A method, system, device and medium for obstacle avoidance and speed regulation of a tram

Abstract

This invention discloses a method, system, equipment, and medium for obstacle avoidance and speed control of intelligent rail transit vehicles, relating to the field of intelligent rail transit technology. It includes acquiring real-time vehicle and obstacle states, simultaneously predicting the future train trajectory and obstacle positions, calculating the global minimum safety margin and occurrence time of collision risk, introducing speed disturbance analysis to assess risk changes, calculating speed disturbance sensitivity, and constructing a deceleration ratio based on three factors: hazard level, time urgency, and sensitivity. This achieves dynamic control of the target speed and is executed periodically in a closed-loop manner. This invention can decelerate in a timely manner when danger is imminent and avoid unnecessary braking when there is sufficient safety margin, thus improving the smoothness and efficiency of intelligent rail transit operation while ensuring safety.

Description

Technical Field

[0001] This invention relates to the field of intelligent rail transit technology, specifically to a method, system, equipment, and medium for obstacle avoidance and speed control of intelligent rail transit vehicles. Background Technology

[0002] With the acceleration of urbanization, the demand for public transportation is increasing daily. However, traditional rail transit systems are costly and time-consuming to construct, making it difficult to quickly adapt to the rapidly growing urban transportation needs. Intelligent rail transit (IRT), as a new type of urban rail transit solution, is gaining increasing application due to its flexibility and economy. However, how to effectively avoid obstacles and dynamically adjust the speed to ensure driving safety during operation remains a pressing issue.

[0003] Existing safety assessment methods typically only consider the distance at the current moment, lacking prediction of future trajectories, leading to delayed responses. Furthermore, speed adjustment strategies are often simplistic and crude (such as fixed-threshold deceleration), failing to consider risk trends and system sensitivity, easily resulting in unnecessary deceleration or insufficient response. Therefore, there is an urgent need for an obstacle avoidance and speed control method for intelligent rail transit vehicles that can accurately predict the trajectories of multiple carriages, dynamically assess future risks, and intelligently adjust speed to ensure safety and smooth operation. Summary of the Invention

[0004] In view of the above-mentioned existing problems, the present invention provides a method, system, device and medium for obstacle avoidance and speed control of intelligent rail transit vehicles, in order to solve the problems in the prior art that make it difficult to coordinate the movement trajectory of each carriage, resulting in inaccurate risk assessment, lack of prediction of future trajectory, inability to deal with dynamic obstacles in advance, and single speed control strategy, which cannot be dynamically adjusted according to the trend of risk change and system sensitivity.

[0005] To address the aforementioned technical problems, a method for obstacle avoidance and speed control of intelligent rail transit is proposed, including: The system acquires operational data and path information, predicts the state of the intelligent rail transit vehicle at future moments based on this data, and simultaneously extrapolates the predicted positions of obstacles at corresponding moments. Based on the predicted state and obstacle positions, it calculates the global minimum safety margin characterizing the collision risk between the train and obstacles, and determines the first time interval at which this margin first appears. A speed disturbance is introduced based on the current speed, and the global minimum safety margin before and after the disturbance is calculated. The speed disturbance sensitivity is calculated based on the relationship between the changes in the global minimum safety margin before and after the disturbance. A three-factor deceleration ratio is constructed based on the minimum safety margin, speed disturbance sensitivity, and the first time interval. The target speed is determined based on the deceleration ratio, and speed control is executed cyclically at a preset period.

[0006] As a preferred embodiment of the intelligent rail transit obstacle avoidance and speed control method described in this invention, the method for predicting the state information of the intelligent rail transit vehicle in the future includes: establishing a position and orientation transfer relationship from the head carriage to the tail carriage based on the articulated structure characteristics of the intelligent rail transit vehicle; and calculating the position and heading angle of each carriage at each future moment based on the transfer relationship according to the current operating data.

