Method and device for generating virtual track information of railway vehicle and railway vehicle

Abstract

The invention provides a method and device for generating virtual rail information of a rail vehicle and the rail vehicle. The rail vehicle is provided with a plurality of position positioning sensors. The method comprises the following steps: before the rail vehicle is started to run, determining each target reference route formed in the running process of the rail vehicle along a virtual rail center based on each position positioning sensor; under the condition that the rail vehicle is started to run, real-time position information of the rail vehicle is collected in real time based on position positioning sensors; based on the real-time position information and a target reference route corresponding to the real-time position information, determining initial preview driving track data formed under each position positioning sensor; and processing the initial preview driving track data to obtain target virtual track information. The virtual track information can be accurately generated, and the accurate sensing ability of the automatic driving system is improved.

Description

Technical Field

[0001] The present invention relates to the field of virtual track technology, and in particular to a method and device for generating virtual track information of a rail vehicle, and a rail vehicle. Background Art

[0002] As a hot topic of research in the current industry and academia, the core goal of autonomous driving technology is to reduce the driver's driving burden and significantly improve the safety of the vehicle during driving. In order to achieve this goal, the autonomous driving system must ensure that the vehicle can continuously and stably stay within the lane line. In order to achieve stable driving of the vehicle, the vehicle's accurate perception of the lane line is particularly important.

[0003] In traditional solutions, autonomous driving systems mainly rely on single sensor data to identify and locate lane lines. However, single sensor data may be affected by environmental conditions, obstructions and other factors, resulting in low recognition accuracy and unable to meet the autonomous driving system's need for accurate perception of vehicle status.

[0004] Therefore, finding a method for generating virtual track information of rail vehicles that can accurately generate virtual track information has become a research hotspot. Summary of the invention

[0005] The present invention provides a method and device for generating virtual track information of a rail vehicle and a rail vehicle, which can accurately generate virtual track information and improve the accurate perception capability of an automatic driving system.

[0006] The present invention provides a method for generating virtual track information of a rail vehicle, wherein the rail vehicle is provided with a plurality of position positioning sensors; the method comprises: before the rail vehicle starts to travel, determining each target reference route formed in the process of the rail vehicle traveling along the center of a virtual track based on each of the position positioning sensors; when the rail vehicle starts to travel, collecting each real-time position information of the rail vehicle in real time based on each of the position positioning sensors; determining initial preview driving track data formed under each of the position positioning sensors based on the real-time position information and the target reference route corresponding to the real-time position information; processing each of the initial preview driving track data to obtain target virtual track information, wherein the target virtual track information is used to characterize the track information on which the rail vehicle is about to travel.

[0007] According to a method for generating virtual track information of a rail vehicle provided by the present invention, the processing of each of the initial preview driving trajectory data to obtain the target virtual track information specifically includes: determining weight values ​​of each of the initial preview driving trajectory data respectively, wherein the weight values ​​are determined according to the positioning accuracy of each of the position positioning sensors; and performing weighted fusion processing based on the weight values ​​and each of the initial preview driving trajectory data to obtain the target virtual track information.

[0008] According to a method for generating virtual track information of a rail vehicle provided by the present invention, before processing each of the initial preview driving trajectory data to obtain the target virtual track information, the method further includes: obtaining a Jacobian matrix of the observation equation for the state quantity based on the position information output by each of the position positioning sensors and a state quantity in a predetermined error state Kalman filter algorithm; processing each of the initial preview driving trajectory data to obtain the target virtual track information specifically includes: substituting the initial preview driving trajectory data into the Jacobian matrix of the observation equation for the state quantity, performing Kalman gain calculation on each observation, and obtaining an error state estimate of the state quantity, wherein the observation includes the position information output by each of the position positioning sensors; the state quantity is used to characterize the state quantity involved in the operation of the rail vehicle; based on the error state estimate and the state quantity, obtaining a corrected state quantity; based on the corrected state quantity, obtaining the target virtual track information.

[0009] According to a method for generating virtual track information of a rail vehicle provided by the present invention, the target virtual track information is obtained based on the corrected state quantity, specifically comprising: determining the target real-time position information of the rail vehicle based on the corrected state quantity, wherein the target real-time position information is used to characterize the real-time position information of the rail vehicle with an accuracy higher than an accuracy threshold; and comparing the target real-time position information with the standard route data in the target reference route to obtain the target virtual track information.

[0010] According to a method for generating virtual track information of a rail vehicle provided by the present invention, the initial preview driving trajectory data formed under each of the position positioning sensors is determined based on the real-time position information and the target reference route corresponding to the real-time position information, specifically including: comparing the real-time position information with the standard route data in the target reference route to obtain the initial preview driving trajectory data formed under each of the position positioning sensors.

[0011] According to a method for generating virtual track information of a rail vehicle provided by the present invention, the rail vehicle is further provided with a visual sensor; before determining each target reference route formed in the process of the rail vehicle traveling along the center of the virtual track based on each of the position positioning sensors, the method further includes: determining a reference distance from the center of the lane based on the visual sensor, wherein the reference distance from the center of the lane is used to characterize the distance by which the rail vehicle deviates from the center of the virtual track during normal driving of the rail vehicle; determining each target reference route formed in the process of the rail vehicle traveling along the center of the virtual track based on each of the position positioning sensors specifically includes: determining each reference route formed in the process of the rail vehicle traveling along the center of the virtual track based on each of the position positioning sensors; performing deviation processing on each of the reference routes based on the reference distance from the center of the lane to obtain each target reference route formed in the process of the rail vehicle traveling along the center of the virtual track under each of the position positioning sensors.

