Aircraft pose detection method, device and equipment

Abstract

The invention provides an aircraft pose detection method, device and equipment. The aircraft pose detection method comprises the following steps: acquiring first pose information of a reference object in a global coordinate system; acquiring a reference point cloud of a reference aircraft, and determining second pose information of the reference aircraft relative to the reference object based on a preset pose relationship between the reference object and the reference aircraft; acquiring a current point cloud of a to-be-detected aircraft, and matching the current point cloud with the reference point cloud to determine third pose information of the to-be-detected aircraft relative to the reference aircraft; and determining fourth pose information of the to-be-detected aircraft in the global coordinate system based on the first pose information, the second pose information and the third pose information.

Description

Technical Field

[0001] This disclosure relates to the field of aviation technology, and more specifically, to an aircraft attitude detection method, apparatus, and equipment. Background Technology

[0002] Airport ground staff can perform ground operations on aircraft located on the tarmac for ground scheduling and management. During these operations, obtaining relevant aircraft information can significantly improve efficiency and completion rates. Therefore, there is a need to acquire relevant aircraft information. Summary of the Invention

[0003] A brief overview of this disclosure is given below to provide a basic understanding of some aspects of it. However, it should be understood that this overview is not an exhaustive summary of this disclosure. It is not intended to identify key or essential parts of this disclosure, nor is it intended to limit the scope of this disclosure. Its purpose is merely to present certain concepts of this disclosure in a simplified form as a prelude to the more detailed description that follows.

[0004] One of the purposes of this disclosure is to provide an aircraft attitude detection method, apparatus, and device.

[0005] According to a first aspect of this disclosure, an aircraft pose detection method is provided, comprising: acquiring first pose information of a reference object in a global coordinate system; acquiring a reference point cloud of a reference aircraft, and determining second pose information of the reference aircraft relative to the reference object based on a preset pose relationship between the reference object and the reference aircraft; acquiring a current point cloud of an aircraft to be detected, and matching the current point cloud with the reference point cloud to determine third pose information of the aircraft to be detected relative to the reference aircraft; and determining fourth pose information of the aircraft to be detected in the global coordinate system based on the first pose information, the second pose information, and the third pose information.

[0006] In some embodiments, the reference object includes a tractor.

[0007] In some embodiments, acquiring a reference point cloud of a reference aircraft includes: acquiring a reference point cloud of the reference aircraft based on sensors on a tractor, wherein the tractor is positioned facing the nose of the reference aircraft.

[0008] In some embodiments, acquiring the current point cloud of the aircraft to be tested includes: in response to the aircraft to be tested being towed by a towing vehicle, acquiring the current point cloud of the aircraft to be tested based on sensors on the towing vehicle.

[0009] In some embodiments, the reference aircraft is the same type as the aircraft to be tested.

[0010] In some embodiments, the preset pose relationship includes: a preset pose of one of the reference object and the reference aircraft relative to the other; and a preset distance between the reference object and the reference aircraft.

[0011] In some embodiments, determining the fourth pose information of the aircraft to be detected in the global coordinate system based on the first pose information, the second pose information, and the third pose information includes: according to Sure The first pose matrix This represents the first pose information and the second pose matrix. This represents the second pose information and the third pose matrix. The third pose information and the fourth pose matrix represent the third pose information and the fourth pose matrix. This represents the fourth pose information.

[0012] In some embodiments, matching the current point cloud with the reference point cloud to determine the third pose information of the aircraft to be detected relative to the reference aircraft includes: determining a target transformation matrix for transforming points in the current point cloud to the reference point cloud with the objective of minimizing the value of a loss function, and determining the third pose information based on the target transformation matrix, wherein the value of the loss function is negatively correlated with the probability density value of the points in the current point cloud under the probability density distribution of the reference point cloud after transformation based on the given transformation matrix.

[0013] In some embodiments, the aircraft pose detection method further includes: using Kalman filtering to predict the fifth pose information of the aircraft in the current frame based on the target pose information of the previous frame of the aircraft to be detected; and determining the target pose information of the aircraft in the current frame based on the fourth pose information and the fifth pose information.

[0014] In some embodiments, determining the target pose information of the current frame of the aircraft to be detected based on the fourth pose information and the fifth pose information includes: determining the target pose information as the fourth pose information in response to the current frame being before a preset frame; determining the target pose information as the fifth pose information in response to the current frame being the preset frame or the current frame being after the preset frame, or determining the target pose information as pose information obtained by performing a preset operation on the fourth pose information and the fifth pose information.

[0015] In some embodiments, obtaining a reference point cloud of a reference aircraft includes: obtaining a candidate reference point cloud for each of one or more candidate aircraft types; determining the aircraft type of the aircraft to be detected based on the current point cloud and the candidate reference point cloud of each candidate aircraft type; and determining the reference point cloud of the corresponding candidate aircraft type among the one or more candidate aircraft types as the reference point cloud of the reference aircraft based on the aircraft type of the aircraft to be detected.

[0016] According to a second aspect of this disclosure, an aircraft pose detection device is provided, comprising: an acquisition module configured to acquire first pose information of a reference object in a global coordinate system, acquire a reference point cloud of a reference aircraft, and acquire a current point cloud of an aircraft to be detected; a first determination module configured to determine second pose information of the reference aircraft relative to the reference object based on a preset pose relationship between the reference object and the reference aircraft; a second determination module configured to match the current point cloud with the reference point cloud to determine third pose information of the aircraft to be detected relative to the reference aircraft; and a third determination module configured to determine fourth pose information of the aircraft to be detected in the global coordinate system based on the first pose information, the second pose information, and the third pose information.