[0007] As a preferred embodiment of the intelligent rail transit obstacle avoidance and speed control method described in this invention, the calculation of the global minimum safety margin characterizing the collision risk between the train and the obstacle includes transforming the predicted position of each obstacle to a local coordinate system of the vehicle body determined by the position and heading angle of the corresponding carriage, and calculating the minimum distance between the obstacle and the outline of the vehicle body in the local coordinate system.

[0008] As a preferred embodiment of the intelligent rail transit obstacle avoidance and speed control method described in this invention, the calculation of the global minimum safety margin characterizing the collision risk between the train and the obstacle further includes calculating the safety margin of each obstacle and each carriage based on the minimum distance, traversing all predicted times, all carriages and all obstacles, and extracting the minimum safety margin as the global minimum safety margin.

[0009] As a preferred embodiment of the intelligent rail transit obstacle avoidance and speed control method described in this invention, the calculation of speed disturbance sensitivity includes comparing the global minimum safety margin obtained at the original speed with the global minimum safety margin obtained by re-predicting and calculating after applying a speed disturbance, and dividing the difference between the two margins by the speed disturbance amount to obtain the speed disturbance sensitivity.

[0010] As a preferred embodiment of the intelligent rail transit obstacle avoidance and speed control method described in this invention, the construction of the three-factor deceleration ratio includes: normalizing the global minimum safety margin to obtain a hazard factor; performing a mathematical transformation on the first time interval to obtain a time approximation factor; processing the direction and magnitude of the speed disturbance sensitivity to obtain a sensitivity factor; and weighting and fusing the hazard factor, time approximation factor, and sensitivity factor to generate the three-factor deceleration ratio.

[0011] As a preferred embodiment of the intelligent rail transit obstacle avoidance and speed control method described in this invention, the step of cyclic execution in a preset period includes: calculating the target speed based on the deceleration ratio and the current speed, limiting the target speed within the range of the minimum stable speed and the maximum safe speed, sending it to the drive control system for adjustment, and in the next control cycle, re-collecting the latest vehicle status and obstacle information, executing the entire process based on the new data, and obtaining dynamic closed-loop control.

[0012] The beneficial effects of this preferred technical solution are as follows: risk assessment is achieved in advance by segmented recursive trajectory prediction and dynamic safety margin calculation, the control direction is revealed by speed disturbance sensitivity analysis, and smooth speed regulation commands are generated based on multi-factor fusion decision-making. Under closed-loop control, the obstacle avoidance safety, operation stability and traffic efficiency of multi-section intelligent rail transit vehicles in dynamic environments are significantly improved.

[0013] As a preferred embodiment of the intelligent rail transit obstacle avoidance and speed control system of the present invention, it is characterized by including a safety margin prediction module, a sensitivity analysis module, a multi-factor fusion decision module, and a control execution and closed-loop feedback module. The safety margin prediction module is used to predict the trajectory sequence of the carriages in the future based on the vehicle's articulated kinematic model and current state. It also infers the corresponding future position sequence based on the current motion state of the obstacles, and transforms the obstacle positions to the coordinate system of each carriage by establishing a local coordinate system of the vehicle body. Using the obstacle envelope model, it calculates the minimum distance between all carriages and all obstacles at all predicted time points, calculates the safety margin based on the minimum distance, and extracts the global minimum safety margin value and the time of its first occurrence.

[0014] The sensitivity analysis module is used to introduce a speed disturbance at the current speed and drive the safety margin prediction module to re-predict the future trajectory and risk at the disturbed speed. By comparing and analyzing the global minimum safety margin at the original speed and the global minimum safety margin at the disturbed speed, the speed disturbance sensitivity is calculated.

[0015] The multi-factor fusion decision module is used to receive the global minimum safety margin, the prediction time of the first occurrence of the margin, and the speed disturbance sensitivity, and to calculate the danger level factor, time proximity factor, and sensitivity factor in parallel. Through a preset weighted fusion algorithm, it comprehensively calculates the deceleration ratio coefficient.

[0016] The control execution and closed-loop feedback module is used to calculate the final target speed value based on the deceleration ratio coefficient, combined with the current speed and the preset allowable speed upper and lower limits, and send the target speed command to the vehicle's underlying drive control system in real time to complete the actual control of the vehicle speed. The entire process from data acquisition to command execution is triggered cyclically in a preset control cycle. After each cycle, the real state of the vehicle and the environment is fed back to the system starting point as the input for prediction and decision-making in the next cycle.

