Flight control system and method for low-altitude transport UAV

Abstract

The present invention belongs to the technical field of drones. A flight control system and method for low-altitude transport drones are provided. The method comprises: a main drone plans a main flight route and an auxiliary flight route of at least one auxiliary drone based on the target placement position of the cargo to be transported, and sends the auxiliary flight route to the corresponding auxiliary drone; wherein the cargo to be transported is located on one side of the obstacle area, and the target placement position is located on the other side of the obstacle area; the main drone lifts the cargo to be transported to the target placement position according to the main flight route, and at least one auxiliary drone lifts the power supply cable according to the corresponding auxiliary flight route, so that the main drone can obtain power supply from the power supply cable uninterruptedly. Compared with the prior art, the present invention enables the main drone to obtain a stable power supply through the dynamic lifting of the power supply cable by the auxiliary drone, without the need for frequent return charging, and can continuously and efficiently carry out cargo lifting.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles (UAVs), and in particular to a flight control system and method for transporting UAVs at low altitude. Background Art

[0002] In current transportation scenarios, obstacles such as rivers, tracks, mountains, and buildings are common. In the absence of conventional transportation methods like roads or ships, detours are often the only option. This not only results in extremely low transportation efficiency but also significantly increases transportation costs. With the continuous development and popularization of drone technology, the use of drones for remote transportation has become a new research direction. However, existing electric drones have many limitations. Their heavy batteries reduce payload capacity; their short flight time makes them incapable of meeting long-distance transportation needs; and their low transport power makes it difficult to continuously and economically transport heavy cargo.

[0003] The above problems seriously restrict the widespread application of drones in the field of remote transportation. Summary of the Invention

[0004] In response to the above technical problems, the present invention provides a flight control method, system, electronic equipment, computer storage medium and computer program product for a low-altitude transport UAV.

[0005] The present invention discloses a flight control method for a low-altitude transport UAV, which is applied to a main UAV. The method comprises the following steps: the main UAV plans a main flight route and a secondary flight route of at least one secondary UAV based on a target placement position of goods to be transported, and sends the secondary flight route to the corresponding secondary UAV; wherein, the goods to be transported are located on one side of an obstacle area, and the target placement position is located on the other side of the obstacle area; the main UAV lifts the goods to be transported to the target placement position according to the main flight route, and at the same time, at least one secondary UAV lifts power cables according to the corresponding secondary flight routes, so that the main UAV can obtain power supply from the power cables uninterruptedly.

[0006] Optionally, the method also includes: during the process of the main UAV flying according to the main flight route, the main UAV communicates with the closest auxiliary UAV to obtain its second real-time position, and the main UAV also takes a video image of the obstacle below; extracts the type information and vertex position dynamic information of the dynamic obstacle below from the video image, and evaluates the probability of the power supply cable being destroyed based on the type information and the vertex position dynamic information; determines the holding angle of the power supply cable based on the probability of the power supply cable being destroyed, and determines the relative position of the closest auxiliary UAV and the main UAV based on the holding angle, the first real-time position of the main UAV and the second real-time position; the main UAV sends the relative position to the closest auxiliary UAV, so that it flies according to the relative position, thereby ensuring that the power supply cable between the closest auxiliary UAV and the main UAV is at the holding angle.

[0007] Optionally, the evaluation of the probability of power cable destruction based on the type information and the vertex position dynamic information includes: using a convolutional network to extract and fuse features of the first real-time position of the main UAV, the second real-time position of the auxiliary UAV and the vertex position dynamic information to obtain dynamic features; using a deep prediction model to process the dynamic features to obtain a predicted preliminary probability of power cable destruction; obtaining a dynamic amplification coefficient based on the type information and a preset relationship matching, multiplying the dynamic amplification coefficient by the preliminary probability of power cable destruction to obtain the probability of power cable destruction; wherein, the type information refers to the ability level of the dynamic obstacle below to resist wind-actuated motion, and according to the ability level, a negative correlation relationship between the type information and the dynamic amplification coefficient, i.e., the preset relationship, is established.

[0008] Optionally, the method also includes: the main drone determines the target auxiliary drone based on the distance between the stacking area of ​​the goods to be transported and the target placement position, and identifies all the auxiliary drones between the stacking area and the target auxiliary drone as the target auxiliary drones; the main drone sends a still command to each of the target auxiliary drones, so that when the main drone completes a transport operation and returns to repeat a new transport operation task, only the auxiliary drones other than the target auxiliary drone keep following the main drone.

