阅读说明：本技术 一种识别列车道岔走向的方法及系统 (Method and system for identifying train turnout trend ) 是由 张宇旻 张强 于 2021-08-18 设计创作，主要内容包括：本发明提供一种识别列车道岔走向的方法及系统,包括：基于实时扫描点云数据和列车电子地图,确定第一走向判断结果；基于获取列车道岔转向角度,确定第二走向判断结果；对所述第一走向判断结果和所述第二走向判断结果进行交叉验证,确定列车走向判断结果。本发明通过实时扫描点云与高精度电子地图的匹配,以及IMU水平角速度的积分实现了两种列车走向的快速识别,并通过两种方法的交叉印证实现了对列车走向的可靠检测。(The invention provides a method and a system for identifying the direction of a train turnout, which comprises the following steps: determining a first trend judgment result based on the real-time scanning point cloud data and the train electronic map; determining a second trend judgment result based on the obtained train turnout turning angle; and performing cross validation on the first trend judgment result and the second trend judgment result to determine a train trend judgment result. The invention realizes the rapid identification of the trends of two trains through the matching of real-time scanning point clouds and a high-precision electronic map and the integral of the horizontal angular velocity of the IMU, and realizes the reliable detection of the trends of the trains through the cross-certification of the two methods.)

1. A method of identifying a switch course of a train, comprising:

determining a first trend judgment result based on the real-time scanning point cloud data and the train electronic map;

determining a second trend judgment result based on the obtained train turnout turning angle;

and performing cross validation on the first trend judgment result and the second trend judgment result to determine a train trend judgment result.

2. The method for identifying the track of a train switch as claimed in claim 1, wherein the determining the first track judgment result based on the real-time scanning point cloud data and the train electronic map comprises:

acquiring point cloud data, inertia measurement data and vehicle speed data of the whole train operation line;

preprocessing the point cloud data to obtain corrected point cloud data;

storing initial data in the corrected point cloud data into an initial train electronic map, and performing pose estimation by combining the inertial measurement data and the speed data to obtain initial estimation pose data;

and superposing and storing subsequent point cloud data in the corrected point cloud data into the initial train electronic map, and estimating the pose by combining the inertial measurement data and the vehicle speed data until all the point cloud data are processed to obtain the train electronic map.

3. The method for identifying the train turnout trend according to claim 1 or 2, wherein the determining the first trend judgment result based on the real-time scanning point cloud data and the train electronic map further comprises:

and acquiring a positioning steering angle and a reverse steering angle of each turnout passing through a preset distance of a turnout point in the whole train running line.

4. The method for identifying the direction of a train turnout according to claim 1, wherein the determining a first direction judgment result based on the real-time scanning point cloud data and the train electronic map comprises:

acquiring current scanning point cloud data in the running process of a train, and preprocessing the real-time scanning point cloud data to obtain corrected current scanning point cloud data;

integrating the vehicle speed data and the inertia measurement angular velocity to obtain the estimation pose of the current scanning point cloud;

based on the current scanning point cloud estimation pose, matching the corrected current scanning point cloud data with the point cloud data in the train electronic map to obtain the accurate position of the train;

and when the train passes through any turnout, respectively acquiring a first distance between the accurate position of the train and the positioning track and a second distance between the accurate position of the train and the positioning track and the inverted track, and determining a first trend judgment result based on the first distance and the second distance.

5. The method of identifying a train switch course according to claim 4, wherein the determining the first course determination result based on the first distance and the second distance comprises:

if the difference between the first distance and the second distance is larger than a first threshold value, determining that the train is located on the inverted track;

and if the difference obtained by subtracting the first distance from the second distance is larger than a second threshold value, determining that the train is located on the positioning track.

6. The method for identifying the direction of a train switch according to claim 1, wherein the determining the second direction determination result based on the obtained train switch turning angle comprises:

calculating the inertia measurement horizontal angular velocity integral of the train passing through any turnout, and acquiring the rotation angle of the train in the horizontal direction when the train passes through a preset distance of a turnout point;

and determining the second trend judgment result based on the rotation angle, the positioning steering angle and the reverse steering angle.