[0017] According to a third aspect of this disclosure, an aircraft pose detection device is provided, including a memory and a processor, wherein the memory stores instructions that, when executed by the processor, implement the operation of the aircraft pose detection method as described above.

[0018] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided, wherein instructions are stored on the non-transitory computer-readable storage medium, and when the instructions are executed by a processor, the operation of the aircraft pose detection method as described above is implemented.

[0019] According to a fifth aspect of this disclosure, a computer program product is provided, the computer program product including instructions that, when executed by a processor, implement the operation of the aircraft pose detection method as described above.

[0020] Other features and advantages of this disclosure will become clearer from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0021] The accompanying drawings, which form part of this specification, illustrate embodiments of this disclosure and, together with the specification, serve to explain the principles of this disclosure.

[0022] This disclosure will become clearer with reference to the accompanying drawings and the following detailed description, wherein:

[0023] Figure 1 A flowchart illustrating an aircraft pose detection method according to some embodiments of the present disclosure is shown.

[0024] Figure 2 A schematic flowchart illustrating the process of obtaining a reference point cloud of a reference aircraft according to some embodiments of the present disclosure is shown.

[0025] Figure 3 A schematic diagram of an aircraft attitude detection apparatus according to some embodiments of the present disclosure is shown;

[0026] Figure 4 A schematic diagram of an aircraft pose detection device according to some embodiments of the present disclosure is shown;

[0027] Figure 5 A schematic block diagram of a computer system on which embodiments of the present disclosure may be implemented is shown.

[0028] Note that in the embodiments described below, the same reference numerals are sometimes used across different figures to denote the same parts or parts having the same function, and repeated descriptions are omitted. In this specification, similar reference numerals and letters are used to denote similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0029] For ease of understanding, the positions, dimensions, and extents of the structures shown in the accompanying drawings and other materials may not represent actual positions, dimensions, and extents. Therefore, the disclosed invention is not limited to the positions, dimensions, and extents disclosed in the accompanying drawings and other materials. Furthermore, the drawings are not necessarily drawn to scale, and some features may be enlarged to show details of specific components. Detailed Implementation

[0030] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0031] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the scope of this disclosure or its application or use. That is, the structures and methods herein are shown in an exemplary manner to illustrate different embodiments of the structures and methods in this disclosure. However, those skilled in the art will understand that they merely illustrate exemplary ways that can be used to implement this disclosure, and not exhaustive ways. Furthermore, the drawings are not necessarily drawn to scale, and some features may be enlarged to show details of specific components.

[0032] 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.

[0033] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0034] During ground operations involving aircraft, airport ground staff can effectively improve the efficiency and completion rate of ground operations by obtaining relevant aircraft information.

[0035] For example, airport ground staff can use tow trucks to tow aircraft located on the tarmac to designated locations, such as boarding gates or hangars. Obtaining relevant information about the aircraft to be towed can improve the towing operation. Currently, towing operations primarily rely on manual visual guidance of the tow truck's movement or on ground markings for direction.

[0036] Typically, the large size of aircraft and the flexible connection between the towing vehicle's tow bar and the aircraft make it difficult to precisely control the towing angle and position. This can easily lead to problems such as aircraft deviation, overshooting, or azimuth errors, posing safety risks. Therefore, it is usually necessary to accurately obtain the aircraft's attitude information to better complete the corresponding ground operations.

[0037] However, considering the airworthiness and safety management requirements of aircraft, it is usually not allowed to install additional sensors on the aircraft body, so it is usually not possible to directly obtain the real-time attitude information of the aircraft.

[0038] In some examples, the position of the towed aircraft can be estimated using the positioning data of the towing vehicle, such as its Global Navigation Satellite System (GNSS) data. However, due to factors such as tow bar angle deviation and wheel slippage, the estimation using the towing vehicle's positioning data has a large error. Alternatively, in some examples, feature points of the aircraft can be identified using a camera, and the attitude can be calculated based on these feature points. However, cameras are greatly affected by lighting and reflection conditions, and the reliability of feature point identification is insufficient, potentially resulting in a large error in the obtained aircraft attitude. Or, in some examples, radar can be used for ranging to determine the aircraft's position, but complete attitude information cannot be obtained.

[0039] To address at least one of the aforementioned problems, this disclosure proposes an aircraft pose detection method, apparatus, and device. By using the global pose of a reference object, the preset pose relationship between the reference object and the reference aircraft, the static reference point cloud of the reference aircraft, and the current point cloud of the aircraft under test, relatively accurate pose information of the aircraft under test in the global coordinate system can be obtained, which helps to better complete the operation for the aircraft under test.

[0040] In some embodiments of this disclosure, such as Figure 1 As shown, aircraft pose detection methods may include:

[0041] Step S110: Obtain the first pose information of the reference object in the global coordinate system.

[0042] The reference object can be equipped with corresponding sensors to acquire its pose information in a global coordinate system. The reference object can correspond to the ground operation to be performed. In some embodiments, the reference object can be a special-purpose vehicle used for airport ground operations. For example, in a traction operation scenario, the reference object can include a tractor unit. By using a Global Navigation Satellite System (GNSS) and Inertial Measurement Unit (IMU) module equipped on the tractor unit, the position and attitude of the tractor unit in the global coordinate system can be acquired in real time, thereby obtaining the tractor unit's real-time pose information.

