A UAV swarm collaborative operation system

Abstract

The present invention relates to the field of data analysis, and in particular to a drone swarm collaborative operation system. The present invention is provided with an instruction parsing module, which is used to obtain control instructions in several time domain segments of an instruction output end, parse the instruction features of the control instructions in each time domain segment, and identify the switching time node according to the change of the instruction features in each time domain segment; a node analysis module, which is connected to the instruction parsing module, is used to determine the difference in instruction features in the time domain segments before and after the switching time node, calculate the instruction difference characterization parameter, and analyze the control instruction propagation impact category of each switching time node; a processing module, which is respectively connected to the instruction parsing module and the node analysis module, is used to adaptively process the control instruction based on the control instruction propagation impact category of the switching time node. The present invention can ensure the continuity and stability of the drone swarm collaborative operation and improve the execution efficiency of the collaborative operation.

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and in particular to a drone swarm collaborative operation system. Background Art

[0002] Technological progress and practical needs have jointly promoted the development of collaborative operations of drone swarms. Through preset control instructions and real-time communication, they work together to complete specific tasks. Among them, real-time data transmission and sharing between drone swarms are the key to the accuracy and stability of cluster control. Collaborative control technology, as a key core technology for multiple intelligent agents to complete tasks through division of labor and cooperation, can solve problems such as drone swarm formation, formation reconstruction, and obstacle avoidance. It is the basis for the normal operation of drone swarms. Artificial intelligence algorithms enable drone swarms to make autonomous decisions and plan paths; machine learning enables drones to learn environmental characteristics and mission modes based on big data and optimize operating processes; distributed algorithms ensure stable communication and collaborative scheduling between several drones, prompting drone swarms to move from simple remote control to intelligent and autonomous collaboration. The combination of the above technologies and their application in drone swarm collaborative operations can improve efficiency, reduce costs, and enhance task flexibility and adaptability.

[0003] Chinese patent application publication number: CN116795141A, discloses a drone cluster collaborative operation system, including: multiple control nodes, multiple drone groups, control terminals and collaborative control equipment. The invention uses mirroring to obtain flight programs, which does not interfere with the program itself. At the same time, the mirrored program is modified accordingly according to changes in environmental information and control instructions. After the modification, a corresponding collaborative control flight program is formed, and a synchronization node is obtained by simulating the execution judgment between the collaborative control flight program and the corresponding flight program, and the synchronization node is written into the synchronization program. The collaborative control flight program and the synchronization program are synchronized to the control terminal to be deployed to the corresponding control node, and the collaborative control flight program and the flight program are associated. When the flight program is executed to the synchronization node position, it automatically jumps to the collaborative control flight program to control the drone group.

[0004] However, there are still the following problems in the prior art:

[0005] When a swarm of drones performs collaborative operations, control instructions are usually transmitted in the form of drone node broadcasts, that is, the instruction output terminal sends the instruction to some drone nodes, and then some drone nodes further distribute the control instructions. However, in the process of the drone swarm performing the predetermined task, the actions required by the drone swarm at different stages may be different. The execution actions of some stages are more complicated, and the corresponding control instructions at different stages are different. When the complexity of the transmitted control instructions changes greatly, it is difficult for the drone swarm to adapt. In the communication dimension, the propagation of control instructions in the drone swarm is affected, which may cause the drone to be unable to receive the next connection control instruction in time, resulting in disorder in the collaborative operation and reducing the execution efficiency of the drone swarm's collaborative operation. Summary of the invention

[0006] To this end, the present invention provides a drone swarm collaborative operation system to overcome the problem in the prior art that, during the process of the drone swarm performing a predetermined task, when the complexity of the transmitted control instructions changes greatly, the drone swarm is difficult to adapt, which affects the propagation of the control instructions in the drone swarm, resulting in different execution speeds of the control instructions during collaborative operation, thereby reducing the execution efficiency of the drone swarm collaborative operation.