7. A system for identifying the course of a train switch, comprising:

the first determining module is used for determining a first trend judging result based on the real-time scanning point cloud data and the train electronic map;

the second determining module is used for determining a second trend judgment result based on the obtained train turnout turning angle;

and the verification module is used for performing cross verification on the first trend judgment result and the second trend judgment result to determine a train trend judgment result.

8. An electronic device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor when executing the program performs the steps of the method of identifying a switch course of a train as claimed in any one of claims 1 to 6.

9. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the method for identifying a switch course of a train as claimed in any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, carries out the steps of a method for identifying the course of a train switch according to any one of claims 1 to 6.

Technical Field

The invention relates to the technical field of rail transit, in particular to a method and a system for identifying the direction of a train turnout.

Background

In the current train operation control system, when a train passes through a turnout, the state of a point switch machine of the point switch machine is generally collected by ground equipment, and the mileage of the train is combined to comprehensively confirm the positioning or the reverse position of the train entering the turnout. The train cannot know the exact direction within a period of time after passing through the turnout, and only the train passes through the nearest transponder, so that the train can know the exact direction and position of the train, as shown in figure 1.

For the above situation, if no ground turnout state is sent to the train, the train does not know the exact direction of the train itself within a period of time after passing the turnout, and is always in the state of 'blind-running' until passing the nearest transponder, the distance is tens of meters as short as one distance, and hundreds of meters as long as one distance, depending on the position of the transponder. For the new generation of active train perception system independent of ground system, the distance of blind train passing through the switch is longer until a recognizable landmark (such as a platform) is encountered. If the exact position of the train is unknown, the active sensing system cannot load a proper map, so that the sensing capability is seriously reduced, the track trend in front cannot be predicted by the train, and the barrier cannot be reliably detected, thereby forming a greater threat to the driving safety.

Therefore, in order to overcome the above-mentioned defects, a new method for identifying the train turnout trend needs to be provided.

Disclosure of Invention

The invention provides a method and a system for identifying the direction of a train turnout, which are used for solving the defect that the identification of the direction of the train turnout in the prior art needs ground equipment.

In a first aspect, the present invention provides a method for identifying a train switch trend, including:

determining a first trend judgment result based on the real-time scanning point cloud data and the train electronic map;

determining a second trend judgment result based on the obtained train turnout turning angle;

and performing cross validation on the first trend judgment result and the second trend judgment result to determine a train trend judgment result.

In one embodiment, the determining a first trend determination result based on the real-time scanning point cloud data and the train electronic map comprises:

acquiring point cloud data, inertia measurement data and vehicle speed data of the whole train operation line;

preprocessing the point cloud data to obtain corrected point cloud data;

storing initial data in the corrected point cloud data into an initial train electronic map, and performing pose estimation by combining the inertial measurement data and the speed data to obtain initial estimation pose data;

and superposing and storing subsequent point cloud data in the corrected point cloud data into the initial train electronic map, and estimating the pose by combining the inertial measurement data and the vehicle speed data until all the point cloud data are processed to obtain the train electronic map.

In one embodiment, the determining a first trend determination result based on the real-time scanning point cloud data and the train electronic map further includes:

and acquiring a positioning steering angle and a reverse steering angle of each turnout passing through a preset distance of a turnout point in the whole train running line.

In one embodiment, the determining a first trend determination result based on the real-time scanning point cloud data and the train electronic map includes:

acquiring current scanning point cloud data in the running process of a train, and preprocessing the real-time scanning point cloud data to obtain corrected current scanning point cloud data;

integrating the vehicle speed data and the inertia measurement angular velocity to obtain the estimation pose of the current scanning point cloud;

based on the current scanning point cloud estimation pose, matching the corrected current scanning point cloud data with the point cloud data in the train electronic map to obtain the accurate position of the train;

and when the train passes through any turnout, respectively acquiring a first distance between the accurate position of the train and the positioning track and a second distance between the accurate position of the train and the positioning track and the inverted track, and determining a first trend judgment result based on the first distance and the second distance.