[0043] In some embodiments, a first coordinate system based on a reference object can be obtained using the first pose information and the global coordinate system, so that the relative pose information of other objects relative to the reference object can be subsequently obtained. In a specific example, the first pose matrix... It can represent the first pose information of the reference object in the global coordinate system. Furthermore, the first pose matrix... It can also indicate the transformation relationship between the global coordinate system and the first coordinate system, which can be achieved through the first pose matrix. Transform the global coordinate system to obtain a first coordinate system based on the reference object.

[0044] like Figure 1 As shown, in some embodiments of this disclosure, the aircraft pose detection method may further include:

[0045] Step S120: Obtain the reference point cloud of the reference aircraft, and determine the second pose information of the reference aircraft relative to the reference object based on the preset pose relationship between the reference object and the reference aircraft.

[0046] The second pose information can be the pose information of the reference aircraft in the first coordinate system based on the reference object, to represent the relative pose information of the reference aircraft relative to the reference object.

[0047] In this disclosure, the reference point cloud of the reference aircraft is a pre-collected static point cloud. Subsequently, the relative pose information of the aircraft under test relative to the reference aircraft can be obtained by matching the current point cloud of the aircraft under test with the pre-collected static point cloud of the reference aircraft, as will be described later.

[0048] Considering that the reference aircraft itself is not suitable for modification, point clouds of the reference aircraft can be acquired using sensors on the reference object. In some embodiments, acquiring the reference point cloud of the reference aircraft may include acquiring the reference point cloud based on sensors on a tractor unit, wherein the tractor unit may be positioned facing the nose of the reference aircraft. In a specific example, corresponding sensors may be installed on the nose of the tractor unit, such as on the top or front of the tractor unit, to acquire the point cloud of the reference aircraft.

[0049] Considering the differences between different aircraft models, in order to make the relative pose information of the aircraft to be detected relative to the reference aircraft obtained by point cloud matching more accurate, in some embodiments, the model of the reference aircraft can be the same as that of the aircraft to be detected.

[0050] In some embodiments, a candidate reference point cloud of a candidate aircraft model that matches the aircraft model to be detected can be selected from the candidate reference point clouds of one or more candidate aircraft models as the reference point cloud of the reference aircraft.

[0051] Specifically, in some embodiments, such as Figure 2 As shown, obtaining the reference point cloud of a reference aircraft can include:

[0052] Step S121: Obtain the candidate reference point cloud for each of the one or more candidate models;

[0053] Step S122: Determine the aircraft type to be detected based on the current point cloud and the candidate reference point cloud for each candidate aircraft type;

[0054] Step S123: Based on the aircraft type to be detected, determine the candidate reference point cloud of the corresponding candidate aircraft type from one or more candidate aircraft types as the reference point cloud of the reference aircraft.

[0055] In this way, the current point cloud of the aircraft to be detected can be matched with the candidate reference point cloud of each candidate aircraft type, thereby identifying the aircraft type to be detected and obtaining the corresponding reference point cloud.

[0056] In some embodiments, obtaining a candidate reference point cloud for each of one or more candidate aircraft types may include: acquiring the candidate reference point cloud for each candidate aircraft type based on sensors on a towing vehicle, wherein the towing vehicle may be positioned facing the nose of the candidate aircraft type. Specifically, for each candidate aircraft type, the towing vehicle can be driven in front of the aircraft of the candidate aircraft type, and the corresponding point cloud can be acquired by sensors mounted on the towing vehicle. This point cloud can then be processed through denoising, downsampling, stitching, coordinate unification, and other processing operations to form a candidate reference point cloud for that candidate aircraft type, which can then be used as a template for subsequent matching.

[0057] In this disclosure, candidate aircraft types can be various known aircraft types, and there is no limitation thereof. In some embodiments, candidate aircraft types can be selected from an aircraft type library that covers all aircraft types, wherein the aircraft type library is updatable. In a specific example, one or more candidate aircraft types can be selected from the aircraft type library as objects for subsequent matching with the aircraft to be detected, based on the operational status of the local airport, such as the aircraft type to be performed on the flight mission and the aircraft type currently performing the flight mission.

[0058] In some embodiments, the preset pose relationship may include: a preset pose of one of the reference object and the reference aircraft relative to the other; and a preset distance between the reference object and the reference aircraft. Thus, one of the reference object and the reference aircraft can be pre-positioned at a preset distance from the other in a preset pose relative to the other to obtain the preset pose relationship between them. For example, the reference aircraft can be positioned at the front of the tractor in a preset pose relative to the tractor to obtain the preset pose relationship between them, and then the relative pose information of the reference aircraft relative to the tractor can be obtained based on the preset pose relationship.

[0059] In some embodiments, a second coordinate system based on a reference aircraft can be obtained using the second pose information and the first coordinate system, so that the relative pose information of other objects relative to the reference aircraft can be subsequently obtained. In a specific example, the second pose matrix... This can represent the second pose information of the reference aircraft in the first coordinate system. Furthermore, the second pose matrix... It can also indicate the transformation relationship between the first coordinate system and the second coordinate system, which can be achieved through the second pose matrix. The first coordinate system is transformed to obtain the second coordinate system based on the reference aircraft.

