow, or off).

[0041] Specifically, the method further includes: Using the weighted fusion method, the features and feature maps of the turnout structure in the point cloud are learned by machine learning. image The fusion weights of the turnout features in the algorithm are used to automatically adjust their respective influences.

[0042] Specifically, the method further includes: confidence calculation: mapping the fused feature vector to a probability distribution through a fully connected layer or a support vector machine SVM to represent the possibility of different turnout states: =Softmax(W fc F fused + b); in, is the state probability distribution of the output, W fc and b are the weight and bias of the fully connected layer respectively; the probability of each switch state is obtained through the softmax function, and the switch state includes normal, abnormal, and alarm; By confidence ,Dynamically adjust the fusion weight α, the dynamic adjustment formula is as follows: a new =a old +β( max -0.5); in, max is the maximum confidence value, β is the adjustment step size, a old is the weight before adjustment, a new is the weight after adjustment.

[0043] Preferably, β=0.1 or 0.05.

[0044] Specifically, the confidence ,Dynamically adjust the fusion weight α, including: When the confidence is low, increase the weight α of the point cloud feature to improve the stability of the system; When the confidence is high, the weight α of the point cloud feature is reduced to enhance the influence of the visual feature.

[0045] Specifically, the present invention sets the confidence threshold in the range of [0.6, 0.9]: When the confidence level is lower than 0.6, the system may not be able to make reliable judgments and the point cloud weight needs to be increased.

[0046] When the confidence is higher than 0.9, the visual features are more credible and the point cloud weight is reduced.

[0047] Specifically, the weighted fusion method is used to learn the features and feature graphs of the turnout structure in the machine learning point cloud. image The fusion weights of the turnout features in the model are automatically adjusted to adjust their respective influences, including: Let the visual feature be F image And the point cloud feature is F pointcloud ; Concatenate these two feature vectors into a comprehensive feature vector F fused : F fused =αF image +(1-α)F pointcloud ; Among them, α∈[0,1] is the fusion weight, which indicates the contribution ratio of visual features and point cloud features. This weight will be automatically adjusted according to system feedback. The initial value of α is preferably 0.5, which means that the initial contribution ratio of visual features and point cloud features is equal.

[0048] Based on the feature fusion vector F fused Make turnout status judgment and calculate the confidence of the recognition result; The rule engine makes the final switch status judgment based on the fused features and confidence levels; the decision rule formula is as follows: State=RuleEngine(F fused , ); The RuleEngine function outputs the turnout state according to the features and confidence. State represents the turnout state, and F fused represents the comprehensive feature vector, is the state probability distribution of the output.

[0049] It is understandable that we use the rule engine to make the final switch status judgment based on the fused features and confidence. The rules are as follows: Normal traffic conditions: If the switch opening and closing status is normal and the traffic light is green, the system allows the locomotive to pass.

[0050] Abnormal status processing: If the turnout status is abnormal (for example, the turnout opening and closing errors or the traffic lights do not match), an alarm is triggered.

[0051] Specifically, the method further includes: The support vector machine (SVM) is used to judge the turnout status. The feature vector F fused Mapped to the turnout state, the decision formula of SVM is: y=sign(w T F fused + b); Among them, W is the weight matrix, b is the bias, sign is the sign function, y represents the final state of the turnout, and T represents the transpose.

[0052] Specifically, y=+1: the turnout state is normal (turnout opening and closing is normal), and the traffic light state complies with the traffic rules. y=−1: the turnout state is abnormal (turnout opening and closing is wrong), and the traffic light state does not comply with the traffic rules.

[0053] Understandably, for higher accuracy, we use a machine learning model, Support Vector Machine (SVM), to make more complex judgments. The model is trained to map feature vectors to turnout states.

[0054] Specifically, the method further includes: During the operation of the system, as more turnout status data is collected, we can perform incremental learning; each time a new data point is obtained, the system will update the model parameters based on this new data point. The incremental update formula is as follows: θ new =θ old +η·∇L(θ old ,F fused ,y true ); Among them, θ old is the parameter of the model before updating, θ new is the parameter of the updated model, η is the learning rate, ∇L is the gradient of the loss function, L is the loss function of the model, and F fused represents the comprehensive feature vector, and ytrue represents the calculated state of the turnout.

