Passenger boarding bridge automatic parking remote driving control method and system

Abstract

The application discloses a kind of passenger boarding ladder automatic parking remote driving control method and system, specifically related to remote control technical field, including building information sharing platform, real-time image acquisition device and vehicle-mounted radar are installed on boarding ladder and real-time data are obtained, information sharing platform, real-time data and obstacle analysis model are connected;Through the information sharing platform, road information, road traffic signal and other vehicle information are obtained through the information sharing platform, can save power consumption, and improve efficiency;In the obstacle analysis process, by directly comparing real-time image data and corresponding background image data, the part in real-time image that does not conform to background image can be quickly identified, so as to accurately judge the existence and position of the obstacle, reduce the obstacle analysis time, effectively solve the problem that remote driving response time is long in the prior art, increase boarding ladder operation risk.

Description

Technical Field

[0001] This invention relates to the field of remote control technology, and more specifically, to a remote driving control method and system for automatic parking of passenger boarding stairs. Background Technology

[0002] An aircraft boarding ladder is a special vehicle used at airports to erect a ladder connecting the ground to the aircraft door, allowing passengers to board and disembark. Automatic parking and remote driving control of the boarding ladder effectively save resources and provide shuttle services for passengers.

[0003] In the prior art with application number 202310084318.1, a remote driving control method for automatic parking of passenger boarding stairs is disclosed, belonging to the field of intelligent driving. The proposed method adopts a new analysis technology framework that combines local image analysis with global image and voice analysis to realize the remote driving control method for boarding stairs. It performs collaborative analysis based on the voice signals of passengers in the vehicle in real time, which greatly improves the safety and accuracy of the remote driving control method for boarding stairs. Furthermore, the attention collaborative analysis model is specifically improved, which significantly improves the analysis results and further enhances the control effect of passenger boarding stairs.

[0004] However, in practical use, the existing technology still has many shortcomings, such as long remote driving response time. Specifically, it relies too much on deep learning models to identify road information, other lane vehicle information and obstacle information of the boarding stairs, which increases the analysis time; it needs to process real-time image information, which consumes huge computing resources, resulting in delays in boarding stairs operation instructions and failing to provide smooth service to passengers. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, the present invention provides a remote driving control method and system for automatic parking of passenger boarding stairs. By establishing an information sharing platform and utilizing Internet of Things (IoT) technology to acquire environmental information of the boarding stairs, the response time during remote driving of the boarding stairs is effectively shortened, thereby solving the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a remote driving control method for automatic parking of a passenger boarding stairs, comprising the following steps:

[0007] Step 1: Build an information sharing platform and verify its reliability; build an obstacle analysis model and verify its reliability.

[0008] Step 2: Real-time data is collected by installing a real-time image acquisition device on the boarding ladder and vehicle-mounted radar, and then the information sharing platform, real-time data and obstacle analysis model are connected.

[0009] Step 3: When the vehicle-mounted radar detects an obstruction in the direction of the boarding stairs, real-time image data is collected through the vehicle-mounted camera.

[0010] Step 4: Retrieve the image data that corresponds to the real-time image data in time and space from the verified information sharing platform as the background image data;

[0011] Step 5: The verified obstacle analysis model receives real-time data and corresponding background image data, and outputs obstacle information; the obstacle information includes: the position, size, shape, and motion status of the obstacle;

[0012] Step 6: Generate and execute remote control commands based on obstacle information and information sharing platform information. The information sharing platform information includes environmental information and vehicle positioning data.

[0013] Preferably, the establishment of the information sharing platform includes: inputting environmental information within the target area into the information sharing platform to build a simulation model of the target area; acquiring real-time vehicle positioning data through vehicle-mounted radar, and uploading the real-time vehicle positioning data and corresponding trajectory information to the simulation model of the target area in real time based on Internet of Things technology; and establishing the information sharing platform after visualization processing.

[0014] Preferably, the traffic signal information and road information are image data.

[0015] Preferably, the method for verifying the reliability of the information sharing platform is as follows:

[0016] Step 101: Collect environmental information and denote it as Ha; retrieve the spatiotemporal corresponding environmental information from the information sharing platform and denote it as Hb;

[0017] Step 102: By analyzing the similarity between environmental information Ha and environmental information Hb, output the shared information consistency index Yz;

[0018] Step 103: By judging the relationship between the shared information consistency index Yz and the preset value, the reliability of the information sharing platform is determined. When the shared information consistency index Yz is lower than the preset value, it indicates that the information sharing platform is abnormal and in an unreliable state; otherwise, it indicates that the information sharing platform is reliable.