[0007] To achieve the above object, the present invention provides a drone swarm collaborative operation system, which includes:

[0008] An instruction parsing module, which is used to obtain control instructions in several time domain segments from the instruction output end, parse the instruction features of the control instructions in each time domain segment, and identify the switching time node according to the changes of the instruction features in each time domain segment;

[0009] A node analysis module, which is connected to the instruction parsing module, is used to determine the difference in instruction characteristics in the time domain before and after the switching time node, calculate the instruction difference characterization parameter, and analyze the control instruction propagation impact category of each switching time node;

[0010] A processing module, which is connected to the instruction parsing module and the node analysis module respectively, and is used to process the control instruction based on the control instruction propagation impact category of the switching time node, including:

[0011] Determine the buffering time based on the instruction difference characterization parameter, determine the control instruction segment corresponding to the buffering time after the switching time node, determine the preloading time, and preload the control instruction segment to the corresponding drone node at the corresponding preloading time;

[0012] Or, transmitting the control instructions to the drone node according to a preset control instruction sequence;

[0013] Among them, the instruction characteristics include the computing power consumption of decoding the control instruction and the amount of transmission data corresponding to the control instruction.

[0014] Furthermore, the instruction parsing module is used to identify the switching time node according to the change of instruction characteristics in each time domain segment, including:

[0015] To determine the control instructions and corresponding instruction features contained in each time domain segment;

[0016] To determine the difference in computing power consumption and data transmission volume corresponding to the control instructions contained in each adjacent time domain segment;

[0017] Determine the time node that meets the instruction characteristic change condition as the switching time node;

[0018] Among them, the instruction feature change conditions include that the difference in computing power consumption corresponding to the adjacent time domain segments before and after the time node is greater than the computing power consumption difference threshold or / and the corresponding transmission data volume difference is greater than the transmission data volume difference threshold.

[0019] Furthermore, the node analysis module is used to calculate instruction difference characterization parameters, including:

[0020] Used to calculate the difference in computing power consumption and the difference in data transmission volume in the time domain before and after the switching time node;

[0021] The ratio of the computing power consumption difference to the computing power consumption difference threshold is used as the first instruction difference feature;

[0022] for taking the ratio of the transmission data amount difference to the transmission data amount difference threshold as the second instruction difference feature;

[0023] The sum of the first instruction difference feature and the second instruction difference feature is determined as the instruction difference characterization parameter.

[0024] Furthermore, the node analysis module is used to analyze the control instruction propagation impact category of each switching time node, including

[0025] If the instruction difference characterization parameter is greater than or equal to the instruction difference characterization parameter threshold, the control instruction propagation of the switching time node is determined to be a high-impact category;

[0026] If the instruction difference characterization parameter is less than the instruction difference characterization parameter threshold, the control instruction propagation of the switching time node is determined to be a low impact category.

[0027] Furthermore, the processing module is used to process the control instruction based on the control instruction propagation impact category of the switching time node, including:

[0028] If the control instruction propagation of the switching time node is a high-impact category, the buffering duration is determined based on the instruction difference characterization parameter, the control instruction segment corresponding to the buffering duration after the switching time node is determined, the preloading time is determined, and the control instruction segment is preloaded to the corresponding drone node at the corresponding preloading time;

[0029] If the control instruction propagation of the switching time node is of the low impact category, the control instruction is transmitted to the drone node according to the pre-set control instruction sequence.

[0030] Furthermore, the processing module is used to determine the buffering time based on the instruction difference characterization parameter, including:

[0031] The buffering time is positively correlated with the instruction difference characterization parameter.

[0032] Furthermore, the processing module is used to determine the control instruction fragment corresponding to the buffering time length after the switching time node, including:

[0033] for delaying the switching time node by the buffering time on the time axis to determine the corresponding buffering moment after the extension;

[0034] Used to determine the control instruction segment corresponding to the switching time node to the buffering time.

[0035] Furthermore, the processing module is used to determine the preloading time, including:

[0036] Used to determine the transmission speed of the current control instruction;

[0037] to determine the transmission time required to transmit the control instruction fragment after reducing the current control instruction transmission speed;

[0038] It is used to extend the transmission duration of the switching time node forward on the time axis, and determine the time corresponding to the extended transmission duration as the preloading time.

[0039] Furthermore, the processing module is also used to determine the previous control instruction segment of the preloaded control instruction segment, and control the drone node to execute the previous control instruction segment and then execute the preloaded control instruction segment in sequence.