[0055] It should be noted here that during the online learning process, the weights are automatically adjusted according to the new data distribution. By monitoring the performance of the system (confidence and recognition accuracy), the system can adjust the feature fusion weight α to ensure that the system is always in the best state.

[0056] S300. If the opening and closing status of the turnout and the status information of the traffic light meet the conditions for passage, control the rail locomotive to pass the turnout; if the opening and closing status of the turnout or the status information of the traffic light do not meet the conditions for passage, output an alarm message indicating that the opening and closing status of the turnout or the status information of the traffic light do not meet the conditions for passage.

[0057] Specifically, in a preferred embodiment, the method further includes: If the switch opening and closing status and traffic lights meet the traffic conditions, the control system allows the locomotive to pass safely. If the switch opening and closing status or traffic lights are abnormal, the system will send an alarm to the dispatching center and wait for further processing and instructions from the dispatching center.

[0058] It can be understood that the present invention has the following technical effects: 1. Save labor costs: Reduce the need for driver confirmation and reduce human resource consumption, especially when double confirmation is required.

[0059] 2. Improve operational efficiency: Speed ​​up the locomotive passing through the turnout and optimize the overall transportation process.

[0060] 3. Enhanced Security: Through automated judgment, the risk of human error is reduced and the safety of railway transportation is ensured.

[0061] 4. Support automated operations: It provides the basis for unmanned and higher-level automated train operations and improves the modernization level of the railway system.

[0062] 5. A deep learning model that combines vision and lidar feature extraction can achieve more accurate turnout recognition.

[0063] 6. Dynamically adjust the fusion strategy based on the confidence of the recognition results to improve the adaptability of the system.

[0064] 7. Continuously optimize the model through real-time feedback and online learning to adapt to different environments and changing conditions.

[0065] See also Figure 2 The present invention provides another embodiment, which provides a rail locomotive control system, the rail locomotive control system comprising: The acquisition module 100 includes a visual camera disposed in front of the rail vehicle, which is used to capture a visual image of the target area; and also includes a laser radar disposed in front of the rail vehicle, which is used to collect point cloud information of the target area; The control module 200 is used to process the visual image and point cloud information of the target area respectively, identify the opening and closing status of the turnout in the target area, and obtain the status information of the traffic light; if the opening and closing status of the turnout and the status information of the traffic light both meet the traffic conditions, control the rail locomotive to pass the turnout; if the opening and closing status of the turnout or the status information of the traffic light do not meet the traffic conditions, output alarm information about the opening and closing status of the turnout or the status information of the traffic light not meeting the traffic conditions.

[0066] It should be noted here that the present invention has the following technical effects: 1. Save labor costs: Reduce the need for driver confirmation and reduce human resource consumption, especially when double confirmation is required.

[0067] 2. Improve operational efficiency: Speed ​​up the locomotive passing through the turnout and optimize the overall transportation process.

[0068] 3. Enhanced Security: Through automated judgment, the risk of human error is reduced and the safety of railway transportation is ensured.

[0069] 4. Support automated operations: It provides the basis for unmanned and higher-level automated train operations and improves the modernization level of the railway system.

[0070] 5. A deep learning model that combines vision and lidar feature extraction can achieve more accurate turnout recognition.

[0071] 6. Dynamically adjust the fusion strategy based on the confidence of the recognition results to improve the adaptability of the system.

[0072] 7. Continuously optimize the model through real-time feedback and online learning to adapt to different environments and changing conditions.

[0073] In a preferred embodiment, the present application further provides an electronic device, the electronic device comprising: A memory; and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the rail vehicle control method is implemented. The computer device can be broadly a server, a terminal, or any other electronic device with necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, a memory, a network interface, a communication interface, etc. connected via a system bus. The processor of the computer device can be used to provide necessary computing, processing and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and an internal memory. An operating system, a computer program, etc. may be stored in or on the non-volatile storage medium. The internal memory may provide an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface and the communication interface of the computer device can be used to connect and communicate with external devices via a network. When the computer program is executed by the processor, the steps of the method of the present invention are performed.