[0017] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of a method for obstacle avoidance and speed control of an intelligent rail transit vehicle.

[0018] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for obstacle avoidance and speed control of an intelligent rail transit vehicle.

[0019] The beneficial effects of this invention are as follows: By employing a segmented recursive kinematic model, this invention achieves accurate and coordinated prediction of the future trajectory of multi-car articulated trains, overcoming the risk assessment error caused by inconsistent trajectories of different carriages during turns or obstacle avoidance in traditional simplified models; by introducing dynamic safety margin calculation and global extraction, future spatiotemporal interaction information is condensed into two quantitative indicators: risk severity and urgency, enabling advanced and accurate assessment of collision risks; by conducting speed disturbance sensitivity analysis, the direction and degree of the impact of speed changes on the safety status are quantified, providing a key decision-making basis for speed regulation; by integrating three factors—danger level, time imminence, and sensitivity—for dynamic weighted decision-making, and through safety limiting and closed-loop execution, unnecessary braking is avoided while ensuring driving safety, significantly improving the smoothness, ride comfort, and traffic efficiency of intelligent rail transit in complex dynamic environments. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating an intelligent rail transit obstacle avoidance and speed control method according to an embodiment of the present invention.

[0022] Figure 2 This is a schematic diagram illustrating the minimum safety margin calculation process of an intelligent rail transit obstacle avoidance and speed control method according to an embodiment of the present invention.

[0023] Figure 3 This is a schematic diagram illustrating the change of the minimum safety margin of the future trajectory over time in an intelligent rail transit obstacle avoidance and speed control method according to an embodiment of the present invention.

[0024] Figure 4 This is a schematic diagram illustrating the sensitivity of a smart rail transit obstacle avoidance and speed control method to the change of speed-safety margin over time, as provided in an embodiment of the present invention.

[0025] Figure 5 This is a schematic diagram of the vehicle speed adjustment curve for an intelligent rail transit obstacle avoidance and speed control method provided in one embodiment of the present invention.

[0026] Figure 6The present invention provides a system scheme flowchart for an intelligent rail transit obstacle avoidance and speed control system according to an embodiment of the present invention. Detailed Implementation

[0027] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0028] Example 1, referring to Figure 1 As an embodiment of the present invention, a method for obstacle avoidance and speed control of an intelligent rail transit vehicle is provided, comprising: S100: Acquire operational data and path information, and based on the operational data and path information, predict the state information of the intelligent rail transit vehicle at future moments, and simultaneously deduce the predicted position of obstacles at the corresponding moments.

[0029] S200: Based on the predicted state information and the predicted location of the obstacle, calculate the global minimum safety margin characterizing the collision risk between the train and the obstacle, and determine the first time interval at which the margin first appears.

[0030] S300: Introduce a speed disturbance based on the current speed, calculate the global minimum safety margin before and after the disturbance, and calculate the speed disturbance sensitivity based on the change relationship between the global minimum safety margin before and after the disturbance.

[0031] S400: Based on the minimum safety margin, speed disturbance sensitivity and the first time interval, a three-factor deceleration ratio is constructed, and the target speed is determined according to the deceleration ratio. Speed ​​control is then performed in a cyclical manner with a preset period.

[0032] It should be noted that this invention achieves accurate assessment of the future collision risks of multi-section intelligent rail transit vehicles, and based on a comprehensive analysis of the risk level, urgency, and speed adjustment effectiveness, performs smooth and reasonable speed control, thereby improving the stability and efficiency of intelligent rail transit vehicle operation.

[0033] Example 2, refer to Figures 1-5 This is a second embodiment of the present invention, which provides a method for obstacle avoidance and speed control of an intelligent rail transit vehicle, including: In step S100, acquiring operating data and path information includes collecting the operating data of the intelligent rail transit vehicle, which includes multiple carriages, at the current moment. Specifically, this includes the pose data of each carriage, the longitudinal speed of the vehicle, the predetermined path information, and the real-time status of external obstacles.

