Forced landing area assessment method, apparatus, aircraft, and readable storage medium

Abstract

The application discloses a forced landing area evaluation method and device, an aircraft and a readable storage medium. The method comprises the following steps: obtaining a trajectory neighborhood semantic set corresponding to a forced landing area of an aircraft, wherein the trajectory neighborhood semantic set comprises forced landing information and semantic information, and the semantic information comprises various obstacle information of a preset area corresponding to the forced landing area; determining a landable area trajectory concentration, a trajectory margin and an obstacle area distribution index corresponding to the aircraft based on the trajectory neighborhood semantic set; and determining score information of the forced landing area based on the landable area trajectory concentration, the trajectory margin and the obstacle area distribution index. According to the forced landing information and the semantic information, the score of the forced landing area can be accurately obtained, the reasonable degree of the selection of the forced landing area is accurately quantified through the semantic information, and then the rationality of the forced landing area can be accurately evaluated according to the score information, so that the safety and rationality of the forced landing of the aircraft are improved.

Description

Technical Field

[0001] This application relates to the field of aircraft technology, and in particular to a method, apparatus, aircraft, and readable storage medium for assessing forced landing areas. Background Technology

[0002] With technological advancements, aircraft have become a major means of transportation. As their service life increases, aircraft inevitably experience various malfunctions. Severe weather conditions can also cause damage of varying degrees, preventing them from safely reaching their destination. When an aircraft encounters unforeseen circumstances and cannot continue flying, it needs to make an emergency landing on land or water to reduce its descent speed; this process is called a forced landing.

[0003] Currently, when selecting an emergency landing area for an aircraft, the choice is often based on real-time monitoring of the terrain and topography. However, when the emergency landing area is in a complex ground environment, such as an urban area with a large flow of people and vehicles, simply relying on terrain and topography information cannot effectively assess the rationality of the emergency landing area, resulting in an unreasonable selection of the emergency landing area.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, aircraft, and readable storage medium for assessing forced landing areas, aiming to solve the technical problem of the difficulty in assessing the rationality of forced landing areas using existing aircraft.

[0006] To achieve the above objectives, this application provides a method for assessing forced landing areas, comprising:

[0007] Obtain the trajectory neighborhood semantic set corresponding to the forced landing area of ​​the aircraft, wherein the trajectory neighborhood semantic set includes forced landing information and semantic information, and the semantic information includes information on various obstacles in a preset area corresponding to the forced landing area;

[0008] Based on the trajectory neighborhood semantic set, determine the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landing area corresponding to the aircraft.

[0009] The scoring information for the forced landing area is determined based on the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landable area.

[0010] Furthermore, the step of determining the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landing area corresponding to the aircraft based on the trajectory neighborhood semantic set includes:

[0011] Based on each landable candidate region in the forced landing information, the trajectory clustering degree of the landable region is determined;

[0012] Based on the various landable candidate areas and semantic information in the forced landing information, the trajectory redundancy is determined;

[0013] Based on the semantic information, the distribution index of the obstacle region is determined.

[0014] Furthermore, the step of determining the trajectory clustering degree of the landable area based on each landable candidate area in the forced landing information includes:

[0015] Based on the trajectory neighborhood semantic set, the distance between two adjacent landable candidate regions is obtained;

[0016] Obtain the area corresponding to each of the landable candidate regions;

[0017] Based on the distance and the area of ​​the region, the trajectory clustering degree of the degradable region is determined.

[0018] Furthermore, the step of determining the clustering degree of the reducible region trajectory based on the distance and the area of ​​the region further includes:

[0019] Obtain the maximum distance among the distances, and obtain the neighborhood area and trajectory length of the trajectory neighborhood corresponding to the trajectory neighborhood semantic set;

[0020] The trajectory clustering degree of the degradable region is determined based on the maximum distance, the area of ​​the region, the area of ​​the neighborhood, and the trajectory length.

[0021] Furthermore, the step of determining the trajectory redundancy based on each landable candidate region and semantic information in the forced landing information includes:

[0022] Based on each landable candidate region, determine the non-landable regions within the trajectory neighborhood corresponding to the trajectory neighborhood semantic set;

[0023] Obstacle information within the non-landing area is determined based on the semantic information;

[0024] The trajectory redundancy is determined based on obstacle information within the non-landing area.

[0025] Furthermore, the step of basing the information on obstacles within the non-landing area includes:

[0026] Based on obstacle information within non-landing zones, determine the trajectory areas within each non-landing zone where there are no obstacles.

[0027] The minimum width is determined based on the width of each trajectory region, and the trajectory margin is determined based on the minimum width and the preset width.

[0028] Further, the step of determining the obstacle region distribution index based on the semantic information includes:

[0029] Obtain the Euclidean distance between obstacles corresponding to each obstacle information, and the cardinality of the semantic set corresponding to the semantic information;

[0030] Based on the potential and the Euclidean distance, the obstacle region distribution index is determined.

[0031] Further, the step of determining the obstacle region distribution index based on the potential and the Euclidean distance includes:

[0032] Based on the Euclidean distance and the number of obstacle information, determine the average distance corresponding to each obstacle information;

[0033] Based on the potential and the average distance, the obstacle region distribution index is determined.