[0074] The present invention may be implemented as a computer-readable storage medium having a computer program stored thereon, which causes the steps of the method of an embodiment of the present invention to be executed when executed by a processor. In one embodiment, the computer program is distributed on a plurality of computer devices or processors coupled to a network so that the computer program is stored, accessed and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, may be performed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations may be performed by one or more computer devices or processors, and one or more other method steps / operations may be performed by one or more other computer devices or processors. One or more computer devices or processors may perform a single method step / operation, or perform two or more method steps / operations.

[0075] It will be appreciated by a person skilled in the art that the method steps of the present invention may be performed by instructing related hardware such as a computer device or a processor through a computer program, and the computer program may be stored in a non-temporary computer-readable storage medium, which causes the steps of the present invention to be performed when the computer program is executed. Depending on the circumstances, any reference to memory, storage, database, or other media herein may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0076] It can be understood that the present invention has the following technical effects: 1. Save labor costs: Reduce the need for driver confirmation and reduce human resource consumption, especially when double confirmation is required.

[0077] 2. Improve operational efficiency: Speed ​​up the locomotive passing through the turnout and optimize the overall transportation process.

[0078] 3. Enhanced Security: Through automated judgment, the risk of human error is reduced and the safety of railway transportation is ensured.

[0079] 4. Support automated operations: It provides the basis for unmanned and higher-level automated train operations and improves the modernization level of the railway system.

[0080] 5. A deep learning model that combines vision and lidar feature extraction can achieve more accurate turnout recognition.

[0081] 6. Dynamically adjust the fusion strategy based on the confidence of the recognition results to improve the adaptability of the system.

[0082] 7. Continuously optimize the model through real-time feedback and online learning to adapt to different environments and changing conditions.

[0083] The various technical features described above can be combined arbitrarily. Although all possible combinations of these technical features are not described, any combination of these technical features should be considered to be covered by this specification as long as there is no contradiction in such combination.

[0084] The specific implementation of the present invention described above does not constitute a limitation on the protection scope of the present invention. Any other corresponding changes and modifications made based on the technical concept of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A rail vehicle control method, characterized in that: The method comprises: S100, using a visual camera disposed in front of the rail vehicle to capture a visual image of the target area; The laser radar installed in front of the rail vehicle is used to collect point cloud information of the target area; S200, respectively processing the visual image and point cloud information of the target area, identifying the opening and closing status of the turnout in the target area, and obtaining the status information of the traffic light; S300. If the opening and closing status of the turnout and the status information of the traffic light meet the conditions for passage, control the rail locomotive to pass the turnout; if the opening and closing status of the turnout or the status information of the traffic light do not meet the conditions for passage, output an alarm message indicating that the opening and closing status of the turnout or the status information of the traffic light do not meet the conditions for passage.

2. The rail vehicle control method according to claim 1, characterized in that: The processing of the image and the point cloud information of the target area respectively to identify the opening and closing state of the turnout and the traffic light state of the target area includes: Apply a 3×3 convolution kernel K to perform a convolution operation on the visual image: Xconv =Conv(I,K); Among them, the convolution kernel K is a weight matrix, and the local features of the turnout in the image are extracted through multi-layer convolution. Xconv represents the result of convolution, Conv represents the convolution function, and I represents the visual image; Residual connections are used to solve the gradient vanishing problem and optimize network training: Yrcs=Xconv+F(Xconv,W); Where F represents the combination of convolution operation and activation function, W is the weight matrix; Xconv represents the result of convolution, and Yrcs represents the result of residual operation; The high-level features of the turnout image are extracted through multiple convolutional layers, and the feature map F is finally output. image , represents the spatial and structural information of the turnout in the image: F image =ResNet(I); Among them, ResNet represents the ResNet network, and I represents the visual image.