[0012] According to a method for generating virtual track information of a rail vehicle provided by the present invention, the multiple position positioning sensors include a combined navigation device, a laser radar and a magnetic sensor; the reference route includes a first reference route corresponding to the combined navigation device, a second reference route corresponding to the laser radar, and a third reference route corresponding to the magnetic sensor; the target reference route includes a first target reference route corresponding to the first reference route, a second target reference route corresponding to the second reference route, and a third target reference route corresponding to the third reference route; the method of determining the reference routes formed in the process of the rail vehicle traveling along the center of the virtual track based on each of the position positioning sensors specifically includes: determining the first reference route formed in the process of the rail vehicle traveling along the center of the virtual track based on the combined navigation device; determining the second reference route formed in the process of the rail vehicle traveling along the center of the virtual track based on the laser radar; and determining the second reference route formed in the process of the rail vehicle traveling along the center of the virtual track based on the laser radar. The magnetic sensor is used to determine the third reference route formed in the process of the rail vehicle traveling along the center of the virtual track; the deviation processing of each reference route based on the reference distance from the center of the lane is performed to obtain each target reference route formed in the process of the rail vehicle traveling along the center of the virtual track under each position positioning sensor, specifically including: performing deviation processing on each reference route based on the reference distance from the center of the lane to obtain a first target reference route formed in the process of the rail vehicle traveling along the center of the virtual track under the combined navigation device; performing deviation processing on each reference route based on the reference distance from the center of the lane to obtain a second target reference route formed in the process of the rail vehicle traveling along the center of the virtual track under the laser radar; performing deviation processing on each reference route based on the reference distance from the center of the lane to obtain a third target reference route formed in the process of the rail vehicle traveling along the center of the virtual track under the magnetic sensor.

[0013] The present invention also provides a device for generating virtual track information of a rail vehicle, wherein the rail vehicle is provided with a plurality of position positioning sensors; the device comprises: a determination module, which is used to determine, before the rail vehicle starts to travel, each target reference route formed in the process of the rail vehicle traveling along the center of the virtual track based on each of the position positioning sensors; a collection module, which is used to collect each real-time position information of the rail vehicle in real time based on each of the position positioning sensors when the rail vehicle starts to travel; a processing module, which is used to determine, based on the real-time position information and the target reference route corresponding to the real-time position information, initial preview driving trajectory data formed under each of the position positioning sensors; and a generation module, which is used to process each of the initial preview driving trajectory data to obtain target virtual track information, wherein the target virtual track information is used to characterize the track information on which the rail vehicle is about to travel.

[0014] The present invention also provides a rail vehicle, comprising: a rail vehicle body, and a processor, wherein the processor is used to execute the method for generating virtual track information of the rail vehicle.

[0015] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for generating virtual track information of a rail vehicle as described in any one of the above is implemented.

[0016] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating virtual track information of a rail vehicle as described in any one of the above is implemented.

[0017] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for generating virtual track information of a rail vehicle as described in any one of the above is implemented.

[0018] The present invention provides a method, device and rail vehicle for generating virtual track information of a rail vehicle, wherein the rail vehicle is provided with a plurality of position positioning sensors; the method comprises: before the rail vehicle starts to travel, determining each target reference route formed during the travel of the rail vehicle along the center of the virtual track based on each position positioning sensor; when the rail vehicle starts to travel, collecting each real-time position information of the rail vehicle based on each position positioning sensor in real time; determining the initial preview driving trajectory data formed under each position positioning sensor based on the real-time position information and the target reference route corresponding to the real-time position information; processing each initial preview driving trajectory data to obtain the target virtual track information. The virtual track information can be accurately generated, and the accurate perception capability of the automatic driving system is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 It is a flow chart of a method for generating virtual track information of a rail vehicle provided by the present invention.

[0021] Figure 2It is a flow chart of processing each initial preview driving trajectory data to obtain target virtual track information provided by the present invention.

[0022] Figure 3 It is a schematic flow chart of determining each target reference route formed during the travel of a rail vehicle along the center of a virtual track based on each position positioning sensor provided by the present invention.

[0023] Figure 4 It is a structural schematic diagram of a device for generating virtual track information of a rail vehicle provided by the present invention.

[0024] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] The method for generating virtual track information of rail vehicles provided by the present invention can realize accurate identification of vehicle target trajectory and lateral offset through multi-sensor data fusion technology combined with vision, lidar, integrated navigation system, magnetic sensor, etc., and generate virtual track information based on this, thereby supporting the realization of vehicle autonomous driving capability.

[0027] Figure 1 It is a flow chart of a method for generating virtual track information of a rail vehicle provided by the present invention.

[0028] The following will be combined Figure 1 The process of the method for generating virtual track information of a rail vehicle provided by the present invention is described.

[0029] In an exemplary embodiment of the present invention, the rail vehicle may be provided with a plurality of position positioning sensors, such as a combined navigation device, a laser radar, a magnetic sensor, a visual sensor, etc. In this embodiment, the position positioning sensor is not specifically limited.