[0060] like Figure 1 As shown, in some embodiments of this disclosure, the aircraft pose detection method may further include:

[0061] Step S130: Obtain the current point cloud of the aircraft to be detected, and match the current point cloud with the reference point cloud to determine the third pose information of the aircraft to be detected relative to the reference aircraft.

[0062] The third pose information can be the pose information of the aircraft to be detected in the second coordinate system based on the reference aircraft, so as to represent the relative pose information of the aircraft to be detected relative to the reference aircraft.

[0063] The reference point cloud of the reference aircraft can be pre-acquired. By matching the current point cloud of the aircraft to be detected acquired in the current frame with the pre-acquired reference point cloud, the third pose information of the aircraft to be detected relative to the reference aircraft in the current frame can be determined in real time.

[0064] Considering that the aircraft itself is not suitable for modification, point clouds of the aircraft under test can be acquired using sensors on a reference object. In a specific example, both the point clouds of the reference aircraft and the point clouds of the aircraft under test can be obtained using sensors on the reference object.

[0065] In towing operation scenarios, the front of the towing vehicle can face the aircraft to be inspected, allowing for continuous acquisition of the aircraft's point cloud data based on sensors mounted on the towing vehicle's front. In some embodiments, acquiring the current point cloud of the aircraft to be inspected can include: acquiring the current point cloud of the aircraft to be inspected based on sensors on the towing vehicle in response to the aircraft being towed by the towing vehicle. In a specific example, the aircraft being towed by the towing vehicle may include the aircraft being held in place by the towing vehicle or being towed by the towing vehicle. When the aircraft is towed by the towing vehicle, the current point cloud of the aircraft can be acquired at preset time intervals using sensors on the towing vehicle. The current point cloud can be the point cloud acquired in the current frame.

[0066] In some embodiments, matching the current point cloud with the reference point cloud may include: matching the point cloud of each feature region in the current point cloud corresponding to a plurality of feature regions of the aircraft to be detected with the point cloud of the corresponding feature region of the reference point cloud corresponding to the reference aircraft. In this way, the sensor can acquire only the point clouds of the corresponding feature regions of the aircraft to be detected and the reference aircraft, without needing to acquire the point clouds of all regions of either aircraft, improving the efficiency of subsequent point cloud matching and thus contributing to improved aircraft pose detection efficiency.

[0067] In some embodiments, a preset point cloud matching algorithm can be used to match the current point cloud with a reference point cloud. For example, the Normal Distributions Transform (NDT) algorithm or the Iterative Closest Point (ICP) algorithm can be used.

[0068] In some embodiments, matching the current point cloud with a reference point cloud to determine the third pose information of the aircraft to be detected relative to the reference aircraft may include: determining a target transformation matrix for transforming points in the current point cloud to the reference point cloud with the goal of minimizing the value of the loss function, and determining the third pose information based on the target transformation matrix.

[0069] The value of the loss function can be negatively correlated with the probability density value of the points in the current point cloud after transformation based on a given transformation matrix, under the probability density distribution of the reference point cloud. For example, with other parameters remaining constant, the larger the probability density value, the smaller the value of the loss function; the smaller the probability density value, the larger the value of the loss function.

[0070] In some embodiments, given the value of the corresponding transformation matrix (e.g., the value of the transformation matrix in an iterative step during the optimization of the corresponding transformation matrix using a loss function), the probability density value of each point in the current point cloud of the aircraft to be detected, after transformation based on the given transformation matrix, is given under the probability density distribution of the reference point cloud. It can be obtained based on the following formula:

[0071] .

[0072] in, The mean of points in the reference point cloud (in this article, calculations based on points in the point cloud are based on the coordinates of the points; for example, the mean of a point refers to the average of the coordinates of the points); For reference, the covariance matrix of points in the point cloud, This is the inverse of the covariance matrix; express The transpose of T(x); T(x) is the given transformation matrix, and T(x) is the transformed point obtained after transforming the current point cloud point x (i.e. the point with coordinates x) based on the transformation matrix T.

[0073] Considering that the probability density values ​​of points in the current point cloud after transformation based on a given transformation matrix are usually relatively small under the probability density distribution of the reference point cloud, in some embodiments, the loss function can be set based on the negative log-likelihood of the probability density values ​​in order to better optimize the transformation matrix.

[0074] In a specific example, the loss function F can be set as:

[0075] F= .

[0076] By minimizing the value of the loss function F, the corresponding target transformation matrix can be obtained. In a specific example, the goal can be to minimize the value of the loss function F by changing the value of the transformation matrix to find the target transformation matrix that makes the value of the loss function F less than a preset loss threshold. In another specific example, the value of the transformation matrix T can be iteratively updated using gradient descent or Newton's method based on the gradient of the loss function F with respect to the transformation matrix T, thereby determining the corresponding target transformation matrix.

[0077] In this way, the transformation relationship between points in the current point cloud and the reference point cloud can be obtained from the target transformation matrix, thereby obtaining the third pose information of the aircraft to be detected relative to the reference aircraft.

[0078] In some embodiments, the third pose matrix This can represent the third pose information of the aircraft to be detected in a second coordinate system based on a reference aircraft. In a specific example, the third pose matrix... It can be obtained based on the target transformation matrix obtained by minimizing the value of the loss function as described above.

[0079] like Figure 1 As shown, in some embodiments of this disclosure, the aircraft pose detection method may further include:

[0080] Step S140: Determine the fourth pose information of the aircraft to be detected in the global coordinate system based on the first pose information, the second pose information and the third pose information.

