Docking guidance method, device and apparatus for an aircraft

Abstract

This application relates to the field of aircraft parking guidance technology, and discloses an aircraft parking guidance method, apparatus, and equipment. The aircraft parking guidance method provided in this application effectively solves the energy waste problem caused by the continuous operation of sensors during non-guidance periods in the prior art by activating a second sensor for position identification and guidance after the target object is determined by a first sensor. It also improves the accuracy of target identification and the continuity of guidance, and has the advantages of saving energy, extending equipment life, and improving system reliability.

Description

Technical Field

[0001] This application relates to the field of aircraft parking guidance technology, specifically to an aircraft parking guidance method, device, and equipment. Background Technology

[0002] In airport ground operations, aircraft parking guidance systems play a crucial role in ensuring flight safety and improving operational efficiency.

[0003] In related technologies, in complex airport environments such as those with strong light reflection or cluttered backgrounds, monitoring equipment is prone to misidentifying non-target objects as target objects, leading to incorrect guidance commands. Different monitoring devices have different recognition capabilities. Continuously operating a single monitoring device not only results in unnecessary energy consumption but also accelerates the aging of optical components and mechanical wear, shortening the equipment's lifespan and increasing maintenance costs. Summary of the Invention

[0004] This application provides a parking guidance method, apparatus, and equipment for aircraft to solve the problems of target identification accuracy and guidance continuity.

[0005] In a first aspect, this application provides a parking guidance method for an aircraft, the method comprising: after determining a target object through a first sensor, activating a second sensor; identifying the target position of the target object through the second sensor; and guiding the target object to parking based on the target position.

[0006] Based on the above technical means, the problem of insufficient robustness in traditional berth guidance technology is effectively solved, and the continuous operation of high-precision sensors during unnecessary periods is avoided, thereby significantly reducing equipment wear and tear.

[0007] In one optional implementation, the second sensor includes a laser sensor, and the target position includes the nose position. Identifying the target position of the target object through the second sensor includes: acquiring point cloud data of the target object through the laser sensor; and identifying the target position of the target object based on the point cloud data to obtain the nose position.

[0008] Based on the above technical means, the accuracy and stability of target location identification have been improved, providing a reliable and accurate data foundation for subsequent aircraft parking guidance, and effectively solving the problem of insufficient identification accuracy at long distances or when point clouds are sparse.

[0009] In one optional implementation, the target location of the target object is identified based on point cloud data to obtain the nose location, including: extracting a preset number of point clouds from the point cloud data and calculating the geometric center of the extracted point clouds to obtain candidate nose locations; determining the number of point clouds within a preset range of the candidate nose locations, and determining the current candidate nose location as the nose location when the number of point clouds is greater than a preset threshold.

[0010] The aforementioned technical methods improve the accuracy and robustness of nose position recognition, enabling subsequent berth guidance processes to be based on more reliable target position information, thereby enhancing the stability and safety of the entire berth guidance system.

[0011] In one optional implementation, determining the number of point clouds within a preset range of the candidate nose position includes: establishing a radar coordinate system with the location of the laser sensor as the origin, wherein the candidate nose position is located in the positive x-axis direction of the radar coordinate system; starting from the candidate nose position, extending a preset distance along the positive x-axis to determine a first position; and obtaining the number of point clouds within the spatial range of the first position and the candidate nose position on the x-axis vertical plane.

[0012] Based on the above technical means, the reliability of verifying the candidate nose position is improved, which enables more accurate identification of the real nose position when judging whether the number of point clouds is greater than the preset threshold. Especially when the point cloud data may be sparse or occluded, the robustness and accuracy of nose recognition are significantly enhanced.

[0013] In one alternative implementation, the target object includes an aircraft, and the preset threshold is determined based on the aircraft's nose size, the scanning degree of the laser sensor, and the distance between the aircraft and the laser sensor.

[0014] Based on the above technical means, the problem of decreased recognition accuracy when the fixed threshold changes with changes in aircraft size, sensor scanning conditions and distance is effectively solved, thereby ensuring the accuracy and safety of berth guidance in various complex and dynamic airport environments.

[0015] In one optional implementation, berthing guidance for a target object based on its target location includes: predicting the predicted position of the target object based on its motion information; within a preset range of the predicted position, performing a step of identifying the target position of the target object using a second sensor, and updating the target position.

[0016] Based on the above technical means, this application can effectively solve the problem of potential interruption of position tracking when the target object moves or is temporarily obstructed during the process of guiding the target object to a berth based on the target location.

[0017] In an optional implementation, the method further includes: converting the radar coordinate system to a berth coordinate system; determining whether the target object has been successfully berthed based on the updated geometric relationship between the target position and the stop line, and based on the updated geometric relationship between the target position and the guide line, wherein the stop line and the guide line are both marking lines used for aircraft berthing in the berth coordinate system.

[0018] The aforementioned technical methods ensured precise alignment between location data and the actual apron environment, thus solving the problem of difficulty in accurately aligning the radar coordinate system with the airport apron physical coordinate system.

[0019] In one alternative implementation, the first sensor includes a vision sensor, and the method further includes: during the activation of the second sensor, if the vision sensor detects an obstacle at the target berth, then reporting an alarm message.

[0020] The aforementioned technical methods effectively compensate for the shortcomings of relying solely on lidar in identifying small obstacles on the apron, significantly improving the safety of berth guidance.

[0021] Secondly, this application provides an aircraft parking guidance device, the device comprising: an activation module for activating a second sensor after a target object is determined by a first sensor; an identification module for identifying the target position of the target object by the second sensor; and a guidance module for guiding the target object to parking based on the target position.

[0022] Thirdly, this application provides an electronic device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the aircraft berthing guidance method of the first aspect or any corresponding embodiment described above.