[0034] Furthermore, the step of determining the scoring information of the forced landing area based on the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the descent area includes:

[0035] Obtain the first weight corresponding to the trajectory clustering degree of the degradable region, the second weight corresponding to the trajectory redundancy, and the third weight corresponding to the obstacle region distribution index;

[0036] The scoring information for the forced landing area is determined based on the trajectory clustering degree, trajectory redundancy, obstacle area distribution index, the first weight, the second weight, and the third weight of the landing area.

[0037] Furthermore, a data acquisition device is installed below the aircraft, and the step of acquiring the trajectory neighborhood semantic set corresponding to the forced landing area of ​​the aircraft includes:

[0038] The forced landing information corresponding to the aircraft is obtained from the cloud server, and the semantic information is obtained based on the data acquisition device;

[0039] Based on the forced landing information and the semantic information, the trajectory neighborhood semantic set is determined.

[0040] Furthermore, the data acquisition device includes a lidar and a camera; the step of acquiring the semantic information based on the data acquisition device includes:

[0041] Based on the current altitude of the aircraft, the target data acquisition device is determined in the lidar and camera;

[0042] The target data acquisition device acquires the collected data, and the semantic information is determined based on the acquired data.

[0043] Furthermore, to achieve the above objectives, this application also provides an aircraft, the aircraft comprising:

[0044] The acquisition module is used to acquire the trajectory neighborhood semantic set corresponding to the forced landing area of ​​the aircraft. The trajectory neighborhood semantic set includes forced landing information and semantic information. The semantic information includes information on various obstacles in a preset area corresponding to the forced landing area.

[0045] The determination module is used to determine the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landing area corresponding to the aircraft based on the trajectory neighborhood semantic set.

[0046] The scoring module is used to determine the scoring information of the forced landing area based on the trajectory clustering degree, trajectory redundancy and obstacle area distribution index of the descent area.

[0047] In addition, to achieve the above objectives, this application also provides a forced landing area assessment device, which includes: a memory, a processor, and a forced landing area assessment program stored in the memory and executable on the processor. When the forced landing area assessment program is executed by the processor, it implements the steps of the forced landing area assessment method as described above.

[0048] In addition, to achieve the above objectives, this application also provides a computer-readable storage medium storing a forced landing area assessment program, which, when executed by a processor, implements the steps of the forced landing area assessment method as described above.

[0049] This application obtains a trajectory neighborhood semantic set corresponding to the emergency landing area of ​​an aircraft. The trajectory neighborhood semantic set includes emergency landing information and semantic information, including obstacle information for each obstacle in a preset area corresponding to the emergency landing area. Then, based on the trajectory neighborhood semantic set, it determines the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landing area corresponding to the aircraft. Subsequently, based on the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landing area, it determines the scoring information of the emergency landing area. This allows for accurate scoring of the emergency landing area based on both the emergency landing information and the semantic information. The semantic information accurately quantifies the rationality of the selected emergency landing area, thereby accurately assessing the rationality of the emergency landing area based on the scoring information, thus improving the safety and rationality of emergency landings. Attached Figure Description

[0050] Figure 1 This is a schematic diagram of the structure of the forced landing area assessment device for the hardware operating environment involved in the embodiments of this application;

[0051] Figure 2 This is a flowchart illustrating the first embodiment of the forced landing area assessment method of this application;

[0052] Figure 3 This is a schematic diagram of a possible scenario for one embodiment of the forced landing area assessment method of this application;

[0053] Figure 4 This is a schematic diagram of a possible scenario for another embodiment of the forced landing area assessment method of this application;

[0054] Figure 5 This is a schematic diagram of a possible scenario for another embodiment of the forced landing area assessment method of this application;

[0055] Figure 6 This is a schematic diagram of the functional modules of an embodiment of the aircraft of this application.

[0056] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0057] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0058] like Figure 1 As shown, Figure 1 This is a schematic diagram of the structure of the forced landing area assessment device for the hardware operating environment involved in the embodiments of this application.

[0059] The forced landing area assessment device in this application embodiment can be an aircraft, such as a drone or a manned aircraft. Figure 1 As shown, the forced landing area assessment device may include: a processor 1001, such as a CPU; a network interface 1004; a user interface 1003; a memory 1005; and a communication bus 1002. The communication bus 1002 is used to establish communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0060] Optionally, the emergency landing area assessment device may also include a camera, RF (Radio Frequency) circuitry, sensors, audio circuitry, a WiFi module, and so on. These sensors may include, for example, light sensors, motion sensors, and other sensors. Of course, the emergency landing area assessment device may also be equipped with other sensors such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, which will not be elaborated upon here.

[0061] Those skilled in the art will understand that Figure 1 The terminal structure shown does not constitute a limitation on the forced landing area assessment device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0062] like Figure 1 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a forced landing area assessment program.

[0063] exist Figure 1 In the forced landing area assessment device shown, the network interface 1004 is mainly used to connect to the backend server and communicate with the backend server; the user interface 1003 is mainly used to connect to the client (user end) and communicate with the client; and the processor 1001 can be used to call the forced landing area assessment program stored in the memory 1005.

[0064] In this embodiment, the forced landing area assessment device includes: a memory 1005, a processor 1001, and a forced landing area assessment program stored in the memory 1005 and executable on the processor 1001. When the processor 1001 calls the forced landing area assessment program stored in the memory 1005, it executes the steps of the forced landing area assessment method in the following embodiments.

[0065] This application also provides a method for assessing forced landing areas, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the forced landing area assessment method of this application.