[0040] Furthermore, the processing module is used to transmit the control instruction to the drone node according to a preset control instruction sequence, including:

[0041] Used to divide the control instruction into a plurality of control instruction fragments and set a transmission order for the control instruction fragments;

[0042] The control instruction segments are transmitted according to the transmission sequence.

[0043] Compared with the prior art, the present invention provides an instruction parsing module, which is used to obtain control instructions in several time domain segments of the instruction output end, parse the instruction characteristics of the control instructions in each time domain segment, and identify the switching time node according to the change of the instruction characteristics in each time domain segment; a node analysis module, which is connected to the instruction parsing module, is used to determine the difference in instruction characteristics in the time domain segments before and after the switching time node, calculate the instruction difference characterization parameter, so as to analyze the control instruction propagation impact category of each switching time node; a processing module, which is respectively connected to the instruction parsing module and the node analysis module, is used to adaptively process the control instruction based on the control instruction propagation impact category of the switching time node. The present invention can ensure the continuity and stability of the collaborative operation of the drone group and improve the execution efficiency of the collaborative operation.

[0044] In particular, the present invention focuses on analyzing the changes in command characteristics in the time domain before and after the switching time node, and can accurately identify when the transmission of control commands needs to be adjusted, thereby improving the response speed of the drone and the control accuracy of the drone.

[0045] In particular, the present invention considers the instruction difference characterization parameters for the switching time nodes. In actual situations, the control instructions applied to the drone swarm may differ in the actions required to be executed by the drone swarm at different stages. The execution actions in some stages are more complex and may include actions in multiple dimensions, such as movement, shooting, calculation, etc., and the complexity of the instructions affects the data transmission volume in the communication link and the parsing time for the control instructions. Therefore, the present invention characterizes the degree of difference in the complexity of the control instructions at the switching time nodes through the instruction difference characterization parameters, and further characterizes the degree of influence of the control instructions on the instruction propagation, providing data support for the subsequent classification of the control instruction propagation influence categories of each switching time node, and then adaptively processing the control instructions, which can ensure the continuity and stability of the collaborative operation of the drone swarm and improve the execution efficiency of the collaborative operation.

[0046] In particular, the present invention determines the buffering time and preloads the control instructions when the control instruction propagation at the switching time node is a high-impact category. In actual situations, due to the large change in the complexity of the control instructions at the switching time node, the drone swarm may not be easy to adapt, affecting the propagation of the control instructions in the drone swarm, and easily leading to a potential risk of jamming and interruption in the execution of the control instructions by the drone swarm before and after the switching time node, affecting the continuity of the execution of the control instructions by the drone swarm. In addition, the present invention fully considers the actual transmission capacity of the control instructions, and sets the preloading time by determining the time required to transmit the instruction fragment after reducing the transmission speed of the current control instruction, avoiding communication link congestion during preloading, and flexibly adjusting the preloading time to avoid preloading failure due to the incompatibility of the fixed transmission mode with the actual situation. The drone cannot receive the control instruction in time, which reduces the continuity of the task execution and causes a waste of computing resources. The present invention can ensure the continuity and stability of the collaborative operation of the drone swarm and improve the execution efficiency of the collaborative operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A functional module diagram of a drone swarm collaborative operation system according to an embodiment of the invention;

[0048] Figure 2 A logic decision diagram for identifying a switching time node for an embodiment of the invention;

[0049] Figure 3 A logic decision diagram for analyzing the control instruction propagation impact category of each switching time node for an embodiment of the invention;

[0050] Figure 4 A logical decision diagram for processing control instructions according to an embodiment of the invention. DETAILED DESCRIPTION

[0051] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0052] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0053] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0054] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0055] See also Figure 1 As shown, it is a functional module diagram of the drone swarm collaborative operation system according to an embodiment of the present invention. The drone swarm collaborative operation system according to an embodiment of the present invention includes:

[0056] An instruction parsing module, which is used to obtain control instructions in several time domain segments of the instruction output end, parse the instruction features of the control instructions in each time domain segment, and identify the switching time node according to the changes of the instruction features in each time domain segment;

[0057] A node analysis module, which is connected to the instruction parsing module, is used to determine the difference in instruction characteristics in the time domain before and after the switching time node, calculate the instruction difference characterization parameter, and analyze the control instruction propagation impact category of each switching time node;