[0023] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the aircraft parking guidance method of the first aspect or any corresponding embodiment described above.

[0024] Fifthly, this application provides a computer program product, including computer instructions for causing a computer to execute the aircraft parking guidance method of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0026] Figure 1 This is a schematic flowchart of a first method for guiding an aircraft to its parking position according to an embodiment of this application. Figure 2This is a schematic diagram of a second method for guiding an aircraft to its parking position according to an embodiment of this application. Figure 3 This is a schematic diagram of a third method for guiding an aircraft to its parking position according to an embodiment of this application. Figure 4 This is a schematic diagram of the fourth process of the aircraft parking guidance method according to the embodiments of this application; Figure 5 This is a structural block diagram of an aircraft parking guidance device according to an embodiment of this application; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] It is understood that before using the technical solutions disclosed in the various embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0029] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0030] In related technologies, aircraft parking guidance technology often suffers from insufficient robustness in identifying target objects due to limited data in a single frame or sparse point clouds at long distances. Continuously relying on high-precision sensors during non-guidance periods will accelerate equipment wear and tear.

[0031] In response, this application proposes an aircraft parking guidance method, applied to a workbench, such as... Figure 1 As shown, the method includes: Step S101: After the target object is determined by the first sensor, the second sensor is activated.

[0032] The workbench refers to the integrated hardware platform and software environment used to execute aircraft parking guidance methods. It typically includes a data processing unit, a storage unit, a communication interface, and a human-machine interface, responsible for receiving sensor data, executing algorithms, issuing guidance commands, and displaying relevant information.

[0033] The first sensor refers to a device used for preliminary detection or confirmation of the presence of a target object. Its main function is to provide a trigger signal when the target object enters a preset area to initiate the subsequent precise identification process.

[0034] The second sensor is a high-precision detection device activated after the first sensor confirms the existence of the target object. Its main function is to acquire detailed spatial information about the target object in order to accurately identify its location.

[0035] The target object refers to the entity that needs to be guided to its berth, such as an aircraft.

[0036] Specifically, in one implementation, the first sensor can be a simple infrared beam sensor or an ultrasonic sensor. When a target object enters its detection range, the sensor outputs a high-level signal, indicating that the target object has been identified. Upon receiving this signal, the worktable sends an activation command to the second sensor. Alternatively, the first sensor can be a basic image sensor configured to trigger a signal indicating that a target object has been identified when a moving object of a preset size or shape is detected in the field of view. This activates the second sensor for more precise detection.

[0037] Step S102: Identify the target location of the target object using the second sensor; The target location refers to a key reference point or area on the target object used for berth guidance. Accurate identification of this location is crucial for subsequent guidance operations.

[0038] Specifically, once the second sensor is activated, it is used to identify the target location of the target object. For example, the second sensor could be a general-purpose radar that measures the distance and angle information of the target object by emitting electromagnetic waves and receiving reflected waves. After receiving this raw radar data, the workbench uses signal processing algorithms, such as those based on intensity thresholds or simple geometric matching, to estimate the coordinates of a specific point on the target object, thereby obtaining the target location. As another implementation, the second sensor could be a sonar system that detects the target object through the propagation and reflection of sound waves and calculates the three-dimensional coordinates of a specific point on the target object as the target location.

[0039] Step S103: Guide the target object to berth based on the target location.

[0040] Among them, berth guidance refers to the process of providing direction, distance and other guidance based on the real-time location information of the target object to help the target object safely and accurately park in the preset berth area.

[0041] Specifically, after identifying the target location of the object, the workstation guides the object to its berth based on this location information. Specifically, the workstation can generate simple guidance instructions based on the distance and directional deviation between the currently identified target location and the preset berth location. For example, these instructions could be displayed on a screen instructing the target object to move left, right, forward, or stop, or voice prompts to the operator for adjustments. As one implementation, the workstation can calculate the geometric relationship between the target location and the berth line and generate a simple error signal. This error signal is used to drive the berth guidance lighting system to indicate how the target object should adjust its movement trajectory.

[0042] It is understood that the embodiments of this application effectively solve the problem of insufficient robustness in traditional berth guidance technology by activating sensors in stages, avoiding the continuous operation of high-precision sensors during unnecessary periods, thereby significantly reducing equipment wear and tear. Preliminary detection by the first sensor followed by precise identification by the second sensor ensures that the target object can be accurately and reliably located during aircraft berth guidance, improving guidance efficiency and safety.

[0043] In some of the embodiments described above in this application, a second sensor is used to identify the target position of the target object for berth guidance. However, in its implementation, due to the limitations of the sensor type or the point cloud data processing method, the recognition robustness is poor. Especially at long distances or when the point cloud is sparse, the target position recognition accuracy is insufficient and the aircraft nose position cannot be accurately captured.

[0044] In response, this application further proposes a parking guidance method for aircraft, such as... Figure 2 As shown, the method includes: Step S201: After the target object is determined by the first sensor, the second sensor is activated. See details... Figure 1 Step S101 in the embodiment will not be described again here.

[0045] Step S202 involves identifying the target location of the target object using the second sensor. Specifically, this includes: Step S2021: Obtain point cloud data of the target object using a laser sensor.

[0046] Specifically, the laser sensor can be a line-scanning LiDAR, which acquires two-dimensional or quasi-three-dimensional data by scanning lines; it can also be an area-scanning LiDAR, which can acquire three-dimensional point cloud data of the entire scene at once; or it can be a hybrid solid-state LiDAR, which combines the advantages of line scanning and area scanning.

[0047] Step S2022 identifies the target position of the target object based on point cloud data to obtain the nose position.

