Unmanned system and method for railway train

By building an unmanned driving system for image acquisition, satellite positioning and GSM-R communication equipment on railway trains, the problem of blind spots and signal interference on ground signal systems is solved, and the automated control of railway trains is realized, and safety and transportation are improved. efficiency and reduce labor costs.

CN119018201APending Publication Date: 2024-11-26陕西君凯科技集团有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411464393.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-21
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing unmanned driving technology of railway trains relies on ground signal systems, which have problems with blind coverage and signal interference, resulting in safety risks and inefficiency.

Method used

Design an unmanned driving system including image acquisition equipment, satellite positioning device and GSM-R communication equipment, generate scene images through image acquisition equipment, satellite positioning device obtains train location, GSM-R communication equipment builds exclusive communication link, train The central control device uploads driving data and receives scheduling instructions to realize automated control.

Benefits of technology

Reduce accidents caused by human errors, improve the safety and efficiency of railway transportation, ensure stable communication between trains and dispatching centers, and reduce dependence on drivers and labor costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119018201A_ABST
    Figure CN119018201A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of automatic driving, and provides a railway train unmanned driving system and method, and the system comprises an image collection device installed on a train head of a railway train, a train central control device interacting with the image collection device, a satellite positioning device connected with the train central control device, and a GSM-R communication device. The image acquisition equipment is used for acquiring a scene image in front of a real-time rail of a railway train; the satellite positioning device is used for acquiring the current position coordinates of the railway train; the GSM-R communication equipment is used for building an exclusive communication link according to the current position coordinate and the scene image; wherein the exclusive communication link comprises a satellite communication link, a wireless mobile communication link and an interactive compensation communication link; and the train central control device is used for uploading the driving data of the ATO system to the train dispatching center through the exclusive communication link and receiving a dispatching instruction of the train dispatching center.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of unmanned railway train driving, and in particular to an unmanned railway train driving system and method. Background Art

[0002] Currently, train driverless technology is developing rapidly. Using technologies such as machine learning, image recognition, and GPU, railway trains are moving towards a more autonomous direction. Since trains run on tracks, their operating environment is relatively simple, so trains are an important area for realizing driverless technology.

[0003] my country has made significant progress in high-speed rail autonomous driving technology. For example, the Beijing-Shenyang Passenger Railway conducted a field test of a 350 km / h high-speed rail autonomous driving system, marking a major breakthrough in China's intelligent high-speed rail technology. It also successfully tested a 20,000-ton heavy-load autonomous driving train, and made important progress in the field of heavy-load autonomous driving trains.

[0004] However, in the existing technology, the unmanned driving technology of railway trains still has huge defects. In terms of signal processing, traditional railway train driving relies on manual operation, which has certain safety risks and efficiency problems. With the development of automation technology, unmanned driving has become an important direction for improving the efficiency and safety of railway transportation. The existing unmanned driving technology mostly relies on the ground signal system, but the ground signal system may have coverage blind spots and signal interference problems. Summary of the invention

[0005] The present invention proposes a railway train unmanned driving system and method, which is used to solve the existing technology. The unmanned driving technology of railway trains still has huge defects. In terms of signal processing, traditional railway train driving relies on manual operation, which has certain safety risks and efficiency problems. With the development of automation technology, unmanned driving has become an important direction for improving the efficiency and safety of railway transportation. The existing unmanned driving technology mostly relies on the ground signal system, but the ground signal system may have coverage blind spots and signal interference problems.

[0006] In a first aspect, the present invention provides an unmanned railway train driving system, comprising: an image acquisition device installed on the front of a railway train, a train central control device interacting with the image acquisition device, a satellite positioning device and a GSM-R communication device communicating with the train central control device; The image acquisition device is used to acquire the scene image in front of the real-time track of the railway train; The satellite positioning device is used to obtain the current position coordinates of the railway train; The GSM-R communication device is used to establish an exclusive communication link according to the current position coordinates and the scene image; wherein the exclusive communication link includes a satellite communication link, a wireless mobile communication link and an interactive compensation communication link; The train central control device is used to upload the travel data of the ATO system to the train dispatching center through a dedicated communication link, and receive dispatching instructions from the train dispatching center.

[0007] In combination with the first aspect, the image acquisition device includes a laser sensing component and a synchronous image component; The laser sensing assembly is configured to generate a first pre-imaging signal based on the echo signal; The synchronized image component is configured to be based on a second pre-imaging signal of a dynamic space; The first pre-imaging signal is loaded into the dynamic scene space generated by the second pre-imaging signal to generate a scene image.

