Virtual track train trajectory tracking method, device and train

Abstract

The present disclosure provides a virtual track train trajectory tracking method, which can be applied to the fields of intelligent transportation and automatic control technology. The method comprises the following steps: constructing a dynamic model based on an energy conversion strategy, initial state information and initial control information of a train, and converting the initial state information of the train into target state information of the train in a vehicle coordinate system by using the dynamic model; determining reference position information corresponding to a virtual track based on a speed component and actual position information of the train, the reference position information representing position information obtained by projecting the actual position information of the train into the virtual track, comprising reference angle information, angle deviation information and reference point position information, and the angle deviation information representing a yaw angle deviation between multiple carriages in the vehicle coordinate system; determining an optimal control amount of the train based on a target function and the reference position information; and tracking a trajectory of the train by using the optimal control amount. The present disclosure also provides a virtual track train trajectory tracking device and a train.

Description

Technical Field

[0001] This disclosure relates to the fields of intelligent transportation and automatic control technology, specifically to a virtual track train trajectory tracking method, device, and train. Background Technology

[0002] The longer body of the virtual track train increases passenger capacity, but the double-articulated structure also places higher demands on steering control. To overcome the rearward amplification effect caused by the articulated structure, vehicles generally adopt an all-axle active steering strategy to eliminate the tail sway phenomenon caused by the response of the first axle steering being delayed step by step through the articulated plate. However, with the introduction of an all-axle steering system, the number of actuators exceeds the train's planar motion degrees of freedom, which can easily lead to overdrive problems, potentially causing motional interference between carriages, resulting in body yaw and excessive wheel slippage. Related technologies mainly involve driver participation in control, using geometric methods and related principles to determine the steering angle of each axle, or using decoupled models to predict control quantities.

[0003] However, the relevant technologies are not suitable for fully autonomous driving. The geometry-based approach lacks consideration of vehicle dynamics, the decoupled model lacks the interaction forces between the vehicle compartments, it is difficult to cope with complex working conditions, and the control accuracy and computational efficiency are low. Summary of the Invention

[0004] In view of the above problems, this disclosure provides a virtual track train trajectory tracking method, device, train, equipment, storage medium and program product.

[0005] According to the first aspect of this disclosure, a virtual track train trajectory tracking method is provided, comprising: constructing a dynamic model based on an energy conversion strategy, initial state information of the train, and initial control information; using the dynamic model to convert the initial state information of the train into target state information of the train in a vehicle coordinate system, wherein the initial state information represents the state information of the train in a global coordinate system, the target state information includes velocity components of actual points on the train in multiple dimensions, the energy conversion strategy represents the relationship between the initial kinetic energy information and initial potential energy information of the train and the initial state information, and the train includes multiple carriages; determining reference position information corresponding to the train and the virtual track based on the velocity components and the actual position information of the train, wherein the reference position information represents the position information obtained by projecting the actual position information of the train onto the virtual track, including reference angle information, angle deviation information, and reference point information, and the angle deviation information represents the yaw angle deviation between multiple carriages in the vehicle coordinate system; determining the optimal control quantity of the train based on an objective function and the reference position information, wherein the objective function is obtained based on the angle deviation information and the lateral deviation information, and the lateral deviation information represents the distance between the actual point and the reference point; and using the optimal control quantity to track the train trajectory.

[0006] According to embodiments of this disclosure, the initial state information includes a state matrix and initial state quantities. The carriages include a head carriage, a middle carriage, and a tail carriage. The actual point includes the first point of the head carriage. The method further includes: determining the state matrix based on the coordinate information of the first point and the first yaw angle of multiple carriages, wherein the state matrix represents the state information of the train in the global coordinate system; and determining the initial state quantities based on the state matrix, the instantaneous rate of change information of the state matrix, and the longitudinal driving torque of the train.

[0007] According to embodiments of this disclosure, the head carriage, middle carriage, and tail carriage each include multiple transverse axes; the method further includes: determining initial control information based on the transverse axis yaw angles of the multiple transverse axes.

[0008] According to embodiments of this disclosure, a dynamic model is constructed based on an energy conversion strategy, initial state information of the train, and initial control information, including: determining mass-related information and force-related information of the train using a state matrix and an energy conversion strategy; summing the mass-related information and force-related information to obtain energy information; and constructing a dynamic model based on the mass-related information, force-related information, and energy information.

[0009] According to embodiments of this disclosure, the method further includes: obtaining a second yaw angle of the head carriage in the vehicle coordinate system; and using the difference between the first yaw angle and the second yaw angle as the yaw angle of the middle carriage or the tail carriage in the vehicle coordinate system.

[0010] According to embodiments of this disclosure, the method further includes: determining a velocity component based on the coordinate information of the second yaw angle and the first point.

[0011] According to embodiments of this disclosure, the method further includes: converting the initial orbit information of the virtual orbit into orbit parameter information based on a preset conversion strategy, wherein the initial orbit information is characterized as the latitude and longitude sequence of the virtual orbit.

[0012] According to embodiments of this disclosure, the actual points include a first point, a second point between the head carriage and the middle carriage, a third point between the middle carriage and the tail carriage, and a fourth point of the tail carriage; the method further includes using the sway angle between the first point and the second point, the sway angle between the second point and the third point, and the sway angle between the third point and the fourth point as reference angle information.

[0013] According to embodiments of this disclosure, the method further includes: determining the reference position information of the first point as the first reference point information; and determining the lateral deviation information based on the difference between the actual position information of the first point and the first reference point information.

[0014] According to embodiments of this disclosure, determining reference position information corresponding to the train and the virtual track based on velocity components and the actual position information of the train includes: determining the train's moving speed based on the train's reference curvature, lateral deviation information, angular deviation information and velocity components; and determining reference position information based on the moving speed and the time corresponding to the moving speed.