[0081] In some embodiments, determining the fourth pose information of the aircraft to be detected in the global coordinate system based on the first pose information, the second pose information, and the third pose information may include: obtaining the pose information of the aircraft to be detected relative to the reference object based on the third pose information of the aircraft to be detected relative to the reference aircraft and the second pose information of the reference aircraft relative to the reference object; and then obtaining the fourth pose information of the aircraft to be detected in the global coordinate system based on the pose information of the aircraft to be detected relative to the reference object and the first pose information of the reference object in the global coordinate system.

[0082] Alternatively, in some embodiments, determining the fourth pose information of the aircraft to be detected in the global coordinate system based on the first pose information, the second pose information, and the third pose information may include: according to Sure The first pose matrix This represents the first pose information and the second pose matrix. This represents the second pose information and the third pose matrix. This represents the third pose information and the fourth pose matrix. This indicates the fourth pose information.

[0083] Here, the third pose matrix It can be a pre-obtained third pose matrix for the same reference object and the same reference aircraft in different frames. It can be unchanged, so it can be based on the first pose matrix obtained in the current frame. and the second pose matrix Obtain the fourth pose matrix Thus, by obtaining the global pose of the reference object in the current frame and the current point cloud of the aircraft to be detected, the global pose of the aircraft to be detected can be obtained accurately and in real time, so as to better carry out related operations on the aircraft to be detected.

[0084] For example, by acquiring the global pose of the towing vehicle and the point cloud of the aircraft under test in real time while the aircraft under test is being towed, the global pose of the aircraft under test can be obtained. This helps the towing vehicle to better complete the towing operation of the aircraft under test. For example, the global pose of the aircraft under test can be used to determine whether the towing vehicle has successfully reported clamping, whether the aircraft under test has deviated from the towing route, and whether the aircraft under test has experienced any unexpected attitude changes.

[0085] To further accurately obtain the pose information of the aircraft under test in the global coordinate system, in some embodiments of this disclosure, the aircraft pose detection method may further include: employing a Kalman filter to predict the fifth pose information of the aircraft under test in the current frame based on the target pose information of the aircraft under test in the previous frame, and determining the target pose information of the aircraft under test in the current frame based on the fourth pose information and the fifth pose information. The Kalman filter may be, for example, an Extended Kalman Filter (EKF).

[0086] The following describes some embodiments of obtaining target pose information of the current frame using Kalman filtering.

[0087] The pose information of the aircraft to be detected in the current frame (the (k+1)th frame) can be used It indicates. Among them, It can represent the position of the aircraft to be detected in the current frame (the (k+1)th frame) in the global coordinate system; It can represent the attitude of the aircraft to be detected in the current frame (the (k+1)th frame), such as roll angle, pitch angle, and yaw angle. The state vector of the Kalman filter can be used... express.

[0088] Next, the state equation for the Kalman filter can be established based on the following formula:

[0089] ;

[0090] .

[0091] in, , The position and attitude of the aircraft to be detected in the previous frame (the k-th frame) can be obtained based on the target pose information of the aircraft to be detected in the previous frame (the k-th frame). For time step; , It is process noise and can satisfy a Gaussian distribution; For the rate of change of position, Let be the rate of change of attitude. In a specific example, , It can be approximated based on the rate of change of position and attitude of the reference object. For example, the corresponding rate of change within the time step can be obtained by solving the GNSS and IMU installed on the tractor.

[0092] In this way, the fifth pose information of the aircraft in the current frame can be predicted based on the target pose information of the previous frame of the aircraft to be detected.

[0093] In some embodiments, the observation vector of the Kalman filter can be obtained based on the fourth pose information of the current frame of the aircraft to be detected. For example, the observation vector of the current frame. It can be represented as: ,in, , It can be based on the fourth pose matrix get.

[0094] In this way, more accurate target pose information of the aircraft to be detected can be obtained based on the observation vector and state vector of the current frame, and the target pose information of the next frame can be obtained based on the target pose information of the current frame.

[0095] Considering that the fifth pose information obtained by Kalman filtering depends on the pose information of the previous frame, in order to reduce the error in the target pose information caused by the low accuracy of the fifth pose information in the previous few frames, in some embodiments, determining the target pose information of the aircraft to be detected in the current frame based on the fourth pose information and the fifth pose information may include: determining the target pose information as the fourth pose information in response to the current frame being before a preset frame; determining the target pose information as the fifth pose information or determining the target pose information as the pose information obtained by performing a preset operation on the fourth pose information and the fifth pose information in response to the current frame being a preset frame or the current frame being after a preset frame.

[0096] For example, if the current frame is before the 10th frame (excluding the 10th frame), the fourth pose information obtained through the first pose information, the second pose information, and the third pose information can be used as the target pose information, without considering the fifth pose information predicted by the pose information of the previous frame; if the current frame is the 10th frame or after the 10th frame, the target pose information can be determined as the fifth pose information or the target pose information can be determined as the pose information obtained by performing a preset operation on the fourth pose information and the fifth pose information.

[0097] Here, the preset operation can be, for example, calculating the average value of the fourth pose information and the fifth pose information, or it can be a weighted summation operation of the fourth pose information and the fifth pose information based on different weights, so that the fourth pose information and the fifth pose information can be comprehensively considered to obtain more accurate target pose information.

[0098] In this way, Kalman filtering can be used to fuse multi-source information and calculate the aircraft's pose more accurately, which helps to reduce errors caused by GNSS data drift and point cloud matching algorithms.