[0008] In combination with the first aspect, the dynamic space generated by loading the first pre-imaging signal into the second pre-imaging signal includes: Acquire a radar echo signal of a first pre-imaging signal at each moment to construct a first three-dimensional space; Based on the first stereoscopic space, a plurality of target sets in the first stereoscopic space are determined; wherein the target set includes a dynamic target set and a static target set, the dynamic target set is obtained based on a preset motion capture, and the motion capture is configured to identify the signal difference in adjacent frame radar echo signals; Marking the detection target in the second pre-imaging signal to generate a static scene space; The static targets in the static scene space are matched with the static target set, and when the match is successful, the dynamic target set is loaded into the static scene space to generate a dynamic scene space.

[0009] In combination with the first aspect, the satellite positioning device includes: a track line statistics component and a satellite signal transmission component; The satellite signal transmission component is used to receive longitude and latitude data from positioning satellites in real time; The track line statistics component is used to count the longitude and latitude change data according to the longitude and latitude data, and determine the real-time position of the railway train and the corresponding track line travel trajectory data; Among them, when the rail line driving trajectory data does not belong to the rail line, the longitude and latitude change data is mapped to the target driving route of the rail train, the positioning deviation is determined, and when the positioning deviation is within the preset deviation range, the deviation correction is performed.

[0010] In combination with the first aspect, the dedicated communication link includes: an emergency braking control unit, an unmanned dispatching unit, and a track obstacle identification unit; The emergency brake control unit includes a periodic repetitive signal and a monitoring side node for supervising the periodic repetitive signal; wherein the periodic repetitive signal has a signal guidance association with the unmanned dispatching unit and the track obstacle identification unit; the monitoring side node is used to determine whether the periodic repetitive signal generates a signal change, and generate an emergency brake signal according to the signal change; The unmanned dispatching unit includes a plurality of aggregation nodes, each of which is configured to generate one or more control instructions for a rail vehicle control process; The track obstacle identification unit includes a plurality of link logic access points, and the link logic access points are used to respond to the target identification mechanism of the image acquisition device and receive the corresponding scene image; wherein, the link logic access point corresponds to a unique target identification mechanism.

[0011] In combination with the first aspect, in the dedicated communication link, the satellite communication link is used to receive the positioning data of the railway train, and the wireless mobile communication link is used to establish the element grid according to the positioning data and the scene image; When the wireless mobile communication link has unstable signal, the interactive compensation communication link locates the scene elements on the scene image in real time according to the element grid, and maps the missing scene elements on the wireless mobile communication link to the train central control device according to the interactive mapping.

[0012] In combination with the first aspect, the train central control device includes: an edge server, a TCMS control server and a signal server; The edge server is used to obtain scene route data and generate driving instructions through a dedicated communication link; The TCMS control server is used to perform train function control and train monitoring according to driving instructions; The signal server is used to monitor train travel data and perform emergency braking.

[0013] In combination with the first aspect, the edge server is further used for: Receive scene images in real time and classify scene elements; According to the classification of scene elements, the first track line violation judgment is performed on different elements on the scene elements; wherein the first track line violation judgment is used to determine the first obstacle that may cause the track line violation; Perform risk assessment on the scene elements after the line-invasion determination, and perform secondary line-invasion determination on the scene elements according to the risk assessment result; wherein the secondary line-invasion determination is used to determine the second obstacle that will move in the first obstacle; Based on the scene elements after the secondary line intrusion judgment, the real-time speed of the rail train, the minimum distance to the obstacle and the emergency braking distance are judged in real time.

[0014] In combination with the first aspect, the train central control device is further used for: Receive control demand instructions from the train dispatching center and determine the target speed and target location; According to the driving data and target speed, a speed compensation model is built to determine the speed error and speed compensation parameters; Based on the speed error, train guidance instructions are issued to the train central control device.

[0015] In a second aspect, the present invention provides a method for unmanned driving of railway trains, which is applicable to the above-mentioned system, and the method comprises: Collect the scene images in front of the railway train track in real time; Get the current position coordinates of the railway train; According to the current position coordinates and scene image, an exclusive communication link is established; wherein the exclusive communication link includes a satellite communication link, a wireless mobile communication link and an interactive compensation communication link; The ATO system's driving data is uploaded to the train dispatching center through a dedicated communication link, and the dispatching instructions from the train dispatching center are received.

[0016] The beneficial effects of the present invention are: The unmanned driving system of the present invention can reduce accidents caused by human errors and improve the safety of railway transportation. It can optimize the train running speed and route through automated control and improve transportation efficiency. By establishing a dedicated communication link, stable communication between the train and the dispatching center can be maintained even in remote areas. The train central control device can upload driving data in real time and receive dispatching instructions, which is convenient for the dispatching center to conduct real-time monitoring and dispatching. In the long run, the unmanned driving system can reduce dependence on drivers and reduce labor costs.