[0030] Combination Figure 1 It can be seen that the method for generating virtual track information of a rail vehicle may include steps 110 to 140, and each step will be introduced below.

[0031] In step 110, before the rail vehicle starts running, each target reference route formed during the rail vehicle running along the center of the virtual track is determined based on each position positioning sensor.

[0032] In one embodiment, before the rail vehicle starts to travel, each target reference route formed during the rail vehicle's travel along the center of the virtual track can be determined based on each position positioning sensor. The target reference route can be considered as the route that the rail vehicle travels on the virtual track during normal operation.

[0033] In step 120, when the rail vehicle starts running, various real-time position information of the rail vehicle is collected in real time based on various position positioning sensors.

[0034] In another embodiment, when the rail vehicle starts to travel, each real-time position information of the rail vehicle can be collected in real time based on each position positioning sensor. In one example, when the position positioning sensor is a combined navigation device, the current real-time position of the vehicle (corresponding real-time position information) can be obtained based on the combined navigation device. When the position positioning sensor is a laser radar, the current real-time position of the vehicle (corresponding real-time position information) can be obtained based on the laser radar through the SLAM algorithm. When the position positioning sensor is a magnetic sensor, the current real-time position of the vehicle (corresponding real-time position information) can be obtained based on the magnetic sensor to detect the ground magnetic nail information.

[0035] In step 130, based on the real-time position information and the target reference route corresponding to the real-time position information, the initial preview driving trajectory data formed under each position positioning sensor is determined.

[0036] In another embodiment, the initial preview driving trajectory data formed at each position positioning sensor can be determined based on the real-time position information obtained by each position sensor and the target reference route corresponding to the real-time position information (corresponding to the target reference route determined at each position sensor).

[0037] In one example, when the position positioning sensor is a combined navigation device, the current real-time position of the vehicle (corresponding real-time position information) can be obtained based on the combined navigation device, and compared with the target data in the target reference route determined under the combined navigation device to obtain the initial preview driving trajectory data formed under the combined navigation device.

[0038] In another example, when the positioning sensor is a lidar, the current real-time position of the vehicle (corresponding real-time position information) can be obtained through a SLAM algorithm based on the lidar, and compared with the target data in the target reference route determined under the lidar, to obtain the initial preview driving trajectory data formed under the lidar.

[0039] In another example, when the position positioning sensor is a magnetic sensor, the current real-time position of the vehicle (corresponding real-time position information) can be obtained based on the magnetic sensor to detect the ground magnetic nail information, and compared with the target data in the target reference route determined under the magnetic sensor to obtain the initial preview driving trajectory data formed under the magnetic sensor.

[0040] In another embodiment, the lane information ahead can be obtained based on the visual sensor device, and the lane center formed by the left and right lanes ahead is used as the target trajectory. The forward preview driving trajectory number based on the vehicle coordinate system is obtained through perspective transformation, that is, the initial preview driving trajectory data formed under the visual sensor is obtained.

[0041] In step 140, each initial preview driving trajectory data is processed to obtain target virtual track information, wherein the target virtual track information is used to represent the track information on which the rail vehicle is about to travel.

[0042] In another embodiment, each initial preview driving trajectory data can be processed to obtain target virtual track information, and the operation of the rail vehicle can be guided based on the target virtual track information, thereby achieving accurate generation of virtual track information and improving the precise perception capability of the automatic driving system.

[0043] In another exemplary embodiment of the present invention, continuing with the above Figure 1 The above embodiment is used as an example for explanation, wherein the processing of each of the initial preview driving trajectory data to obtain the target virtual track information (corresponding to step 140) can be implemented in the following manner: Determine the weight value of each initial preview driving trajectory data respectively, wherein the weight value is determined according to the positioning accuracy of each position positioning sensor; Based on the weight value and each initial preview driving trajectory data, weighted fusion processing is performed to obtain the target virtual track information.

[0044] In one embodiment, when each initial preview driving trajectory data determined by each position sensor is obtained, the weight value of each initial preview driving trajectory data can also be determined respectively, wherein the weight value can be determined according to the positioning accuracy of each position positioning sensor. It can be understood that the higher the positioning accuracy of the position positioning sensor, the higher the corresponding weight value.

[0045] In the application process, weighted fusion processing can be performed based on the weight value and each initial preview driving trajectory data, so as to obtain the target virtual track information. In this embodiment, the obtained target virtual track information is determined based on multiple groups of position positioning sensors, and the positioning accuracy of each position positioning sensor is also integrated, so as to ensure the rationality and referenceability of the obtained target virtual track information.

[0046] Figure 2 It is a flow chart of processing each initial preview driving trajectory data to obtain target virtual track information provided by the present invention.

[0047] The following will be combined Figure 2 The process of processing each initial preview driving trajectory data to obtain the target virtual track information is described.

[0048] In an exemplary embodiment of the present invention, Figure 2 It can be seen that processing each initial preview driving trajectory data to obtain the target virtual track information may include steps 210 to 240, and each step will be introduced below.

[0049] In step 210, the Jacobian matrix of the observation equation for the state quantity is obtained based on the position information output by each position positioning sensor and the state quantity in the predetermined error state Kalman filter algorithm.