[0034] Specifically, the pose data for each carriage includes the global position coordinates and heading angle of each carriage; the real-time status of external obstacles includes, for each detected obstacle, obtaining the current position, movement speed, and the envelope radius (for circular envelopes) or the circumscribed rectangle size (for rectangular envelopes).

[0035] Furthermore, in step S100, the prediction of the state information of the intelligent rail transit vehicle at future moments includes prediction based on the articulated structural characteristics of the intelligent rail transit vehicle using a segmented recursive kinematic model, specifically including steps S101~S103: S101: Define the positions of the three carriages (lead car, middle car, and tail car) as the system state vector, where the state vector contains the global coordinates and heading angle of each carriage.

[0036] S102: The segmented recursive kinematic model starts from the current state and recursively calculates the state of the next multiple steps according to the set time step. It calculates the position and heading of the lead car at the next moment based on the current speed and heading angle, and calculates the global coordinates of the first articulation point connecting the lead car and the middle car by combining the length of the car body and the heading angle of the lead car. The kinematic equations of the lead car are expressed as follows: in, Let i+1 be the heading angle of the lead vehicle at prediction step i+1. Let i be the heading angle of the lead vehicle at prediction step i. Let i be the longitudinal speed of the vehicle at time i, Let i be the front wheel steering angle at prediction step i. The length of a single carriage. The time step used by the prediction model, Let i+1 be the global X-axis coordinate of the lead car. Let i be the global X-axis coordinate of the lead vehicle at prediction step i. Let i+1 be the global Y-axis coordinate of the lead car. Let be the global Y-axis coordinate of the lead car at prediction step index i.

[0037] The first hinge point transmission model is represented as follows: in, Let i+1 be the global X-axis coordinate of the first hinge point at prediction step i+1. Let be the global Y-axis coordinate of the first hinge point at prediction step i+1.

[0038] S103: The heading angle of the CRRC is determined by the direction of the link formed by the lead car and the CRRC, and the position is calculated in reverse based on the heading angle and the coordinates of the first articulation point; following the same logic, the position of the tail car is updated by transmitting the coordinates of the second articulation point.

[0039] The kinematic update formula for the intermediate car is expressed as: in, Let i+1 be the global X-axis coordinate of the vehicle at prediction step i+1. Let i+1 be the global Y-axis coordinate of the vehicle at prediction step i+1. Let i+1 be the heading angle of the vehicle at prediction step i+1. This is the offset distance of the hinge point. Let i be the global X-axis coordinate of the vehicle at prediction step i. Let be the global Y-axis coordinate of the vehicle at prediction step i.

[0040] The second hinge point transmission model is represented as follows: in, Let i+1 be the global X-axis coordinate of the second hinge point at prediction step i+1. Let be the global Y-axis coordinate of the second hinge point at prediction step i+1.

[0041] The formula for updating the pose of the tail car is expressed as follows: in, Let i+1 be the global X-axis coordinate of the tail car. Let i+1 be the global Y-axis coordinate of the tail car. Let i+1 be the heading angle of the tail car at prediction step i+1. Let i+1 be the global X-axis coordinate of the second hinge point at prediction step i+1. Let i+1 be the global Y-axis coordinate of the second hinge point at prediction step i+1. Let i be the global X-axis coordinate of the tail car at prediction step i. Let i be the global Y-axis coordinate of the tail car at prediction step i. It is the arctangent function in the four quadrants.

[0042] Furthermore, in step S100, the deducing of the predicted position of the obstacle at the corresponding time includes using an obstacle envelope approximation algorithm, assuming that the obstacle maintains uniform linear motion after the current time. The formula for the predicted position of the obstacle at the i-th prediction time is expressed as: in, Let be the global X-axis coordinate of the obstacle at the i-th prediction time (i.e., prediction step i). Let be the global Y-axis coordinate of the obstacle at the i-th prediction time (i.e., prediction step i). Let be the initial global X-axis coordinate of obstacle j at the current moment. Let be the initial global Y-axis coordinate of obstacle j at the current moment. Let be the velocity of obstacle j along the X-axis. Let be the velocity of obstacle j along the Y-axis. This is the time elapsed from the current moment to the i-th prediction moment (i.e., prediction step i).