[0019] Preferably, when the environmental information only includes image data, the consistency index of shared information is represented by image similarity. Based on the location of the point of interest, the image is divided into several regions, and a weight coefficient is matched for each region. The consistency analysis model is obtained by weighted summation of the image similarity and weight coefficient of each region.

[0020] Preferably, when the environmental information only includes vehicle location data, the similarity of vehicle location data is used to represent the consistency index of shared information;

[0021] Preferably, when the environmental information includes image data and vehicle positioning data, the consistency index of shared information is represented by the sum of image similarity and vehicle positioning data similarity.

[0022] Preferably, the obstacle analysis model includes a static obstacle feature analysis model, a dynamic obstacle feature analysis model, and a feature fusion unit;

[0023] The obstacle static feature analysis model is used to analyze image data in real-time data, predict the static features of obstacles, and present the obstacle location box in the form of bounding box and confidence score.

[0024] The obstacle dynamic feature analysis model obtains the obstacle location box based on the obstacle static feature analysis model, and predicts the obstacle motion characteristics by analyzing the location data of the obstacle location box.

[0025] The feature fusion unit is used to output obstacle information, fusing static and motion features of the obstacle.

[0026] Preferably, the obstacle static feature analysis model includes an input layer, a feature extraction layer, and a classification and regression layer. The input layer receives real-time image data and corresponding background image data as input. The feature extraction layer uses a convolutional neural network algorithm to extract features from the input image data, including edge, texture, color, and semantic features (such as the shape and category of the object). The classification and regression layer performs classification and regression operations on each pixel or region in the real-time image based on the extracted features. The classification operation is used to determine whether a pixel or region belongs to the obstacle category, while the regression operation is used to estimate the position and size parameters of the obstacle.

[0027] Preferably, the method for verifying the reliability of the obstacle analysis model is as follows:

[0028] Step 201: Conduct several tests on the obstacle analysis model and record the test results;

[0029] Step 202: Analyze the test results to obtain the average processing time, the average real-time data feature information entropy, and the obstacle accuracy parameters, which are denoted as Za, Zb, and Zc, respectively.

[0030] Step 204, using the formula The obstacle recognition performance index Xb is calculated. The Form(·) function is used to normalize the contents in parentheses so that the values ​​in parentheses are in the range of 0 to 1. X1, X2, and X3 are used to correct the obstacle accuracy parameters, processing time loss rate, and feature information entropy, and adjust their influence on the obstacle recognition performance index.

[0031] Preferably, the obstacle accuracy parameters are obtained in the following way:

[0032] The difference between the predicted static features of obstacles and the actual static features of obstacles is analyzed to obtain the static feature loss parameter La;

[0033] The difference between the predicted obstacle motion characteristics and the actual obstacle motion characteristics is analyzed to obtain the motion characteristic loss parameter Lb;

[0034] The static feature loss parameter La and the motion feature loss parameter Lb are combined using the formula... The obstacle accuracy parameter Za is calculated, where La_max represents the maximum value of the static feature loss parameter and Lb_max represents the maximum value of the motion feature loss parameter.

[0035] To achieve the objective of this invention, the following technical solution is provided: a remote driving control system for automatic parking of passenger boarding stairs, comprising:

[0036] The information sharing platform management module is used to build the information sharing platform and verify its reliability based on the shared information consistency index.

[0037] The obstacle analysis management module is used to build obstacle analysis models and verify the reliability of obstacle analysis models based on obstacle recognition performance indices.

[0038] The real-time image data acquisition module acquires real-time image data through the vehicle-mounted camera when the vehicle-mounted radar detects an obstruction in the direction of the boarding ladder.

[0039] The background image data acquisition module retrieves image data that corresponds to the real-time image data in time and space from the verified information sharing platform as background image data;

[0040] The obstacle information acquisition module receives real-time data and corresponding background image data from the verified obstacle analysis model and outputs obstacle information.

[0041] The remote control module generates and executes remote control commands based on obstacle information and information sharing platform information.