[0050] In one embodiment, the Jacobian matrix of the observation equation for the state quantity can be obtained based on the position information output by each position positioning sensor and the state quantity in the predetermined error state Kalman filter algorithm. The state quantity can be used to characterize the state quantity involved in the operation of the rail vehicle. The state quantity may include the translation p in the three-dimensional space of the world coordinate system; the velocity v in the three-dimensional space of the world coordinate system; the rotation R in the three-dimensional space of the world coordinate system; the accelerometer zero bias b a ; Angular velocity meter zero bias b g ; The gravitational acceleration g in the three-dimensional space of the world coordinate system; The lateral offset e between the vehicle center and the virtual trajectory.

[0051] In step 220, the initial preview driving trajectory data is substituted into the Jacobian matrix of the observation equation for the state quantity, and the Kalman gain is calculated for each observation to obtain an error state estimate about the state quantity, wherein the observation includes the position information output by each position positioning sensor; the state quantity is used to characterize the state quantity involved in the operation of the rail vehicle.

[0052] In step 230, based on the error state estimation and the state quantity, a corrected state quantity is obtained.

[0053] In step 240, target virtual track information is obtained based on the corrected state quantity.

[0054] In another embodiment, the initial preview driving trajectory data can be substituted into the Jacobian matrix of the state quantity of the observation equation, and the Kalman gain calculation is performed on each observation to obtain an error state estimate about the state quantity, wherein the observation may include the position information output by each position positioning sensor. Further, based on the error state estimate and the state quantity, a corrected state quantity is obtained, and based on the corrected state quantity, the target virtual track information is obtained. In this embodiment, an error state Kalman filter (ESKF) algorithm is used to estimate the state of the vehicle system. By simultaneously estimating a group of state quantities, a tight coupling of multiple observation modules is achieved, so that the target virtual track information can be accurately obtained based on each initial preview driving trajectory data.

[0055] In another exemplary embodiment of the present invention, continuing with the above Figure 2 The above embodiment is used as an example for explanation, wherein, based on the corrected state quantity, obtaining the target virtual track information (corresponding to step 240) can be implemented in the following manner: Determine the target real-time position information of the rail vehicle based on the corrected state quantity, wherein the target real-time position information is used to represent the real-time position information of the rail vehicle with an accuracy higher than an accuracy threshold; The target real-time position information is compared with the standard route data in the target reference route to obtain the target virtual track information.

[0056] In one embodiment, the target real-time position information of the rail vehicle can be determined based on the corrected state quantity determined by the error state Kalman filter (ESKF) algorithm. In one example, the corrected state quantity can be used as the target real-time position information of the rail vehicle. It can be understood that the target real-time position information can be considered as real-time position information with higher accuracy than the real-time position information collected by the position positioning sensor.

[0057] Furthermore, the target real-time position information is compared with the standard route data in the target reference route, so as to obtain the target virtual track information. The target reference route may be a target reference route formed under any position positioning sensor. In this embodiment, the target real-time position information obtained is more accurate than the real-time position information collected by the position positioning sensor, and then the target virtual track information with higher accuracy can be obtained based on the target real-time position information and the standard route data in the target reference route.

[0058] In another exemplary embodiment of the present invention, continuing with the above Figure 1The above embodiment is used as an example for explanation, wherein, based on the real-time position information and the target reference route corresponding to the real-time position information, the initial preview driving trajectory data formed under each position positioning sensor is determined (compared with step 130), which can be implemented in the following manner: The real-time position information is compared with the standard route data in the target reference route to obtain the initial preview driving trajectory data formed under the positioning sensor at each position.

[0059] In one embodiment, the real-time position information may be compared with the standard route data in the target reference route, so as to obtain the forward preview driving trajectory data (corresponding to the initial preview driving trajectory data) formed under each position positioning sensor.

[0060] Figure 3 It is a schematic flow chart of determining each target reference route formed during the travel of a rail vehicle along the center of a virtual track based on each position positioning sensor provided by the present invention.

[0061] The following will be combined Figure 3 The process of determining each target reference route formed when the rail vehicle travels along the center of the virtual track based on each position positioning sensor is described.

[0062] In an exemplary embodiment of the present invention, Figure 3 It can be seen that rail vehicles are also equipped with visual sensors. Figure 3 It can be seen that determining each target reference route formed during the rail vehicle's travel along the center of the virtual track based on each position positioning sensor may include steps 310 to 330, and each step will be introduced below.

[0063] In step 310, a reference distance of deviation from the center of the lane is determined based on a visual sensor, wherein the reference distance of deviation from the center of the lane is used to characterize the distance by which the rail vehicle deviates from the center of the virtual track during normal travel of the rail vehicle.

[0064] In one embodiment, a lane center deviation reference distance may be determined based on a visual sensor, wherein the lane center deviation reference distance may be used to characterize a distance by which a rail vehicle deviates from a virtual track center during normal travel of the rail vehicle.

[0065] In one embodiment, the visual sensor device can obtain the lane information ahead at a frequency of 30 Hz, and detect the left and right lane lines through a lane line detection algorithm, and then obtain the lane line coordinates based on the vehicle coordinate system through perspective transformation, and store the information [left lane line point set, right lane line point set, vehicle deviation from lane center distance] in text form. Among them, the vehicle deviation from the lane center distance can be a deviation from the lane center reference distance. It should be noted that during the normal driving process of rail vehicles, such as in station entry scenarios, waiting for transfer, etc., it is often necessary for rail vehicles to deviate from the center of the track. Therefore, the deviation from the lane center reference distance can be determined based on the visual sensor, and the deviation from the lane center reference distance can be processed for each reference route determined by each position positioning sensor based on the deviation from the lane center reference distance to obtain each target reference route.