[0066] The method for assessing the forced landing area includes:

[0067] Step S101: Obtain the trajectory neighborhood semantic set corresponding to the forced landing area of ​​the aircraft, wherein the trajectory neighborhood semantic set includes forced landing information and semantic information, and the semantic information includes information on various obstacles in the preset area corresponding to the forced landing area;

[0068] After the aircraft triggers an emergency landing event and selects an emergency landing area, the trajectory neighborhood semantic set corresponding to the emergency landing area is acquired. This trajectory neighborhood semantic set is a collection of data collected within a preset area (the trajectory neighborhood corresponding to the trajectory neighborhood semantic set) corresponding to the emergency landing area. The preset area is the region between the projection point of the aircraft's current position on the ground and the emergency landing area. The trajectory neighborhood semantic set includes emergency landing information and semantic information. The emergency landing information includes multiple candidate landing areas within the trajectory neighborhood, and may also include terrain and geomorphological information within the trajectory neighborhood, meteorological information corresponding to the trajectory neighborhood, and trajectory information. The system includes 3D model information of buildings within the trajectory neighborhood. This 3D model information can be a 3D model of a tall building. For example, a building with a height greater than a preset height can be set as a tall building. The preset height can be set to a height that affects airflow, such as 20 meters, 30 meters, or 50 meters. The semantic information includes information on various obstacles in the preset area corresponding to the forced landing area. For example, the semantic information includes information on people (human flow), vehicle flow, and buildings within the trajectory neighborhood. The semantic information can also include information on water surfaces (rivers, lakes, etc.), airflow, terrain slope, and landforms within the trajectory neighborhood.

[0069] Specifically, the aircraft can obtain emergency landing information from a cloud-based database (server), while semantic information can be obtained from a data acquisition device installed beneath the aircraft.

[0070] Step S102: Based on the trajectory neighborhood semantic set, determine the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landing area corresponding to the aircraft.

[0071] When the trajectory neighborhood semantic set is obtained, the aircraft calculates the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the corresponding landing area based on the trajectory neighborhood semantic set. Specifically, the aircraft can calculate the trajectory clustering degree of the landing area through the landing candidate areas in the emergency landing information. For example, the trajectory clustering degree of the landing area can be calculated by the area of ​​each landing candidate area and the distance between two adjacent landing candidate areas. The trajectory clustering degree of the landing area is the degree of clustering of landing candidate areas within the trajectory neighborhood. The larger the trajectory clustering degree of the landing area, the lower the degree of clustering of landing candidate areas. The smaller the trajectory clustering degree of the landing area, the higher the degree of clustering of landing candidate areas. For example, if the ground directly below the aircraft is within the entire trajectory neighborhood, the degree of clustering of landing candidate areas is high. Although the landing candidate areas are not the recommended optimal emergency landing areas, a large number of landing candidate areas help prevent the aircraft from making an emergency landing when a secondary accident occurs during the journey to the candidate emergency landing point.

[0072] The aircraft can calculate trajectory redundancy through various landable candidate areas. For example, based on the trajectory neighborhood and various landable candidate areas, the non-landable areas within the trajectory neighborhood are determined. Obstacle information in the non-landable areas is determined based on semantic information. Based on the aircraft's flight trajectory (the estimated flight trajectory between the current position and the forced landing area) and obstacle information, the trajectory areas without obstacles within the non-landable areas are determined. The minimum width of each trajectory area is obtained, and trajectory redundancy is calculated based on each minimum width. The larger the trajectory redundancy, the wider the minimum narrow area within the trajectory neighborhood, which helps the aircraft to cross the non-forced landing area more quickly.

[0073] Meanwhile, the aircraft can calculate the obstacle area distribution index through semantic information. That is, the obstacle area distribution index is calculated through the information of each obstacle in the semantic information. The obstacle area distribution index indicates the degree of disorder of the distribution of obstacles in the trajectory neighborhood. If the obstacle area distribution index is low, it means that the distribution of obstacles in the trajectory neighborhood is relatively orderly, which helps the aircraft to make fine planning during landing.

[0074] Step S103: Based on the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the descent area, determine the scoring information of the forced landing area.

[0075] When the landing area trajectory clustering degree, trajectory redundancy, and obstacle area distribution index are obtained, the aircraft calculates the scoring information of the emergency landing area based on the landing area trajectory clustering degree, trajectory redundancy, and obstacle area distribution index to obtain a score of the reasonableness of the emergency landing area. Specifically, the aircraft first obtains the weights corresponding to the landing area trajectory clustering degree, trajectory redundancy, and obstacle area distribution index, and calculates the scoring information based on the landing area trajectory clustering degree, trajectory redundancy, obstacle area distribution index, and the obtained weights.

[0076] Among them, the smaller the trajectory clustering of the landing area, the more favorable it is for the aircraft to make an emergency landing, and the smaller the score information; the larger the trajectory margin, the more favorable it is for the aircraft to make an emergency landing, and the smaller the score information; the smaller the obstacle area distribution index, the more favorable it is for the aircraft to make an emergency landing, and the smaller the score information; therefore, the smaller the score information, the more reasonable the selection of the emergency landing area.

[0077] It should be noted that the aircraft can also obtain the aircraft's current status information, which includes the aircraft's remaining controlled flight characteristics due to damage. The controlled flight characteristics are used to determine the aircraft's corresponding controlled flight characteristic matching degree. The more remaining controlled flight characteristics, the greater the controlled flight characteristic matching degree, which is more conducive to the aircraft's forced landing. Based on the controlled flight characteristic matching degree, the trajectory clustering degree of the landing area, the trajectory redundancy, and the obstacle area distribution index, the scoring information of the forced landing area is determined.