[0015] The second aspect of this disclosure provides a virtual track train trajectory tracking device, comprising: a model building module, used to build a dynamic model based on an energy conversion strategy, initial state information of the train, and initial control information, and to convert the initial state information using the dynamic model to obtain target state information of the train in the vehicle coordinate system, wherein the initial state information represents the state information of the train in the global coordinate system, the target state information includes the velocity components of the actual points on the train in multiple dimensions, the energy conversion strategy is used to convert the initial kinetic energy information and initial potential energy information of the train into initial state information, and the train includes multiple carriages; an information conversion module, used to determine the reference position information corresponding to the train and the virtual track based on the velocity components and the actual position information of the train, wherein the reference position information represents the position information obtained by projecting the actual position information of the train onto the virtual track, including reference angle information, angle deviation information, and reference point information, the angle deviation information representing the yaw angle deviation between multiple carriages in the vehicle coordinate system; and a control quantity determination module, used to determine the optimal control quantity of the train based on an objective function and the reference position information, wherein the objective function is obtained based on the angle deviation information and the lateral deviation information, and the lateral deviation information represents the distance between the actual point and the reference point. The trajectory tracking module is used to track the train trajectory using optimal control inputs.

[0016] A third aspect of this disclosure provides a train, comprising: a carriage; a steering actuator for tracking the train's trajectory according to an optimal control quantity; and a virtual track train trajectory tracking device as described above.

[0017] A fourth aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the methods described above.

[0018] A fifth aspect of this disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the methods described above.

[0019] A sixth aspect of this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0020] According to the virtual track train trajectory tracking method, device, train, equipment, storage medium, and program products provided in this disclosure, by fully considering the dynamic characteristics of the vehicle and the real-time changes in the curvature of the virtual track through the dynamic model, tracking responses can be made in advance, improving the tracking accuracy of the train. Since the energy conversion strategy can simplify the initial kinetic energy and initial potential energy information of the train to obtain the dynamic model, the complexity of model prediction is reduced, and the consumption of system computing resources is lowered. The reference position information is obtained in real time based on the actual point position information, realizing the real-time linear optimization of the nonlinear optimization problem, further improving computational efficiency and the control accuracy of train trajectory tracking. Attached Figure Description

[0021] The above and other objects, features and advantages of this disclosure will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0022] Figure 1 The illustration schematically depicts an application scenario of a virtual track train trajectory tracking method, apparatus, and train according to embodiments of the present disclosure;

[0023] Figure 2 A flowchart illustrating a virtual rail train trajectory tracking method according to an embodiment of the present disclosure is shown schematically.

[0024] Figure 3A A schematic diagram of the structure of a virtual rail train according to an embodiment of the present disclosure is shown.

[0025] Figure 3B This diagram schematically illustrates an example of the process of projecting the actual position of a train onto a reference position in a virtual track according to an embodiment of the present disclosure.

[0026] Figure 4 A schematic diagram illustrating the structure of a virtual rail train trajectory tracking device according to an embodiment of the present disclosure is shown.

[0027] Figure 5 A block diagram schematically illustrates an electronic device suitable for implementing a virtual rail train trajectory tracking method according to an embodiment of the present disclosure. Detailed Implementation

[0028] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0029] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0030] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0031] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0032] In the technical solution disclosed herein, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, and displayed data) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse.

[0033] For steering control of virtual rail trains, the relevant technologies are designed for situations where a driver is present, but are not suitable for fully automated driving. Geometric methods lack consideration of vehicle dynamics, and decoupled models lack consideration of the forces between carriages, making it difficult to cope with complex operating conditions, resulting in low control accuracy and computational efficiency.

[0034] This disclosure fully considers the dynamic characteristics of the vehicle and the real-time changes in the curvature of the virtual track through a dynamic model, enabling early tracking responses and improving train tracking accuracy. Since the energy conversion strategy simplifies the initial kinetic and potential energy information of the train to obtain the dynamic model, it reduces the complexity of model prediction and lowers the consumption of system computing resources. The reference position information is obtained in real-time based on actual point information, realizing real-time linear optimization of the nonlinear optimization problem, further improving computational efficiency and control accuracy of train trajectory tracking.

[0035] This disclosure provides a virtual track train trajectory tracking method, comprising: constructing a dynamic model based on an energy conversion strategy, initial state information of the train, and initial control information; using the dynamic model to convert the initial state information of the train into target state information of the train in the vehicle coordinate system, wherein the initial state information represents the state information of the train in the global coordinate system, the target state information includes the velocity components of the actual points on the train in multiple dimensions, the energy conversion strategy represents the relationship between the initial kinetic energy information and the initial potential energy information of the train and the initial state information, and the train includes multiple carriages; determining reference position information corresponding to the train and the virtual track based on the velocity components and the actual position information of the train, wherein the reference position information represents the position information obtained by projecting the actual position information of the train onto the virtual track, including reference angle information, angle deviation information, and reference point information, and the angle deviation information represents the yaw angle deviation between multiple carriages in the vehicle coordinate system; determining the optimal control quantity of the train based on an objective function and the reference position information, wherein the objective function is obtained based on the angle deviation information and the lateral deviation information, and the lateral deviation information represents the distance between the actual point and the reference point; and using the optimal control quantity to track the train trajectory.

[0036] Figure 1 The illustration schematically depicts an application scenario of a virtual track train trajectory tracking method, apparatus, and train according to embodiments of the present disclosure.

[0037] like Figure 1 As shown, the application scenario according to this embodiment may include a train 101, a network 102, a sensor 103, and a server 104. The network 102 serves as a medium for providing a communication link between the sensor 103 and the server 104. The network 102 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc. The train 101 may include a steering actuator.

[0038] Train 101 could be an electronically guided trackless rubber-tired train that uses ground transportation lines as virtual tracks and can recognize and autonomously travel along these virtual tracks. Understandably, the specific type of Train 101 can be determined based on actual conditions, such as a 3-car, 8-axle train. Trackless rubber-tired trains typically use articulated vehicles and can be all-axle steering trains.

[0039] Sensor 103 can be used to collect relevant information about the train, including but not limited to vision sensors, radar sensors, navigation sensors, and magnetic nail sensors. It is understood that the sensors can be installed on the train body or in other locations outside the train body, such as on a virtual track, depending on actual needs.