[0009] Optionally, at least some of the auxiliary drones obtain power from power supply cables.

[0010] The present invention also discloses a flight control system for a low-altitude transport UAV, which is applied to a main UAV. The system includes a processing device and a storage device. The computer code stored in the storage device is called and executed by the processing device to achieve: the main UAV plans a main flight route and an auxiliary flight route of at least one auxiliary UAV based on the target placement position of the goods to be transported, and sends the auxiliary flight route to the corresponding auxiliary UAV; wherein the goods to be transported are located on one side of an obstacle area, and the target placement position is located on the other side of the obstacle area; the main UAV lifts the goods to be transported to the target placement position according to the main flight route, and at the same time, at least one auxiliary UAV lifts power cables according to the corresponding auxiliary flight routes, so that the main UAV can obtain power supply from the power cables uninterruptedly.

[0011] Optionally, the computer code stored in the storage device is called and executed by the processing device, and is also used to achieve: during the process of the main UAV flying according to the main flight route, the main UAV communicates with the closest auxiliary UAV to obtain its second real-time position, and the main UAV also takes a video image of the obstacle below; extracts the type information and vertex position dynamic information of the dynamic obstacle below from the video image, and evaluates the probability of the power supply cable being destroyed based on the type information and the vertex position dynamic information; determines the holding angle of the power supply cable based on the probability of the power supply cable being destroyed, and determines the relative position of the closest auxiliary UAV and the main UAV based on the holding angle, the first real-time position of the main UAV and the second real-time position; the main UAV sends the relative position to the closest auxiliary UAV, so that it flies according to the relative position, thereby ensuring that the power supply cable between the closest auxiliary UAV and the main UAV is at the holding angle.

[0012] Optionally, the evaluation of the probability of power cable destruction based on the type information and the vertex position dynamic information includes: using a convolutional network to extract and fuse features of the first real-time position of the main UAV, the second real-time position of the auxiliary UAV and the vertex position dynamic information to obtain dynamic features; using a deep prediction model to process the dynamic features to obtain a predicted preliminary probability of power cable destruction; obtaining a dynamic amplification coefficient based on the type information and a preset relationship matching, multiplying the dynamic amplification coefficient by the preliminary probability of power cable destruction to obtain the probability of power cable destruction; wherein, the type information refers to the ability level of the dynamic obstacle below to resist wind-actuated motion, and according to the ability level, a negative correlation relationship between the type information and the dynamic amplification coefficient, i.e., the preset relationship, is established.

[0013] Optionally, the computer code stored in the storage device is called and executed by the processing device, and is also used to achieve: the main drone determines the target auxiliary drone based on the distance between the stacking area of ​​the goods to be transported and the target placement position, and all the auxiliary drones between the stacking area and the target auxiliary drone are identified as the target auxiliary drones; the main drone sends a still command to each of the target auxiliary drones, so that when the main drone completes a transport operation and returns to repeat a new transport operation task, only the auxiliary drones other than the target auxiliary drone keep following the main drone.

[0014] Optionally, at least some of the auxiliary drones obtain power from power supply cables.

[0015] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement any of the above methods.

[0016] The present invention further discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0017] The present invention further discloses a computer program product, which includes computer code. When the computer code is executed by a processor of an electronic device, any of the above methods is implemented.

[0018] Compared with the existing technology, the present invention enables the main drone to obtain a stable power supply by dynamically lifting the power supply cable through the auxiliary drone, without the need to frequently return to charge, and can continuously and efficiently carry out cargo lifting. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 This is a schematic diagram of a scenario in which a main UAV and an auxiliary UAV cooperate to carry out transportation, as disclosed in an embodiment of the present invention.

[0021] Figure 2 The present invention is a flowchart of a flight control method for a low-altitude transport UAV disclosed in an embodiment of the present invention.

[0022] Figure 3 Schematic diagram of different holding angles between a master UAV and a slave UAV disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following specific embodiments illustrate the implementation of this application. Those familiar with the art can easily understand the other advantages and functions of this application from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of this application, but not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0024] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0025] In response to the above technical issues, such as Figure 1 、 Figure 2 As shown, an embodiment of the present invention discloses a flight control method for a low-altitude transport UAV, which is applied to a main UAV, and the method includes the following steps: the main UAV plans a main flight route and an auxiliary flight route of at least one auxiliary UAV based on the target placement position of the goods to be transported, and sends the auxiliary flight route to the corresponding auxiliary UAV; wherein, the goods to be transported are located on one side of an obstacle area, and the target placement position is located on the other side of the obstacle area; the main UAV lifts the goods to be transported to the target placement position according to the main flight route, and at the same time, at least one auxiliary UAV lifts the power supply cable according to the corresponding auxiliary flight route, so that the main UAV can obtain power supply from the power supply cable uninterruptedly.