[0078] Of course, if the score is greater than the preset value, it indicates that the selection of the emergency landing area is unreasonable, and the aircraft can be prompted to replan the emergency landing area.

[0079] By acquiring the trajectory neighborhood semantic set corresponding to the emergency landing area of ​​the aircraft, wherein the trajectory neighborhood semantic set includes emergency landing information and semantic information, the semantic information including obstacle information of each obstacle in the preset area corresponding to the emergency landing area; then, based on the trajectory neighborhood semantic set, the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landing area corresponding to the aircraft are determined; then, based on the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landing area, the scoring information of the emergency landing area is determined. The scoring of the emergency landing area can be accurately obtained according to the emergency landing information and semantic information, and the rationality of the selection of the emergency landing area can be accurately quantified through semantic information. In addition, the rationality of the emergency landing area can be accurately evaluated based on the scoring information, thereby improving the safety and rationality of the emergency landing of the aircraft.

[0080] Based on the first embodiment, a second embodiment of the forced landing area assessment method of this application is proposed, wherein step S102 includes:

[0081] Step S201: Based on each landable candidate area in the forced landing information, determine the trajectory clustering degree of the landable area;

[0082] Step S202: Determine the trajectory redundancy based on each landable candidate region and semantic information in the forced landing information;

[0083] Step S203: Based on the semantic information, determine the obstacle region distribution index.

[0084] After obtaining the trajectory neighborhood semantic set, the aircraft can calculate the trajectory clustering degree of the landable area through the landable candidate areas in the emergency landing information. For example, the trajectory clustering degree of the landable area can be calculated by the area of ​​each landable candidate area and the distance between two adjacent landable candidate areas. The trajectory clustering degree of the landable area is the degree of clustering of landable candidate areas within the trajectory neighborhood. The larger the trajectory clustering degree of the landable area, the lower the degree of clustering of the landable candidate areas. The smaller the trajectory clustering degree of the landable area, the higher the degree of clustering of the landable candidate areas. For example, if the ground directly below the aircraft is within the entire trajectory neighborhood, the degree of clustering of the landable candidate areas is relatively high. Although the landable candidate areas are not the recommended optimal emergency landing areas, a large number of landable candidate areas help prevent the aircraft from making an emergency landing when a secondary accident occurs during the journey to the candidate emergency landing point.

[0085] The aircraft can calculate trajectory redundancy through various landable candidate areas and semantic information. For example, based on the trajectory neighborhood and various landable candidate areas, the non-landable areas within the trajectory neighborhood are determined. The obstacle information of the non-landable areas is determined based on the semantic information. Based on the aircraft's flight trajectory (the estimated flight trajectory between the current position and the forced landing area) and the obstacle information, the trajectory area without obstacles within the non-landable area is determined. The minimum width of each trajectory area is obtained, and the trajectory redundancy is calculated based on each minimum width. The larger the trajectory redundancy, the larger the width of the smallest narrow area within the trajectory neighborhood, which helps the aircraft to cross the non-forced landing area more quickly.

[0086] Meanwhile, the aircraft can calculate the obstacle area distribution index through semantic information. That is, the obstacle area distribution index is calculated through the information of each obstacle in the semantic information. The obstacle area distribution index indicates the degree of disorder of the distribution of obstacles in the trajectory neighborhood. If the obstacle area distribution index is low, it means that the distribution of obstacles in the trajectory neighborhood is relatively orderly, which helps the aircraft to make fine planning during landing.

[0087] By determining the trajectory clustering degree of the landable area based on each landable candidate area in the forced landing information; then, based on each landable candidate area in the forced landing information and semantic information, determining the trajectory redundancy; and then, based on the semantic information, determining the obstacle area distribution index. This allows for the accurate acquisition of the landable area trajectory clustering degree, trajectory redundancy, and obstacle area distribution index based on the forced landing information and semantic information, thereby improving the accuracy of the scoring information. This enables accurate assessment of the rationality of the forced landing area based on the scoring information, further enhancing the safety and rationality of aircraft forced landings.

[0088] Based on the second embodiment, a third embodiment of the forced landing area assessment method of this application is proposed, wherein step S201 includes:

[0089] Step S301: Based on the trajectory neighborhood semantic set, obtain the distance between two adjacent landable candidate regions;

[0090] Step S302: Obtain the area corresponding to each of the landable candidate areas;

[0091] Step S303: Determine the trajectory clustering degree of the reducible region based on the distance and the area of ​​the region.

[0092] After obtaining the trajectory neighborhood semantic set, the distance between two adjacent candidate landing regions is obtained. Specifically, the distance between two adjacent candidate landing regions can be calculated by the coordinate range of each candidate landing region. This distance is the minimum distance between two adjacent candidate landing regions. At the same time, the area of ​​the corresponding region of the candidate landing region is calculated to obtain the area of ​​each candidate landing region.