[0042] Preferably, the passenger boarding stairs automatic parking remote driving control system further includes:

[0043] The driving operation management module is used to obtain the autonomous driving operation reliability index. This index is obtained by comparing the actual and expected response parameters of the boarding elevator under operating commands. The autonomous driving operation reliability index is obtained as follows:

[0044] To obtain the instruction response time loss rate and instruction operation accuracy loss rate, suppose there are m operation instructions, and let j represent the sequence number of the operation instructions;

[0045] Let st_j be the average response time loss rate and sac_j be the average operation accuracy loss rate for the j-th operation command. The autonomous driving operation reliability index is then calculated using the following formula.

[0046]

[0047] Where f1 and f2 represent correction factors for time loss rate and accuracy loss rate, respectively, which are used to adjust the degree of influence of time loss rate and accuracy loss rate on the reliability index of autonomous driving operation.

[0048] Preferably, the passenger boarding stairs automatic parking remote driving control system also includes

[0049] The monitoring and early warning module monitors the shared information consistency index Xa, obstacle recognition performance index Xb, and autonomous driving operation reliability index Xc in real time. When the monitored data is lower than the corresponding threshold, an early warning is issued. Maintenance is performed based on the fault knowledge graph to eliminate anomalies.

[0050] The remote driving control performance analysis module jointly analyzes the shared information consistency index, obstacle recognition performance index, and autonomous driving operation reliability index to obtain the remote driving control coefficient, and takes measures based on the remote driving control coefficient.

[0051] Preferably, the remote driving control performance analysis module includes:

[0052] The thresholds for obtaining the shared information consistency index, obstacle recognition performance index, and autonomous driving operation reliability index are denoted as Tha, Thb, and Thc, respectively.

[0053] Using the formula YK=e -max(Xa-Tha，0) *e -max(Xb-Thb，0) *e -max(Xc-Thc，0) The remote driving control coefficient YK is calculated.

[0054] When the remote driving control coefficient is lower than the corresponding threshold, an early warning is issued, indicating that the reliability of remote unmanned driving is low and more monitoring and maintenance resources need to be allocated.

[0055] When the remote driving control coefficient is not lower than the corresponding threshold, it indicates that the remote driving performance of the boarding ladder is normal, and no measures are taken.

[0056] The technical effects and advantages of this invention are as follows:

[0057] (1) The passenger boarding ladder automatic parking remote driving control method provided by the present invention can save computing power and improve efficiency by using an information sharing platform to obtain road information, road traffic signals and other vehicle information. In the process of obstacle analysis, by directly comparing real-time image data and corresponding background image data, the part in the real-time image that does not match the background image can be quickly identified, thereby accurately determining the existence and location of obstacles, reducing obstacle analysis time, and effectively solving the problems of long remote driving response time and increased risk of boarding ladder operation in the prior art.

[0058] (2) The passenger boarding ladder automatic parking remote driving control method provided by the present invention effectively ensures the quality of remote control by verifying the reliability of the information sharing platform and the obstacle analysis model, and avoids the reduction of obstacle recognition efficiency due to erroneous information.

[0059] (3) The passenger boarding elevator automatic parking remote driving control system provided by the present invention obtains the automatic driving operation reliability index through the driving operation management module, effectively quantifies the performance quality of the boarding elevator, and jointly analyzes the shared information consistency index, obstacle recognition performance index and automatic driving operation reliability index to obtain the quality of remote control of the passenger boarding elevator and improve the safety of the boarding elevator. Attached Figure Description

[0060] Figure 1 This is a flowchart of the automatic parking remote driving control method for boarding stairs according to the present invention.

[0061] Figure 2 This is a block diagram of the obstacle analysis model of the present invention. Detailed Implementation

[0062] Exemplary examples of this disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary real-time examples of this disclosure are shown in the drawings, it should be understood that this disclosure may be implemented in various forms and should not be limited to the real-time examples set forth herein. Rather, these examples are provided to enable a more thorough understanding of this disclosure and to fully convey the scope of this disclosure to those skilled in the art.

[0063] The following description of at least one exemplary instance is merely illustrative and is in no way intended to limit this application or its application or use.

[0064] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0065] Real-time example 1, see Figure 1The present invention provides a method for remote driving control of automatic parking of passenger boarding stairs, comprising the following steps:

[0066] Step 1: Build an information sharing platform and verify its reliability; build an obstacle analysis model and verify its reliability.