[0043] It should be noted that the obstacle envelope approximation algorithm supports obstacles of arbitrary shapes (such as pedestrians, vehicles, and static obstacles) and uses circumscribed rectangles or circles for modeling; for dynamic obstacles (such as vehicles and pedestrians), a circular envelope is used; and for static obstacles (such as curbs and guardrails), a rectangular envelope is used, ensuring the universality and accuracy of distance calculation.

[0044] In step S200, the calculation of the global minimum safety margin characterizing the collision risk between the train and the obstacle includes steps S201-S204: S201: Coordinate transformation includes, for the k-th carriage at the i-th prediction time, establishing a local coordinate system of the vehicle body with the center as the origin and the heading angle as the positive direction of the U-axis, and transforming the predicted position of obstacle j to the current coordinate system through rotation and translation operations.

[0045] The coordinate transformation formula is expressed as: in, Let be the difference in the X-axis coordinates between obstacle j and the k-th carriage at the i-th prediction time (i.e., prediction step i). Let be the difference in the Y-axis coordinate between obstacle j and the k-th carriage at the i-th prediction time (i.e., prediction step i). Let be the global X-axis coordinate of obstacle j at the i-th prediction time (i.e., prediction step i). Let be the global Y-axis coordinate of obstacle j at the i-th prediction time (i.e., prediction step i). Let be the global X-axis coordinate of the k-th carriage at the i-th prediction time (i.e., prediction step i). Let be the global Y-axis coordinate of the k-th carriage at the i-th prediction time (i.e., prediction step i). Let be the heading angle of the k-th carriage at the i-th prediction time (i.e., prediction step i). Let the coordinate of obstacle j at the i-th prediction time (i.e., prediction step i) be relative to the U-axis of the local coordinate system of the k-th carriage. Let V be the coordinate of obstacle j relative to the V-axis of the local coordinate system of the k-th carriage at the i-th prediction time (i.e., prediction step i).

[0046] S202: Distance calculation includes simplifying each carriage into a rectangle of a specific length and width, and calculating the shortest distance from the obstacle point to the current rectangle in the local coordinate system.

[0047] The minimum distance between an obstacle and the vehicle body is expressed as: in, This represents the minimum extrapolation distance from the obstacle point to the edge of the rectangular U-axis of the carriage. This represents the minimum extrapolation distance from the obstacle point to the edge of the rectangular carriage along the V-axis. Let j be the shortest geometric distance between obstacle j and the k-th carriage at the i-th prediction time (i.e., prediction step i).

[0048] S203: Safety margin calculation includes defining the safety margin between obstacle j and carriage k at time i, which is the shortest distance minus the envelope radius of the obstacle. When the safety margin value is greater than zero, it indicates that there is a safety margin. When the safety margin value is less than zero, a collision is predicted to occur.

[0049] The safety margin is calculated as follows: in, Let be the safety margin between obstacle j and the k-th carriage at the i-th prediction time (i.e., prediction step i). Let be the radius of the envelope of obstacle j.

[0050] S204: By traversing all obstacles, carriages and predicted times, extract the minimum value as the global minimum safety margin, and at the same time record the prediction step index of the first occurrence of the minimum value, and calculate the corresponding first time interval.

[0051] The formula for calculating the global minimum safety margin is as follows: in, To determine the minimum safety margin between all cars and all obstacles at the i-th prediction time (i.e., prediction step i), This represents the total number of obstacles currently detected. To determine the global minimum safety margin over the entire prediction time span (N steps), This is the index of the prediction steps that first appear with the global minimum safety margin. The time interval corresponding to the first occurrence of the global minimum safety margin. The earliest time the risk appears, This represents the total number of steps in the prediction.