[0093] Next, the trajectory clustering degree of the descent region is calculated using the area of ​​each descent candidate region and the distance between two adjacent descent candidate regions. This trajectory clustering degree represents the degree of clustering of descent candidate regions within the trajectory's neighborhood. Figure 3 , Figure 3 In the diagram, A, B, and C represent landable candidate areas (landable areas), L1 is the distance between A and B, and L2 is the distance between B and C. The greater the clustering of landable area trajectories, the lower the clustering of landable candidate areas; conversely, the smaller the clustering of landable area trajectories, the higher the clustering of landable candidate areas. For example, if the ground directly below the aircraft is within the entire trajectory neighborhood, the clustering of landable candidate areas is high. Although landable candidate areas are not the recommended optimal emergency landing areas, a large number of landable candidate areas help prevent the aircraft from making an emergency landing if a secondary accident occurs during its journey to a candidate emergency landing point.

[0094] Furthermore, in one possible implementation, step S303 includes:

[0095] Step S3031: Obtain the maximum distance among the distances, and obtain the neighborhood area and trajectory length of the trajectory neighborhood corresponding to the trajectory neighborhood semantic set;

[0096] Step S3032: Determine the reducible region trajectory clustering degree based on the maximum distance, the region area, the neighborhood area, and the trajectory length.

[0097] After obtaining the area of ​​each landable candidate region and the distance between two adjacent landable candidate regions, the distances are compared to obtain the maximum distance among all distances. At the same time, the neighborhood area and trajectory length of the trajectory neighborhood corresponding to the trajectory neighborhood semantic set are obtained. The trajectory neighborhood can be determined based on the projection point of the aircraft's current position on the ground and the forced landing area. That is, the trajectory neighborhood is the area that includes the flight trajectory between the current position and the forced landing area.

[0098] When the neighborhood area and trajectory length are obtained, the reducible region trajectory clustering degree is determined based on the maximum distance, the region area, the neighborhood area, and the trajectory length. Specifically, the formula for the reducible region trajectory clustering degree is:

[0099]

[0100] Where σ is the trajectory clustering degree of the degradable region, S Gi Let ΣS be the area of ​​the i-th landable candidate region. Gi The sum of the areas of all candidate landing zones. For the maximum distance, SG L represents the neighborhood area. G The trajectory length is given by this formula. This formula can then be used to accurately determine the trajectory clustering degree of the landing area, allowing for accurate scoring information. This scoring information can then be used to accurately assess the rationality of the forced landing area, further improving the safety and rationality of the aircraft's forced landing.

[0101] By obtaining the distance between two adjacent candidate landing areas based on the trajectory neighborhood semantic set, the area corresponding to each candidate landing area is then obtained. Based on the distance and the area, the trajectory clustering degree of the landing area is determined. The trajectory clustering degree of the landing area can be accurately obtained based on the distance and the area, thereby improving the accuracy of the scoring information. Based on the scoring information, the rationality of the emergency landing area can be accurately evaluated, further improving the safety and rationality of the aircraft emergency landing.

[0102] Based on the second embodiment, a fourth embodiment of the forced landing area assessment method of this application is proposed. In this embodiment, step S202 includes:

[0103] Step S301: Based on each landable candidate region, determine the non-landable region within the trajectory neighborhood corresponding to the trajectory neighborhood semantic set;

[0104] Step S402: Determine obstacle information within the non-landing area based on the semantic information;

[0105] Step S403: Determine the trajectory redundancy based on the obstacle information in the non-landing area.

[0106] When calculating trajectory redundancy, the aircraft first determines the trajectory neighborhood corresponding to the trajectory neighborhood semantic set. The trajectory neighborhood can be determined based on the projection point of the aircraft's current position on the ground and the emergency landing area. That is, the trajectory neighborhood is the area that includes the flight trajectory between the current position and the emergency landing area. Then, based on each landable candidate area of ​​the emergency landing information, the aircraft determines the non-landable area within the trajectory neighborhood. The non-landable area can be the area within the trajectory neighborhood other than each landable candidate area.

[0107] Next, the aircraft determines the obstacle information in the non-landing area based on the semantic information, that is, the obstacle information of the obstacle in the semantic information falling into the non-landing area.

[0108] Then, based on obstacle information in the non-landing area, trajectory redundancy is determined. Further, in one possible implementation, step S403 includes:

[0109] Step S4031: Based on the obstacle information in the non-landing area, determine the trajectory area where there are no obstacles in each non-landing area;

[0110] Step S4032: Determine the minimum width based on the width of each trajectory region, and determine the trajectory margin based on the minimum width and the preset width.

[0111] After obtaining obstacle information within the no-landing zone, the system determines obstacle-free trajectory areas within each no-landing zone based on this information. Specifically, this is done using the aircraft's flight trajectory (the estimated flight trajectory from the current position to the emergency landing area) and obstacle information. The flight trajectory traverses each trajectory area. The width of each trajectory area is then obtained, with the minimum width being the lowest possible value. The aircraft obtains the minimum width among the widths of each trajectory area. Based on this minimum width and a preset width, the trajectory margin is determined, thus accurately obtaining the trajectory margin and further improving the safety and rationality of the aircraft's emergency landing. (Refer to...) Figure 4 , Figure 4 In the diagram, the area enclosed by the dashed line is the trajectory region, and the triangle represents obstacles within the non-landing zone. A larger trajectory margin indicates a larger width of the smallest narrow area within the trajectory neighborhood, which helps the aircraft traverse the non-landing zone more quickly.

[0112] The preset width can be set reasonably according to the size of the aircraft.