[0017] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0018] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 A system composition diagram of an unmanned railway train driving system according to an embodiment of the present invention; Figure 2A method flow chart of an unmanned driving method for a railway train in an embodiment of the present invention; Figure 3 1 is a composition diagram of an image acquisition device in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0021] like Figure 1 As shown, this embodiment provides an unmanned railway train driving system, including: an image acquisition device installed on the front of a railway train, a train central control device interacting with the image acquisition device, a satellite positioning device and a GSM-R communication device communicating with the train central control device; The image acquisition device is used to acquire the scene image in front of the real-time track of the railway train; The satellite positioning device is used to obtain the current position coordinates of the railway train; The GSM-R communication device is used to establish an exclusive communication link according to the current position coordinates and the scene image; wherein the exclusive communication link includes a satellite communication link, a wireless mobile communication link and an interactive compensation communication link; The train central control device is used to upload the travel data of the ATO system to the train dispatching center through a dedicated communication link, and receive dispatching instructions from the train dispatching center.

[0022] The principle of the above technical solution is: In the actual implementation process, the railway train of the present invention is a rail train, including but not limited to freight trains, mining rail vehicles and passenger trains. First, the main function of the image acquisition device at the front position of the train is to capture the image information of the scene in front of the railway train in real time and generate raw data. Then, the image information will be transmitted to the train central control device for processing.

[0023] The train central control device is responsible for receiving information from various sensors and devices in the train, as well as communicating with external devices. It can receive image information from the image acquisition device on the front of the train, and can also obtain the current location information of the train through the satellite positioning device. The information of the equipment and various sensors will be transmitted through the dedicated communication link inside the train.

[0024] The satellite positioning device is mainly responsible for obtaining the specific location information of the train on the railway. By using the global satellite navigation system (such as the Beidou system, etc.), the geographical location of the train is accurately determined and the geographical coordinates are generated.

[0025] GSM-R communication equipment is a wireless communication device designed specifically for railway transportation, providing communication services for trains in areas without signal coverage. Through interaction with the on-board central control device and other related equipment, a communication link dedicated to the current operating state is constructed. The exclusive communication link includes not only satellite communication links, but also wireless mobile communication links and interactive compensation communication links. The combination of the three links ensures the stability and safety of the train during operation.

[0026] Finally, the train central control device is used to safely and effectively transmit the train travel data sent from the image acquisition device on the front of the train to the train dispatching center through the communication link provided by the satellite positioning device and the GSM-R communication equipment. At the same time, it can also receive dispatching instructions from the train dispatching center and remotely control the train.

[0027] The beneficial effects of the above technical solution are: The unmanned driving system of the present invention can reduce accidents caused by human errors and improve the safety of railway transportation. It can optimize the train running speed and route through automated control and improve transportation efficiency. By establishing a dedicated communication link, stable communication between the train and the dispatching center can be maintained even in remote areas. The train central control device can upload driving data in real time and receive dispatching instructions, which is convenient for the dispatching center to conduct real-time monitoring and dispatching. In the long run, the unmanned driving system can reduce dependence on drivers and reduce labor costs.

[0028] As an embodiment of the present invention: Figure 2 As shown, the image acquisition device includes a laser sensing component and a synchronous image component; The laser sensing assembly is configured to generate a first pre-imaging signal based on the echo signal; The synchronized image component is configured to be based on a second pre-imaging signal of a dynamic space; The first pre-imaging signal is loaded into the dynamic scene space generated by the second pre-imaging signal to generate a scene image.

[0029] The principle of the above technical solution is: In the specific implementation process of the present invention: the laser sensing component obtains the first pre-imaging signal by emitting laser and receiving the reflected echo signal. Based on the laser radar (LIDAR), accurate distance information about the surrounding environment can be provided. The synchronous image component generates a second pre-imaging signal based on the dynamic space, which is a camera or other type of visual sensor that captures the visual information of the scene. In the signal fusion, the first pre-imaging signal (distance information) and the second pre-imaging signal (visual information) are fused to generate a scene image containing depth information, thereby realizing the three-dimensional construction of the surrounding environment, and also having the depth information of the current environment.

[0030] In the specific scenario, the front of the train is equipped with a laser radar, which can emit laser pulses and measure the time difference of the reflected light signal to calculate the distance to the object in front. Installed side by side with the laser radar is a high-definition camera, which can capture real-time visual images of the track ahead. When the train approaches a curve, the laser radar emits laser pulses and receives echo signals from the environment around the curve to generate a first pre-imaging signal. At the same time, the camera captures the visual image of the curve and generates a second pre-imaging signal. The distance information in the first pre-imaging signal is mapped to the corresponding pixels of the second pre-imaging signal to generate a scene image containing depth information. The train's central control device receives this fused scene image and adjusts the speed and driving path of the train based on this information to ensure safe and smooth passage through the curve.