[0040] Server 104 can be a server that provides various services, such as constructing a dynamic model based on energy conversion strategies, the train's initial state information, and initial control information. For example, it can determine the reference position information corresponding to the train and the virtual track based on velocity components and the train's actual position information.

[0041] For example, sensor 103 can be used to collect initial state information and initial control information of the train, and transmit the data to server 104 via network 102. Server 104 analyzes the collected information and generates control commands. Server 104 sends the control commands to the train's steering actuator via network 102, and the steering actuator adjusts the train's steering angle according to the commands. After the steering actuator executes the control commands, sensor 103 continues to monitor the train's operating status and feeds back new data to server 104, which then performs steering control and trajectory tracking based on the feedback data.

[0042] It should be noted that the virtual train trajectory tracking method provided in this embodiment can generally be executed by server 104. Correspondingly, the virtual train trajectory tracking device provided in this embodiment can generally be located in server 104. The virtual train trajectory tracking method provided in this embodiment can also be executed by a server or server cluster that is different from server 104 but capable of communicating with server 104. Correspondingly, the virtual train trajectory tracking device provided in this embodiment can also be located in a server or server cluster that is different from server 104 but capable of communicating with server 104.

[0043] It should be understood that Figure 1 The number of trains, networks, sensors, and servers shown is merely illustrative. Any number of trains, networks, sensors, and servers can be included depending on implementation needs.

[0044] Figure 2 A flowchart illustrating a virtual rail train trajectory tracking method according to an embodiment of the present disclosure is shown schematically.

[0045] like Figure 2 As shown, the virtual track train trajectory tracking method of this embodiment may include operations S210 to S240.

[0046] In operation S210, a dynamic model is constructed based on the energy conversion strategy, the initial state information of the train, and the initial control information. The dynamic model is used to convert the initial state information of the train into the target state information of the train in the vehicle coordinate system. The initial state information represents the state information of the train in the global coordinate system, and the target state information includes the velocity components of the actual points on the train in multiple dimensions. The energy conversion strategy represents the relationship between the initial kinetic energy information and the initial potential energy information of the train and the initial state information. The train includes multiple carriages.

[0047] In embodiments of this disclosure, the train may include multiple carriages and multiple actual points. A single carriage can be considered as a trainset, and each trainset may include multiple horizontal axes and actual points corresponding to the trainset. Energy conversion strategies can be used for dynamic modeling of multi-train articulated trains, and may include the Lagrange method and the Newton-Euler method. Initial state information can be represented by the train's state matrix in the global coordinate system. Initial control information can be determined by the initial yaw angles of multiple horizontal axes. Velocity components can characterize the longitudinal and lateral velocities of the first point of the train's head car in the vehicle coordinate system.

[0048] For example, using the Lagrange method, the initial kinetic and potential energy information of a train system can be represented as system variables. Substituting these variables into the Lagrange equations and taking partial derivatives yields a yaw dynamics model of the train. Similarly, the Newton-Euler method can be used to simulate and analyze the yaw and braking stability of a train, and a dynamic model of the train vehicle can be constructed to analyze its dynamic response during a turn along a virtual track.

[0049] In operation S220, based on the velocity component and the actual position information of the train, the reference position information corresponding to the virtual track is determined. The reference position information represents the position information obtained by projecting the actual position information of the train onto the virtual track, including reference angle information, angle deviation information and reference point information. The angle deviation information represents the yaw angle deviation between multiple carriages in the vehicle coordinate system.

[0050] In the embodiments of this disclosure, the actual position information can characterize the position information of the train during its operation. By projecting multiple actual points of the train onto the virtual track, multiple reference points can be obtained, and the reference angle information can characterize the angle information between the multiple reference points of the train.

[0051] For example, the actual location of the train can be projected onto a virtual track to obtain reference locations. Then, the angle between adjacent reference locations can be used to determine reference angle information, which can be converted to the vehicle coordinate system to obtain the angle deviation information of each carriage.

[0052] In operation S230, the optimal control quantity of the train is determined based on the objective function and reference position information. The objective function is obtained based on the angle deviation information and the lateral deviation information. The lateral deviation information represents the distance between the actual position and the reference position.

[0053] When operating S240, the train trajectory is tracked using the optimal control quantity.

[0054] In the embodiments of this disclosure, the objective function can be used to predict the vehicle state information and optimal control information for vehicle steering within a target time period. After determining the optimal control quantity using the objective function, the optimal control quantity can be used to perform trajectory tracking control of the train based on rolling optimization and hot-start strategies.

[0055] For example, by combining the train's state prediction and optimal control variables within the target time period, the target time period can be divided into multiple small optimization intervals, and optimization can be performed within each interval. This allows the existing optimization results to be used as the initial solution for the next new optimization problem, thereby accelerating the convergence of the optimization process.

[0056] According to embodiments of this disclosure, by fully considering the dynamic characteristics of the vehicle and the real-time changes in the curvature of the virtual track through a dynamic model, a tracking response can be made in advance, improving the tracking accuracy of the train. Since the energy conversion strategy can simplify the initial kinetic and potential energy information of the train to obtain the dynamic model, the complexity of model prediction is reduced, and the consumption of system computing resources is lowered. The reference position information is obtained in real time based on actual point information, realizing real-time linear optimization of the nonlinear optimization problem, further improving computational efficiency and the control accuracy of train trajectory tracking.

[0057] As you can understand, the above text has already explained how to track the train's trajectory. The following text will explain how to determine the initial state variables.

[0058] According to embodiments of this disclosure, the initial state information includes a state matrix and initial state quantities. The carriages include a head carriage, a middle carriage, and a tail carriage. The actual point includes the first point of the head carriage. The method further includes: determining the state matrix based on the coordinate information of the first point and the first yaw angle of multiple carriages, wherein the state matrix represents the state information of the train in the global coordinate system; and determining the initial state quantities based on the state matrix, the instantaneous rate of change information of the state matrix, and the longitudinal driving torque of the train.