3. The rail vehicle control method according to claim 2, characterized in that: The processing of the image and the point cloud information of the target area respectively to identify the opening and closing state of the turnout and the traffic light state of the target area includes: Input point cloud data P={p1,p2,…,p n }∈R n×3 , where n is the number of points in the point cloud, p i =(C i ,y i ,z i ) is the three-dimensional coordinate of the i-th point in the point cloud; Each point in the point cloud is converted into a high-dimensional feature vector through a multi-layer perceptron network: f i =MLP(p i ,W); Among them, MLP is a multi-layer perceptron, and W is a weight matrix; PointNet uses the maximum pooling operation to aggregate the features of all points to obtain a global feature representation: F pointcloud =max(f i ); This operation performs maximum pooling on the features of all points to obtain the global descriptor F pointcloud , representing the characteristics of the turnout structure in the point cloud.

4. The rail vehicle control method according to claim 3, characterized in that: The method further comprises: Using the weighted fusion method, the features and feature maps of the turnout structure in the point cloud are learned by machine learning. image The fusion weights of the turnout features in the algorithm are used to automatically adjust their respective influences.

5. The rail vehicle control method according to claim 4, characterized in that: The method further includes: confidence calculation: mapping the fused feature vector to a probability distribution through a fully connected layer or a support vector machine (SVM) to represent the possibility of different turnout states: =Softmax(W fc F fused +b); in, is the state probability distribution of the output, W fc and b are the weight and bias of the fully connected layer respectively; the probability of each switch state is obtained through the softmax function, and the switch state includes normal, abnormal, and alarm; By confidence ,Dynamically adjust the fusion weight α, the dynamic adjustment formula is as follows: a new =a old +β( max -0.5); in, max is the maximum confidence value, β is the adjustment step size, a old is the weight before adjustment, a new is the weight after adjustment.

6. The rail vehicle control method according to claim 5, characterized in that: The weighted fusion method is used to learn the features and feature maps of the turnout structure in the point cloud by machine learning. image The fusion weights of the turnout features in the model are automatically adjusted to adjust their respective influences, including: Let the visual feature be F image And the point cloud feature is F pointcloud ; Concatenate these two feature vectors into a comprehensive feature vector F fused : F fused =αF image +(1-α)F pointcloud ; Among them, α∈[0,1] is the fusion weight, which indicates the contribution ratio of visual features and point cloud features; Based on the feature fusion vector F fused Make turnout status judgment and calculate the confidence of the recognition result; The rule engine makes the final switch status judgment based on the fused features and confidence levels; the decision rule formula is as follows: State=RuleEngine(F fused , ); The RuleEngine function outputs the turnout state according to the features and confidence. State represents the turnout state, and F fused represents the comprehensive feature vector, is the state probability distribution of the output.

7. The rail vehicle control method according to claim 6, characterized in that: The method further comprises: The support vector machine (SVM) is used to judge the turnout status. The feature vector F fused Mapped to the turnout state, the decision formula of SVM is: y=sign(w T F fused +b); Among them, W is the weight matrix, b is the bias, sign is the sign function, y represents the final state of the turnout, and T represents the transpose.

8. The rail vehicle control method according to claim 1, characterized in that: The method further comprises: During the operation of the system, as more turnout status data is collected, we can perform incremental learning; each time a new data point is obtained, the system will update the model parameters based on this new data point. The incremental update formula is as follows: i new =θ old +η·∇L(θ old ,F fused ,y true ); Among them, θ old is the parameter of the model before updating, θ new is the parameter of the updated model, η is the learning rate, ∇L is the gradient of the loss function, L is the loss function of the model, and F fused represents the comprehensive feature vector, y true Indicates the calculated state of the turnout.

9. A rail vehicle control system, characterized in that: include: The acquisition module includes a visual camera arranged in front of the rail vehicle, which is used to capture the visual image of the target area; and also includes a laser radar arranged in front of the rail vehicle, which is used to collect point cloud information of the target area; The control module is used to process the visual image and point cloud information of the target area respectively, identify the opening and closing status of the turnout in the target area, and obtain the status information of the traffic light; if the opening and closing status of the turnout and the status information of the traffic light both meet the traffic conditions, control the rail locomotive to pass the turnout; if the opening and closing status of the turnout or the status information of the traffic light do not meet the traffic conditions, output alarm information about the opening and closing status of the turnout or the status information of the traffic light not meeting the traffic conditions.

10. An electronic device, characterized in that: include: Memory; and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the rail vehicle control method according to any one of claims 1 to 8 is implemented.

Images