In one embodiment, the determining the first trend determination result based on the first distance and the second distance includes:

if the difference between the first distance and the second distance is larger than a first threshold value, determining that the train is located on the inverted track;

and if the difference obtained by subtracting the first distance from the second distance is larger than a second threshold value, determining that the train is located on the positioning track.

In one embodiment, the determining the second trend determination result based on the obtained train switch turning angle includes:

calculating the inertia measurement horizontal angular velocity integral of the train passing through any turnout, and acquiring the rotation angle of the train in the horizontal direction when the train passes through a preset distance of a turnout point;

and determining the second trend judgment result based on the rotation angle, the positioning steering angle and the reverse steering angle.

In a second aspect, the present invention further provides a system for identifying the direction of a train switch, including:

the first determining module is used for determining a first trend judging result based on the real-time scanning point cloud data and the train electronic map;

the second determining module is used for determining a second trend judgment result based on the obtained train turnout turning angle;

and the verification module is used for performing cross verification on the first trend judgment result and the second trend judgment result to determine a train trend judgment result.

In a third aspect, the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and operable on the processor, wherein the processor executes the program to implement the steps of the method for identifying the direction of a train switch as described in any one of the above.

In a fourth aspect, the present invention further provides a non-transitory computer readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the steps of the method for identifying the switch directions of a train as described in any one of the above.

In a fifth aspect, the present invention further provides a computer program product, which includes a computer program, and the computer program is executed by a processor to implement the steps of the method for identifying the switch direction of a train as described in any one of the above.

The method and the system for identifying the train turnout direction realize the rapid identification of the two train directions by matching the real-time scanning point cloud with the high-precision electronic map and integrating the horizontal angular velocity of the IMU, and realize the reliable detection of the train direction by the cross-certification of the two methods.

Drawings

In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.

FIG. 1 is a schematic diagram of a prior art train operation control system;

FIG. 2 is a schematic flow chart of a method for identifying the direction of a train turnout provided by the invention;

FIG. 3 is a schematic diagram of a train operation control system provided by the present invention;

FIG. 4 is a schematic diagram of a process for generating an electronic map of a train according to the present invention;

FIG. 5 is a schematic diagram of a train switch angle provided by the present invention;

FIG. 6 is a schematic view of a comprehensive train direction identification process provided by the present invention;

FIG. 7 is a schematic illustration of the positioning and flipping track trajectories provided by the present invention;

FIG. 8 is a schematic structural diagram of a system for identifying the direction of a train turnout provided by the invention;

fig. 9 is a schematic structural diagram of an electronic device provided by the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Aiming at the defects in the prior art, the invention provides a method for identifying the direction of a train turnout, which comprises the following steps of:

step S1, determining a first trend judgment result based on the real-time scanning point cloud data and the train electronic map;

step S2, determining a second trend judgment result based on the obtained train turnout turning angle;

and step S3, performing cross validation on the first trend judgment result and the second trend judgment result, and determining a train trend judgment result.

Specifically, firstly, the invention identifies the train direction after the train passes through the turnout based on the matching of the real-time scanning point cloud and the high-precision electronic map, and the train direction is on a positioning track or a reverse track.

It should be noted that the multiple track positions divided by the switch are defined as follows: the common travel position of the turnout is positioning, and the less common travel position is reverse, namely the positioning and the reverse are relative, and the two different directions of the travel track of the turnout are presented.

As shown in fig. 3, the method for identifying the direction of a train after passing through a turnout provided by the invention mainly comprises a vehicle-mounted sensor and a vehicle-mounted computer, wherein the vehicle-mounted sensor comprises a laser radar, an IMU (Inertial Measurement Unit), a millimeter wave radar, a speed sensor and the like; the laser radar scans the front of the train and outputs real-time scanning point cloud, and the positioning and environment perception of the train can be realized based on the point cloud; the IMU outputs the angular speed and the acceleration of the train in all directions in real time, and the estimation of the position and the posture of the train can be realized by combining the speed information provided by the millimeter wave radar or the speed sensor. A high-precision electronic map is built in the vehicle-mounted computer, the positioning steering angle and the reverse steering angle of each turnout are determined, and the matching of real-time scanning point cloud output by the laser radar and the high-precision electronic map is used for realizing the accurate determination of the position of the vehicle, so that the identification of the direction of the vehicle after passing the turnout is realized.