[0113] By determining non-landing areas within the trajectory neighborhood corresponding to the trajectory neighborhood semantic set based on each landable candidate area, obstacle information within the non-landing area is then determined based on the semantic information. Subsequently, the trajectory redundancy is determined based on the obstacle information within the non-landing area. The trajectory redundancy can be accurately obtained based on the non-landing areas within the trajectory neighborhood and the semantic information, thereby improving the accuracy of the scoring information. This allows for accurate assessment of the rationality of the forced landing area based on the scoring information, further enhancing the safety and rationality of the aircraft's forced landing.

[0114] Based on the second embodiment, a fifth embodiment of the forced landing area assessment method of this application is proposed, wherein step S203 includes:

[0115] Step S501: Obtain the Euclidean distance between obstacles corresponding to each obstacle information, and the cardinality of the semantic set corresponding to the semantic information;

[0116] Step S502: Determine the obstacle region distribution index based on the potential and the Euclidean distance.

[0117] The aircraft first acquires the coordinates corresponding to each obstacle, and then calculates the Euclidean distance between each obstacle based on these coordinates. This means calculating the pairwise Euclidean distance between obstacles. Finally, it obtains the cardinality of the semantic set corresponding to the semantic information; the cardinality of the semantic set is the number of elements (obstacles) in the semantic set. The obstacle information includes vehicle flow information, pedestrian flow dynamics information, building information, and terrain information. (Refer to...) Figure 5 , Figure 5 The ellipse, rhombus, and triangle are all obstacles.

[0118] Next, the aircraft determines the obstacle region distribution index based on the potential and the Euclidean distance. Further, in one possible implementation, step S502 includes:

[0119] Step S5021: Based on the Euclidean distance and the number of obstacle information, determine the average distance corresponding to each obstacle information;

[0120] Step S5022: Determine the obstacle area distribution index based on the potential and the average distance.

[0121] After obtaining the Euclidean distance, based on the Euclidean distance and the number of obstacle information, the average distance corresponding to each obstacle information is determined. For each obstacle information corresponding to an obstacle, the sum of the Euclidean distances of that obstacle and the obstacles corresponding to other obstacle information is obtained, and the sum of the Euclidean distances is divided by the number to obtain the average distance corresponding to that obstacle information.

[0122] Next, based on the potential and the average distance, the obstacle area distribution index is calculated. Specifically, the formula for the obstacle area distribution index is:

[0123]

[0124] Where ||γ|| is the potential, and is For distance.

[0125] d is the obstacle area distribution index. ij Let Euclidean distance be the distance between the obstacle corresponding to the i-th obstacle and the obstacle corresponding to the j-th obstacle. Then, the obstacle area distribution index can be accurately obtained through the potential and the average distance, further improving the safety and rationality of aircraft emergency landings.

[0126] By acquiring the Euclidean distance between obstacles corresponding to each obstacle information and the potential of the semantic set corresponding to the semantic information; then, based on the potential and the Euclidean distance, the obstacle area distribution index and the trajectory redundancy are determined. The obstacle area distribution index can be accurately obtained based on the Euclidean distance between obstacles and the potential of the semantic set, thereby improving the accuracy of the scoring information. Based on the scoring information, the rationality of the forced landing area can be accurately assessed, further improving the safety and rationality of the aircraft forced landing.

[0127] Based on the first embodiment, a sixth embodiment of the forced landing area assessment method of this application is proposed, wherein step S103 includes:

[0128] Step S601: Obtain the first weight corresponding to the trajectory clustering degree of the degradable area, the second weight corresponding to the trajectory redundancy, and the third weight corresponding to the obstacle area distribution index.

[0129] Step S602: Based on the trajectory clustering degree of the descent area, trajectory redundancy, obstacle area distribution index, the first weight, the second weight, and the third weight, determine the scoring information of the forced landing area.

[0130] When acquiring the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landable area, the aircraft acquires the first weight corresponding to the trajectory clustering degree of the landable area, the second weight corresponding to the trajectory redundancy, and the third weight corresponding to the obstacle area distribution index. The first weight, the second weight, and the third weight can all be reasonably set in advance.

[0131] Next, based on the trajectory clustering degree of the descent area, trajectory redundancy, obstacle area distribution index, the first weight, the second weight, and the third weight, the scoring information of the forced landing area is determined. Since the smaller the trajectory clustering degree of the descent area, the more favorable it is for the forced landing of the aircraft, and the smaller the scoring information; the larger the trajectory redundancy, the more favorable it is for the forced landing of the aircraft, and the smaller the scoring information; the smaller the obstacle area distribution index, the more favorable it is for the forced landing of the aircraft, and the smaller the scoring information; therefore, the formula for the scoring information can be: trajectory clustering degree of descent area * first weight + (1 - trajectory redundancy) * second weight + obstacle area distribution index * third weight.

[0132] By acquiring the first weight corresponding to the trajectory clustering degree of the descent area, the second weight corresponding to the trajectory redundancy, and the third weight corresponding to the obstacle area distribution index; then, based on the trajectory clustering degree of the descent area, the trajectory redundancy, the obstacle area distribution index, the first weight, the second weight, and the third weight, the scoring information of the forced landing area is determined. The scoring information can be accurately obtained based on the trajectory clustering degree of the descent area, the trajectory redundancy, and the obstacle area distribution index, so as to accurately assess the rationality of the forced landing area and further improve the safety and rationality of the aircraft's forced landing.