[0026] In response to the various defects of existing drones mentioned in the background technology when transporting cargo across obstacle areas, the present invention provides a main drone and a corresponding auxiliary drone. The auxiliary drone can ensure that the main drone has a continuous power supply. Specifically: First, the main drone plans its own main flight route according to the target placement position of the cargo to be transported. The cargo to be transported in the present invention is located on one side of the obstacle area, while the target placement position is on the other side of the obstacle area. The obstacle areas in the present invention include complex geographical environments such as rivers, canyons, and densely built-up areas that are not suitable for people and vehicles to pass through. They usually bring great difficulties to traditional transportation methods, but the main drone can effectively overcome these obstacles with its flexible flight capabilities to achieve efficient transportation of cargo.

[0027] At the same time, the master drone must also consider the actions of at least one slave drone and plan corresponding auxiliary flight routes for each. Auxiliary flight route planning must take into account factors such as the topography of the obstacle area, the length and difficulty of the power cable, the master drone's own flight performance, and the weight and volume of the cargo to ensure that the planned route is both safe and efficient. After the master drone completes the auxiliary flight route planning, it will transmit this route information to the corresponding slave drone via a communication link, so that the slave drone can accurately understand its flight mission and path.

[0028] When the lifting operation officially begins, the primary drone follows a planned primary flight route. Simultaneously, at least one secondary drone takes off, hoisting the power cable, at a predetermined time difference (the time difference is included in the secondary flight route). The secondary flight route then allows the primary drone to maintain a suitable connection with the power cable, thereby maintaining a continuous power supply and stable flight and lifting operations, gradually lifting the multiple pieces of cargo to their target locations. The power cable can be powered by a vehicle power supply, generator, or mains electricity, located on one side of the obstruction area, though this is not a limitation of the present invention.

[0029] Compared with the existing technology, the present invention enables the main drone to obtain a stable power supply by dynamically lifting the power supply cable through the auxiliary drone, without the need to frequently return to charge, and can continuously and efficiently carry out cargo lifting.

[0030] Optionally, the method also includes: during the process of the main UAV flying according to the main flight route, the main UAV communicates with the closest auxiliary UAV to obtain its second real-time position, and the main UAV also takes a video image of the obstacle below; extracts the type information and vertex position dynamic information of the dynamic obstacle below from the video image, and evaluates the probability of the power supply cable being destroyed based on the type information and the vertex position dynamic information; determines the holding angle of the power supply cable based on the probability of the power supply cable being destroyed, and determines the relative position of the closest auxiliary UAV and the main UAV based on the holding angle, the first real-time position of the main UAV and the second real-time position; the main UAV sends the relative position to the closest auxiliary UAV, so that it flies according to the relative position, thereby ensuring that the power supply cable between the closest auxiliary UAV and the main UAV is at the holding angle.

[0031] In this embodiment, if Figure 3As shown, there may be dynamic obstacles such as trees below the drone's flight path. The tops of these dynamic obstacles will swing significantly under the wind. The drone itself is equipped with detection equipment such as cameras and radars, which can detect real-time dynamic information about these dynamic obstacles. Using obstacle avoidance algorithms, it can avoid these dynamic obstacles, allowing it to penetrate into these dynamic obstacles to perform operations such as placing cargo. However, existing drone obstacle avoidance algorithms do not take into account the power cables between the main drone and the auxiliary drone. This makes it easy for the power cables to come into contact with the tops of these dynamic obstacles, resulting in accidents such as hanging and entanglement. This can damage the power cables and cause the main drone to lose power, and may also cause the auxiliary drone to be pulled out of control.

[0032] To address the above technical issues, the present invention configures the primary drone to obtain the real-time position of the secondary drone while it is flying along the primary flight path (for example, upon reaching the area above the target placement location). It also extracts dynamic vertex position information of underlying dynamic obstacles (such as the obstacle's movement direction, speed, and real-time changes in vertex coordinates) from video images captured by the onboard camera. Because different types of dynamic obstacles present varying motion characteristics and threats to cables, the present invention uses information about the type of dynamic obstacle (e.g., trees, bamboo, etc.) and the detected vertex position dynamic information to assess the probability of damage to the power supply cable by these dynamic obstacles (i.e., the probability of the aforementioned snags, entanglements, and other accidents occurring).