[0099] According to the solution disclosed herein, by using the global pose of the reference object, the preset pose relationship between the reference object and the reference aircraft, the static reference point cloud of the reference aircraft, and the current point cloud of the aircraft under test, the pose information of the aircraft under test can be obtained with high precision, continuously and stably without modifying the aircraft, which helps to better complete the operation for the aircraft under test. According to some embodiments of this disclosure, by using a matrix-level coordinate fusion method, based on the global coordinates of the reference object, the relative coordinates of the reference aircraft relative to the reference object, and the relative coordinates of the aircraft under test relative to the reference aircraft, the global attitude of the aircraft can be deduced from the inverse motion solution of the tractor. This can effectively solve the problem of error accumulation in single coordinate calculation (e.g., calculation based only on the coordinates of the tractor), and can output the position and attitude of the aircraft in the global coordinate system in real time, and can continuously update the pose of the aircraft during, for example, traction operations, to form a complete pose trajectory. Furthermore, according to some embodiments of this disclosure, by using extended Kalman filtering to dynamically estimate the aircraft pose, a more accurate aircraft pose can be obtained by combining the aircraft pose predicted from the previous frame with the aircraft pose calculated based on a reference object and a reference aircraft. This achieves multi-source information fusion, effectively eliminating errors from various noise sources and significantly improving the stability of the pose detection results. Moreover, the solution of this disclosure is a non-intrusive design, requiring no modification to the aircraft or the addition of sensors, thus meeting aviation safety regulations. According to some embodiments of this disclosure, reference point clouds for various aircraft models can be pre-acquired, allowing subsequent pose calculations to be performed using reference point clouds consistent with the aircraft model to be detected. This method is simple to operate, highly scalable, and adaptable to pose calculations for different aircraft models.

[0100] According to another aspect of this disclosure, an aircraft pose detection apparatus is also provided, which can be configured to perform the aircraft pose detection method as described above. Figure 3 As shown, in some exemplary embodiments of this disclosure, the aircraft pose detection device 300 may include an acquisition module 310, a first determination module 320, a second determination module 330, and a third determination module 340.

[0101] The acquisition module 310 can be configured to acquire the first pose information of the reference object in the global coordinate system, acquire the reference point cloud of the reference aircraft, and acquire the current point cloud of the aircraft to be detected. The first determination module 320 can be configured to determine the second pose information of the reference aircraft relative to the reference object based on a preset pose relationship between the reference object and the reference aircraft. The second determination module 330 can be configured to match the current point cloud with the reference point cloud to determine the third pose information of the aircraft to be detected relative to the reference aircraft. The third determination module 340 can be configured to determine the fourth pose information of the aircraft to be detected in the global coordinate system based on the first pose information, the second pose information, and the third pose information.

[0102] The specific operation of the various modules in the aircraft attitude detection device 300 can be found in the detailed descriptions of some embodiments of the aircraft attitude detection method above, and will not be repeated here.

[0103] According to another aspect of this disclosure, an aircraft attitude detection device is also provided. For example... Figure 4 As shown, in some exemplary embodiments of this disclosure, the aircraft pose detection device 400 may include a memory 410 and a processor 420. The memory 410 may store instructions, which, when executed by the processor 420, can implement the operation of the aircraft pose detection method as described above.

[0104] Specifically, processor 420 can perform various actions and processes according to instructions stored in memory 410. Processor 420 can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this disclosure. The general-purpose processor can be a microprocessor or any conventional processor, and can be an x86 architecture or an ARM architecture, etc.

[0105] Memory 410 stores executable instructions that, when executed by processor 420, implement the aircraft pose detection method described above. Memory 410 may be volatile memory or non-volatile memory, or may include both. Non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may be random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct memory bus random access memory (DR RAM). It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0106] This disclosure also proposes a non-transitory computer-readable storage medium storing instructions that, when executed by a processor, can implement the aircraft pose detection method described above.

[0107] Similarly, the non-transitory computer-readable storage media in the embodiments of this disclosure are intended to include, but are not limited to, the above and any other suitable types of memory.

[0108] This disclosure also proposes a computer program product that may include instructions that, when executed by a processor, can implement the operation of the aircraft pose detection method as described above.

[0109] Instructions can be any set of instructions that will be executed directly by one or more processors, such as machine code, or any set of instructions that will be executed indirectly, such as scripts. The terms “instruction,” “application,” “procedure,” “step,” and “program” used herein are used interchangeably. Instructions can be stored in object code format for direct processing by one or more processors, or stored in any other computer language, including scripts or sets of independent source code modules that are interpreted on demand or compiled ahead of time. The function, methods, and routines of instructions are explained in more detail in other parts of this document.