[0048] The nose position refers to a specific point or area at the very front of the aircraft's nose. In aircraft parking guidance, the nose position is a crucial reference point because it directly affects the aircraft's final parking position and alignment with the stop line. This nose position can be the geometric center of the aircraft's nose; it can be a pre-defined feature point associated with the nose based on the aircraft model; or it can be a representative point within the aircraft's nose area identified using a specific algorithm.

[0049] Specifically, a laser sensor emits a laser beam and receives reflected signals, measuring the distance and angle of each point to generate a series of discrete three-dimensional coordinate points. These points collectively constitute the point cloud data of the target object. The point cloud data comprehensively and accurately reflects the spatial geometric information of the target object. The laser sensor can scan at a fixed frequency, continuously acquiring the point cloud data stream of the target object; it can also perform on-demand scanning at specific times or in specific areas according to system instructions, saving resources and improving efficiency. The acquired point cloud data can include X, Y, and Z coordinate information, as well as additional information such as reflection intensity and color.

[0050] Specifically, this step aims to accurately extract feature points or regions representing the aircraft's nose from complex point cloud data acquired by laser sensors using specific algorithms and processing procedures, thereby determining its precise spatial location. Specifically, point cloud segmentation algorithms can be used to separate the aircraft body from the background, followed by feature extraction from the aircraft point cloud, such as using shape matching, principal component analysis (PCA), or cluster analysis to locate the nose; alternatively, deep learning models can be used to directly identify and regress the nose's coordinates from the raw point cloud data; or geometric feature analysis methods can be employed, such as finding the region with the greatest curvature change or the vertices of a specific geometric shape in the point cloud to determine the nose.

[0051] Step S203: Identify the target location of the target object using the second sensor. (See details...) Figure 1 Step S102 in the embodiment will not be described again here.

[0052] It is understood that the technical solution described in this embodiment, employing a laser sensor as the second sensor, can acquire high-resolution, high-density three-dimensional point cloud data, effectively overcoming the limitations of traditional sensors and providing sufficient information even when the aircraft is at a distance. Simultaneously, clearly defining the target location as the aircraft's nose position makes the identification process more targeted, avoiding misidentification of non-critical parts. Identifying the nose position based on point cloud data allows for precise analysis and feature extraction using the rich geometric information of the point cloud. Even with relatively sparse point cloud data, algorithm optimization can maintain high recognition accuracy and robustness. This improves the accuracy and stability of target position identification, providing a reliable and accurate data foundation for subsequent aircraft parking guidance, and effectively solving the problem of insufficient recognition accuracy at long distances or with sparse point clouds.

[0053] In some of the embodiments described above in this application, the nose position of the aircraft is obtained by identifying the target position based on point cloud data in order to improve the recognition accuracy. However, in the implementation process, the point cloud data may be sparse or contain noise, resulting in inaccurate recognition results.

[0054] In response, this application further proposes a method for identifying the target location of a target object based on point cloud data, and obtaining the nose position, including the following steps: Step a1: Extract a preset number of point clouds from the point cloud data and calculate the geometric center of the extracted point clouds to obtain the candidate nose position.

[0055] Step a2: Determine the number of point clouds within the preset range of the candidate nose position, and when the number of point clouds is greater than the preset threshold, determine the current candidate nose position as the nose position.

[0056] Specifically, after acquiring point cloud data of the target object using a laser sensor, to improve the accuracy and robustness of nose position recognition, a predetermined number of point clouds needs to be extracted from the original point cloud data. This "predetermined number of point clouds" refers to a representative subset of point clouds or those located in key regions, selected from massive point cloud data based on the characteristics of the target object or recognition requirements. For example, spatial clustering algorithms such as DBSCAN and K-means can be used to group the point clouds and select clusters containing the nose features of the target object; alternatively, selection can be based on a predetermined region of interest (ROI) or the geometric features of the target object, such as shape and size, to extract point clouds located in that region or conforming to those features. This approach effectively focuses on the key regions of the target object, reducing interference from irrelevant noise.

[0057] After extracting a predetermined number of point clouds, the geometric center of these extracted point clouds is calculated to obtain a preliminary candidate nose position. This "geometric center" typically refers to the average position of the point cloud set in three-dimensional space. For example, the average of the X, Y, and Z coordinates of all extracted point clouds can be calculated as its geometric center; alternatively, a weighted average method can be used, assigning different weights based on the point cloud density or distance from the sensor to calculate a weighted geometric center, thus obtaining a preliminary estimate of the nose position.

[0058] Subsequently, to verify the reliability of the candidate nose location, it is necessary to determine the number of point clouds within a preset range of the candidate nose location. This "preset range" is a spatial region centered on the candidate nose location, defined based on the target nose size and sensor accuracy. For example, a spherical or cubic region with a preset radius centered on the candidate nose location can be defined, and the number of point clouds within this region can be counted; alternatively, an ellipsoidal or conical region matching the target nose size can be defined, and the number of point clouds within this region can be counted. This step aims to evaluate the local density and integrity of the point cloud around the candidate nose location.

[0059] Finally, the determined number of point clouds is compared with a preset threshold. Only when the number of point clouds exceeds the preset threshold is the current candidate nose position finally determined as the nose position. This "preset threshold" is a reference value used to determine whether the point cloud density is sufficient to support accurate identification. For example, this preset threshold can be set based on empirical values, the typical size of the target object, the performance of the laser sensor, and environmental conditions; or, the threshold can be dynamically adjusted, for example, adaptively adjusted based on the distance between the target object and the laser sensor, with the threshold appropriately lowered as the distance increases. This density verification mechanism effectively avoids misjudgments caused by sparse point cloud data or outliers, ensuring that the final nose position confirmation is only performed when the point cloud density is sufficient.

[0060] In one example, the process of identifying a candidate nose is as follows: Let the point cloud data be P = {p1, p2, ..., p...} n}(pi=(x i y i , z i In a 3D coordinate system, extract the k scattered points at the front to form a subset P. _front ={p f1 p f2 , ..., p fk}, then the geometric center of the candidate nose vertex is obtained by the following expression, where C=(C x C y C z ).