[0033] The holding angle of the power cable is determined based on the probability of the power cable being destroyed. The holding angle refers to the straight line angle between the main UAV and the closest auxiliary UAV. If the probability of destruction is high, a larger holding angle is required (refer to Figure 3 If the probability of being destroyed is low, the angle can be appropriately reduced (refer to Figure 3 The right side shows a more horizontal position) to ensure flight efficiency. Furthermore, the transport drone of the present invention has a large payload capacity and generates significant ground wind. By appropriately reducing the proximity of the closest auxiliary drone to the target placement location, the ground wind force in the area surrounding the auxiliary drone's target placement location can be reduced, facilitating the reception and transfer of cargo by personnel and vehicles below.

[0034] Then, based on the determined holding angle, the closest auxiliary drone determines its relative position to the primary drone (i.e., the auxiliary drone's new second real-time position to be maintained) with the primary drone's first real-time position as a reference. The closest auxiliary drone then flies according to this relative position, maintaining the power cable between them at a suitable angle to reduce the probability of the power cable being damaged by dynamic obstacles.

[0035] It should be noted that during this process, the relative positions should be dynamically updated. That is, the master drone continuously updates the relative position as it descends and transmits it to the closest slave drone. Furthermore, the master drone also needs to plan corresponding position sequences for the other slave drones, though this will not be detailed here.

[0036] Optionally, the evaluation of the probability of power cable destruction based on the type information and the vertex position dynamic information includes: using a convolutional network to extract and fuse features of the first real-time position of the main UAV, the second real-time position of the auxiliary UAV and the vertex position dynamic information to obtain dynamic features; using a deep prediction model to process the dynamic features to obtain a predicted preliminary probability of power cable destruction; obtaining a dynamic amplification coefficient based on the type information and a preset relationship matching, multiplying the dynamic amplification coefficient by the preliminary probability of power cable destruction to obtain the probability of power cable destruction; wherein, the type information refers to the ability level of the dynamic obstacle below to resist wind-actuated motion, and according to the ability level, a negative correlation relationship between the type information and the dynamic amplification coefficient, i.e., the preset relationship, is established.

[0037] In this embodiment, the real-time position information of the main UAV and the auxiliary UAV can reflect the current spatial state of the power supply cable, while the vertex position dynamic information includes information such as the motion trajectory and change trend of the dynamic obstacle. The present invention first uses the powerful feature extraction capability of the convolutional network to extract and fuse the first real-time position of the main UAV, the second real-time position of the auxiliary UAV, and the dynamic information of the vertex position of the dynamic obstacle to obtain dynamic features. Then, a pre-built and fully trained deep prediction model is used to perform in-depth analysis and pattern recognition on the fused dynamic features, thereby predicting a preliminary probability of power supply cable destruction. The above-mentioned deep prediction model is preferably constructed using Transformer or DNN (deep neural network), and the details will not be repeated here.

[0038] The aforementioned dynamic characteristics actually represent the current top dynamics of a dynamic obstacle. However, gusty winds often occur in the obstacle area. For example, during a drone's descent, the wind generated by its own rotors causes the top of the dynamic obstacle to become more dynamic. Furthermore, different types of dynamic obstacles have different levels of resistance to wind-induced actuation, which directly impacts the threat level to power cables. For example, tall, sturdy trees have a higher level of resistance to wind-induced actuation, making their top dynamics less susceptible to such gusts. Resilient trees, such as bamboo and willow, tend to have a lower level of resistance to wind-induced actuation, making their top dynamics more susceptible to such gusts. Therefore, the present invention assigns smaller dynamic amplification coefficients, such as 1.0 or 1.1, to dynamic obstacle types with higher levels of resistance to wind-induced actuation, while assigning larger dynamic amplification coefficients, such as 1.4 or 1.5, to dynamic obstacle types with lower levels of resistance to wind-induced actuation. The dynamic amplification coefficient is used to appropriately correct the preliminary power cable damage probability predicted by the aforementioned deep prediction model, thereby obtaining a more accurate power cable damage probability. In this way, even when the main drone descends into the middle of the trees, the probability of damage to the power cables due to contact with the surrounding trees can be minimized.