[0067] Step 2: Real-time data is obtained by installing a real-time image acquisition device and vehicle-mounted radar on the boarding stairs. The vehicle-mounted radar is used to record the real-time positioning data of the boarding stairs and connects the information sharing platform, real-time data and obstacle analysis model. The real-time data includes real-time positioning data and real-time image data.

[0068] Step 3: When the vehicle-mounted radar detects an obstruction in the direction of the boarding stairs, real-time image data is collected through the vehicle-mounted camera.

[0069] Step 4: Retrieve the image data that corresponds to the real-time image data in time and space from the verified information sharing platform as the background image data;

[0070] Step 5: The verified obstacle analysis model receives real-time data and corresponding background image data, and outputs obstacle information; the obstacle information includes: the position, size, shape, and motion status of the obstacle;

[0071] Step 6: Generate and execute remote control commands based on obstacle information and information sharing platform information. Remote control commands include obstacle avoidance, deceleration, pausing, and path replanning. Information sharing platform information includes environmental information and vehicle positioning data.

[0072] In this embodiment of the invention, it is necessary to further explain that building an information sharing platform includes: inputting environmental information within the target area, such as traffic signal information and road information, into the information sharing platform to build a simulation model of the target area; acquiring real-time vehicle positioning data through vehicle-mounted radar, and uploading the real-time vehicle positioning data and corresponding trajectory information to the simulation model of the target area in real time based on Internet of Things technology; and building the information sharing platform after visualization processing; preferably, the traffic signal information and road information are image data.

[0073] In this embodiment of the invention, it needs to be further explained that the method for verifying the reliability of the information sharing platform is as follows:

[0074] Step 101: Collect environmental information and denote it as Ha; retrieve the spatiotemporal corresponding environmental information from the information sharing platform and denote it as Hb;

[0075] Step 102: By analyzing the similarity between environmental information Ha and environmental information Hb, output the shared information consistency index Yz;

[0076] Step 103: By judging the relationship between the shared information consistency index Yz and the preset value, the reliability of the information sharing platform is determined. When the shared information consistency index Yz is lower than the preset value, it indicates that the information sharing platform is abnormal and in an unreliable state; otherwise, it indicates that the information sharing platform is reliable.

[0077] In one possible real-time example, when the environmental information only includes image data, the consistency index of shared information is represented by image similarity. Based on the location of the point of interest, the image is divided into several regions, and a weight coefficient is matched for each region. The consistency analysis model is obtained by weighted summation of the image similarity and weight coefficient of each region.

[0078] In a possible real-time example, when the environmental information only includes vehicle location data, the similarity of vehicle location data is used to represent the consistency index of shared information.

[0079] In a possible real-time example, when environmental information includes image data and vehicle location data, the consistency index of shared information is represented by the sum of image similarity and vehicle location data similarity.

[0080] See Figure 2 The obstacle analysis model structure diagram includes an obstacle static feature analysis model, an obstacle dynamic feature analysis model, and a feature fusion unit;

[0081] The obstacle static feature analysis model is used to analyze image data in real-time data and predict the static features of obstacles, such as obstacle location, obstacle size, and obstacle shape.

[0082] The obstacle static feature analysis model includes an input layer, a feature extraction layer, and a classification and regression layer. The input layer receives real-time image data and corresponding background image data as input. The feature extraction layer uses a convolutional neural network algorithm to extract features from the input image data, including edge, texture, color, and semantic features (such as the shape and category of objects). The classification and regression layer performs classification and regression operations on each pixel or region in the real-time image based on the extracted features. The classification operation is used to determine whether a pixel or region belongs to the obstacle category, while the regression operation is used to estimate the position and size parameters of the obstacle.

[0083] The obstacle dynamic feature analysis model obtains the obstacle location box based on the obstacle static feature analysis model. By analyzing the positioning data of the obstacle location box, the movement characteristics of the obstacle, such as the obstacle's moving speed and moving direction, are predicted.

[0084] The feature fusion unit is used to output obstacle information, fusing static and motion features of the obstacle.

[0085] In this embodiment of the invention, it needs to be further explained that the method for verifying the reliability of the obstacle analysis model is as follows:

[0086] Step 201: Conduct several tests on the obstacle analysis model and record the test results;

[0087] Step 202: Analyze the test results to obtain the average processing time, the average real-time data feature information entropy, and the obstacle accuracy parameters, which are denoted as Za, Zb, and Zc, respectively.