[0059] In embodiments of this disclosure, the first yaw angle can characterize the yaw angles of multiple carriages in the global coordinate system, including a first head yaw angle corresponding to the head carriage, a first middle yaw angle corresponding to the middle carriage, and a first tail yaw angle corresponding to the tail carriage. Instantaneous rate of change information can be obtained by transforming the state matrix to obtain the vehicle's instantaneous velocity and instantaneous acceleration. The longitudinal driving torque can characterize the vehicle's longitudinal driving torque in the global coordinate system. Initial state quantities can be determined based on the state matrix, the instantaneous rate of change information of the state matrix, and the longitudinal driving torque.

[0060] For example, a dynamic model can be constructed in a global coordinate system. The global coordinate system has the virtual track starting point as the origin, the eastward direction of the vehicle's forward movement as the X-axis, and the northward direction of the vehicle's forward movement as the Y-axis. The state matrix and initial state information can be determined, and can be denoted as q and x, respectively. vs As shown in the following formulas (1)-(2):

[0061] (1);

[0062] (2);

[0063] Where, x vs,Mc1 and y vs,Mc1 The global coordinate information of the first point at the front end of the Mc1 carriage can be represented separately. These can be used to characterize the first head yaw angle, the first middle yaw angle, and the first tail yaw angle in the global coordinate system, respectively. It can characterize the instantaneous velocity in the instantaneous rate of change information. F lon It can characterize the longitudinal driving torque of a train.

[0064] According to embodiments of this disclosure, the head carriage, middle carriage, and tail carriage each include multiple transverse axes; the method further includes: determining initial control information based on the transverse axis yaw angles of the multiple transverse axes.

[0065] In embodiments of this disclosure, the horizontal axis can characterize the steering actuator (e.g., steering shaft) of each carriage, and the number of horizontal axes in each carriage can be determined according to actual conditions.

[0066] Figure 3A A schematic diagram of the structure of a virtual rail train according to an embodiment of the present disclosure is shown.

[0067] like Figure 3AAs shown, taking a three-car train with eight axles as an example, in the vehicle coordinate system x,y, the head car 31 has three horizontal axes: the first horizontal axis 311, the second horizontal axis 312, and the third horizontal axis 313; the middle car 32 has two horizontal axes: the fourth horizontal axis 321 and the fifth horizontal axis 322; and the tail car 33 has three horizontal axes: the sixth horizontal axis 331, the seventh horizontal axis 332, and the eighth horizontal axis 333, denoted as δ1, δ2, δ3, δ4, δ5, δ6, δ7, and δ8 respectively. The first horizontal axis 311, the second horizontal axis 312, the seventh horizontal axis 332, and the eighth horizontal axis 333 steer together, while the remaining horizontal axes can steer independently. The actual point 34 may include the first point 341 at the front end of the head car Mc1, the second point 342 between the head car and the middle car, the third point 343 between the middle car and the tail car, and the fourth point 344 of the tail car.

[0068] After obtaining the yaw angles of multiple carriages, the initial control information of the train can be determined using the yaw angles of multiple horizontal axes, denoted as u. The initial control information u is shown in the following formula (3):

[0069] (3);

[0070] Where, δ i It can characterize the yaw angle of the i-th horizontal axis.

[0071] According to embodiments of this disclosure, a dynamic model is constructed based on an energy conversion strategy, initial state information of the train, and initial control information, including: determining mass-related information and force-related information of the train using a state matrix and an energy conversion strategy; summing the mass-related information and force-related information to obtain energy information; and constructing a dynamic model based on the mass-related information, force-related information, and energy information.

[0072] In the embodiments of this disclosure, mass-related information can be represented by the train's mass-related matrix, which can be determined based on the state matrix, instantaneous velocity, and instantaneous acceleration. Force-related information can be represented by a matrix characterizing the Coriolis forces acting on the train. Energy information can be represented by the train's energy matrix.

[0073] For example, taking the Lagrange method as the energy conversion strategy, the vehicle's kinetic energy can be solved using the Lagrange function based on the vehicle's geometric and inertial parameters, and the generalized force can be solved using the principle of virtual work. This yields the following vehicle dynamics equations:

[0074] (4);

[0075] Among them, M,C,τ do not contain x vs,Mc1 and y vs,Mc1 Related items. It can characterize the instantaneous velocity in the instantaneous rate of change information. It can characterize the instantaneous acceleration in the instantaneous rate of change information, F lon It can characterize the longitudinal driving torque of the train. It should be noted that for the dynamic modeling of multi-unit articulated vehicles, the Newton-Euler method can also be used to eliminate the inter-vehicle constraint forces to obtain the vehicle's dynamic model.

[0076] In the embodiments of this disclosure, based on the energy conversion strategy, by introducing the vehicle's geometric and inertial parameters, the dynamic behavior of the vehicle can be described more accurately. By using the dynamic model for the design of the vehicle control system, the handling performance and stability of the vehicle can be improved.

[0077] According to embodiments of this disclosure, the method further includes: obtaining a second yaw angle of the head carriage in the vehicle coordinate system; and using the difference between the first yaw angle and the second yaw angle as the yaw angle of the middle carriage or the tail carriage in the vehicle coordinate system.

[0078] In embodiments of this disclosure, the second yaw angle can characterize the yaw angle of the head carriage at the target time (sampling time). After obtaining the second yaw angle, the difference between the first yaw angle and the second yaw angle can be calculated to obtain the yaw angles of the middle and rear carriages in the vehicle coordinate system, denoted as . As shown in the following formula (5):

[0079] (5);

[0080] in, It can represent the initial yaw angle of the i-th carriage in the vehicle coordinate system, which is the angle between the target time and the initial yaw angle of the head carriage.

[0081] According to embodiments of this disclosure, the method further includes: determining a velocity component based on the coordinate information of the second yaw angle and the first point.