[0039] Optionally, the method also includes: the main drone determines the target auxiliary drone based on the distance between the stacking area of ​​the goods to be transported and the target placement position, and identifies all the auxiliary drones between the stacking area and the target auxiliary drone as the target auxiliary drones; the main drone sends a still command to each of the target auxiliary drones, so that when the main drone completes a transport operation and returns to repeat a new transport operation task, only the auxiliary drones other than the target auxiliary drone keep following the main drone.

[0040] In this embodiment, the primary drone is used to repeatedly complete multiple transport tasks, thereby transporting multiple items to the target placement location on the other side of the obstruction area. Therefore, each time it completes a transport task and returns to pick up new items, the secondary drones used to hang power cables must also return with it. Some secondary drones located on the obstruction side may even need to land. This requires the primary drone to coordinate and dispatch multiple secondary drones simultaneously, significantly increasing the processing load and hindering efficient transport.

[0041] In response to the above-mentioned problem, the present invention further configures the main drone to determine the target auxiliary drone based on the distance between the stacking area of ​​the goods to be transported and the target placement location. For example, an auxiliary drone at a distance less than half the distance is determined as a target auxiliary drone, and then all auxiliary drones between the stacking area and the target auxiliary drone are identified as target auxiliary drones. These target auxiliary drones maintain their own positions at different levels when the main drone returns to lift new goods to be transported, that is, only non-target auxiliary drones follow the main drone to maintain uninterrupted power supply to the main drone. Among them, the proportion of the number of target auxiliary drones to all auxiliary drones should be less than 50% to ensure that the main drone has sufficient power supply cable length to smoothly return to the stacking area to lift new goods to be transported.

[0042] In this way, the number of auxiliary drones that the main drone needs to coordinate can be significantly reduced, the processing load is greatly reduced, and efficient transportation can be achieved.

[0043] Optionally, at least some of the auxiliary drones obtain power from power supply cables.

[0044] In this embodiment, the auxiliary drone used to install the power cable can also obtain power from the power cable, which is conducive to achieving long-term cargo transportation. In addition, some auxiliary drones can be equipped with their own batteries and interfaces for obtaining power from the power cable. The power cable can also be equipped with a suitable supporting interface. This makes it easy to temporarily withdraw some auxiliary drones from the auxiliary drone performing the power cable installation. That is, the withdrawn auxiliary drones can use their own batteries to fly, for example, to install the power cable for the new main drone.

[0045] The main UAV and auxiliary UAV in the present invention can have the same software and hardware configuration so as to switch their respective roles, that is, whether to transport cargo or hoist power cables. Both the main UAV and the auxiliary UAV can accept unified control of the ground remote control, and the details will not be repeated.

[0046] An embodiment of the present invention further discloses a flight control system for a low-altitude transport UAV, which is applied to a master UAV. The system includes a processing device and a storage device. Computer code stored in the storage device is called and executed by the processing device to implement: the master UAV plans a primary flight route and a secondary flight route of at least one secondary UAV based on a target placement location of the cargo to be transported, and sends the secondary flight route to the corresponding secondary UAV; wherein the cargo to be transported is located on one side of an obstacle area, and the target placement location is located on the other side of the obstacle area;

[0047] The main UAV lifts the cargo to be transported to the target placement location according to the main flight route. At the same time, at least one auxiliary UAV lifts the power supply cable according to the corresponding auxiliary flight route, so that the main UAV can obtain power supply from the power supply cable uninterruptedly.

[0048] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in the aforementioned embodiment.

[0049] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the above embodiment.

[0050] An embodiment of the present invention further discloses a computer program product, which includes computer code. When the computer code is executed by a processor of an electronic device, the method described in the above embodiment is implemented.