[0088] The explanation is as follows: Processing time refers to the time required for the obstacle analysis model to complete recognition and response from receiving image data. It is calculated by averaging the processing times of multiple tests; the average processing time reflects the response speed of the obstacle analysis model. Information entropy is an indicator that measures the complexity and uncertainty of data. In obstacle analysis, real-time data feature information entropy can reflect the complexity of the data processed by the obstacle analysis model. It is calculated by averaging the real-time data feature information entropy of multiple tests; Obstacle accuracy parameter is a key indicator for measuring the accuracy of the model in recognizing obstacles. It is calculated by comparing the differences between the obstacles recognized by the model and the actual obstacles.

[0089] Step 204, using the formula The obstacle recognition performance index Xb is calculated. The Form(·) function is used to normalize the contents in parentheses so that the values ​​in parentheses are in the range of 0 to 1. X1, X2, and X3 are used to correct the obstacle accuracy parameters, processing time loss rate, and feature information entropy, and adjust their influence on the obstacle recognition performance index.

[0090] In this embodiment of the invention, it needs to be further explained that the method for obtaining the obstacle accuracy parameter is as follows:

[0091] The static feature loss parameter La is obtained by analyzing the difference between the predicted static features of obstacles and the actual static features of obstacles. In one possible instance, the static feature loss parameter La is represented by the sum of the mean square value of the coordinate error, the mean square value of the IOU error, and the mean square value of the classification error between the predicted data and the actual data.

[0092] The difference between the predicted obstacle motion characteristics and the actual obstacle motion characteristics is analyzed to obtain the motion feature loss parameter Lb; in a possible real-time example, the motion feature loss parameter Lb is represented by the mean square value of the motion vector error between the predicted data and the actual data.

[0093] The static feature loss parameter La and the motion feature loss parameter Lb are combined using the formula... The obstacle accuracy parameter Za is calculated, where La_max represents the maximum value of the static feature loss parameter and Lb_max represents the maximum value of the motion feature loss parameter.

[0094] In this explanation, when using an obstacle analysis model to predict obstacles, the predicted static features of the obstacles constitute a static feature set. There may be inconsistencies between the predicted static features and the actual observed static features. The difference between the predicted and actual static features is obtained by calculating a certain distance (such as Euclidean distance, Manhattan distance, etc.) or similarity (such as cosine similarity, Pearson correlation coefficient, etc.) between the predicted and actual features. The motion feature loss parameter Lb is used to quantify the degree of inconsistency between the predicted and actual motion features. Its calculation method may be similar to that of the static feature loss parameter La, but it will be applied to motion features. This invention does not provide specific explanations or limitations on this.

[0095] Real-time Example 2: This invention provides a remote driving control system for automatic parking of a passenger boarding stairs, comprising:

[0096] The information sharing platform management module is used to build the information sharing platform and verify its reliability based on the shared information consistency index.

[0097] The obstacle analysis management module is used to build obstacle analysis models and verify the reliability of obstacle analysis models based on obstacle recognition performance indices.

[0098] The real-time image data acquisition module acquires real-time image data through the vehicle-mounted camera when the vehicle-mounted radar detects an obstruction in the direction of the boarding ladder.

[0099] The background image data acquisition module retrieves image data that corresponds to the real-time image data in time and space from the verified information sharing platform as background image data;

[0100] The obstacle information acquisition module receives real-time data and corresponding background image data from the verified obstacle analysis model and outputs obstacle information.

[0101] The remote control module generates and executes remote control commands based on obstacle information and information sharing platform information.

[0102] In this embodiment of the invention, it should be further explained that the passenger boarding stairs automatic parking remote driving control system also includes:

[0103] The driving operation management module is used to obtain the autonomous driving operation reliability index. This index is obtained by comparing the actual and expected response parameters of the boarding elevator under operating commands. The autonomous driving operation reliability index is obtained as follows:

[0104] To obtain the instruction response time loss rate and instruction operation accuracy loss rate, suppose there are m operation instructions, and let j represent the sequence number of the operation instructions;

[0105] Let st_j be the average response time loss rate and sac_j be the average operation accuracy loss rate for the j-th operation command. The autonomous driving operation reliability index is then calculated using the following formula.

[0106]

[0107] Where f1 and f2 represent correction factors for time loss rate and accuracy loss rate, respectively, which are used to adjust the degree of influence of time loss rate and accuracy loss rate on the reliability index of autonomous driving operation.