[0082] In the embodiments of this disclosure, after determining the initial yaw angle of the carriage in the vehicle coordinate system, the longitudinal and lateral velocity components of the first actual position J1 of the head carriage can be determined based on the global coordinate information of the first point at the front end of the head carriage Mc1. Assuming the longitudinal driving torque F of the train... lon At the target time, the velocity components of the first actual point J1 in the longitudinal and lateral directions can be denoted as v, which is a constant value. x v y It can be shown in the following formulas (6)-(7):

[0083] (6);

[0084] (7);

[0085] in, The initial yaw angle of the i-th carriage in the vehicle coordinate system can be represented by x. vs,Mc1 and y vs,Mc1 The global coordinate information of the first point at the front end of the head carriage can be represented separately. After obtaining the velocity component, the second yaw angle, and the dynamic model, the target state information of the vehicle in the vehicle coordinate system can be obtained, as shown in the following formula (8):

[0086] (8);

[0087] in, It can respectively characterize the instantaneous rate of change of the yaw angle of the middle carriage or the rear carriage in the vehicle coordinate system.

[0088] As we have already explained how to use energy conversion strategies to construct the train's dynamic model, the following section will explain how to determine the parameter information of the virtual track.

[0089] According to embodiments of this disclosure, the method further includes: converting the initial orbit information of the virtual orbit into orbit parameter information based on a preset conversion strategy, wherein the initial orbit information is characterized as the latitude and longitude sequence of the virtual orbit.

[0090] In embodiments of this disclosure, the initial track information can be a series of discrete points or paths, representing the route the train should follow. Depending on the specific application scenario, these points can be coordinates in two-dimensional space or coordinates in three-dimensional space. The virtual track can be obtained through various methods such as map data, GPS data, and sensor data.

[0091] In the embodiments of this disclosure, the initial orbit information of the virtual orbit can be a set of latitude and longitude sequences of length n. To simplify processing and improve computational efficiency, the initial orbit information can be converted into an n×8 information matrix. Each row of the information matrix is ​​structured as shown in the following formula (9):

[0092] (9);

[0093] Where s can represent the absolute distance traversed from the virtual orbit's starting point to the current point at the target time. It can represent the global coordinates of the current point, t and n can represent the tangent vector and normal vector of the current point respectively, and c can be the curvature of the point.

[0094] For example, converting initial orbit information into orbit parameter information can include the following operations S401 to S405.

[0095] By operating S401, latitude and longitude can be converted into rectangular coordinates to obtain a latitude and longitude sequence.

[0096] In operation S402, the entire latitude and longitude sequence is traversed, and every three points can be fitted into a circle.

[0097] In operation S403, the curvature of the fitted circle is used as the curvature of the midpoint, with counterclockwise rotation being positive. The tangent vector of the midpoint on the circle is used as the tangent vector at that point, and rotated 90° counterclockwise to become the normal vector.

[0098] In operation S404, the starting point and ending point are based on the center of the circle of the adjacent point, and the calculation of each quantity is the same as above.

[0099] In operation S405, the arc lengths of each arc are accumulated from the starting point to determine the absolute distance traversed from the starting point of the virtual track to that point.

[0100] According to embodiments of this disclosure, by converting a virtual track into a discrete point sequence and calculating the curvature, tangent vector, and normal vector of each point, the shape and dynamic characteristics of the track can be described more accurately. This parameterization method can effectively improve the accuracy of trajectory generation, especially in trajectory planning under complex environments. In virtual track trains or autonomous vehicles, more precise tracking control can be achieved by calculating the geometric features of trajectory points. For example, a curvature-based longitudinal velocity decision model and speed adjustment method can ensure the stability of the vehicle under different operating modes. Furthermore, the accuracy of tracking control can be further improved by estimating the coordinates of discrete points of the target trajectory through multi-sensor fusion.

[0101] As we have already explained in the previous text how to determine orbital parameter information, the following text will further explain how to determine reference angle information.

[0102] According to embodiments of this disclosure, the actual points include a first point, a second point between the head carriage and the middle carriage, a third point between the middle carriage and the tail carriage, and a fourth point of the tail carriage; the method further includes using the sway angle between the first point and the second point, the sway angle between the second point and the third point, and the sway angle between the third point and the fourth point as reference angle information.

[0103] In the embodiments of this disclosure, to assess the degree of train deviation from the virtual track for feedback control, the actual position information of the train can be projected onto the virtual track as reference position information. Unlike ordinary four-wheeled vehicles, virtual track trains, due to their multiple carriages, cannot be projected as point masses. Because the vehicle has rigid body characteristics, it has a total of four degrees of freedom for lateral movement, therefore, there may be four control points simultaneously located on the virtual track. The second point between the head carriage and the middle carriage is denoted as the first hinge point J2, the third point between the middle carriage and the tail carriage is denoted as the second hinge point J3, and the fourth point between the tail carriage is denoted as J4.

[0104] Figure 3B The diagram illustrates a schematic example of the process of projecting the actual position of a train onto a reference position in a virtual track according to an embodiment of the present disclosure.

[0105] like Figure 3B As shown, the first point J1 at the front end of the head carriage 31, the first hinge point J2, the second hinge point J3, and the fourth point J4 at the rear end of the tail carriage 33 are used as control points in the actual position of the train. Due to the rigid constraint of the train body length, once the position of one point on the virtual track is determined, the positions of the other points can also be determined accordingly.

[0106] For example, the projection method may include: projecting J1 vertically onto point R1 of the virtual track, then using R1 as the center and the distance between J1 and J2 as the radius to draw a circle, intersecting the virtual track at point R2, thus obtaining the projection point of J2; repeating the above operation yields R3 and R4; then using the angles of R1R2, R2R3, and R3R4 as reference yaw angles, denoted as φ. ref Then, transform to the vehicle coordinate system to obtain the yaw angle deviation. The reference positions of each carriage can be represented by the following formula (10):

[0107] (10);

[0108] in, It can characterize the yaw angle of the i-th carriage in the vehicle coordinate system.

[0109] According to embodiments of this disclosure, the method further includes: determining the reference position information of the first point as the first reference point information; and determining the lateral deviation information based on the difference between the actual position information of the first point and the first reference point information.

[0110] In the embodiments of this disclosure, after determining the reference position information of the first point J1, the difference between the actual position information of the first point and the first reference position information can be calculated to obtain the distance between the sampling time J1 and its reference position, i.e., the lateral deviation information of point J1. After determining the lateral deviation information, the real-time moving speed of the train can be calculated.