[0051] The computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or apparatuses, or any suitable combination thereof. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media may include electrical connections based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0052] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0053] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A flight control method for a low-altitude transport UAV, applied to a master UAV, characterized by: The method includes the following steps: the master drone plans a primary flight route and a secondary flight route of at least one secondary drone based on a target placement location of the cargo to be transported, and sends the secondary flight routes to the corresponding secondary drones; wherein the cargo to be transported is located on one side of an obstacle area, and the target placement location is located on the other side of the obstacle area; the master drone lifts the cargo to be transported to the target placement location according to the primary flight route, and at the same time, the at least one secondary drone lifts a power supply cable according to the corresponding secondary flight route, so that the master drone can obtain uninterrupted power supply from the power supply cable; The method further includes: during the flight of the master UAV according to the master flight route, the master UAV communicates with the closest slave UAV to obtain its second real-time position, and the master UAV also captures a video image of an obstacle below; extracting type information and vertex position dynamic information of the dynamic obstacle below from the video image, and evaluating a probability of a power cable being destroyed based on the type information and the vertex position dynamic information; determining a holding angle of the power cable based on the probability of the power cable being destroyed, and determining a relative position of the closest slave UAV to the master UAV based on the holding angle, the first real-time position of the master UAV, and the second real-time position; the master UAV sends the relative position to the closest slave UAV, so that the slave UAV flies according to the relative position, thereby ensuring that the power cable between the closest slave UAV and the master UAV is at the holding angle; The evaluation of the probability of power cable destruction based on the type information and the vertex position dynamic information includes: using a convolutional network to extract and fuse features of the first real-time position of the main UAV, the second real-time position of the auxiliary UAV and the vertex position dynamic information to obtain dynamic features; using a deep prediction model to process the dynamic features to obtain a predicted preliminary probability of power cable destruction; obtaining a dynamic amplification coefficient based on the type information and a preset relationship matching, multiplying the dynamic amplification coefficient by the preliminary power cable destruction probability to obtain the power cable destruction probability; wherein, the type information refers to the ability level of the dynamic obstacle below to resist wind-actuated motion, and according to the ability level, a negative correlation relationship between the type information and the dynamic amplification coefficient, i.e., the preset relationship, is established.

2. The flight control method for a low-altitude transport UAV according to claim 1, characterized in that: The method also includes: the main drone determines a target auxiliary drone based on the distance between the stacking area of ​​the goods to be transported and the target placement position, and identifies all the auxiliary drones between the stacking area and the target auxiliary drone as the target auxiliary drones; the main drone sends a stationary command to each of the target auxiliary drones, so that when the main drone completes a transport operation and returns to repeat a new transport operation task, only the auxiliary drones other than the target auxiliary drone keep following the main drone.

3. The flight control method for a low-altitude transport UAV according to claim 2, characterized in that: At least some of the auxiliary drones obtain power from power supply cables.

4. A flight control system for a low-altitude transport UAV, applied to a host UAV, comprising a processing device and a storage device, characterized in that: The computer code stored in the storage device is called and executed by the processing device to implement: the master drone plans a primary flight route and a secondary flight route of at least one secondary drone based on a target placement location of the cargo to be transported, and sends the secondary flight routes to the corresponding secondary drones; wherein the cargo to be transported is located on one side of an obstacle area, and the target placement location is located on the other side of the obstacle area; the master drone lifts the cargo to be transported to the target placement location according to the primary flight route, and at the same time, the at least one secondary drone lifts a power supply cable according to the corresponding secondary flight route, so that the master drone can obtain uninterrupted power supply from the power supply cable; The computer code stored in the storage device is called and executed by the processing device, and is further used to implement: during the flight of the main UAV according to the main flight route, the main UAV communicates with the closest auxiliary UAV to obtain its second real-time position, and the main UAV also captures a video image of the obstacle below; extracts type information and vertex position dynamic information of the dynamic obstacle below from the video image, and evaluates the probability of power cable damage based on the type information and the vertex position dynamic information; determines a holding angle of the power cable based on the power cable damage probability, and determines the relative position of the closest auxiliary UAV to the main UAV based on the holding angle, the first real-time position of the main UAV, and the second real-time position; the main UAV sends the relative position to the closest auxiliary UAV, so that it flies according to the relative position, thereby ensuring that the power cable between the closest auxiliary UAV and the main UAV is at the holding angle; The evaluation of the probability of power cable destruction based on the type information and the vertex position dynamic information includes: using a convolutional network to extract and fuse features of the first real-time position of the main UAV, the second real-time position of the auxiliary UAV and the vertex position dynamic information to obtain dynamic features; using a deep prediction model to process the dynamic features to obtain a predicted preliminary probability of power cable destruction; obtaining a dynamic amplification coefficient based on the type information and a preset relationship matching, multiplying the dynamic amplification coefficient by the preliminary power cable destruction probability to obtain the power cable destruction probability; wherein, the type information refers to the ability level of the dynamic obstacle below to resist wind-actuated motion, and according to the ability level, a negative correlation relationship between the type information and the dynamic amplification coefficient, i.e., the preset relationship, is established.

5. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 3.

6. A computer storage medium storing a computer program, wherein: The computer program is executed by a processor to implement the method according to any one of claims 1 to 3.

7. A computer program product, characterized in that: The computer program product includes computer code, and when the computer code is executed by a processor of an electronic device, the method according to any one of claims 1 to 3 is implemented.

Images