[0066] In step 320, each reference route formed during the rail vehicle's travel along the center of the virtual track is determined based on each position positioning sensor.

[0067] In step 330, deviation processing is performed on each reference route based on the reference distance from the center of the lane to obtain each target reference route formed when the rail vehicle travels along the center of the virtual track under each position positioning sensor.

[0068] In another embodiment, each reference route formed by the rail vehicle traveling along the center of the virtual track can be determined based on each position positioning sensor. It can be understood that the reference route can be considered as the route formed by the rail vehicle traveling in the center of the track. In addition, during the normal driving process of the rail vehicle, such as in the scene of entering the station, waiting for transfer, etc., the rail vehicle is often required to deviate from the center of the track. Therefore, the reference distance from the center of the lane can be determined based on the visual sensor, and the process deviation of each reference route determined by each position positioning sensor is processed based on the reference distance from the center of the lane to obtain each target reference route.

[0069] In the application process, each reference route can be processed for deviation based on the reference distance from the lane center, so that each target reference route formed when the rail vehicle travels along the center of the virtual track under each position positioning sensor can be obtained. This lays the foundation for accurately and reasonably determining each initial preview driving trajectory data.

[0070] In another exemplary embodiment of the present invention, continuing with the embodiment described above as an example, the multiple position positioning sensors may include a combined navigation device, a laser radar, and a magnetic sensor; the reference route may include a first reference route corresponding to the combined navigation device, a second reference route corresponding to the laser radar, and a third reference route corresponding to the magnetic sensor; the target reference route may include a first target reference route corresponding to the first reference route, a second target reference route corresponding to the second reference route, and a third target reference route corresponding to the third reference route.

[0071] Among them, based on each position positioning sensor, each reference route formed during the rail vehicle's travel along the center of the virtual track can be determined in the following ways: Based on the integrated navigation device, determining the first reference route formed during the rail vehicle's travel along the center of the virtual track; Based on the laser radar, a second reference route formed when the rail vehicle travels along the center of the virtual track is determined; Based on the magnetic sensor, determining a third reference route formed when the rail vehicle travels along the center of the virtual track; Furthermore, the deviation processing of each reference route is performed based on the reference distance from the center of the lane, and each target reference route formed when the rail vehicle travels along the center of the virtual track under each position positioning sensor is obtained. This can be achieved in the following manner: Deviation processing is performed on each reference route based on a reference distance from the center of the lane to obtain a first target reference route formed during the rail vehicle's travel along the center of the virtual track under the integrated navigation device; Deviation processing is performed on each reference route based on a reference distance from the center of the lane to obtain a second target reference route formed when the rail vehicle travels along the center of the virtual track under the laser radar; Deviation processing is performed on each reference route based on a reference distance from the center of the lane to obtain a third target reference route formed when the rail vehicle travels along the center of the virtual track under the magnetic sensor.

[0072] In one embodiment, a first reference route formed by a rail vehicle traveling along the center of a virtual track can be determined based on a combined navigation device. During application, the combined navigation device can output the position of the vehicle at a frequency of 100 Hz and store [longitude, latitude, vehicle orientation] information in text form, so that the first reference route formed by the rail vehicle traveling along the center of the virtual track can be determined. The combined navigation device can be installed on the top of the vehicle, and can achieve centimeter-level positioning of the vehicle.

[0073] In another embodiment, based on the laser radar, a second reference route formed by the rail vehicle traveling along the center of the virtual track can be determined. During the application process, the laser radar device can output a point cloud around the vehicle at a frequency of 10Hz, and an electronic map of the driving route can be determined based on the point cloud. For example, a point cloud map file can be constructed and stored through a laser SLAM algorithm, which is called an "electronic map". The map is stored in pcd format; [longitude, latitude, vehicle orientation] is stored in text form, so that the second reference route formed by the rail vehicle traveling along the center of the virtual track can be determined. Among them, the laser radar can be installed on the top of the front of the vehicle, and the measurement of the vehicle's position, posture and other states can be achieved by running the laser SLAM algorithm.

[0074] In another embodiment, a third reference route formed by a rail vehicle traveling along the center of a virtual track can be determined based on a magnetic sensor. During the application process, the magnetic sensor device can detect ground magnetic nail information at a frequency of 100 Hz, and store the information [magnetic nail serial number, magnetic nail located at the magnetic sensor position] in text form, so as to determine the third reference route formed by a rail vehicle traveling along the center of a virtual track. The magnetic sensor can be installed at the bottom of the vehicle, and the position and posture of the vehicle can be measured by detecting the magnetic nails pre-installed on the ground.