[0111] According to embodiments of this disclosure, by projecting control points onto a virtual track based on the rigidity characteristics of the train vehicle, and calculating the reference yaw angle and yaw angle deviation, the position and attitude of the vehicle on the virtual track can be determined more accurately, effectively reducing trajectory deviation and improving the trajectory tracking accuracy of the vehicle. Simultaneously, this method can dynamically adjust the control strategy based on the rigidity characteristics of the vehicle. For example, under different loads, road surface adhesion coefficients, and other operating conditions, by calculating the yaw angle deviation, the control torque of the vehicle can be adjusted in real time, thereby optimizing the adaptability of the trajectory tracking algorithm.

[0112] According to embodiments of this disclosure, determining reference position information corresponding to the train and the virtual track based on velocity components and the actual position information of the train includes: determining the train's moving speed based on the train's reference curvature, lateral deviation information, angular deviation information and velocity components; and determining reference position information based on the moving speed and the time corresponding to the moving speed.

[0113] In embodiments of this disclosure, after determining the train's reference curvature, lateral deviation information, angular deviation information, and velocity components, predictions can be made using a vehicle dynamics model through Model Predictive Control (MPC).

[0114] Because the train moves along the track, its projected position also moves along the track. The speed at which the projected position moves along the track... It can be represented by the following formula (11):

[0115] (11);

[0116] Among them, K ref It can characterize the reference curvature. It can characterize the yaw rate deviation of the carriage, e d This can characterize the distance between sampling time J1 and its reference position (lateral deviation information of J1). Assume the moving speed during the prediction period... It is a fixed value, which can be adjusted according to the movement speed. The reference position information of the train at each time step within the prediction period is estimated using the time step.

[0117] In embodiments of this disclosure, determining the optimal control parameters of the train based on the objective function and reference position information may include: when the lateral deviation information at point J1 and the yaw angle deviation of each carriage are both preset values ​​(e.g., 0), the four points are located on the virtual track. The lateral deviation at point J1 and the yaw angle deviation of each carriage can be selected as optimization objectives.

[0118] For example, the cost function is constructed as shown in formula (12):

[0119] (12);

[0120] Where, N p It can characterize the prediction period. Q can be represented as a weighted matrix; u k The control variable ξ, which can characterize the train steering at time k, is related to the initial state information x in the global coordinate system. vs The relationship between them is shown in the following formula (13):

[0121] (13);

[0122] in, For example Figure 3A The vehicle coordinate system shown points to point R1 at an angle, and the initial state information is x. vs The dynamic equations satisfy the equation shown in formula (4). For ease of solution, the values ​​of M, C, and τ at the initial time can be used as constant matrices during the prediction period; for x near these initial values... vs A first-order Taylor expansion yields its linear dynamic equations near the point. Its discrete form can be obtained using the forward Euler method, as shown in equation (14):

[0123] (14);

[0124] Where u(k) can characterize the control quantity at time k, x vs (k) can represent the initial state information corresponding to time k, x vs (k+1) can represent the initial state information corresponding to time k+1. Due to the physical limitations of the steering mechanism, the control quantity u can satisfy u min ≤u≤u max .

[0125] This allows us to construct the standard form of the time-varying linear model predictive control (MPC) problem. The problem can be transformed into a quadratic programming problem, which can be solved numerically using the interior-point method to obtain the optimal control quantity for each time step of the prediction period.

[0126] In the embodiments of this disclosure, after the linear model predictive control problem is transformed into a quadratic programming problem, the optimal control quantity can be determined by various methods.

[0127] For example, methods for determining the optimal control quantity using interior point methods include: transforming the aforementioned model predictive control problem into a standard quadratic programming form, extracting the objective function and constraints; selecting an initial feasible solution A0 and initializing the dual variable B and slack variable s; constructing the central path equation by introducing a logarithmic barrier function; solving the central path equation using Newton's method to obtain the search directions of the original variable A and the dual variable B; updating A and B according to the search directions and performing a line search to ensure that the iteration points remain within the feasible region; calculating the dual gap, and stopping the iteration when the dual gap is less than a set threshold. It should be noted that the optimal control quantity can also be determined using the active set method or gradient projection.

[0128] In the embodiments of this disclosure, after determining the optimal control quantity, the optimal control quantity can be applied to the steering actuator to perform trajectory tracking and steering control of the train. It can be understood that the obtained optimal control quantity is represented by a sequence of optimal control quantities for the predicted time period. The first control quantity in the sequence can be applied to the steering actuator (e.g., steering axle-tire). At the next sampling time, after updating the state quantities from the sensors, the optimal control solution is re-applied, realizing a rolling optimization process. The optimal control quantity sequence obtained from the previous sampling time can be used as the initial value for the next solution, achieving a hot start of the solution.

[0129] According to embodiments of this disclosure, the virtual track train trajectory tracking method based on Model Predictive Control (MPC) employs a warm start technique. By using the optimal control sequence from the previous sampling time as the initial guess for the current optimization, the computation time of the system can be reduced. Particularly for vehicle control systems with high real-time requirements, warm start can shorten the single solution time by 30%-70%, meeting the millisecond-level control cycle requirement. Furthermore, warm start utilizes historical information to accelerate convergence, enabling the controller to adapt more quickly to environmental disturbances (such as trajectory deviation and sudden changes in wind resistance). The smoothness of historical solutions is passed to the current optimization, suppressing high-frequency jitter in control quantities (such as sudden changes in steering angle), thus improving the robustness of the vehicle control system to dynamic environments.

[0130] Based on the above-described virtual track train trajectory tracking method, this disclosure also provides a virtual track train trajectory tracking device. The following will be combined with... Figure 4 The device is described in detail.

[0131] Figure 4A schematic block diagram of a virtual rail train trajectory tracking device according to an embodiment of the present disclosure is shown.

[0132] like Figure 4 As shown, the virtual track train trajectory tracking device in this embodiment includes a model building module 410, an information conversion module 420, a control quantity determination module 430, and a trajectory tracking module 440.