[0031] In the actual implementation process, the laser sensing component and the synchronous image component of the image acquisition device can be adaptively combined with the ultrasonic sensing component, the electromagnetic wave sensing component and the infrared sensing component.

[0032] In the actual implementation process, the ultrasonic sensing component includes a first sensing unit and a second sensing unit. The first sensing unit is used to detect the first pre-imaging signal to determine whether there is any missing scene element. The second sensing unit is activated when receiving a signal that the scene element is not missing. It is used to establish a contour space of the scene element based on the first pre-imaging signal; and to determine whether there is an imaging missing area of ​​the scene element based on the contour space.

[0033] The electromagnetic wave sensing component is used to detect the spacing layer between different scene elements in the first pre-imaging signal. During the detection process, the spacing space between different scene elements is divided into multiple test units of preset sizes, and then the multiple test units are spliced ​​to reconstruct the spacing space, so that obstacles on the rails and obstacles close to the rails can be judged, and the depth distance from the rails can be judged, which can provide accurate depth information for the scene image in judging the collision detection between obstacles and trains.

[0034] The infrared sensing component is used in conjunction with the electromagnetic wave sensing component and is mainly used for ranging. In its specific implementation, in the process of reconstructing the interval space, based on the contour space, the first distance between different coordinate points of two adjacent scene elements is judged, and in the process of constructing the interval space, the second distance between two scene elements on the horizontal plane or the vertical plane is judged. Based on the spatial coordinate system of the current scene, it is judged whether the first distance and the second distance are consistent, thereby achieving multiple accuracy verifications in judging the distance between adjacent scene elements on the scene image.

[0035] In the above scheme, the ultrasonic sensing component, electromagnetic wave sensing component and infrared sensing component have their own independent component functions, and can also be combined with other components to realize the data collection and verification function of the scene image. In the actual implementation process, the priority is pre-set for the areas and scene elements that need to be identified, so as to accurately perform track intrusion detection.

[0036] The laser sensing components, synchronous image components, ultrasonic sensing components, electromagnetic wave sensing components and infrared sensing components of the image acquisition device work together to form a highly integrated and high-precision 3D scene reconstruction system. This system can not only effectively identify scene elements in the image, but also accurately locate them in 3D, and then construct a more refined scene image based on this information.

[0037] The laser sensing component is responsible for capturing the first pre-imaging signal and converting it into distance information in the physical world, while the synchronous image component is responsible for capturing the dynamic information in the image and then constructing a scene image containing time and space information.

[0038] Ultrasonic sensing components and electromagnetic wave sensing components are mainly used for image processing and optimization. Ultrasonic sensing components can determine the distance information of obstacles by detecting the spacing layers between different scene elements, thereby improving the accuracy of scene images. Electromagnetic wave sensing components can visualize the spatial relationship between different scene elements by detecting the spacing layers between these elements, further improving the accuracy of scene images.

[0039] The beneficial effects of the above technical solution are: By combining laser sensing and visual images in the above solution, the system can more accurately perceive and understand the surrounding environment, including the location, shape and material of obstacles; by fusing depth information and visual information, the unmanned driving system can make more accurate driving decisions, especially in complex or changing environments; accurate environmental perception and decision-making capabilities help reduce misjudgments and potential accidents caused by insufficient environmental perception.

[0040] As an embodiment of the present invention: the first pre-imaging signal is loaded into the dynamic space generated by the second pre-imaging signal, including: Acquire a radar echo signal of a first pre-imaging signal at each moment to construct a first three-dimensional space; Based on the first stereoscopic space, a plurality of target sets in the first stereoscopic space are determined; wherein the target set includes a dynamic target set and a static target set, the dynamic target set is obtained based on a preset motion capture, and the motion capture is configured to identify the signal difference in adjacent frame radar echo signals; Marking the detection target in the second pre-imaging signal to generate a static scene space; The static targets in the static scene space are matched with the static target set, and when the match is successful, the dynamic target set is loaded into the static scene space to generate a dynamic scene space.

[0041] The principle of the above technical solution is: When the present invention is implemented, the radar echo signal of the first pre-imaging signal at each moment is continuously acquired, and these signals are used to construct a three-dimensional space model, namely the first stereoscopic space. In this three-dimensional space model, the system will determine a number of target sets according to preset rules. Among them, one part is a dynamic target set, and this part of the targets is captured according to a preset motion trajectory. The other part is a static target set, and this part of the targets is obtained based on other information that has been collected, such as static objects or terrain. For the targets in the second pre-imaging signal, the system will perform further processing and add labels to these targets, thus forming a static scene space. By merging this static scene space with the first stereoscopic space, a new dynamic scene space can be obtained. In the new dynamic scene space, the system will load the previously marked dynamic target set, thereby completing a complete workflow.