[0075] In another embodiment, each reference route can be processed for deviation based on the reference distance from the center of the lane, so as to obtain the first target reference route formed in the process of the rail vehicle traveling along the center of the virtual track under the combined navigation device. In another example, each reference route can be processed for deviation based on the reference distance from the center of the lane, so as to obtain the second target reference route formed in the process of the rail vehicle traveling along the center of the virtual track under the laser radar. In another example, each reference route can be processed for deviation based on the reference distance from the center of the lane, so as to obtain the third target reference route formed in the process of the rail vehicle traveling along the center of the virtual track under the magnetic sensor. In this embodiment, each reference route (including the first reference route, the second reference route and the third reference route) is processed for deviation based on the reference distance from the center of the lane, so as to obtain each target reference route (including the first target reference route, the second target reference route and the third target reference route) formed in the process of the rail vehicle traveling along the center of the virtual track under each position positioning sensor, thereby laying a foundation for accurately and reasonably determining each initial preview driving trajectory data.

[0076] According to the foregoing description, the method for generating virtual track information of rail vehicles provided by the present invention solves the problems of insufficient accuracy of a single sensor and high risk of sensor failure in traditional systems by adopting multi-sensor data fusion technology. By comprehensively utilizing data from multiple sensors such as vision and lidar, accurate recognition of road information and vehicle lateral offset is achieved, and virtual track information is generated, thereby improving the automatic driving system's ability to accurately perceive the vehicle state, reducing the risk of sensor failure, and further improving the robustness and safety of the system.

[0077] The device for generating virtual track information of a rail vehicle provided by the present invention is described below. The device for generating virtual track information of a rail vehicle described below and the method for generating virtual track information of a rail vehicle described above can be referred to each other.

[0078] Figure 4 It is a structural schematic diagram of a device for generating virtual track information of a rail vehicle provided by the present invention.

[0079] The following will be combined Figure 4 The structure of the device for generating virtual track information of rail vehicles will be described.

[0080] In an exemplary embodiment of the present invention, the rail vehicle may be provided with a plurality of position positioning sensors; Figure 4 It can be known that the device may include a determination module 410, a collection module 420, a processing module 430, and a generation module 440, and each module will be introduced below.

[0081] The determination module 410 may be configured to determine, before the rail vehicle starts to travel, the target reference routes formed during the travel of the rail vehicle along the center of the virtual track based on the position positioning sensors respectively; The acquisition module 420 may be configured to acquire the real-time position information of the rail vehicle based on each of the position positioning sensors in real time when the rail vehicle starts to travel; The processing module 430 may be configured to determine initial preview driving trajectory data formed under each of the position positioning sensors based on the real-time position information and a target reference route corresponding to the real-time position information; The generation module 440 may be configured to process each of the initial preview driving trajectory data to obtain target virtual track information, wherein the target virtual track information is used to represent the track information on which the rail vehicle is about to travel.

[0082] In an exemplary embodiment of the present invention, the generation module 440 can process each of the initial preview driving trajectory data to obtain the target virtual track information in the following manner: Determining weight values ​​of each of the initial preview driving trajectory data respectively, wherein the weight values ​​are determined according to the positioning accuracy of each of the position positioning sensors; A weighted fusion process is performed based on the weight value and each of the initial preview driving trajectory data to obtain the target virtual track information.

[0083] In an exemplary embodiment of the present invention, the generating module 440 may also be configured to: According to the position information output by each of the position positioning sensors and the state quantity in the predetermined error state Kalman filter algorithm, the Jacobian matrix of the observation equation for the state quantity is obtained; The generation module 440 can process the initial preview driving trajectory data to obtain the target virtual track information in the following manner: Substituting the initial preview driving trajectory data into the Jacobian matrix of the observation equation for the state quantity, performing Kalman gain calculation on each observation, and obtaining an error state estimate about the state quantity, wherein the observation includes the position information output by each position positioning sensor; the state quantity is used to characterize the state quantity involved in the operation of the rail vehicle; Based on the error state estimate and the state quantity, obtaining a corrected state quantity; Based on the corrected state quantity, target virtual track information is obtained.

[0084] In an exemplary embodiment of the present invention, the generation module 440 may obtain the target virtual track information based on the corrected state quantity in the following manner: Based on the corrected state quantity, determining the target real-time position information of the rail vehicle, wherein the target real-time position information is used to represent the real-time position information of the rail vehicle with an accuracy higher than an accuracy threshold; The target real-time position information is compared with the standard route data in the target reference route to obtain the target virtual track information.

[0085] In an exemplary embodiment of the present invention, the processing module 430 may determine the initial preview driving trajectory data formed under each of the position positioning sensors based on the real-time position information and the target reference route corresponding to the real-time position information in the following manner: The real-time position information is compared with the standard route data in the target reference route to obtain the initial preview driving trajectory data formed under each of the position positioning sensors.

[0086] In an exemplary embodiment of the present invention, the rail vehicle is further provided with a visual sensor; the processing module 430 may also be configured to: Determine a reference distance of deviation from the center of the lane based on the visual sensor, wherein the reference distance of deviation from the center of the lane is used to characterize the distance of deviation of the rail vehicle from the center of the virtual track during normal driving of the rail vehicle; The processing module 430 may determine the target reference routes formed during the rail vehicle's travel along the center of the virtual track based on the position positioning sensors respectively in the following manner: Based on each of the position positioning sensors, determining each reference route formed during the rail vehicle's travel along the center of the virtual track; Deviation processing is performed on each of the reference routes based on the reference distance from the center of the lane to obtain each target reference route formed during the movement of the rail vehicle along the center of the virtual track under each of the position positioning sensors.