[0058] A processing module, which is connected to the instruction parsing module and the node analysis module respectively, and is used to process the control instruction based on the control instruction propagation impact category of the switching time node, including:

[0059] Determine the buffering time based on the instruction difference characterization parameter, determine the control instruction segment corresponding to the buffering time after the switching time node, determine the preloading time, and preload the control instruction segment to the corresponding drone node at the corresponding preloading time;

[0060] Or, transmitting the control instructions to the drone node according to a preset control instruction sequence;

[0061] Among them, the instruction characteristics include the computing power consumption of decoding the control instruction and the amount of transmission data corresponding to the control instruction.

[0062] Specifically, there is no limitation on the specific structures of the instruction parsing module, the node analysis module and the processing module, and they themselves or each unit therein can be composed of logic components or a combination of logic components, and the logic components include a field programmable processor, a computer or a microprocessor in a computer.

[0063] Specifically, the control instructions for the drone swarm can be pre-generated at the instruction output end so that the drone swarm can perform corresponding actions within a predetermined time domain segment, where different time domain segments correspond to different control instructions. The pre-generated control instructions can be obtained through the instruction parsing module, which will not be repeated here.

[0064] Specifically, after receiving the corresponding control instructions, the drone can perform actions according to the corresponding control instructions, including several flight actions, executing calculations, etc., which will not be repeated here.

[0065] Specifically, the computing power consumption of decoding the control instruction is the power consumption when the drone node decodes the control instruction after receiving the control instruction.

[0066] Specifically, see Figure 2 As shown, it is a logical decision diagram for identifying a switching time node according to an embodiment of the present invention. The instruction parsing module is used to identify the switching time node according to the change of instruction features in each time domain segment, including:

[0067] To determine the control instructions and corresponding instruction features contained in each time domain segment;

[0068] To determine the difference in computing power consumption and data transmission volume corresponding to the control instructions contained in each adjacent time domain segment;

[0069] Determine the time node that meets the instruction characteristic change condition as the switching time node;

[0070] Among them, the instruction feature change conditions include that the difference in computing power consumption corresponding to the adjacent time domain segments before and after the time node is greater than the computing power consumption difference threshold or / and the corresponding transmission data volume difference is greater than the transmission data volume difference threshold.

[0071] In this embodiment, the purpose of the computing power consumption difference threshold and the transmission data volume difference threshold is to characterize the situation where the complexity of the control instructions of the adjacent time domain segments before and after the time node is too different. The computing power consumption difference threshold and the transmission data volume difference threshold are determined based on the average value of the computing power consumption difference and the average value of the transmission data volume difference, respectively.

[0072] Among them, by obtaining relevant historical data of several drone groups working together to perform the same flight operations, the historical data of computing power consumption difference and the historical data of transmission data volume difference are extracted, and the average value of the computing power consumption difference and the average value of the transmission data volume difference are solved. Based on the purpose of setting the above two thresholds, the computing power consumption difference threshold is determined between 1.5 times and 1.6 times the average value of the computing power consumption difference, and the transmission data volume difference threshold is determined between 1.2 times and 1.3 times the average value of the transmission data volume difference.

[0073] Specifically, the present invention focuses on analyzing the changes in command characteristics in the time domain segments before and after the switching time node, and can accurately identify when the transmission of control commands needs to be adjusted, thereby improving the response speed of the drone and the control accuracy of the drone.

[0074] Specifically, the node analysis module is used to calculate instruction difference characterization parameters, including:

[0075] Used to calculate the difference in computing power consumption and the difference in data transmission volume in the time domain before and after the switching time node;

[0076] The ratio of the computing power consumption difference to the computing power consumption difference threshold is used as the first instruction difference feature;

[0077] for taking the ratio of the transmission data amount difference to the transmission data amount difference threshold as the second instruction difference feature;

[0078] The sum of the first instruction difference feature and the second instruction difference feature is determined as the instruction difference characterization parameter.