[0042] The beneficial effects of the above technical solution are: Through the above scheme, a more accurate model of the train operation environment can be obtained, which is convenient for the train control system to make more accurate and timely responses when unmanned operation is in progress. It can not only take into account the movement of the train itself, but also the dynamic changes of the surrounding environment, so that the automatic driving of the train can be dynamically combined with the surrounding environment.

[0043] As an embodiment of the present invention: the satellite positioning device comprises: a track line statistics component and a satellite signal transmission component; The satellite signal transmission component is used to receive longitude and latitude data from positioning satellites in real time; The track line statistics component is used to count the longitude and latitude change data according to the longitude and latitude data, and determine the real-time position of the railway train and the corresponding track line travel trajectory data; Among them, when the rail line driving trajectory data does not belong to the rail line, the longitude and latitude change data is mapped to the target driving route of the rail train, the positioning deviation is determined, and when the positioning deviation is within the preset deviation range, the deviation correction is performed.

[0044] The principle of the above technical solution is: In the specific implementation process of the present invention, the satellite positioning device realizes real-time positioning and path planning through the track line statistics component and the satellite signal transmission component. The satellite signal transmission component is responsible for receiving the longitude and latitude data from the positioning satellite in real time to achieve precise positioning. These longitude and latitude data contain the precise coordinate information of the train's location and are the input data of the train control system. The track line statistics component is responsible for processing these longitude and latitude data and calculating the corresponding track line driving trajectory data according to its characteristics. It provides real-time location information and driving routes for the train control system so that the train can travel on the correct track. When the track line driving trajectory data does not belong to the track line, the longitude and latitude change data is mapped to the target driving route of the track train, the position change of the train is monitored in real time, and it is determined whether there is a positioning deviation. If the positioning deviation is within the preset error range, the deviation correction is automatically performed to ensure that the train's driving track is correct.

[0045] The beneficial effects of the above technical solution are: The above solution enables the railway train unmanned driving system to maintain a high level of operational stability and safety when facing complex environments and abnormal situations.

[0046] As an embodiment of the present invention: the dedicated communication link includes: an emergency braking control unit, an unmanned dispatching unit and a track obstacle identification unit; The emergency brake control unit includes a periodic repetitive signal and a monitoring side node for supervising the periodic repetitive signal; wherein the periodic repetitive signal has a signal guidance association with the unmanned dispatching unit and the track obstacle identification unit; the monitoring side node is used to determine whether the periodic repetitive signal generates a signal change, and generate an emergency brake signal according to the signal change; The unmanned dispatching unit includes a plurality of aggregation nodes, each of which is configured to generate one or more control instructions for a rail vehicle control process; The track obstacle identification unit includes a plurality of link logic access points, and the link logic access points are used to respond to the target identification mechanism of the image acquisition device and receive the corresponding scene image; wherein, the link logic access point corresponds to a unique target identification mechanism.

[0047] The principle of the above technical solution is: The exclusive communication link of the present invention is subdivided into an emergency braking control unit, an unmanned dispatching unit and a track obstacle identification unit, each of which has its specific functions and signal guidance associations. There is a periodic repetitive signal in the emergency braking control unit: the emergency braking control unit sends a periodic repetitive signal to continuously monitor the operating status of the train. The monitoring side node is responsible for monitoring the periodic repetitive signal and determining whether there is a signal change. If a signal change is detected, indicating that an abnormal situation may have occurred, the monitoring side node will generate an emergency braking signal to trigger the train's emergency braking system.

[0048] Aggregation node in the unmanned dispatching unit: responsible for generating control instructions for the rail vehicle control process. Each aggregation node can generate one or more control instructions to adjust the speed, direction, etc. of the train.

[0049] The link logic access point in the track obstacle identification unit corresponds to the target recognition mechanism of the image acquisition device, which is responsible for receiving and processing scene images to identify obstacles on the track. The target recognition mechanism is that each link logic access point corresponds to a unique target recognition mechanism to ensure the accuracy and uniqueness of obstacle identification.

[0050] The beneficial effects of the above technical solution are: The above solution uses the emergency braking control unit, so that the system can quickly take braking measures when abnormal conditions are detected, reducing the risk of accidents. The aggregation node of the unmanned dispatching unit can generate precise control instructions to optimize train operation. The track obstacle recognition unit improves the accuracy and response speed of obstacle recognition through a dedicated link logic access point and target recognition mechanism.