[0087] In an exemplary embodiment of the present invention, the multiple position positioning sensors include a combined navigation device, a laser radar, and a magnetic sensor; the reference route includes a first reference route corresponding to the combined navigation device, a second reference route corresponding to the laser radar, and a third reference route corresponding to the magnetic sensor; the target reference route includes a first target reference route corresponding to the first reference route, a second target reference route corresponding to the second reference route, and a third target reference route corresponding to the third reference route; The processing module 430 may determine the reference routes formed during the rail vehicle's travel along the center of the virtual track based on the position positioning sensors respectively in the following manner: Based on the combined navigation device, determining the first reference route formed during the rail vehicle's travel along the center of the virtual track; Based on the laser radar, determining the second reference route formed by the rail vehicle during its travel along the center of the virtual track; Based on the magnetic sensor, determining the third reference route formed during the rail vehicle's travel along the center of the virtual track; The processing module 430 may implement deviation processing on each of the reference routes based on the reference distance from the center of the lane in the following manner to obtain each target reference route formed during the rail vehicle's travel along the center of the virtual track under each of the position positioning sensors: Performing deviation processing on each of the reference routes based on the reference distance from the center of the lane to obtain a first target reference route formed during the rail vehicle traveling along the center of the virtual track under the combined navigation device; Performing deviation processing on each of the reference routes based on the reference distance from the center of the lane to obtain a second target reference route formed when the rail vehicle travels along the center of the virtual track under the laser radar; Deviation processing is performed on each of the reference routes based on the reference distance from the center of the lane to obtain a third target reference route formed when the rail vehicle travels along the center of the virtual track under the magnetic sensor.

[0088] Based on the same inventive concept, the present invention also provides a rail vehicle, which will be described below in conjunction with the following embodiments.

[0089] In an exemplary embodiment of the present invention, a rail vehicle may include a rail vehicle body and a processor, wherein the processor is used to execute the method for generating virtual track information of the rail vehicle described in any of the above items, so as to achieve accurate generation of virtual track information and improve the accurate perception capability of the automatic driving system.

[0090] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the method for generating virtual track information of a rail vehicle, wherein the rail vehicle is provided with a plurality of position positioning sensors; the method comprises: before the rail vehicle starts to travel, determining each target reference route formed during the travel of the rail vehicle along the center of the virtual track based on each of the position positioning sensors; when the rail vehicle starts to travel, collecting each real-time position information of the rail vehicle based on each of the position positioning sensors in real time; determining the initial preview driving trajectory data formed under each of the position positioning sensors based on the real-time position information and the target reference route corresponding to the real-time position information; processing each of the initial preview driving trajectory data to obtain the target virtual track information, wherein the target virtual track information is used to characterize the track information of the rail vehicle to be driven.

[0091] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0092] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for generating virtual track information of a rail vehicle provided by the above-mentioned methods, wherein the rail vehicle is provided with multiple position positioning sensors; the method includes: before the rail vehicle starts to travel, determining each target reference route formed during the travel of the rail vehicle along the center of the virtual track based on each of the position positioning sensors; when the rail vehicle starts to travel, collecting each real-time position information of the rail vehicle in real time based on each of the position positioning sensors; based on the real-time position information and the target reference route corresponding to the real-time position information, determining the initial preview driving trajectory data formed under each of the position positioning sensors; processing each of the initial preview driving trajectory data to obtain the target virtual track information, wherein the target virtual track information is used to characterize the track information on which the rail vehicle is about to travel.

[0093] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the processor executes the method for generating virtual track information of a rail vehicle provided by the above-mentioned methods, wherein the rail vehicle is provided with a plurality of position positioning sensors; the method comprises: before the rail vehicle starts to travel, determining, based on each of the position positioning sensors, each target reference route formed during the travel of the rail vehicle along the center of the virtual track; when the rail vehicle starts to travel, collecting, based on each of the position positioning sensors, each real-time position information of the rail vehicle in real time; determining, based on the real-time position information and the target reference route corresponding to the real-time position information, initial preview driving trajectory data formed under each of the position positioning sensors; processing each of the initial preview driving trajectory data to obtain target virtual track information, wherein the target virtual track information is used to characterize the track information on which the rail vehicle is about to travel.

[0094] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0095] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating virtual track information of a rail vehicle, characterized in that: The rail vehicle is provided with a plurality of position positioning sensors; the method comprises: Before the rail vehicle starts to travel, determining each target reference route formed during the rail vehicle's travel along the center of the virtual track based on each of the position positioning sensors; When the rail vehicle starts to travel, each real-time position information of the rail vehicle is collected in real time based on each position positioning sensor; Based on the real-time position information and the target reference route corresponding to the real-time position information, determine the initial preview driving trajectory data formed under each of the position positioning sensors; Each of the initial preview driving trajectory data is processed to obtain target virtual track information, wherein the target virtual track information is used to represent the track information on which the rail vehicle is about to travel.

2. The method for generating virtual track information of a rail vehicle according to claim 1, characterized in that: The processing of each of the initial preview driving trajectory data to obtain target virtual track information specifically includes: Determining weight values ​​of each of the initial preview driving trajectory data respectively, wherein the weight values ​​are determined according to the positioning accuracy of each of the position positioning sensors; A weighted fusion process is performed based on the weight value and each of the initial preview driving trajectory data to obtain the target virtual track information.