[0133] Based on the above embodiments, a seventh embodiment of the forced landing area assessment method of this application is proposed, wherein a data acquisition device is provided below the aircraft, and step S101 includes:

[0134] Step S701: Obtain the forced landing information corresponding to the aircraft from the cloud server, and obtain the semantic information based on the data acquisition device;

[0135] Step S702: Based on the forced landing information and the semantic information, determine the trajectory neighborhood semantic set.

[0136] After the aircraft triggers an emergency landing event and selects a landing area, it can obtain emergency landing information from the cloud server. This information includes multiple candidate landing areas within the trajectory neighborhood, as well as terrain and landform information, meteorological information, and 3D model images of buildings within the trajectory neighborhood. These 3D model images can be of tall buildings; for example, buildings taller than a preset height can be designated as tall buildings. Semantic information is also acquired based on the data acquisition device. This semantic information includes information on people (human flow), vehicle flow, and buildings within the trajectory neighborhood. It can also include information on water surfaces (rivers, lakes, etc.), airflow, terrain slope, and landforms within the trajectory neighborhood.

[0137] Next, based on the forced landing information and the semantic information, the trajectory neighborhood semantic set is determined, that is, the trajectory neighborhood semantic set can be a set of forced landing information and semantic information.

[0138] Furthermore, in one possible implementation, the data acquisition device includes a lidar and a camera; step S701 includes:

[0139] Step S7011: Based on the current altitude of the aircraft, determine the target data acquisition device in the lidar and camera;

[0140] Step S7012: Obtain the data collected by the target data acquisition device, and determine the semantic information based on the data collected.

[0141] The lidar and camera can be used to collect data at different altitudes so that the aircraft can obtain accurate semantic information at different altitudes. Therefore, the current altitude of the aircraft is first obtained, and the target data acquisition device is determined in the lidar and camera based on the current altitude. Specifically, the data acquisition altitude range of the lidar and camera can be preset, and the target data acquisition device is determined in the lidar and camera according to the current altitude and the data acquisition altitude range, so as to select the data acquisition device with the most accurate data acquisition at the time from the lidar and camera for data acquisition operation.

[0142] Next, the data collected by the target data acquisition device is acquired, and semantic information is determined based on the acquired data. For example, when the target data acquisition device is a lidar, the semantic information is determined by the lidar's acquired data and existing algorithms. When the target data acquisition device is a camera, the semantic information is determined by the images captured by the camera and existing image recognition algorithms, so as to improve the accuracy of the semantic information.

[0143] By obtaining the emergency landing information corresponding to the aircraft from the cloud server and acquiring the semantic information based on the data acquisition device, and then determining the trajectory neighborhood semantic set based on the emergency landing information and the semantic information, the trajectory neighborhood semantic set can be accurately obtained. This facilitates the accurate acquisition of scoring information based on the trajectory neighborhood semantic set, so as to accurately assess the rationality of the emergency landing area based on the scoring information, and further improve the safety and rationality of the aircraft emergency landing.

[0144] In addition, this application also proposes an aircraft, referring to Figure 6 The aircraft includes:

[0145] The acquisition module 10 is used to acquire the trajectory neighborhood semantic set corresponding to the forced landing area of ​​the aircraft. The trajectory neighborhood semantic set includes forced landing information and semantic information. The semantic information includes information on various obstacles in a preset area corresponding to the forced landing area.

[0146] The determination module 20 is used to determine the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landing area corresponding to the aircraft based on the trajectory neighborhood semantic set.

[0147] The scoring module 30 is used to determine the scoring information of the forced landing area based on the trajectory clustering degree, trajectory redundancy and obstacle area distribution index of the descent area.

[0148] The methods executed by the above-mentioned program units can be referred to in the various embodiments of the forced landing area assessment method of this application, and will not be repeated here.

[0149] Furthermore, this application also proposes a computer-readable storage medium storing a forced landing area assessment program, which, when executed by a processor, implements the steps of the forced landing area assessment method as described above.

[0150] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0151] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0152] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0153] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for assessing forced landing areas, characterized in that, include: Obtain the trajectory neighborhood semantic set corresponding to the forced landing area of ​​the aircraft, wherein the trajectory neighborhood semantic set includes forced landing information and semantic information, and the semantic information includes information on various obstacles in a preset area corresponding to the forced landing area; Based on the trajectory neighborhood semantic set, determine the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landing area corresponding to the aircraft. The scoring information of the forced landing area is determined by weighted summation based on the trajectory clustering degree, trajectory redundancy and obstacle area distribution index of the landable area. The steps of determining the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landing area corresponding to the aircraft based on the trajectory neighborhood semantic set include: Based on each landable candidate region in the forced landing information, the trajectory clustering degree of the landable region is determined. Specifically, based on the trajectory neighborhood semantic set, the distance between two adjacent landable candidate regions is obtained; the area corresponding to each landable candidate region is obtained; the maximum distance is obtained, and the neighborhood area and trajectory length of the trajectory neighborhood corresponding to the trajectory neighborhood semantic set are obtained; based on the maximum distance, the area, the neighborhood area, and the trajectory length, the trajectory clustering degree of the landable region is calculated using the formula for trajectory clustering degree of the landable region. Based on the candidate landing regions and semantic information in the forced landing information, the trajectory redundancy is determined, wherein, based on each candidate landing region, a non-landing region within the trajectory neighborhood corresponding to the trajectory neighborhood semantic set is determined; obstacle information within the non-landing region is determined according to the semantic information; trajectory regions without obstacles within each non-landing region are determined according to the obstacle information within the non-landing region; a minimum width is determined according to the width of each trajectory region, and the trajectory redundancy is determined based on the minimum width and a preset width. Based on the semantic information, the obstacle region distribution index is determined, wherein the Euclidean distance between obstacles corresponding to each obstacle information and the potential of the semantic set corresponding to the semantic information are obtained; based on the Euclidean distance and the number of obstacle information, the average distance corresponding to each obstacle information is determined; based on the potential and the average distance, the obstacle region distribution index is calculated using the formula for the obstacle region distribution index.