[0061] .

[0062] Let the distance threshold be d and the point cloud quantity threshold be T. Count the number N points in the original point cloud that are located behind candidate point C and whose distance from C is ≤ d. Here, x is greater than Cx (i.e., behind), and the subset of point clouds satisfying this condition is P. _back .

[0063] Screening P _back Points in the set P that are ≤ d distance from C form a subset P. _check Its quantity N=|P _check |

[0064] If N > T, then C is determined to be the nose vertex, where point p belongs to P. _back The formula for the distance from C is: .

[0065] It is understood that, through the technical solution described in this embodiment, by extracting a preset number of point clouds from point cloud data and calculating their geometric centers, the nose position can be initially located, and the influence of irrelevant noise can be reduced. Furthermore, by determining the number of point clouds within a preset range of candidate nose positions and comparing it with a preset threshold, it is ensured that the nose position is only ultimately confirmed when the point cloud density is sufficiently high and the data reliability is strong. This improves the accuracy and robustness of nose position recognition, enabling subsequent berth guidance processes to be based on more reliable target position information, thereby enhancing the stability and safety of the entire berth guidance system.

[0066] In some of the embodiments described above in this application, a method is proposed to determine the number of point clouds within a preset range of the candidate nose position to verify whether the candidate nose position is the nose position. However, in its implementation, due to the unclear definition of the coordinate system or its inconsistency with the actual physical coordinate system, the calculation of the number of point clouds is inaccurate, which affects the reliability of nose position recognition.

[0067] In response, this application further proposes a method for determining the number of point clouds within a preset range of the candidate nose position, the method comprising: Step b1: Establish a radar coordinate system with the location of the laser sensor as the origin, where the candidate nose position is located in the positive x-axis direction of the radar coordinate system.

[0068] Step b2: Starting from the candidate nose position, extend a preset distance along the positive x-axis to determine the first position.

[0069] Step b3: Obtain the number of point clouds within the spatial range of the first position and the candidate nose position on the x-axis vertical plane.

[0070] Specifically, a radar coordinate system is established with the location of the laser sensor as the origin, where the candidate nose position is located on the positive x-axis of the radar coordinate system. This step aims to provide a unified and clear reference framework for subsequent point cloud data processing and spatial position calculations. By setting the laser sensor's own position as the origin, it ensures that all subsequent spatial measurements and calculations are based on a fixed and known reference point, thus avoiding calculation deviations caused by inconsistencies in the coordinate system. For example, precise calibration can be performed during laser sensor installation, using the sensor's optical or geometric center as the origin of the radar coordinate system, and defining its main scanning direction or a preset reference direction as the positive x-axis.

[0071] Starting from the candidate aircraft nose position, a preset distance is extended along the positive x-axis to determine the first position. This step aims to accurately delineate a spatial region in the radar coordinate system for point cloud quantity statistics. The setting of the preset distance is crucial, as it determines the size and shape of the statistical region. For example, this preset distance can be a fixed value, determined empirically or through statistical analysis based on the typical aircraft nose size, the scanning characteristics of the laser sensor, and the accuracy requirements of parking guidance. Alternatively, the preset distance can be dynamically adjusted, for example, adaptively using algorithms based on the real-time distance between the target aircraft and the laser sensor, the sparsity of the point cloud data, or the required recognition robustness.

[0072] This involves acquiring the number of point clouds within the spatial range of the first position and the candidate nose position on the x-axis vertical plane. The aim is to accurately count point cloud data within a specific region to verify the validity of the candidate nose position. Specifically, in the radar coordinate system, firstly, a range defined on the x-axis by the candidate nose position and the first position is determined. Then, within this x-axis range, a specific two-dimensional region is defined on the x-axis vertical plane, i.e., the yz plane. This region can be a rectangle or a circle, and its size can be set according to the aircraft's nose cross-sectional dimensions. Finally, the number of point clouds falling within the intersection of this three-dimensional space, the x-axis range, and the yz plane region is counted. Alternatively, the original point cloud data can be filtered twice: first, point clouds with x-coordinate values ​​between the candidate nose position and the first position are selected; second, point clouds whose y and z coordinate values ​​also fall within a preset range are selected. Finally, the number of point clouds after both filtering processes is counted.

[0073] It is understood that, through the above-described technical solution in this embodiment, this application effectively solves the problem of inaccurate point cloud quantity calculation caused by unclear coordinate system definition or inconsistency with the actual physical coordinate system, thereby improving the reliability of nose position recognition. Specifically, by establishing a radar coordinate system with the laser sensor as the origin and clearly defining the candidate nose position in the positive x-axis direction, a unified and accurate reference benchmark is provided for subsequent spatial calculations, eliminating errors that may be introduced by coordinate system transformation or alignment. Based on this, starting from the candidate nose position, a preset distance is extended along the positive x-axis to determine the first position, and the number of point clouds within the spatial range of the first position and the candidate nose position on the x-axis vertical plane is obtained, which can accurately define the statistical area of ​​the point cloud. This ensures that the statistical point cloud data is highly concentrated on the actual physical structure of the aircraft nose, effectively eliminating interference from background noise or point clouds from other parts of the aircraft. Therefore, the number of point clouds within the preset range of the candidate nose position is more accurate and representative, which improves the reliability of verifying the candidate nose position. This enables the real nose position to be identified more accurately when judging whether the number of point clouds is greater than the preset threshold. Especially when the point cloud data may be sparse or occluded, the robustness and accuracy of nose recognition are significantly enhanced.