[0133] The model building module 410 is used to construct a dynamic model based on the energy conversion strategy, the initial state information of the train, and the initial control information. The dynamic model is used to transform the initial state information to obtain the target state information of the train in the vehicle coordinate system. The initial state information represents the state information of the train in the global coordinate system, and the target state information includes the velocity components of the actual points on the train in multiple dimensions. The energy conversion strategy is used to convert the initial kinetic energy information and initial potential energy information of the train into initial state information. The train includes multiple carriages. In one embodiment, the model building module 410 can be used to execute the operation S210 described above, which will not be repeated here.

[0134] The information conversion module 420 is used to determine the reference position information corresponding to the train and the virtual track based on the velocity component and the actual position information of the train. The reference position information represents the position information obtained by projecting the actual position information of the train onto the virtual track, including reference angle information, angle deviation information, and reference point information. The angle deviation information represents the yaw angle deviation between multiple carriages in the vehicle coordinate system. In one embodiment, the information conversion module 420 can be used to perform the operation S220 described above, which will not be repeated here.

[0135] The control quantity determination module 430 is used to determine the optimal control quantity of the train based on an objective function and reference position information. The objective function is obtained based on angular deviation information and lateral deviation information, whereby the lateral deviation information represents the distance between the actual position and the reference position. In one embodiment, the control quantity determination module 430 can be used to perform the operation S230 described above, which will not be repeated here.

[0136] The trajectory tracking module 440 is used to track the train trajectory using optimal control quantities. In one embodiment, the trajectory tracking module 440 can be used to perform the operation S240 described above, which will not be repeated here.

[0137] According to embodiments of this disclosure, a virtual track train trajectory tracking device comprises a model building module 410, an information conversion module 420, a control quantity determination module 430, and a trajectory tracking module 440. By fully considering the vehicle's dynamic characteristics and the real-time changes in the curvature of the virtual track through a dynamic model, a tracking response is made in advance, improving the train's tracking accuracy. Since the energy conversion strategy simplifies the initial kinetic and potential energy information of the train to obtain a dynamic model, the complexity of model prediction is reduced, and the consumption of system computing resources is lowered. The reference position information is obtained in real-time based on actual point information, realizing real-time linear optimization of nonlinear optimization problems, further improving computational efficiency and the control accuracy of train trajectory tracking.

[0138] According to embodiments of this disclosure, the initial state information includes a state matrix and initial state quantities. The carriages include a head carriage, a middle carriage, and a tail carriage, and the actual point includes the first point of the head carriage. The device further includes a state matrix determination module and an initial state quantity determination module. The state matrix determination module is used to determine the state matrix based on the coordinate information of the first point and the first yaw angle of multiple carriages. The state matrix represents the state information of the train in the global coordinate system. The initial state quantity determination module is used to determine the initial state quantities based on the state matrix, the instantaneous rate of change information of the state matrix, and the longitudinal driving torque of the train.

[0139] According to embodiments of this disclosure, the head carriage, middle carriage, and tail carriage each include multiple transverse axes; the device further includes: an initial control information determination module, used to determine initial control information based on the transverse axis yaw angles of the multiple transverse axes.

[0140] According to embodiments of this disclosure, the model building module 410 includes: an information determination submodule, a summation submodule, and a dynamic model building submodule. The information determination submodule is used to determine the train's mass-related information and force-related information using a state matrix and an energy conversion strategy; the summation submodule is used to sum the mass-related information and force-related information to obtain energy information; and the dynamic model building submodule is used to build a dynamic model based on the mass-related information, force-related information, and energy information.

[0141] According to embodiments of this disclosure, the apparatus further includes: a second yaw angle acquisition module and a yaw angle assuming module. The second yaw angle acquisition module is used to acquire the second yaw angle of the head carriage in the vehicle coordinate system; the yaw angle assuming module is used to take the difference between the first yaw angle and the second yaw angle as the yaw angle of the middle carriage or the rear carriage in the vehicle coordinate system.

[0142] According to an embodiment of this disclosure, the apparatus further includes a velocity component determination module, used to determine the velocity component based on the coordinate information of the second yaw angle and the first point.

[0143] According to an embodiment of this disclosure, the apparatus further includes: an information conversion module, used to convert the initial orbit information of the virtual orbit into orbit parameter information based on a preset conversion strategy, wherein the initial orbit information is characterized as the latitude and longitude sequence of the virtual orbit.

[0144] According to embodiments of this disclosure, the actual points include a first point, a second point between the head carriage and the middle carriage, a third point between the middle carriage and the tail carriage, and a fourth point of the tail carriage; the device further includes: an angle information module, used to use the sway angle between the first point and the second point, the sway angle between the second point and the third point, and the sway angle between the third point and the fourth point as reference angle information.

[0145] According to embodiments of this disclosure, the apparatus further includes: a first reference point information determination module and a lateral deviation information determination module. The first reference point information determination module is used to determine the reference position information of the first point as the first reference point information; the lateral deviation information determination module is used to determine the lateral deviation information based on the difference between the actual position information of the first point and the first reference point information.

[0146] According to embodiments of this disclosure, the information conversion module 420 includes a moving speed determination submodule and a moving speed determination submodule. The moving speed determination submodule is used to determine the moving speed of the train based on the train's reference curvature, lateral deviation information, angular deviation information, and velocity components; the reference position information determination submodule is used to determine reference position information based on the moving speed and the time corresponding to the moving speed.

[0147] According to embodiments of this disclosure, any plurality of modules among the model building module 410, information conversion module 420, control quantity determination module 430, and trajectory tracking module 440 can be combined into one module, or any one of these modules can be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules can be combined with at least part of the functionality of other modules and implemented in one module. According to embodiments of this disclosure, at least one of the model building module 410, information conversion module 420, control quantity determination module 430, and trajectory tracking module 440 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the model building module 410, information conversion module 420, control quantity determination module 430, and trajectory tracking module 440 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0148] According to embodiments of this disclosure, a train is provided, including: a carriage; a steering actuator for tracking the train's trajectory according to an optimal control quantity; and a virtual track train trajectory tracking device as described above.