2. The forced landing area assessment method as described in claim 1, characterized in that, The step of determining the scoring information of the forced landing area by weighted summation based on the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the descent area includes: Obtain the first weight corresponding to the trajectory clustering degree of the degradable region, the second weight corresponding to the trajectory redundancy, and the third weight corresponding to the obstacle region distribution index; The scoring information for the forced landing area is determined by weighted summation based on the trajectory clustering degree, trajectory redundancy, obstacle area distribution index, first weight, second weight, and third weight of the landing area.

3. The forced landing area assessment method as described in any one of claims 1 to 2, characterized in that, A data acquisition device is installed below the aircraft. The step of acquiring the trajectory neighborhood semantic set corresponding to the forced landing area of ​​the aircraft includes: The forced landing information corresponding to the aircraft is obtained from the cloud server, and the semantic information is obtained based on the data acquisition device; Based on the forced landing information and the semantic information, the trajectory neighborhood semantic set is determined.

4. The forced landing area assessment method as described in claim 3, characterized in that, The data acquisition device includes a lidar and a camera; the step of acquiring the semantic information based on the data acquisition device includes: Based on the current altitude of the aircraft, the target data acquisition device is determined in the lidar and camera; The target data acquisition device acquires the collected data, and the semantic information is determined based on the acquired data.

5. An aircraft, characterized in that, The aircraft includes: The acquisition module is used to acquire the trajectory neighborhood semantic set corresponding to the forced landing area of ​​the aircraft. The trajectory neighborhood semantic set includes forced landing information and semantic information. The semantic information includes information on various obstacles in a preset area corresponding to the forced landing area. The determination module is used to determine the trajectory clustering degree, trajectory redundancy, and obstacle area distribution index of the landing area corresponding to the aircraft based on the trajectory neighborhood semantic set. The scoring module is used to determine the scoring information of the forced landing area by performing a weighted sum based on the trajectory clustering degree, trajectory redundancy and obstacle area distribution index of the descent area; The determining module is further configured to: Based on each landable candidate region in the forced landing information, the trajectory clustering degree of the landable region is determined. Specifically, based on the trajectory neighborhood semantic set, the distance between two adjacent landable candidate regions is obtained; the area corresponding to each landable candidate region is obtained; the maximum distance is obtained, and the neighborhood area and trajectory length of the trajectory neighborhood corresponding to the trajectory neighborhood semantic set are obtained; based on the maximum distance, the area, the neighborhood area, and the trajectory length, the trajectory clustering degree of the landable region is calculated using the formula for trajectory clustering degree of the landable region. Based on the candidate landing regions and semantic information in the forced landing information, the trajectory redundancy is determined, wherein, based on each candidate landing region, a non-landing region within the trajectory neighborhood corresponding to the trajectory neighborhood semantic set is determined; obstacle information within the non-landing region is determined according to the semantic information; trajectory regions without obstacles within each non-landing region are determined according to the obstacle information within the non-landing region; a minimum width is determined according to the width of each trajectory region, and the trajectory redundancy is determined based on the minimum width and a preset width. Based on the semantic information, the obstacle region distribution index is determined, wherein the Euclidean distance between obstacles corresponding to each obstacle information and the potential of the semantic set corresponding to the semantic information are obtained; based on the Euclidean distance and the number of obstacle information, the average distance corresponding to each obstacle information is determined; based on the potential and the average distance, the obstacle region distribution index is calculated using the formula for the obstacle region distribution index.

6. The aircraft as described in claim 5, characterized in that, The scoring module is also used for: Obtain the first weight corresponding to the trajectory clustering degree of the degradable region, the second weight corresponding to the trajectory redundancy, and the third weight corresponding to the obstacle region distribution index; The scoring information for the forced landing area is determined by weighted summation based on the trajectory clustering degree, trajectory redundancy, obstacle area distribution index, first weight, second weight, and third weight of the landing area.

7. The aircraft as described in any one of claims 5 to 6, characterized in that, A data acquisition device is installed below the aircraft, and the acquisition module is further used for: The forced landing information corresponding to the aircraft is obtained from the cloud server, and the semantic information is obtained based on the data acquisition device; Based on the forced landing information and the semantic information, the trajectory neighborhood semantic set is determined.

8. The aircraft as claimed in claim 7, characterized in that, The data acquisition device includes a lidar and a camera, and the acquisition module is further used for: Based on the current altitude of the aircraft, the target data acquisition device is determined in the lidar and camera; The target data acquisition device acquires the collected data, and the semantic information is determined based on the acquired data.

9. A forced landing area assessment device, characterized in that, The forced landing area assessment device includes: a memory, a processor, and a forced landing area assessment program stored in the memory and executable on the processor. When the forced landing area assessment program is executed by the processor, it implements the steps of the forced landing area assessment method as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a forced landing area assessment program, which, when executed by a processor, implements the steps of the forced landing area assessment method as described in any one of claims 1 to 4.

Images