[0074] In some of the embodiments described above in this application, a preset threshold is proposed to determine whether the number of point clouds is greater than the threshold to identify the nose position. However, in its implementation, the preset threshold is fixed and cannot be dynamically adjusted according to the size of the aircraft nose, the scanning degree of the laser sensor, and the distance between the aircraft and the laser sensor. This leads to a decrease in recognition accuracy when the aircraft size is different, the distance changes, or the scanning conditions are different, and misjudgment or missed judgment is likely to occur.

[0075] In this regard, this application further proposes that the target object includes an aircraft, and the preset threshold is determined based on the size of the aircraft's nose, the scanning degree of the laser sensor, and the distance between the aircraft and the laser sensor.

[0076] The target object includes aircraft, clearly defining the application of this berth guidance method. This means the method is specifically optimized and designed for aircraft. By limiting the target object to aircraft, it ensures that subsequent identification and guidance algorithms can fully utilize the inherent characteristics of aircraft, such as their unique geometry and size range, thereby improving the accuracy of identification and the reliability of berth guidance.

[0077] The preset threshold is determined based on the aircraft's nose size, the laser sensor's scanning range, and the distance between the aircraft and the laser sensor. This aims to dynamically adjust the preset threshold to adapt to different parking guidance scenarios. Specifically, the preset threshold can be determined as follows: One implementation approach involves the system building a pre-trained model, such as a machine learning-based regression model or lookup table. This model takes the aircraft's nose size, the laser sensor's scanning range, and the distance between the aircraft and the laser sensor as input parameters, and outputs an optimized preset threshold. This model can be trained using a large amount of real-world parking space data or simulation data to cover various aircraft types, sensor configurations, and distance conditions.

[0078] Another approach is for the system to dynamically adjust preset thresholds using a predefined set of rules or calculation formulas. For example, when a large aircraft nose is detected, the preset threshold can be increased accordingly to ensure that only sufficiently dense point cloud clusters are identified as the nose, thus reducing noise interference. When the laser sensor's scanning degree is low, resulting in a sparse point cloud, the preset threshold can be appropriately decreased to avoid missing the nose. When the distance between the aircraft and the laser sensor is large, the point cloud data becomes even sparser, and the preset threshold should be decreased to improve recognition sensitivity. Conversely, when the distance is close and the point cloud is dense, the threshold can be increased to reduce false positives. These rules or formulas can be set based on expert experience or experimental data and can take the form of piecewise functions or nonlinear functions.

[0079] It is understood that, through the above technical solution in this embodiment, this application can dynamically adjust the preset threshold used to identify the nose position, effectively solving the problem of decreased identification accuracy when the fixed threshold changes with changes in aircraft size, sensor scanning conditions and distance, thereby ensuring the accuracy and safety of berth guidance in various complex and dynamic airport environments.

[0080] In some of the embodiments described above in this application, berthing guidance for target objects based on target location is proposed. However, during its implementation, when the target object moves or is briefly obstructed, the position tracking may be interrupted, resulting in inaccurate guidance.

[0081] In response, this application further proposes a parking guidance method for aircraft, such as... Figure 3 As shown, the method includes: Step S301: After the target object is determined by the first sensor, the second sensor is activated. See details... Figure 1 Step S101 in the embodiment will not be described again here.

[0082] Step S302 involves identifying the target location of the target object using the second sensor. Specifically, this includes: Step S3021: Acquire point cloud data of the target object using a laser sensor. See details in [reference needed]. Figure 2 Step S2021 in the embodiment will not be repeated here.

[0083] Step S3022, based on point cloud data, identifies the target location of the target object to obtain the nose position. See details... Figure 2 Step S2022 in the embodiment will not be repeated here.

[0084] Step S303: Identify the target location of the target object using the second sensor. Specifically, this includes: Step S3031: Based on the motion information of the target object, predict the predicted position of the target object.

[0085] Specifically, motion information can include dynamic parameters such as the target object's position, velocity, and acceleration over a past period. This information can be obtained through continuous sensor data acquisition and processing. For example, the instantaneous velocity and direction of the target object can be calculated based on a sequence of historically identified target positions. Predicting the target object's position can be achieved using various methods. For instance, Kalman filtering or extended Kalman filtering algorithms can be used to estimate the target object's future position by fusing historical motion information and sensor measurements. Alternatively, multinomial extrapolation can be employed to fit the motion trajectory based on the target object's position data from the most recent frames and predict its position at the next moment. The predicted position is an estimate made by the system based on the target object's historical motion trends, suggesting its possible location at the next moment or some future moment. Its purpose is to provide a narrowed search area for subsequent sensor identification, thereby improving identification efficiency and robustness.

[0086] Step S3032: Within the preset range of the predicted location, perform the step of identifying the target location of the target object through the second sensor and update the target location.

[0087] Specifically, the preset range refers to a defined search area centered on the predicted position. This range can be a circular area, a rectangular area, or other shaped area determined based on the size and motion uncertainty of the target object. For example, a circular area with radius R centered on the predicted position can be defined; or a rectangular area with side length L centered on the predicted position can be defined. The size of this range should be determined comprehensively based on factors such as the maximum possible moving speed of the target object, the sensor refresh rate, and the accuracy of the prediction algorithm, to ensure that the target object can be effectively covered when it is near the predicted position. Performing recognition within the preset range means that the sensor no longer needs to blindly search the entire scanning area, but instead concentrates the computational resources of the recognition algorithm on a local area near the predicted position, thereby significantly reducing the computational load and improving the recognition speed. Simultaneously, updating the target position refers to using the target position information actually identified by the sensor to correct or replace previous predicted or historical position data. Update methods can include direct replacement, weighted averaging, or fusing the new measurement value with the predicted value through a filtering algorithm to obtain a more accurate current target position. This update mechanism ensures that the system can dynamically respond to the actual movement of the target object, maintaining the real-time performance and accuracy of berth guidance.