In addition, the steering angle of the train after passing through the turnout can be obtained by integrating the IMU output angular velocity, and the trend of the train is determined by comparing the positioned steering angle with the reversed steering angle.

And comprehensively performing cross verification on the two train moving direction judgment results to obtain a real-time moving direction identification result of the train.

The invention realizes the rapid identification of the trends of two trains through the matching of real-time scanning point clouds and a high-precision electronic map and the integral of the horizontal angular velocity of the IMU, and realizes the reliable detection of the trends of the trains through the cross-certification of the two methods.

Based on the above embodiment, the method step S1 includes:

acquiring point cloud data, inertia measurement data and vehicle speed data of the whole train operation line;

preprocessing the point cloud data to obtain corrected point cloud data;

storing initial data in the corrected point cloud data into an initial train electronic map, and performing pose estimation by combining the inertial measurement data and the speed data to obtain initial estimation pose data;

and superposing and storing subsequent point cloud data in the corrected point cloud data into the initial train electronic map, and estimating the pose by combining the inertial measurement data and the vehicle speed data until all the point cloud data are processed to obtain the train electronic map.

Specifically, before the train is subjected to turnout identification, a high-precision train electronic map needs to be constructed.

The high-precision electronic map mainly comprises a scene point cloud and a track. The scene point cloud is obtained by performing pose estimation and mutual matching on a plurality of frames of pre-collected and preprocessed laser radar point cloud to find out an accurate pose relation, then superposing the pose relations together based on the pose relation, and compressing the pose relations by means of down-sampling and the like.

Before a high-precision electronic map is established, laser radar point cloud data, IMU data and vehicle speed data of the whole line need to be collected, wherein the vehicle speed data can be obtained by a self-millimeter wave radar or a self-speed sensor.

When the point cloud is collected, the influence of any obstacle in front, such as a vehicle or a pedestrian, is avoided, so that the established high-precision electronic map is free from the interference of the obstacle, and then the point cloud is preprocessed, noise is eliminated, and intra-frame correction is carried out.

Further, the obtained initial point cloud data, namely the first frame point cloud, is directly added into the electronic map, then the accurate relative pose of the subsequent point cloud and the electronic map is obtained through pose estimation and matching with the electronic map, and then the subsequent point cloud is successively superposed into the high-precision electronic map according to the accurate pose until all the point cloud data are processed, wherein the process is shown in fig. 4.

Because the position relation between the laser radar and the vehicle body is fixed, and the vehicle body is right above the track, the position of the track center right below the radar can be converted through the position of the laser radar. In the process of overlaying the point clouds to the high-precision electronic map, the coordinate origin (namely the position of the radar) of each frame of point cloud is taken and converted into the position of the center of the track right below the radar, and the point cloud and the position are gathered together to form the track, so that the train electronic map for subsequent use is obtained.

According to the invention, the accurate data of the running track is obtained by constructing the electronic map of the train in advance, so that the trend of the train can be conveniently identified subsequently, and the identification precision and efficiency are improved.

According to any of the above embodiments, the method step S1 is preceded by:

and acquiring a positioning steering angle and a reverse steering angle of each turnout passing through a preset distance of a turnout point in the whole train running line.

Specifically, before identification, in addition to constructing an electronic map of the train, the positioning and the reverse steering angle at a certain distance after each turnout along the running track passes through the turnout point need to be recorded, as shown in fig. 5, it is assumed that the steering angle positioned at a distance of 20 meters from the turnout point is 0 degree, and the corresponding steering angle is 6 degrees.

And completely recording the positioning steering angle and the reverse steering angle corresponding to all turnouts along the running track for comparison and use during subsequent identification.

The invention obtains the angle data of positioning and reverse position by recording the positioning steering angle and the reverse position steering angle of the turnout, combines the angle data with the position information to judge the train direction, and can effectively improve the identification precision.