3. The method for generating virtual track information of a rail vehicle according to claim 1, characterized in that: Before processing each of the initial preview driving trajectory data to obtain the target virtual track information, the method further includes: According to the position information output by each of the position positioning sensors and the state quantity in the predetermined error state Kalman filter algorithm, the Jacobian matrix of the observation equation for the state quantity is obtained; The processing of each of the initial preview driving trajectory data to obtain target virtual track information specifically includes: Substituting the initial preview driving trajectory data into the Jacobian matrix of the observation equation for the state quantity, performing Kalman gain calculation on each observation, and obtaining an error state estimate about the state quantity, wherein the observation includes the position information output by each position positioning sensor; the state quantity is used to characterize the state quantity involved in the operation of the rail vehicle; Based on the error state estimate and the state quantity, obtaining a corrected state quantity; Based on the corrected state quantity, target virtual track information is obtained.

4. The method for generating virtual track information of a rail vehicle according to claim 3, characterized in that: The obtaining target virtual orbit information based on the corrected state quantity specifically includes: Based on the corrected state quantity, determining the target real-time position information of the rail vehicle, wherein the target real-time position information is used to represent the real-time position information of the rail vehicle with an accuracy higher than an accuracy threshold; The target real-time position information is compared with the standard route data in the target reference route to obtain the target virtual track information.

5. The method for generating virtual track information of a rail vehicle according to claim 1, characterized in that: The determining of the initial preview driving trajectory data formed under each of the position positioning sensors based on the real-time position information and the target reference route corresponding to the real-time position information specifically includes: The real-time position information is compared with the standard route data in the target reference route to obtain the initial preview driving trajectory data formed under each of the position positioning sensors.

6. The method for generating virtual track information of a rail vehicle according to any one of claims 1 to 5, characterized in that: The rail vehicle is also provided with a visual sensor; before determining each target reference route formed during the rail vehicle's travel along the center of the virtual track based on each of the position positioning sensors, the method further includes: Determine a reference distance of deviation from the center of the lane based on the visual sensor, wherein the reference distance of deviation from the center of the lane is used to characterize the distance of deviation of the rail vehicle from the center of the virtual track during normal driving of the rail vehicle; The determining, based on each of the position positioning sensors, each target reference route formed during the rail vehicle's travel along the center of the virtual track specifically includes: Based on each of the position positioning sensors, determining each reference route formed during the rail vehicle's travel along the center of the virtual track; Deviation processing is performed on each of the reference routes based on the reference distance from the center of the lane to obtain each target reference route formed during the movement of the rail vehicle along the center of the virtual track under each of the position positioning sensors.

7. The method for generating virtual track information of a rail vehicle according to claim 6, characterized in that: The multiple position positioning sensors include a combined navigation device, a laser radar and a magnetic sensor; the reference route includes a first reference route corresponding to the combined navigation device, a second reference route corresponding to the laser radar, and a third reference route corresponding to the magnetic sensor; The target reference route includes a first target reference route corresponding to the first reference route, a second target reference route corresponding to the second reference route, and a third target reference route corresponding to the third reference route; The determining, based on each of the position positioning sensors, each reference route formed during the rail vehicle's travel along the center of the virtual track specifically includes: Based on the combined navigation device, determining the first reference route formed during the rail vehicle's travel along the center of the virtual track; Based on the laser radar, determining the second reference route formed by the rail vehicle during its travel along the center of the virtual track; Based on the magnetic sensor, determining the third reference route formed during the rail vehicle's travel along the center of the virtual track; The deviation processing of each reference route based on the reference distance from the center of the lane is performed to obtain each target reference route formed when the rail vehicle travels along the center of the virtual track under each position positioning sensor, specifically includes: Performing deviation processing on each of the reference routes based on the reference distance from the center of the lane to obtain a first target reference route formed during the rail vehicle traveling along the center of the virtual track under the combined navigation device; Performing deviation processing on each of the reference routes based on the reference distance from the center of the lane to obtain a second target reference route formed when the rail vehicle travels along the center of the virtual track under the laser radar; Deviation processing is performed on each of the reference routes based on the reference distance from the center of the lane to obtain a third target reference route formed when the rail vehicle travels along the center of the virtual track under the magnetic sensor.

8. A device for generating virtual track information of a rail vehicle, characterized in that: The rail vehicle is provided with a plurality of position positioning sensors; the device comprises: A determination module, used for determining, before the rail vehicle starts to travel, each target reference route formed during the rail vehicle's travel along the center of the virtual track based on each of the position positioning sensors; A collection module, used for collecting each real-time position information of the rail vehicle in real time based on each position positioning sensor when the rail vehicle starts running; A processing module, configured to determine initial preview driving trajectory data formed under each of the position positioning sensors based on the real-time position information and a target reference route corresponding to the real-time position information; A generation module is used to process each of the initial preview driving trajectory data to obtain target virtual track information, wherein the target virtual track information is used to represent the track information on which the rail vehicle is about to travel.

9. A rail vehicle, characterized in that: The rail vehicle comprises: The rail vehicle body, and A processor, wherein the processor is used to execute the method for generating virtual track information of a rail vehicle as described in any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for generating virtual track information of a rail vehicle as claimed in any one of claims 1 to 7 is implemented.

Images