[0088] It is understood that, through the above-described technical solution in this embodiment, this application can effectively solve the problem of potential interruption of position tracking when the target object moves or is briefly obstructed during berthing guidance based on the target location. Specifically, by predicting the predicted position of the target object based on its motion information, the system can utilize the dynamic behavioral characteristics of the target for prediction, rather than relying solely on static estimation. This makes the prediction result more closely match the actual movement trajectory, thereby effectively reducing tracking deviations caused by target movement. Based on this, within a preset range of the predicted position, the system performs a step of identifying the target object's position using a second sensor. This limits the identification operation to a local area near the predicted position. When the target object temporarily disappears or is obstructed, the system can quickly recapture the target within a reasonable range, avoiding complete tracking loss. Simultaneously, by updating the target position in real time, the system can dynamically respond to actual changes in the target object, maintaining the timeliness and reliability of the guidance information, thereby significantly improving the continuity, stability, and accuracy of overall berthing guidance.

[0089] In some of the embodiments described above in this application, a target position update based on a radar coordinate system is proposed for berth guidance. However, in its implementation, it is difficult to precisely align the radar coordinate system with the physical coordinate system of the airport apron, resulting in a deviation between the guidance data and the actual position, which affects the accuracy and reliability of berth determination.

[0090] In this regard, this application further proposes that the above-mentioned berth guidance method also includes: Step c1: Convert the radar coordinate system to the berth coordinate system.

[0091] Step c2: Based on the updated geometric relationship between the target position and the stop line, and based on the updated geometric relationship between the target position and the guide line, determine whether the target object has successfully parked. Here, the stop line and the guide line are both marking lines used for aircraft parking in the parking coordinate system.

[0092] Specifically, converting the radar coordinate system to the berth coordinate system aims to resolve the alignment issue between the local coordinate system established by the laser sensor itself (i.e., the radar coordinate system) and the global physical coordinate system used for aircraft berthing on the airport apron (i.e., the berth coordinate system). The radar coordinate system typically uses the laser sensor's installation location as its origin, with its axis related to the sensor's own direction; while the berth coordinate system uses a specific point at the berth center or stop line as its origin, with its axis aligned with the actual direction of the apron. This conversion eliminates data deviations caused by differences in radar installation angles, ensuring precise alignment of position data with the actual apron environment. Methods for achieving this conversion include, but are not limited to: one method involves pre-setting multiple calibration points with known precise coordinates in the berth area, using the laser sensor to acquire the positions of these calibration points in the radar coordinate system, and combining these with their known precise positions in the berth coordinate system. Then, using coordinate transformation algorithms, such as the least squares method, the rotation matrix and translation vector from the radar coordinate system to the berth coordinate system are calculated. Another approach is to integrate an inertial measurement unit (IMU) and a high-precision global positioning system (GPS) module onto the laser sensor. The IMU provides the sensor's attitude information, while the GPS provides the sensor's absolute position information. By combining the pre-calibrated relative relationship between the sensor and the IMU / GPS, the point cloud data in the radar coordinate system is transformed to the global geographic coordinate system, and then further transformed to the berth coordinate system.

[0093] After converting the radar coordinate system to the berth coordinate system, the system determines whether the target object has successfully berthed based on the updated geometric relationship between the target position and the stop line, and also based on the updated geometric relationship between the target position and the guide line. The stop line and guide line are marking lines in the berth coordinate system used for aircraft berthing; they define the aircraft's final stopping position and flight path within the berth area. The updated target position refers to the aircraft's real-time position in the berth coordinate system after coordinate system transformation, such as the aircraft's nose position. This judgment method comprehensively considers the aircraft's position and attitude within the berth area. Specifically, the updated target position, such as the vertical distance from the nose point to the stop line, can be calculated. When this distance is less than a preset threshold, the aircraft is judged to have reached the stopping position. Simultaneously, the updated target position, such as the lateral distance from the nose point or the aircraft's centerline to the guide line, can be calculated. When this distance consistently remains within a preset allowable deviation range, the aircraft is judged to be traveling correctly along the guide line. Only when the aircraft simultaneously meets the dual geometric relationship requirements of the stop line and guide line is berthing considered successful.

[0094] The stop line and guide line are both marking lines in the berth coordinate system used for aircraft parking positions. They are physical markers actually drawn on the airport apron, used to indicate the precise position and movement path of the aircraft at the parking position. In the berth coordinate system, these marking lines are precisely modeled as geometric entities, serving as a unified and clear reference standard for the berth guidance system to determine parking positions. The geometric information of these marking lines can be acquired in advance through high-precision measurements, such as RTK-GPS and total stations, and stored in the database of the berth guidance system as a reference model in the berth coordinate system.

[0095] It is understood that the technical solution described in this embodiment, which converts the radar coordinate system into a berth coordinate system, effectively eliminates data deviations caused by differences in radar installation angles, ensuring precise alignment of position data with the actual apron environment. This solves the problem of difficulty in precisely aligning the radar coordinate system with the airport apron physical coordinate system. Based on this, a judgment is made according to the updated geometric relationship between the target position and the stop line, utilizing the converted precise position information to avoid misjudgments of the stop point due to coordinate system inconsistencies. Simultaneously, supplementary judgments are made based on the updated geometric relationship between the target position and the guide line, combined with the spatial constraints of the guide line, enhancing comprehensive monitoring of the aircraft berth path. Through the comprehensive analysis of the above geometric relationships, highly reliable berth status determination is achieved, ensuring the accuracy and reliability of berth guidance.

[0096] In some of the embodiments described above in this application, berth guidance is proposed using a second sensor. However, in its implementation, relying solely on lidar makes it difficult to reliably identify small obstacles on the apron, posing a safety hazard. Furthermore, continuous use of lidar during unnecessary periods will accelerate equipment wear and tear.