Based on any of the above embodiments, the method step S1 includes:

acquiring current scanning point cloud data in the running process of a train, and preprocessing the real-time scanning point cloud data to obtain corrected current scanning point cloud data;

integrating the vehicle speed data and the inertia measurement angular velocity to obtain the estimation pose of the current scanning point cloud;

based on the current scanning point cloud estimation pose, matching the corrected current scanning point cloud data with the point cloud data in the train electronic map to obtain the accurate position of the train;

and when the train passes through any turnout, respectively acquiring a first distance between the accurate position of the train and the positioning track and a second distance between the accurate position of the train and the positioning track and the inverted track, and determining a first trend judgment result based on the first distance and the second distance.

Wherein the determining the first trend determination result based on the first distance and the second distance includes:

if the difference between the first distance and the second distance is larger than a first threshold value, determining that the train is located on the inverted track;

and if the difference obtained by subtracting the first distance from the second distance is larger than a second threshold value, determining that the train is located on the positioning track.

Specifically, the high-precision electronic map, the turnout positioning steering angle and the inverted steering angle obtained in the foregoing embodiment are loaded into an on-board computer, as shown in fig. 6, in the vehicle operation process, firstly, the real-time scanning point cloud output by the on-board laser radar is preprocessed, noise points are eliminated, intra-frame correction is performed, then, the estimated pose of the current scanning point cloud is obtained through integration of the vehicle speed and the IMU angular speed, and on the basis of pose estimation, the scanning point cloud is matched with the scene point cloud in the high-precision electronic map, so that the accurate pose of the vehicle is obtained, wherein the accurate pose includes the vehicle position.

After the vehicle passes through the switch point, the distance between the position of the vehicle and the track of the positioning track and the track of the inverted track is calculated, when the difference between the two distances exceeds a certain threshold value, the vehicle is judged to be on one track, as shown in fig. 7, the matching of the scanning point cloud and the high-precision electronic map determines that the vehicle is at the point P, the distance between the point P and the positioning track is d1, namely a first distance, and the distance between the point P and the positioning track is d2, namely a second distance, when the values of d1-d2 are greater than the first threshold value (for example, set to be 2 meters), the train is considered to be in the inverted position, and when the values of d2-d1 are greater than the second threshold value, the train is considered to be in the positioning position.

The invention realizes the rapid identification of the train direction after the train passes through the turnout by means of the vehicle-mounted equipment, does not depend on ground equipment, solves the problem that the train does not know the train direction for a long time after passing through the turnout, enhances the autonomous sensing capability of the train, and obviously improves the intelligent degree of the train.

Based on any of the above embodiments, the method step S2 includes:

calculating the inertia measurement horizontal angular velocity integral of the train passing through any turnout, and acquiring the rotation angle of the train in the horizontal direction when the train passes through a preset distance of a turnout point;

and determining the second trend judgment result based on the rotation angle, the positioning steering angle and the reverse steering angle.

Specifically, the invention also calculates the angle that the train turns in the horizontal direction when the train runs from the switch point (O point) to the P point by integrating the horizontal angular velocity of the IMU, as shown in FIG. 7, if the turned angle is 0 degree, the train is positioned, and if the turned angle is beta, the train is considered to be in the reverse position.

And finally, performing cross certification on the train direction obtained in the embodiment and the train direction obtained in the embodiment, and if the train direction is consistent with the train direction obtained in the embodiment, determining that an accurate train direction identification result is obtained.

The invention calculates the steering angle of the train after passing through the turnout switch at a certain distance by integrating the angular speed output by the IMU, identifies the track of the train, namely the trend of the train according to different steering angles of inversion and positioning, and is used as the identification of supplementary verification, thereby further improving the identification accuracy, realizing real-time verification and error correction, enabling the train to report the accurate position of the train to a control center in time, further shortening the running interval of the train and improving the running efficiency.

The implementation of the invention is illustrated below in a complete example:

1) point cloud, IMU and vehicle speed data are collected. And acquiring data of a line for establishing the high-precision electronic map through a vehicle-mounted laser radar, an IMU (inertial measurement Unit), a millimeter wave radar or a speed sensor.