[0051] As an embodiment of the present invention: in the dedicated communication link, the satellite communication link is used to receive the positioning data of the railway train, and the wireless mobile communication link is used to establish the element grid according to the positioning data and the scene image; When the wireless mobile communication link has unstable signal, the interactive compensation communication link locates the scene elements on the scene image in real time according to the element grid, and maps the missing scene elements on the wireless mobile communication link to the train central control device according to the interactive mapping.

[0052] The principle of the above technical solution is: The dedicated communication link includes a satellite communication link and a wireless mobile communication link. The satellite communication link is mainly used to receive the positioning data of railway trains, which is the basis for realizing unmanned train driving. The wireless mobile communication link can establish a real-time element grid based on the positioning data of the train in the real-time scene and the scene image captured by the camera in the carriage.

[0053] When the wireless mobile communication link has unstable signals, the interactive compensation communication link needs to intervene. It locates all scene elements on the scene image in real time according to the element grid, and then maps the missing scene elements on the wireless mobile communication link to the train central control device in real time according to the interactive mapping. Under this mapping condition, even if the wireless mobile communication link signal is unstable, the train can still operate normally and can continuously obtain all kinds of required information, ensuring the accuracy and stability of the train's automatic driving.

[0054] As an embodiment of the present invention: the train central control device includes: an edge server, a TCMS control server and a signal server; The edge server is used to obtain scene route data and generate driving instructions through a dedicated communication link; The TCMS control server is used to perform train function control and train monitoring according to driving instructions; The signal server is used to monitor train travel data and perform emergency braking.

[0055] The principle of the above technical solution is: The train central control device consists of three subsystems: edge server, TCMS control server and signal server. These three subsystems together form an efficient and coordinated working mechanism to ensure the safety and smooth operation of the train.

[0056] First, the edge server connects to the cameras and other sensor devices in each carriage through a dedicated communication link to obtain real-time scene line data. This data includes information such as the position, speed, and direction of the carriage, which are all necessary data for automatic train driving. After processing this data, the edge server generates the corresponding driving instructions and sends them to the TCMS control server through a dedicated communication link.

[0057] Next, the TCMS control server is responsible for functional control and monitoring of the train according to the generated driving instructions. The TCMS control server will update the train's position, speed and other information in real time based on the received data, and issue an alarm or take other measures when necessary to ensure the safe operation of the train.

[0058] Finally, the signal server is responsible for monitoring the real-time status of the train's driving data and sending out emergency braking signals when necessary. If the train encounters an abnormal situation, such as excessive speed or deviation from the track, the signal server will immediately send out a braking signal to stop the train as soon as possible to avoid an accident.

[0059] As an embodiment of the present invention: the edge server is further used for: Receive scene images in real time and classify scene elements; According to the classification of scene elements, the first track line violation judgment is performed on different elements on the scene elements; wherein the first track line violation judgment is used to determine the first obstacle that may cause the track line violation; Perform risk assessment on the scene elements after the line-invasion determination, and perform secondary line-invasion determination on the scene elements according to the risk assessment result; wherein the secondary line-invasion determination is used to determine the second obstacle that will move in the first obstacle; Based on the scene elements after the secondary line intrusion judgment, the real-time speed of the rail train, the minimum distance to the obstacle and the emergency braking distance are judged in real time.

[0060] The principle of the above technical solution is: In addition to obtaining scene line data, the present invention also has the function of receiving scene images in real time and classifying scene elements. It can not only perceive and understand the actual environmental conditions, but also respond quickly to environmental changes.

[0061] First, the edge server can receive scene images in real time, process the images, and feed back the processed results to the TCMS control server. This image processing technology may include image recognition, deep learning and other technologies, which can accurately distinguish different elements in the scene, such as roads, pedestrians, obstacles, etc.

[0062] Then, the edge server will make a track intrusion judgment on different elements on the scene elements according to the results of scene element classification. The purpose of the track intrusion judgment here is to find the first obstacle that may threaten the safety of train driving. This judgment is based on the dynamic understanding and analysis of scene elements, so it is real-time and can be continuously updated as the train's driving position changes.

[0063] Next, based on the result of the line-intrusion determination, the edge server will conduct a risk assessment on the scene elements and conduct a secondary line-intrusion determination on the scene elements based on the risk assessment result. The purpose of this secondary line-intrusion determination is to find the second obstacle that may move in the first obstacle. This is to avoid the train from colliding with the first obstacle, and also to ensure that the train can respond in time when encountering a new obstacle.