[0149] Figure 5 A block diagram schematically illustrates an electronic device suitable for implementing a virtual rail train trajectory tracking method according to an embodiment of the present disclosure.

[0150] like Figure 5 As shown, an electronic device according to an embodiment of this disclosure includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage portion 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this disclosure.

[0151] RAM 503 stores various programs and data required for the operation of the electronic device. Processor 501, ROM 502, and RAM 503 are interconnected via bus 504. Processor 501 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 502 and / or RAM 503. It should be noted that the programs may also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0152] According to embodiments of this disclosure, the electronic device may further include an input / output (I / O) interface 505, which is also connected to a bus 504. The electronic device may also include one or more of the following components connected to the input / output (I / O) interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 510 as needed so that computer programs read from it can be installed into the storage section 508 as needed.

[0153] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0154] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 502 and / or RAM 503 and / or one or more memories other than ROM 502 and RAM 503 described above.

[0155] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code enables the computer system to implement the virtual track train trajectory tracking method provided in the embodiments of this disclosure.

[0156] When the computer program is executed by the processor 501, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0157] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 509, and / or installed from a removable medium 511. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0158] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by processor 501, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0159] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on a user's computing device, partially on a user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0160] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0161] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0162] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A virtual track train trajectory tracking method, comprising: constructing a dynamic model based on an energy conversion strategy, initial state information and initial control information of a train, and converting the initial state information of the train into target state information of the train in a vehicle coordinate system by using the dynamic model, wherein the initial state information represents state information of the train in a global coordinate system, the target state information includes velocity components of an actual point on the train in multiple dimensions, the energy conversion strategy represents a relationship between initial kinetic energy information and initial potential energy information of the train and the initial state information, and the train includes multiple carriages; determining reference position information corresponding to a virtual track of the train based on the velocity components and actual position information of the train, wherein the reference position information represents position information obtained by projecting the actual position information of the train into the virtual track, includes reference angle information, angle deviation information and reference point information, and the angle deviation information represents yaw angle deviation between the multiple carriages in the vehicle coordinate system; determining an optimal control amount of the train based on a target function and the reference position information, wherein the target function is obtained based on the angle deviation information and lateral deviation information representing a distance between the actual point and the reference point; tracking a trajectory of the train by using the optimal control amount. 2.The tracking method of claim 1, wherein the initial state information includes a state matrix and initial state quantity, the carriages include a head carriage, a middle carriage and a tail carriage, and the actual point includes a first point of the head carriage. The method further comprises: determining the state matrix based on coordinate information of the first point and first yaw angles of the multiple carriages, wherein the state matrix represents state information of the train in the global coordinate system; determining the initial state quantity based on the state matrix, instantaneous change rate information of the state matrix and a longitudinal driving torque of the train. 3.The tracking method of claim 2, wherein the head carriage, the middle carriage and the tail carriage each include multiple lateral shafts. The method further comprises: determining the initial control information based on lateral shaft yaw angles of the multiple lateral shafts. 4.The tracking method of claim 2, wherein constructing the dynamic model based on the energy conversion strategy, the initial state information and the initial control information comprises: determining mass-related information and force-related information of the train by using the state matrix and the energy conversion strategy; adding the mass-related information and the force-related information to obtain energy information; constructing the dynamic model based on the mass-related information, the force-related information and the energy information. 5.The tracking method of claim 2, wherein the method further comprises: obtaining a second yaw angle of the head carriage in the vehicle coordinate system; taking a difference between the first yaw angle and the second yaw angle as a yaw angle of the middle carriage or the tail carriage in the vehicle coordinate system.

6. The tracking method according to claim 5, further comprising: The velocity component is determined based on the second yaw angle and the coordinate information of the first point.

7. The tracking method according to claim 1, further comprising: Based on a preset conversion strategy, the initial orbit information of the virtual orbit is converted into orbit parameter information, wherein the initial orbit information is represented as the latitude and longitude sequence of the virtual orbit.

8. The tracking method according to any one of claims 2 to 6, wherein the actual location includes the first location, the second location between the head carriage and the middle carriage, the third location between the middle carriage and the tail carriage, and the fourth location of the tail carriage; The method further includes: The lateral angle between the first point and the second point, the lateral angle between the second point and the third point, and the lateral angle between the third point and the fourth point are used as the reference angle information.

9. The tracking method according to claim 2, further comprising: The reference position information of the first point is determined as the first reference point information; The lateral deviation information is determined based on the difference between the actual location information of the first point and the information of the first reference point.

10. The tracking method according to claim 9, wherein determining reference position information corresponding to the virtual track based on the velocity component and the actual position information of the train includes: The train's speed is determined based on the train's reference curvature, the lateral deviation information, the angular deviation information, and the velocity components. The reference position information is determined based on the moving speed and the time corresponding to the moving speed.

11. A virtual rail train trajectory tracking device, comprising: The model building module is used to construct a dynamic model based on the energy conversion strategy, the initial state information and initial control information of the train. The dynamic model is used to transform the initial state information to obtain the target state information of the train in the vehicle coordinate system. The initial state information represents the state information of the train in the global coordinate system. The target state information includes the velocity components of the actual points on the train in multiple dimensions. The energy conversion strategy is used to convert the initial kinetic energy information and initial potential energy information of the train into the initial state information. The train includes multiple carriages. The information conversion module is used to determine the reference position information of the train and the virtual track based on the velocity component and the actual position information of the train. The reference position information represents the position information obtained by projecting the actual position information of the train onto the virtual track, including reference angle information, angle deviation information and reference point information. The angle deviation information represents the yaw angle deviation between multiple carriages in the vehicle coordinate system. The control quantity determination module is used to determine the optimal control quantity of the train based on the objective function and the reference position information, wherein the objective function is obtained based on the angle deviation information and the lateral deviation information, and the lateral deviation information represents the distance between the actual point and the reference point. The trajectory tracking module is used to track the train's trajectory using the optimal control quantity.

12. A train, comprising: car; A steering actuator is used to track the train's trajectory according to the optimal control quantity; The virtual rail train trajectory tracking device as described in claim 11.

Images