2) And establishing a high-precision electronic map of the track line. Directly adding the first frame of point cloud into an electronic map, then obtaining the accurate relative pose of the subsequent point cloud and the electronic map through pose estimation and matching with the electronic map, then successively superposing the subsequent point cloud into the high-precision electronic map according to the accurate pose until all point cloud data are processed, finally compressing the electronic map through modes of down-sampling and the like, and finishing map building. Wherein the pose estimate is obtained by integrating the angular velocity of the IMU output and the vehicle velocity.

3) In the process of overlaying the point clouds to the high-precision electronic map, the coordinate origin (namely the position of the radar) of each frame of point cloud is taken and converted into the position of the center of the track right below the radar, and the point clouds are gathered together to form the track.

4) And recording the positioning and reverse steering angle of each turnout at a certain distance after the turnout passes through the turnout point.

5) And loading the high-precision electronic map and the turnout positioning inverted steering angle into the vehicle-mounted computer.

6) Preprocessing the real-time scanning point cloud, acquiring the estimated pose of the current scanning point cloud through integration of vehicle speed and IMU angular speed, and matching the scanning point cloud with the scene point cloud in the high-precision electronic map on the basis of pose estimation to acquire the accurate pose of the vehicle.

7) After the vehicle passes through the switch point, the distances between the position of the vehicle and the positioning track and the track of the inverted track are calculated respectively, and when the difference between the two distances exceeds a certain threshold value, the vehicle is judged to be on one track.

8) And calculating the angle of the train which rotates in the horizontal direction after the train starts from the fork point and runs for a certain distance by integrating the horizontal angular velocity of the IMU, and determining that the train is on one track by matching with the positioning and reversing steering angle.

9) And performing cross certification on the train trends obtained by the two methods, and obtaining the determined trend of the train if the train trends are consistent.

The system for identifying the train turnout trend provided by the invention is described below, and the system for identifying the train turnout trend described below and the method for identifying the train turnout trend described above can be referred to correspondingly.

Fig. 8 is a schematic structural diagram of a system for identifying the direction of a train switch provided by the present invention, as shown in fig. 8, including: a first determination module 81, a second determination module 82, and a verification module 83, wherein:

the first determining module 81 is configured to determine a first trend judgment result based on the real-time scanning point cloud data and the train electronic map; the second determining module 82 is configured to determine a second trend judgment result based on the acquired train turnout turning angle; the verification module 83 is configured to perform cross verification on the first trend judgment result and the second trend judgment result, and determine a train trend judgment result.

The invention realizes the rapid identification of the trends of two trains through the matching of real-time scanning point clouds and a high-precision electronic map and the integral of the horizontal angular velocity of the IMU, and realizes the reliable detection of the trends of the trains through the cross-certification of the two methods.

Fig. 9 illustrates a physical structure diagram of an electronic device, and as shown in fig. 9, the electronic device may include: a processor (processor)910, a communication Interface (Communications Interface)920, a memory (memory)930, and a communication bus 940, wherein the processor 910, the communication Interface 920, and the memory 930 communicate with each other via the communication bus 940. Processor 910 may invoke logic instructions in memory 930 to perform a method of identifying a train switch course, the method comprising: determining a first trend judgment result based on the real-time scanning point cloud data and the train electronic map; determining a second trend judgment result based on the obtained train turnout turning angle; and performing cross validation on the first trend judgment result and the second trend judgment result to determine a train trend judgment result.

Furthermore, the logic instructions in the memory 930 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

In another aspect, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer readable storage medium, when the computer program is executed by a processor, a computer can execute the method for identifying train switch directions provided by the above methods, the method includes: determining a first trend judgment result based on the real-time scanning point cloud data and the train electronic map; determining a second trend judgment result based on the obtained train turnout turning angle; and performing cross validation on the first trend judgment result and the second trend judgment result to determine a train trend judgment result.

In yet another aspect, the present invention further provides a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements a method for identifying a train switch course provided by the above methods, the method comprising: determining a first trend judgment result based on the real-time scanning point cloud data and the train electronic map; determining a second trend judgment result based on the obtained train turnout turning angle; and performing cross validation on the first trend judgment result and the second trend judgment result to determine a train trend judgment result.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.