[0052] In step S300, sensitivity analysis is the core prerequisite for the speed control strategy. It addresses the technical pain point that precise, safe, and efficient speed adjustment cannot be achieved solely based on the degree of danger and time urgency. This analysis adapts to the structural characteristics and operational requirements of the intelligent rail transit system. The calculation of speed disturbance sensitivity includes steps S301-S303: S301: Apply a positive disturbance to the current velocity to obtain the disturbance velocity, expressed by the formula: in, The velocity after the disturbance, The current speed refers to the actual longitudinal speed of the intelligent rail transit vehicle at the current moment. This is the preset velocity disturbance.

[0053] S302: Using the current disturbance velocity as a new initial condition, repeat the trajectory prediction and safety margin calculation steps to obtain the global minimum safety margin after the disturbance.

[0054] S303: Calculation of velocity disturbance sensitivity index. This index is used to quantify the specific impact of velocity changes on safety. The calculation formula is as follows: in, This is a velocity disturbance sensitivity index. To the perturbation speed As the initial velocity, the global minimum safety margin after perturbation is obtained by re-performing trajectory prediction and safety margin calculation. This is the original global minimum safety margin calculated using the original current speed v.

[0055] When the speed disturbance sensitivity index is greater than zero, it means that the increase in speed increases the safety margin and makes the operation safer; when the speed disturbance sensitivity index is less than zero, it means that the increase in speed leads to a decrease in the safety margin and an increase in danger; when the speed disturbance sensitivity index is approximately equal to zero, it means that the change in speed has almost no impact on the safety margin under the most dangerous condition.

[0056] In step S400, to construct the deceleration ratio, three factors are defined. Constructing the three-factor deceleration ratio includes calculating three factors: a hazard level factor, a time proximity factor, and a sensitivity factor. Specifically, this includes steps S401-S404: S401: Calculate the hazard factor based on the global minimum safety margin, set the maximum reasonable safety margin, and take the maximum value of 1 when a collision is predicted, and take the minimum value of 0 when the maximum safety margin is reached, with a linear transition in between.

[0057] The formula for calculating the risk factor is expressed as follows: in, As a risk factor, To provide the maximum reasonable safety margin.

[0058] S402: Calculate the time approach factor based on the first time interval, set the warning time threshold, take the maximum value of 1 when the current moment is the most dangerous, take the minimum value of 0 when the threshold is exceeded, and make a linear transition in between.

[0059] The formula for calculating the time proximity factor is expressed as follows: in, As the time proximity factor, The first time interval is the time when the global minimum safety margin first occurs. It is a time constant. It is a natural constant.

[0060] S403: Calculate the sensitivity factor based on the sensitivity index, and map it to a specific range by multiplying it by the adjustment coefficient to adjust the deceleration intensity.

[0061] The formula for calculating the sensitivity factor is expressed as follows: in, For sensitivity factor, This is a velocity disturbance sensitivity index. For adjustment coefficients, This is the saturation limit.

[0062] When the velocity disturbance sensitivity is less than zero, the vehicle should actively decelerate, and the sensitivity factor is positive. When the velocity disturbance sensitivity is greater than zero, the vehicle can be conservatively decelerated or even maintained, and the sensitivity factor is negative or zero.

[0063] S404: The three factors are fused by weighted summation. Using preset weight coefficients that satisfy the sum of 1, a proportional coefficient for speed adjustment is generated. The value range of the coefficient is designed to include the range from full braking to maintaining the original speed or even slight acceleration.

[0064] The weighted summation formula is expressed as: in, This is the final deceleration ratio coefficient.

[0065] Furthermore, in step S400, the execution speed adjustment includes steps S411~S413: S411: After generating the deceleration ratio coefficient, the system calculates the final target vehicle speed based on the current coefficient and the current vehicle speed.

[0066] The formula for calculating the target vehicle speed is expressed as: in, To achieve the minimum stable vehicle speed, For the maximum safe speed, The final target speed.

[0067] To ensure driving safety and smooth operation, the target speed must be limited between the preset minimum stable speed and the maximum safe speed.