[0079] Specifically, the present invention considers the instruction difference characterization parameters for the switching time nodes. In actual situations, the control instructions applied to the drone swarm may differ in the actions required to be executed by the drone swarm at different stages. The execution actions in some stages are more complex and may include actions in multiple dimensions, such as movement, shooting, calculation, etc., and the complexity of the instructions affects the data transmission volume in the communication link and the parsing time for the control instructions. Therefore, the present invention characterizes the degree of difference in the complexity of the control instructions at the switching time nodes through the instruction difference characterization parameters, and further characterizes the degree of influence of the control instructions on the instruction propagation, providing data support for the subsequent division of the control instruction propagation influence categories of each switching time node, and then adaptively processing the control instructions, which can ensure the continuity and stability of the collaborative operation of the drone swarm and improve the execution efficiency of the collaborative operation.

[0080] Specifically, see Figure 3 As shown, it is a logic decision diagram for analyzing the control instruction propagation impact category of each switching time node according to an embodiment of the present invention. The node analysis module is used to analyze the control instruction propagation impact category of each switching time node, including

[0081] If the instruction difference characterization parameter is greater than or equal to the instruction difference characterization parameter threshold, the control instruction propagation of the switching time node is determined to be a high-impact category;

[0082] If the instruction difference characterization parameter is less than the instruction difference characterization parameter threshold, the control instruction propagation of the switching time node is determined to be a low impact category.

[0083] The instruction difference characterization parameter threshold is selected in the interval [2.45, 2.56].

[0084] Specifically, see Figure 4As shown, it is a logic decision diagram for processing control instructions in an embodiment of the present invention, and the processing module is used to process the control instruction based on the control instruction propagation impact category of the switching time node, including:

[0085] If the control instruction propagation of the switching time node is a high-impact category, the buffering duration is determined based on the instruction difference characterization parameter, the control instruction segment corresponding to the buffering duration after the switching time node is determined, the preloading time is determined, and the control instruction segment is preloaded to the corresponding drone node at the corresponding preloading time;

[0086] If the control instruction propagation of the switching time node is of the low impact category, the control instruction is transmitted to the drone node according to the pre-set control instruction sequence.

[0087] Specifically, the present invention determines the buffering time and preloads the control instructions when the control instruction propagation at the switching time node is a high-impact category. In actual situations, due to the large change in the complexity of the control instructions at the switching time node, the drone swarm may not be easy to adapt, affecting the propagation of the control instructions in the drone swarm, and easily leading to a potential risk of jamming in the execution of the control instructions by the drone swarm before and after the switching time node, affecting the continuity of the execution of the control instructions by the drone swarm. In addition, the present invention fully considers the actual transmission capacity of the control instructions, and sets the preloading time by determining the time required to transmit the instruction fragment after reducing the transmission speed of the current control instruction, avoiding communication link congestion during preloading, and flexibly adjusting the preloading time to avoid preloading failure due to the incompatibility of the fixed transmission mode with the actual situation. The drone cannot receive the control instruction in time, which reduces the continuity of the task execution and causes a waste of computing resources. The present invention can ensure the continuity and stability of the collaborative operation of the drone swarm and improve the execution efficiency of the collaborative operation.

[0088] Specifically, the processing module is used to determine the buffering time based on the instruction difference characterization parameter, including:

[0089] The buffering time is positively correlated with the instruction difference characterization parameter.

[0090] In this embodiment, optionally,

[0091] The instruction difference characterization parameter is compared with a preset first instruction difference characterization parameter comparison threshold and a second instruction difference characterization parameter comparison threshold,

[0092] When the instruction difference characterization parameter is greater than the second instruction difference characterization parameter comparison threshold, the buffering time is determined to be the first buffering time, and the first buffering time is set to be 1.58 times the benchmark buffering time;

[0093] When the instruction difference characterization parameter is greater than or equal to the first instruction difference characterization parameter comparison threshold and less than or equal to the second instruction difference characterization parameter comparison threshold, the buffering time is determined to be the second buffering time, and the second buffering time is set to be 1.46 times the benchmark buffering time;

[0094] When the instruction difference characterization parameter is less than the first instruction difference characterization parameter comparison threshold, the buffering time is determined to be the third buffering time, and the third buffering time is set to be 1.34 times the benchmark buffering time;

[0095] Among them, the first instruction difference characterization parameter comparison threshold is 1.65 times the instruction difference characterization parameter threshold, and the second instruction difference characterization parameter comparison threshold is 1.8 times the instruction difference characterization parameter threshold.