[0110] Figure 5A schematic block diagram of a computer system 500 on which embodiments of the present disclosure may be implemented is shown. The computer system 500 includes a bus 510 or other communication mechanism for transmitting information, and a processing means 520 coupled to the bus 510 for processing information. The computer system 500 also includes a memory coupled to the bus 510 for storing instructions to be executed by the processing means 520; the memory may be random access memory (RAM) or other dynamic storage device. The memory (such as RAM 530) may also be used to store temporary variables or other intermediate information during the execution of instructions to be executed by the processing means 520. The computer system 500 may also include a read-only memory (ROM) 540 or other static storage device coupled to the bus 510 for storing static information and instructions for the processing means 520. A storage device 550, such as a magnetic disk or optical disk, is provided and coupled to the bus 510 for storing information and instructions. Computer system 500 may be coupled via bus 510 to output device 560 for providing output to a user, such as, but not limited to, a display (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD)), speakers, etc. Input device 570, such as a keyboard, mouse, microphone, etc., is coupled to bus 510 for transmitting information and command selection to processing device 520. Computer system 500 may perform embodiments of this disclosure. Consistent with certain implementations of this disclosure, computer system 500 provides results by executing one or more sequences of one or more instructions contained in memory (e.g., RAM 530) in response to processing device 520. Such instructions may be read into memory (e.g., RAM 530) from another computer-readable medium, such as storage device 550. Execution of the sequence of instructions contained in memory (e.g., RAM 530) causes processing device 520 to perform the methods described herein. Alternatively, hard-wired circuitry may be used in place of or in combination with software instructions to implement the teachings. Therefore, implementations of this disclosure are not limited to any particular combination of hardware circuitry and software. In various embodiments, computer system 500 can be connected across a network to one or more other computer systems, such as computer system 500, to form a networked system. This network may include a private network or a public network such as the Internet. In a networked system, one or more computer systems can store data and supply data to other computer systems. As used herein, the term "computer-readable medium" refers to any medium that participates in providing instructions to processing device 520 for execution. Such media can take many forms, including but not limited to non-volatile media, volatile media, and transmission media. Non-volatile media include, for example, optical discs or magnetic disks such as storage device 550. Volatile media include dynamic memory such as memory (e.g., RAM 530).Transmission media include coaxial cable, copper wire, and optical fiber, including cabling containing bus 510. Common forms of computer-readable media or computer program products include, for example, floppy disks, flexible disks, hard disks, magnetic tape, or any other magnetic media, CD-ROMs, digital video discs (DVDs), Blu-ray discs, any other optical media, thumb drives, memory cards, RAM, PROMs and EPROMs, fast EPROMs, any other memory chips or cartridges, or any other tangible media from which a computer can read. Various forms of computer-readable media may be involved when carrying one or more sequences of one or more instructions to processing device 520 for execution. For example, instructions may initially be carried on a disk of a remote computer. The remote computer may load the instructions into its dynamic memory and transmit them over a telephone line using a modem. A modem local to computer system 500 may receive data over a telephone line and convert the data into an infrared signal using an infrared transmitter. An infrared detector coupled to bus 510 may receive the data carried in the infrared signal and place the data on bus 510. Bus 510 carries data to memory (such as RAM 530), and processing device 520 retrieves instructions from memory (such as RAM 530) and executes the instructions. Optionally, instructions received from memory (such as RAM 530) may be stored on storage device 550 before or after execution by processing device 520.

[0111] According to various embodiments, instructions configured to be executed by processing device 520 to perform a method are stored on a computer-readable medium. The computer-readable medium may be a device for storing digital information. For example, the computer-readable medium includes a compact disc read-only memory (CD-ROM) as known in the art for storing software. The computer-readable medium is accessed by a processor adapted to execute the instructions configured to be executed.

[0112] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0113] In general, the various exemplary embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. When aspects of embodiments of this disclosure are illustrated or described as block diagrams, flowcharts, or using some other graphical representation, it will be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented as non-limiting examples in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0114] The terms “left,” “right,” “front,” “back,” “top,” “bottom,” “upper,” “lower,” “high,” “lower,” etc., used in the specification and claims, if present, are for descriptive purposes and are not necessarily used to describe unchanging relative positions. It should be understood that such terms are interchangeable where appropriate, so that embodiments of this disclosure described herein can, for example, operate on orientations different from those shown or otherwise described herein.

[0115] As used herein, the term “exemplary” means “serving as an example, instance, or illustration” and not as a “model” to be precisely copied. Any implementation described herein by example is not necessarily to be construed as preferred or advantageous over other implementations. Moreover, this disclosure is not limited to any theory expressed or implied as given in the field of art, background art, summary of invention, or detailed description.

[0116] As used herein, the term "substantially" means any minor variation resulting from design or manufacturing defects, device or component tolerances, environmental influences, and / or other factors. The term "substantially" also allows for differences from the perfect or ideal situation due to parasitic effects, noise, and other practical considerations that may exist in the actual implementation.

[0117] Furthermore, terms such as “first,” “second,” etc., may be used in this document for reference purposes only and are not intended to be limiting. For example, unless the context clearly indicates otherwise, the words “first,” “second,” and other such numerical terms relating to structures or elements do not imply order or sequence.

[0118] It should also be understood that when the term “including / contains” is used herein, it indicates the presence of the indicated feature, whole, step, operation, unit and / or component, but does not preclude the presence or addition of one or more other features, wholes, steps, operations, units and / or components and / or combinations thereof.

[0119] In this disclosure, the term “provide” is used broadly to cover all ways of obtaining an object, and therefore “provide an object” includes, but is not limited to, “purchasing,” “preparing / manufacturing,” “arranging / setting up,” “installing / assembling,” and / or “ordering” an object.

[0120] As used herein, the term “and / or” includes any and all combinations of one or more of the listed items in association. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of this disclosure. As used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise.