[0068] S412: The target vehicle speed command, after being processed by the speed limiter, is sent to the vehicle drive control system in real time to execute the actual speed adjustment, and the control process within a single control cycle is completed.

[0069] S413: The preset cycle refers to the system running continuously with a fixed control cycle. Each new fixed control cycle re-collects the latest vehicle pose, actual speed and obstacle status as input, and fully executes the entire process from trajectory prediction, safety margin calculation, sensitivity analysis to multi-factor fusion decision-making and vehicle speed execution.

[0070] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0071] Example 3, referring to Figure 6 This is the third embodiment of the present invention. This embodiment provides an intelligent rail transit obstacle avoidance and speed control system, including a safety margin prediction module, a sensitivity analysis module, a multi-factor fusion decision module, and a control execution and closed-loop feedback module. The safety margin prediction module is used to predict the trajectory sequence of the carriages in the future based on the vehicle's articulated kinematic model and current state. It also infers the corresponding future position sequence based on the current motion state of the obstacles, and transforms the obstacle positions to the coordinate system of each carriage by establishing a local coordinate system of the vehicle body. Using the obstacle envelope model, it calculates the minimum distance between all carriages and all obstacles at all predicted time points, calculates the safety margin based on the minimum distance, and extracts the global minimum safety margin value and the time of its first occurrence.

[0072] The sensitivity analysis module is used to introduce a speed disturbance at the current speed and drive the safety margin prediction module to re-predict the future trajectory and risk at the disturbed speed. By comparing and analyzing the global minimum safety margin at the original speed and the global minimum safety margin at the disturbed speed, the speed disturbance sensitivity is calculated.

[0073] The multi-factor fusion decision module is used to receive the global minimum safety margin, the prediction time of the first occurrence of the margin, and the speed disturbance sensitivity, and to calculate the danger level factor, time proximity factor, and sensitivity factor in parallel. Through a preset weighted fusion algorithm, it comprehensively calculates the deceleration ratio coefficient.

[0074] The control execution and closed-loop feedback module is used to calculate the final target speed value based on the deceleration ratio coefficient, combined with the current speed and the preset allowable speed upper and lower limits, and send the target speed command to the vehicle's underlying drive control system in real time to complete the actual control of the vehicle speed. The entire process from data acquisition to command execution is triggered cyclically in a preset control cycle. After each cycle, the real state of the vehicle and the environment is fed back to the system starting point as the input for prediction and decision-making in the next cycle.

[0075] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0076] Example 4, the fourth embodiment of the present invention, differs from the previous three embodiments in that: If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0077] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0078] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0079] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

Claims

1. A method for obstacle avoidance and speed control of an intelligent rail transit vehicle, characterized in that: include, Based on operational data and path information, the system predicts the state of the intelligent rail transit vehicle at future moments and simultaneously infers the predicted positions of obstacles at corresponding moments. Based on the predicted state information and the predicted location of obstacles, calculate the global minimum safety margin characterizing the collision risk between the train and the obstacle, and determine the first time interval at which the margin first appears. Based on the current speed, a speed disturbance is introduced to induce a speed disturbance. The global minimum safety margin before and after the disturbance is calculated respectively. The speed disturbance sensitivity is calculated based on the change relationship between the global minimum safety margin before and after the disturbance. A three-factor deceleration ratio is constructed based on the minimum safety margin, speed disturbance sensitivity, and first time interval. The target speed is determined according to the deceleration ratio, and speed regulation is executed in a cyclical manner with a preset period.

2. The method for obstacle avoidance and speed control of an intelligent rail transit vehicle as described in claim 1, characterized in that: The predicted state information of the intelligent rail transit vehicle at future moments includes establishing the pose transfer relationship from the front carriage to the rear carriage based on the articulated structure characteristics of the intelligent rail transit vehicle. Based on current operational data, the position and heading angle of each carriage at every future moment are calculated according to the transmission relationship.