[0097] In response, this application further provides a method for guiding aircraft to parking positions, such as... Figure 4 As shown, the method includes: Step S401: After the target object is determined by the first sensor, the second sensor is activated. See details... Figure 1 Step S101 in the embodiment will not be described again here.

[0098] Step S402: Identify the target location of the target object using the second sensor. Specifically, this includes: Step S4021: Acquire point cloud data of the target object using a laser sensor. See details in [reference needed]. Figure 2 Step S2021 in the embodiment will not be repeated here.

[0099] Step S4022, based on point cloud data, identifies the target location of the target object to obtain the nose position. See details... Figure 2 Step S2022 in the embodiment will not be repeated here.

[0100] Step S403: Identify the target location of the target object using the second sensor. Specifically, this includes: Step S4031: Based on the motion information of the target object, predict the predicted position of the target object. (See details...) Figure 3 Step S3031 in the embodiment will not be repeated here.

[0101] Step S4032: Within a preset range of the predicted location, perform the step of identifying the target location of the target object using the second sensor, and update the target location. See details... Figure 3 Step S3032 in the embodiment will not be described again here.

[0102] In step S404, the first sensor includes a vision sensor. During the activation of the second sensor, if the vision sensor detects an obstacle in the target berth, an alarm message is reported.

[0103] Specifically, the first sensor can be a vision sensor, capable of capturing and processing image information. It typically consists of an optical lens, an image sensor (such as a CCD or CMOS), and an image processing unit. By simulating the function of the human eye, the vision sensor acquires two-dimensional or three-dimensional visual data of the scene. Its role is to identify obstacles, especially small obstacles, within the target berth area, compensating for the limitations of lidar in identifying details and close-range objects. For example, a high-resolution industrial camera can be used, coupled with image processing algorithms such as target detection and image segmentation, to analyze image data of the berth area in real time; alternatively, a stereo vision system can be used, acquiring depth information through two or more cameras to more accurately identify the size and location of obstacles; or, an infrared vision sensor can be used to provide effective obstacle detection capabilities in low-light or nighttime environments.

[0104] The phrase "if the visual sensor detects an obstacle at the target berth" describes the judgment condition when the visual sensor detects an anomaly. The visual sensor uses pre-defined image recognition algorithms, such as deep learning-based object detection models like YOLO and Faster R-CNN, to identify whether there are predefined small obstacles in the image, such as luggage, tools, or debris; alternatively, it can combine background subtraction to detect whether there are newly added objects that do not belong to the background within the berth area; or it can use image segmentation technology to classify different regions in the image, thereby identifying abnormal objects.

[0105] When the visual sensors detect an obstacle at the target berth, the system will "report an alarm message" to ensure that operators or the system are notified promptly upon detection of the obstacle so that appropriate safety measures can be taken. For example, an alarm can be triggered via audible and visual warnings, while simultaneously displaying the obstacle's location and type on the control panel screen; alternatively, the alarm information can be sent via network to a remote monitoring center or the mobile devices of relevant personnel; or, it can trigger an emergency stop or deceleration command from the berth guidance system to avoid a collision.

[0106] Step S405: When the target object is detected to be outside the target berth, the second sensor is turned off.

[0107] Specifically, after real-time determination of the target object's location information, if the target object is identified as being outside the preset target berth, i.e., the aircraft has been pushed out of the berth, the second sensor is immediately shut down to stop the sensor's signal acquisition and data transmission, thereby reducing system power consumption and avoiding invalid data interference.

[0108] It is understandable that by introducing a visual sensor as the first sensor, working in conjunction with a second sensor such as a laser sensor, the aforementioned technical solution effectively compensates for the shortcomings of relying solely on lidar in identifying small obstacles on the apron, significantly improving the safety of berth guidance. Simultaneously, the visual sensor only operates during berth guidance when the second sensor is activated, avoiding continuous operation of the lidar during unnecessary periods, thereby reducing wear and tear on the lidar equipment and extending its lifespan. When the visual sensor detects an obstacle in the target berth, it promptly reports an alarm, quickly alerting operators to take intervention measures, further ensuring the safety and reliability of the aircraft berthing process.

[0109] In one example, the following provides a more detailed explanation of the technical solution through a more specific example: In an airport parking area, precise parking guidance is required for arriving aircraft. This parking guidance method is applied to a workstation, and its workflow is as follows: First, when an aircraft approaches the berth area, a first sensor, such as a vision sensor, continuously monitors the area. When the vision sensor successfully identifies the target object—that is, the aircraft—within a preset range, it triggers and activates a second sensor, which is a laser sensor. This phased sensor activation mechanism avoids continuous operation of the laser sensor during unnecessary periods, effectively reducing equipment wear and extending its lifespan. Simultaneously, while the laser sensor is activated, the vision sensor continuously identifies any obstacles in the target berth. If any obstacle is detected, the system immediately reports an alarm, significantly improving the safety of apron operations.

[0110] Once the laser sensor is activated, it begins to identify the target aircraft's location. Specifically, the laser sensor acquires point cloud data of the target aircraft. To improve the robustness of the identification, the system identifies the target object's location based on this point cloud data, obtaining the aircraft's nose position. This identification process includes: extracting a predetermined number of points from the acquired point cloud data and calculating the geometric center of these extracted points to obtain a candidate nose position. To further verify the accuracy of this candidate position, the system establishes a radar coordinate system with the laser sensor's location as the origin and positions the candidate nose position along the positive x-axis of this radar coordinate system. Then, starting from the candidate nose position, a predetermined distance is extended along the positive x-axis to determine a first position. The system then acquires the number of points within the spatial range of the first position and the candidate nose position on the x-axis vertical plane. If this number of points exceeds a predetermined threshold, which is dynamically determined based on the aircraft's nose size, the laser sensor's scanning degree, and the distance between the aircraft and the laser sensor, then the current candidate nose position is ultimately determined as the aircraft's nose position. This verification method based on point cloud density and geometric features significantly improves the accuracy and robustness of nose position recognition, effectively solving the problem of difficulty in recognition by traditional line-scan or area-scan lidar when point cloud data is sparse.