[0064] Finally, based on the results of the secondary line intrusion judgment, the edge server can determine the real-time speed of the train, the minimum distance from the obstacle and the emergency braking distance in real time, so as to control the movement of the train and ensure the safety of the train.

[0065] As an embodiment of the present invention: the train central control device is also used for: Receive control demand instructions from the train dispatching center and determine the target speed and target location; According to the driving data and target speed, a speed compensation model is built to determine the speed error and speed compensation parameters; According to the speed error, the train guidance instructions are sent to the train central control device. The principle of the above technical solution is: The present invention receives control demand instructions from a train dispatching center, such as setting a target speed and a target location. These instructions come from the train dispatching center and are used to guide the travel path and speed of the train.

[0066] According to the driving data and the target speed, a speed compensation model is built to determine the speed error and speed compensation parameters. These parameters are used to correct the actual speed deviation caused by various factors (such as curves, slopes, etc.) during the actual driving of the train.

[0067] According to the speed error, train guidance instructions are sent to the train central control device. These instructions are used to guide the train to perform emergency braking or adjust the running speed when necessary to ensure that the train always maintains a safe speed range.

[0068] like Figure 2 As shown, the present invention also provides a method for unmanned driving of railway trains as described above, the method comprising: Collect the scene images in front of the railway train track in real time; Get the current position coordinates of the railway train; According to the current position coordinates and scene image, an exclusive communication link is established; wherein the exclusive communication link includes a satellite communication link, a wireless mobile communication link and an interactive compensation communication link; The ATO system's driving data is uploaded to the train dispatching center through a dedicated communication link, and the dispatching instructions from the train dispatching center are received.

[0069] The principle of the above technical solution is: In the actual implementation process, the railway train of the present invention is a rail train, including but not limited to freight trains, mining rail vehicles and passenger trains. First, the main function of the image acquisition device at the front position of the train is to capture the image information of the scene in front of the railway train in real time and generate raw data. Then, the image information will be transmitted to the train central control device for processing.

[0070] The train central control device is responsible for receiving information from various sensors and devices in the train, as well as communicating with external devices. It can receive image information from the image acquisition device on the front of the train, and can also obtain the current location information of the train through the satellite positioning device. The information of the equipment and various sensors will be transmitted through the dedicated communication link inside the train.

[0071] The satellite positioning device is mainly responsible for obtaining the specific location information of the train on the railway. By using the global satellite navigation system (such as the Beidou system, etc.), the geographical location of the train is accurately determined and the geographical coordinates are generated.

[0072] GSM-R communication equipment is a wireless communication device designed specifically for railway transportation, providing communication services for trains in areas without signal coverage. Through interaction with the on-board central control device and other related equipment, a communication link dedicated to the current operating state is constructed. The exclusive communication link includes not only satellite communication links, but also wireless mobile communication links and interactive compensation communication links. The combination of the three links ensures the stability and safety of the train during operation.

[0073] Finally, the train central control device is used to safely and effectively transmit the train travel data sent from the image acquisition device on the front of the train to the train dispatching center through the communication link provided by the satellite positioning device and the GSM-R communication equipment. At the same time, it can also receive dispatching instructions from the train dispatching center and remotely control the train.

[0074] The beneficial effects of the above technical solution are: The unmanned driving system of the present invention can reduce accidents caused by human errors and improve the safety of railway transportation. It can optimize the train running speed and route through automated control and improve transportation efficiency. By establishing a dedicated communication link, stable communication between the train and the dispatching center can be maintained even in remote areas. The train central control device can upload driving data in real time and receive dispatching instructions, which is convenient for the dispatching center to conduct real-time monitoring and dispatching. In the long run, the unmanned driving system can reduce dependence on drivers and reduce labor costs.

[0075] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A railway train unmanned driving system, characterized in that: include: An image acquisition device installed on the front of a railway train, a train central control device interacting with the image acquisition device, a satellite positioning device and a GSM-R communication device communicating with the train central control device; The image acquisition device is used to acquire the scene image in front of the real-time track of the railway train; The satellite positioning device is used to obtain the current position coordinates of the railway train; The GSM-R communication device is used to establish an exclusive communication link according to the current position coordinates and the scene image; wherein the exclusive communication link includes a satellite communication link, a wireless mobile communication link and an interactive compensation communication link; The train central control device is used to upload the travel data of the ATO system to the train dispatching center through a dedicated communication link, and receive dispatching instructions from the train dispatching center.

2. The unmanned railway train driving system according to claim 1, characterized in that: The image acquisition device includes a laser sensing component and a synchronous image component; The laser sensing assembly is configured to generate a first pre-imaging signal based on the echo signal; The synchronized image component is configured to be based on a second pre-imaging signal of a dynamic space; The first pre-imaging signal is loaded into the dynamic scene space generated by the second pre-imaging signal to generate a scene image.