3. The method for obstacle avoidance and speed control of an intelligent rail transit vehicle as described in claim 2, characterized in that: The calculation of the global minimum safety margin characterizing the collision risk between the train and the obstacle includes transforming the predicted position of each obstacle to a local coordinate system of the vehicle body determined by the position and heading angle of the corresponding carriage, and calculating the minimum distance between the obstacle and the vehicle body outline in the local coordinate system.

4. The method for obstacle avoidance and speed control of an intelligent rail transit vehicle as described in claim 3, characterized in that: The calculation of the global minimum safety margin characterizing the collision risk between the train and the obstacle also includes calculating the safety margin between each obstacle and each carriage based on the minimum distance. Iterate through all predicted times, all carriages, and all obstacles, and extract the minimum safety margin as the global minimum safety margin.

5. The method for obstacle avoidance and speed control of an intelligent rail transit vehicle as described in claim 4, characterized in that: The calculation of velocity disturbance sensitivity includes comparing the global minimum safety margin obtained at the original velocity with the global minimum safety margin obtained by re-predicting and calculating after applying a velocity disturbance, and dividing the difference between the two margins by the velocity disturbance amount to obtain the velocity disturbance sensitivity.

6. The method for obstacle avoidance and speed control of an intelligent rail transit vehicle as described in claim 5, characterized in that: The construction of the three-factor deceleration ratio includes normalizing the global minimum safety margin to obtain the danger level factor, and performing a mathematical transformation on the first time interval to obtain the time approximation factor. The velocity disturbance sensitivity is processed in terms of direction and magnitude to obtain a sensitivity factor. The danger level factor, time proximity factor and sensitivity factor are then weighted and fused to generate a three-factor deceleration ratio.

7. The method for obstacle avoidance and speed control of an intelligent rail transit vehicle as described in claim 6, characterized in that: The cyclic execution with a preset period includes calculating the target speed based on the deceleration ratio and the current speed, limiting the target speed to the range between the minimum stable speed and the maximum safe speed, and sending it to the drive control system for adjustment. In the next control cycle, the latest vehicle status and obstacle information are collected again, and the entire process is executed based on the new data to obtain dynamic closed-loop control.

8. A smart rail transit obstacle avoidance and speed control system, employing the smart rail transit obstacle avoidance and speed control method as described in any one of claims 1 to 7, characterized in that, It includes a safety margin prediction module, a sensitivity analysis module, a multi-factor fusion decision module, and a control execution and closed-loop feedback module; The safety margin prediction module is used to predict the trajectory sequence of the carriages in the future based on the vehicle's articulated kinematics model and current state, to deduce the corresponding future position sequence based on the current motion state of the obstacles, and to transform the obstacle positions to the coordinate system of each carriage by establishing a local coordinate system of the vehicle body. It also uses the obstacle envelope model to calculate the minimum distance between all carriages and all obstacles at all predicted time points, calculates the safety margin based on the minimum distance, and extracts the global minimum safety margin value and the time of its first occurrence. The sensitivity analysis module is used to introduce a speed disturbance at the current speed and drive the safety margin prediction module to re-predict the future trajectory and risk at the disturbed speed. By comparing and analyzing the global minimum safety margin at the original speed and the global minimum safety margin at the disturbed speed, the speed disturbance sensitivity is calculated. The multi-factor fusion decision module is used to receive the global minimum safety margin, the prediction time of the first occurrence of the margin, and the speed disturbance sensitivity, and to calculate the danger level factor, time approach factor, and sensitivity factor in parallel. Through a preset weighted fusion algorithm, it comprehensively calculates the deceleration ratio coefficient. The control execution and closed-loop feedback module is used to calculate the final target speed value based on the deceleration ratio coefficient, combined with the current speed and the preset allowable speed upper and lower limits, and send the target speed command to the vehicle's underlying drive control system in real time to complete the actual control of the vehicle speed. The entire process from data acquisition to command execution is triggered cyclically in a preset control cycle. After each cycle, the real state of the vehicle and the environment is fed back to the system starting point as the input for prediction and decision-making in the next cycle.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent rail transit obstacle avoidance and speed control method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent rail transit obstacle avoidance and speed control method according to any one of claims 1 to 7.

Images