[0121] Those skilled in the art will recognize that the boundaries between the above operations are merely illustrative. Multiple operations may be combined into a single operation, a single operation may be distributed among additional operations, and operations may be performed with at least partial overlap in time. Moreover, alternative embodiments may include multiple instances of a particular operation, and the order of operations may be changed in various other embodiments. However, other modifications, variations, and substitutions are equally possible. Aspects and elements of all the embodiments disclosed above may be combined in any way and / or in combination with aspects or elements of other embodiments to provide multiple additional embodiments. Therefore, this specification and the accompanying drawings should be considered illustrative rather than restrictive.

[0122] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. The various embodiments disclosed herein can be combined in any way without departing from the spirit and scope of this disclosure. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. An aircraft pose detection method, characterized in that, The aircraft pose detection method comprises: obtaining first pose information of a reference object in a global coordinate system; obtaining reference point cloud of a reference aircraft, and determining second pose information of the reference aircraft relative to the reference object based on a preset pose relationship between the reference object and the reference aircraft; obtaining current point cloud of a to-be-detected aircraft, and matching the current point cloud with the reference point cloud to determine third pose information of the to-be-detected aircraft relative to the reference aircraft; determining fourth pose information of the to-be-detected aircraft in the global coordinate system based on the first pose information, the second pose information and the third pose information.

2. The aircraft pose detection method according to claim 1, characterized in that, The reference object comprises a tractor.

3. The aircraft pose detection method according to claim 2, characterized in that, The reference point cloud of the reference aircraft comprises: collecting the reference point cloud of the reference aircraft based on a sensor on the tractor, wherein the tractor is arranged towards the nose of the reference aircraft.

4. The aircraft pose detection method according to claim 2, characterized in that, The current point cloud of the to-be-detected aircraft comprises: in response to the to-be-detected aircraft being in a state of being towed by the tractor, collecting the current point cloud of the to-be-detected aircraft based on a sensor on the tractor.

5. The aircraft pose detection method of claim 1, wherein, The reference aircraft and the to-be-detected aircraft are of the same type.

6. The aircraft pose detection method of claim 1, wherein, The preset pose relationship comprises: a preset attitude of one of the reference object and the reference aircraft relative to the other; a preset distance between the reference object and the reference aircraft.

7. The aircraft pose detection method of claim 1, wherein, Determining the fourth pose information of the to-be-detected aircraft in the global coordinate system based on the first pose information, the second pose information and the third pose information comprises: According to determined wherein a first pose matrix represents the first pose information, a second pose matrix represents the second pose information, a third pose matrix represents the third pose information, and a fourth pose matrix represents the fourth pose information.

8. The aircraft pose detection method of claim 1, wherein, matching the current point cloud with the reference point cloud to determine the third pose information of the to-be-detected aircraft relative to the reference aircraft comprises: determining a target transformation matrix for transforming points of the current point cloud into the reference point cloud to minimize the value of a loss function, and determining the third pose information according to the target transformation matrix, wherein the value of the loss function is negatively related to the probability density value of the points of the current point cloud in the probability density distribution of the reference point cloud after being transformed based on a given transformation matrix.

9. The aircraft pose detection method of claim 1, wherein, The aircraft pose detection method further comprises: adopting Kalman filtering to predict fifth pose information of a current frame of the to-be-detected aircraft according to target pose information of a previous frame of the to-be-detected aircraft; determining target pose information of the current frame of the to-be-detected aircraft according to the fourth pose information and the fifth pose information.

10. The aircraft pose detection method of claim 9, wherein, Determining the target pose information of the current frame of the to-be-detected aircraft according to the fourth pose information and the fifth pose information comprises: in response to the current frame being before a preset frame, determining the target pose information as the fourth pose information; in response to the current frame being the preset frame or the current frame being after the preset frame, determining the target pose information as the fifth pose information or determining the target pose information as pose information obtained by performing a preset operation on the fourth pose information and the fifth pose information.

11. The aircraft pose detection method of claim 1, wherein, The reference point cloud of the reference aircraft comprises: obtaining candidate reference point cloud of each candidate type in one or more candidate types; determining the type of the to-be-detected aircraft based on the current point cloud, the candidate reference point cloud of each candidate type; The reference point cloud of a corresponding candidate aircraft model in the one or more candidate aircraft models is determined as the reference point cloud of the reference aircraft based on a model of the aircraft to be detected.

12. An aircraft pose detection apparatus, characterized in that The aircraft pose detection apparatus comprises: an acquisition module configured to acquire first pose information of a reference object in a global coordinate system, to acquire a reference point cloud of a reference aircraft, and to acquire a current point cloud of an aircraft to be detected; a first determination module configured to determine second pose information of the reference aircraft relative to the reference object based on a preset pose relationship between the reference object and the reference aircraft; a second determination module configured to match the current point cloud with the reference point cloud to determine third pose information of the aircraft to be detected relative to the reference aircraft; a third determination module configured to determine fourth pose information of the aircraft to be detected in the global coordinate system based on the first pose information, the second pose information, and the third pose information.

13. An aircraft pose detection apparatus, characterized by The aircraft pose detection apparatus comprises a memory and a processor, and the memory stores instructions thereon, and when the instructions are executed by the processor, the operations of the aircraft pose detection method according to any one of claims 1 to 11 are implemented.

14. A non-transitory computer-readable storage medium, comprising: The non-transitory computer-readable storage medium stores instructions thereon, and when the instructions are executed by the processor, the operations of the aircraft pose detection method according to any one of claims 1 to 11 are implemented.

15. A computer program product, characterised in that, The computer program product comprises instructions, and when the instructions are executed, the operations of the aircraft pose detection method according to any one of claims 1 to 11 are implemented.

Images