3. The unmanned railway train driving system according to claim 2, characterized in that: The first pre-imaging signal is loaded into the dynamic space generated by the second pre-imaging signal, comprising: Acquire a radar echo signal of a first pre-imaging signal at each moment to construct a first three-dimensional space; Based on the first stereoscopic space, a plurality of target sets in the first stereoscopic space are determined; wherein the target set includes a dynamic target set and a static target set, the dynamic target set is obtained based on a preset motion capture, and the motion capture is configured to identify the signal difference in adjacent frame radar echo signals; Marking the detection target in the second pre-imaging signal to generate a static scene space; The static targets in the static scene space are matched with the static target set, and when the match is successful, the dynamic target set is loaded into the static scene space to generate a dynamic scene space.

4. The unmanned railway train driving system according to claim 3, characterized in that: The satellite positioning device comprises: a track line statistics component and a satellite signal transmission component; The satellite signal transmission component is used to receive longitude and latitude data from positioning satellites in real time; The track line statistics component is used to count the longitude and latitude change data according to the longitude and latitude data, and determine the real-time position of the railway train and the corresponding track line travel trajectory data; Among them, when the rail line driving trajectory data does not belong to the rail line, the longitude and latitude change data is mapped to the target driving route of the rail train, the positioning deviation is determined, and when the positioning deviation is within the preset deviation range, the deviation correction is performed.

5. The unmanned railway train driving system according to claim 1, characterized in that: The dedicated communication link includes: an emergency brake control unit, an unmanned dispatch unit and a track obstacle identification unit; The emergency brake control unit includes a periodic repetitive signal and a monitoring side node for supervising the periodic repetitive signal; wherein the periodic repetitive signal has a signal guidance association with the unmanned dispatching unit and the track obstacle identification unit; the monitoring side node is used to determine whether the periodic repetitive signal generates a signal change, and generate an emergency brake signal according to the signal change; The unmanned dispatching unit includes a plurality of aggregation nodes, each of which is configured to generate one or more control instructions for a rail vehicle control process; The track obstacle identification unit includes a plurality of link logic access points, and the link logic access points are used to respond to the target identification mechanism of the image acquisition device and receive the corresponding scene image; wherein, the link logic access point corresponds to a unique target identification mechanism.

6. The unmanned railway train driving system according to claim 1, characterized in that: In the dedicated communication link, the satellite communication link is used to receive the positioning data of the railway train, and the wireless mobile communication link is used to establish the element grid according to the positioning data and the scene image; When the wireless mobile communication link has unstable signal, the interactive compensation communication link locates the scene elements on the scene image in real time according to the element grid, and maps the missing scene elements on the wireless mobile communication link to the train central control device according to the interactive mapping.

7. The unmanned railway train driving system according to claim 1, characterized in that: The train central control device includes: an edge server, a TCMS control server and a signal server; The edge server is used to obtain scene route data and generate driving instructions through a dedicated communication link; The TCMS control server is used to perform train function control and train monitoring according to driving instructions; The signal server is used to monitor train travel data and perform emergency braking.

8. The unmanned railway train driving system according to claim 7, characterized in that: The edge server is also used for: Receive scene images in real time and classify scene elements; According to the classification of scene elements, the first track line violation judgment is performed on different elements on the scene elements; wherein the first track line violation judgment is used to determine the first obstacle that may cause the track line violation; Perform risk assessment on the scene elements after the line-invasion determination, and perform secondary line-invasion determination on the scene elements according to the risk assessment result; wherein the secondary line-invasion determination is used to determine the second obstacle that will move in the first obstacle; Based on the scene elements after the secondary line intrusion judgment, the real-time speed of the rail train, the minimum distance to the obstacle and the emergency braking distance are judged in real time.

9. The unmanned railway train driving system according to claim 1, characterized in that: The train central control device is also used for: Receive control demand instructions from the train dispatching center and determine the target speed and target location; According to the driving data and target speed, a speed compensation model is built to determine the speed error and speed compensation parameters; Based on the speed error, train guidance instructions are issued to the train central control device.

10. A method for unmanned driving of railway trains, applicable to the system of any one of claims 1 to 9, characterized in that: The method comprises: Collect the scene images in front of the railway train track in real time; Get the current position coordinates of the railway train; According to the current position coordinates and scene image, an exclusive communication link is established; wherein the exclusive communication link includes a satellite communication link, a wireless mobile communication link and an interactive compensation communication link; The ATO system's driving data is uploaded to the train dispatching center through a dedicated communication link, and the dispatching instructions from the train dispatching center are received.