[0108] In this embodiment of the invention, it should be further explained that the passenger boarding stairs automatic parking remote driving control system also includes

[0109] The monitoring and early warning module monitors the shared information consistency index Xa, obstacle recognition performance index Xb, and autonomous driving operation reliability index Xc in real time. When the monitored data is lower than the corresponding threshold, an early warning is issued. Maintenance is performed based on the fault knowledge graph to eliminate anomalies.

[0110] The remote driving control performance analysis module jointly analyzes the shared information consistency index, obstacle recognition performance index, and autonomous driving operation reliability index to obtain the remote driving control coefficient, and takes measures based on the remote driving control coefficient.

[0111] In this embodiment of the invention, it should be further explained that the remote driving control performance analysis module includes:

[0112] The thresholds for obtaining the shared information consistency index, obstacle recognition performance index, and autonomous driving operation reliability index are denoted as Tha, Thb, and Thc, respectively.

[0113] Using the formula YK=e -max(Xa-Tha，0) *e -max(Xb-Thb，0) *e -max(Xc-Thc，0) The remote driving control coefficient YK is calculated.

[0114] When the remote driving control coefficient is lower than the corresponding threshold, an early warning is issued, indicating that the reliability of remote unmanned driving is low and more monitoring and maintenance resources need to be allocated.

[0115] When the remote driving control coefficient is not lower than the corresponding threshold, it indicates that the remote driving performance of the boarding ladder is normal, and no measures are taken.

[0116] In summary, by setting remote driving control coefficients and corresponding thresholds, the embodiments of the present invention can effectively assess the reliability of remote unmanned driving systems. Based on the assessment results, the system can automatically take corresponding measures to ensure the safety and reliability of remote driving, which helps to improve the safety and efficiency of remote unmanned driving systems.

[0117] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for automatic parking remote driving control of a passenger boarding bridge, characterized in that, Includes the following steps: Step 1: Build an information sharing platform and verify its reliability; build an obstacle analysis model and verify its reliability; the obstacle analysis model includes a static obstacle feature analysis model, a dynamic obstacle feature analysis model, and a feature fusion unit. The obstacle static feature analysis model is used to analyze image data in real-time data, predict the static features of obstacles, and present the obstacle location box in the form of bounding box and confidence score; the obstacle dynamic feature analysis model obtains the obstacle location box based on the obstacle static feature analysis model, and predicts the obstacle motion features by analyzing the positioning data of the obstacle location box; the feature fusion unit is used to output obstacle information and fuse the obstacle static features and obstacle motion features. The reliability of the obstacle analysis model is verified as follows: The model is tested several times, and the results are recorded. The test results are analyzed to obtain the average processing time, the average real-time data feature entropy, and the obstacle accuracy parameters, denoted as Za, Zb, and Zc, respectively. The model is then verified using the formula... The obstacle recognition performance index Xb is calculated. The Form() function is used to normalize the contents in the brackets so that the values ​​in the brackets are in the range of 0 to 1. X1, X2, and X3 are used to correct the obstacle accuracy parameters, processing time loss rate, and feature information entropy, and adjust the degree of influence on the obstacle recognition performance index. The obstacle accuracy parameters are obtained as follows: The difference between the predicted and actual static characteristics of the obstacle is analyzed to obtain the static feature loss parameter La; the difference between the predicted and actual motion characteristics of the obstacle is analyzed to obtain the motion feature loss parameter Lb; the static feature loss parameter La and the motion feature loss parameter Lb are combined and then calculated using the formula... The obstacle accuracy parameter Za is calculated, where La_max represents the maximum value of the static feature loss parameter and Lb_max represents the maximum value of the motion feature loss parameter. Step 2: Real-time data is collected by installing a real-time image acquisition device on the boarding ladder and vehicle-mounted radar, and then the information sharing platform, real-time data and obstacle analysis model are connected. Step 3: When the vehicle-mounted radar detects an obstruction in the direction of the boarding stairs, real-time image data is collected through the vehicle-mounted camera. Step 4: Retrieve the image data that corresponds to the real-time image data in time and space from the verified information sharing platform as the background image data; Step 5: The verified obstacle analysis model receives real-time data and corresponding background image data, and outputs obstacle information; the obstacle information includes: the position, size, shape, and motion status of the obstacle; Step 6: Generate and execute remote control commands based on obstacle information and information sharing platform information.