[0111] After successfully identifying the aircraft's nose position, the system guides the aircraft to its parking spot based on that target location. To ensure continuous guidance, the system predicts the nose position based on the aircraft's motion information. In subsequent identification cycles, the laser sensor performs the target location identification step within a preset range of the predicted position and updates the nose position accordingly. This combined prediction and update mechanism ensures stable and continuous tracking of the aircraft, even during brief obstructions or data fluctuations, thus solving the problem of easy interruption in existing tracking algorithms.

[0112] To ensure the accuracy of berth guidance, the system converts the updated nose position in the radar coordinate system to the berth coordinate system. The berth coordinate system is the physical coordinate system of the airport apron, which includes markers such as stop lines and guide lines for aircraft parking. Through coordinate system transformation, the system can accurately determine whether the aircraft has successfully parked based on the geometric relationship between the updated nose position and the stop line, as well as its geometric relationship with the guide lines. This unified coordinate system approach solves the problem of difficulty in accurately aligning traditional lidar data with the airport's physical coordinate system, ensuring the accuracy of berth guidance.

[0113] This embodiment also provides an aircraft parking guidance device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0114] This embodiment provides an aircraft parking guidance device, such as... Figure 5 As shown, it includes: The activation module 501 is used to activate the second sensor after the target object is determined by the first sensor; The identification module 502 is used to identify the target location of the target object through the second sensor; The guidance module 503 is used to guide the target object to berth based on the target location.

[0115] The alarm module 504 is used to report an alarm message if the visual sensor detects an obstacle in the target berth during the activation of the second sensor.

[0116] The stop module 505 is used to shut down the second sensor when the target object is detected to be outside the target berth.

[0117] In some alternative implementations, the identification module 502 includes: The first unit is used to acquire point cloud data of the target object through a laser sensor.

[0118] The second unit is used to identify the target location of the target object based on point cloud data, and obtain the nose position.

[0119] In some alternative implementations, the boot module 503 includes: The third unit is used to predict the predicted position of the target object based on the motion information of the target object.

[0120] The fourth unit is used to perform the step of identifying the target location of the target object through the second sensor within a preset range of the predicted location, and to update the target location.

[0121] The aircraft parking guidance device provided in this application embodiment can execute the aircraft parking guidance method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0122] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0123] The following is a detailed reference. Figure 6 This diagram illustrates a suitable structural schematic for implementing the electronic device described in the embodiments of this application. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0124] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0125] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the aircraft parking guidance method of embodiments of this application.

[0126] Figure 6 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0127] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the aircraft parking guidance method shown in the above embodiments is implemented.

[0128] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0129] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method of guiding a berth of an aircraft, characterized in that, Applied to a workbench, the method includes: Once the target object is identified by the first sensor, the second sensor is activated. The target location of the target object is identified by the second sensor; Based on the target location, guide the target object to its berth.

2. The method of claim 1, wherein, The second sensor includes a laser sensor, and the target location includes the nose position. The step of identifying the target location of the target object through the second sensor includes: The laser sensor is used to acquire point cloud data of the target object; Based on the point cloud data, the target position of the target object is identified to obtain the nose position.

3. The method of claim 2, wherein, The step of identifying the target position of the target object based on the point cloud data to obtain the nose position includes: A preset number of points are extracted from the point cloud data, and the geometric center of the extracted point clouds is calculated to obtain the candidate nose position. The number of point clouds within a preset range of the candidate nose position is determined, and when the number of point clouds is greater than a preset threshold, the current candidate nose position is determined as the nose position.

4. The method of claim 3, wherein, Determining the number of point clouds within a preset range of the candidate nose position includes: A radar coordinate system is established with the location of the laser sensor as the origin, wherein the candidate nose position is located on the positive x-axis of the radar coordinate system. Starting from the candidate nose position, extend a preset distance along the positive x-axis to determine the first position; Obtain the number of point clouds within the spatial range of the first position and the candidate nose position on the x-axis vertical plane.

5. The method according to any of claims 3-4, characterized by, The target object includes an aircraft, and the preset threshold is determined based on the aircraft's nose size, the scanning degree of the laser sensor, and the distance between the aircraft and the laser sensor.

6. The method of claim 1, wherein, The step of guiding the target object to berth based on the target location includes: Based on the motion information of the target object, predict the predicted position of the target object; Within a preset range of the predicted location, the step of identifying the target location of the target object through the second sensor is performed, and the target location is updated.

7. The method of claim 6, wherein, The method further includes: Convert the radar coordinate system to the berth coordinate system; Based on the updated geometric relationship between the target position and the stop line, and based on the updated geometric relationship between the target position and the guide line, it is determined whether the target object has successfully parked. Here, the stop line and the guide line are both marking lines used for aircraft parking in the parking coordinate system.

8. The method of claim 1, wherein, The first sensor includes a vision sensor, and the method further includes: If the visual sensor detects an obstacle at the target berth during the activation of the second sensor, an alarm message will be reported.

9. A docking guidance apparatus for an aircraft, characterised in that, The device includes: An activation module is used to activate the second sensor after the target object is determined by the first sensor; The identification module is used to identify the target location of the target object through the second sensor; The guidance module is used to guide the target object to a berth based on the target location.

10. An electronic device, comprising: include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the parking guidance method for an aircraft as described in any one of claims 1 to 8.

Images