2. The remote driving control method for automatic parking of passenger boarding stairs according to claim 1, characterized in that, The process of building an information sharing platform includes: inputting environmental information within the target area into the information sharing platform to build a simulation model of the target area; acquiring real-time vehicle positioning data through vehicle-mounted radar and uploading the real-time vehicle positioning data and corresponding trajectory information to the simulation model of the target area in real time based on Internet of Things technology; and finally, after visualization processing, building the information sharing platform.

3. The remote driving control method for automatic parking of passenger boarding stairs according to claim 2, characterized in that, The methods for verifying the reliability of the information sharing platform are as follows: Step 101: Collect environmental information and denote it as Ha; retrieve the spatiotemporal corresponding environmental information from the information sharing platform and denote it as Hb; Step 102: By analyzing the similarity between environmental information Ha and environmental information Hb, output the shared information consistency index Yz; Step 103: By judging the relationship between the shared information consistency index Yz and the preset value, the reliability of the information sharing platform is determined. When the shared information consistency index Yz is lower than the preset value, it indicates that the information sharing platform is abnormal and in an unreliable state; otherwise, it indicates that the information sharing platform is reliable.

4. A remote driving control system for automatic parking of passenger boarding stairs, used to implement the remote driving control method for automatic parking of passenger boarding stairs as described in claim 1, characterized in that, include: The information sharing platform management module is used to build the information sharing platform and verify its reliability based on the shared information consistency index. The obstacle analysis management module is used to build obstacle analysis models and verify the reliability of obstacle analysis models based on obstacle recognition performance indices. The real-time image data acquisition module acquires real-time image data through the vehicle-mounted camera when the vehicle-mounted radar detects an obstruction in the direction of the boarding ladder. The background image data acquisition module retrieves image data that corresponds to the real-time image data in time and space from the verified information sharing platform as background image data; The obstacle information acquisition module receives real-time data and corresponding background image data from the verified obstacle analysis model and outputs obstacle information. The remote control module generates and executes remote control commands based on obstacle information and information sharing platform information.

5. The passenger boarding stairs automatic parking remote driving control system according to claim 4, characterized in that, The automatic parking remote driving control system for the passenger boarding stairs also includes: The driving operation management module is used to obtain the autonomous driving operation reliability index. This index is obtained by comparing the actual and expected response parameters of the boarding elevator under operating commands. The autonomous driving operation reliability index is obtained as follows: To obtain the instruction response time loss rate and instruction operation accuracy loss rate, suppose there are m operation instructions, and let j represent the sequence number of the operation instructions; Let st_j be the average response time loss rate and sac_j be the average operation accuracy loss rate for the j-th operation command. The autonomous driving operation reliability index is then calculated using the following formula. Where f1 and f2 represent correction factors for time loss rate and accuracy loss rate, respectively, which are used to adjust the degree of influence of time loss rate and accuracy loss rate on the reliability index of autonomous driving operation.

6. The remote driving control system for automatic parking of passenger boarding stairs according to claim 5, characterized in that, The passenger boarding stairs automatic parking remote driving control system also includes The monitoring and early warning module monitors the shared information consistency index Xa, obstacle recognition performance index Xb, and autonomous driving operation reliability index Xc in real time. When the monitoring data is lower than the corresponding threshold, an early warning is issued. Maintenance is performed based on fault knowledge graphs to eliminate anomalies; The remote driving control performance analysis module jointly analyzes the shared information consistency index, obstacle recognition performance index, and autonomous driving operation reliability index to obtain the remote driving control coefficient, and takes measures based on the remote driving control coefficient.

7. The passenger boarding stairs automatic parking remote driving control system according to claim 6, characterized in that, The remote driving control performance analysis module includes: The thresholds for obtaining the consistency index of shared information, the obstacle recognition performance index, and the reliability index of autonomous driving operation are denoted as Tha, Thb, and Thc, respectively. Through formula The remote driving control coefficient YK is calculated. When the remote driving control coefficient is lower than the corresponding threshold, an early warning is issued, indicating that the reliability of remote unmanned driving is low and more monitoring and maintenance resources need to be allocated; when the remote driving control coefficient is not lower than the corresponding threshold, it indicates that the remote driving performance of the boarding ladder is normal and no measures are taken.

Images