[0096] The baseline buffering time is selected in the range [3ms, 5ms].

[0097] Specifically, the processing module is used to determine the control instruction fragment corresponding to the buffering time length after the switching time node, including:

[0098] for delaying the switching time node by the buffering time on the time axis to determine the corresponding buffering moment after the extension;

[0099] Used to determine the control instruction segment corresponding to the switching time node to the buffering time.

[0100] Specifically, the processing module is used to determine the preloading time, including:

[0101] Used to determine the transmission speed of the current control instruction;

[0102] to determine the transmission time required to transmit the control instruction fragment after reducing the current control instruction transmission speed;

[0103] It is used to extend the transmission duration of the switching time node forward on the time axis, and determine the time corresponding to the extended transmission duration as the preloading time.

[0104] It is understandable that the purpose of reducing the control instruction transmission speed is to avoid transmission link congestion during synchronous transmission, and the reduction amount can be selected by those skilled in the art, for example, reduced to 0.3 to 0.5 times the initial transmission speed.

[0105] Specifically, the processing module is also used to determine the previous control instruction segment of the preloaded control instruction segment, and control the drone node to execute the previous control instruction segment and then execute the preloaded control instruction segment in sequence.

[0106] Specifically, the processing module is used to transmit the control instruction to the drone node according to a preset control instruction sequence, including:

[0107] It is used to divide the control instruction into several control instruction segments and set the transmission order for the control instruction segments. Preferably, the control instruction can be divided into several control instruction segments with the same data volume, which will not be repeated here.

[0108] The control instruction segments are transmitted according to the transmission sequence.

[0109] Specifically, there is no limitation on the specific method of transmitting the control instruction fragment, which can be matched according to the corresponding communication link, for example, encapsulated into several data packets for transmission. Of course, other methods can also be used, which will not be described in detail.

[0110] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A drone swarm collaborative operation system, characterized in that: include: An instruction parsing module, which is used to obtain control instructions in several time domain segments of the instruction output end, parse the instruction features of the control instructions in each time domain segment, and identify the switching time node according to the changes of the instruction features in each time domain segment; A node analysis module, which is connected to the instruction parsing module, is used to determine the difference in instruction characteristics in the time domain before and after the switching time node, calculate the instruction difference characterization parameter, and analyze the control instruction propagation impact category of each switching time node; A processing module, which is connected to the instruction parsing module and the node analysis module respectively, and is used to process the control instruction based on the control instruction propagation impact category of the switching time node, including: Determine the buffering time based on the instruction difference characterization parameter, determine the control instruction segment corresponding to the buffering time after the switching time node, determine the preloading time, and preload the control instruction segment to the corresponding drone node at the corresponding preloading time; Or, transmitting the control instructions to the drone node according to a preset control instruction sequence; Among them, the instruction characteristics include the computing power consumption of decoding the control instruction and the amount of transmission data corresponding to the control instruction.

2. The drone swarm collaborative operation system according to claim 1, characterized in that: The instruction parsing module is used to identify the switching time node according to the change of instruction characteristics in each time domain segment, including: To determine the control instructions and corresponding instruction features contained in each time domain segment; To determine the difference in computing power consumption and data transmission volume corresponding to the control instructions contained in each adjacent time domain segment; Determine the time node that meets the instruction characteristic change condition as the switching time node; Among them, the instruction feature change conditions include that the difference in computing power consumption corresponding to the adjacent time domain segments before and after the time node is greater than the computing power consumption difference threshold or / and the corresponding transmission data volume difference is greater than the transmission data volume difference threshold.

3. The drone swarm collaborative operation system according to claim 1, characterized in that: The node analysis module is used to calculate instruction difference characterization parameters, including: Used to calculate the difference in computing power consumption and the difference in data transmission volume in the time domain before and after the switching time node; The ratio of the computing power consumption difference to the computing power consumption difference threshold is used as the first instruction difference feature; for taking the ratio of the transmission data amount difference to the transmission data amount difference threshold as the second instruction difference feature; The sum of the first instruction difference feature and the second instruction difference feature is determined as the instruction difference characterization parameter.

4. The drone swarm collaborative operation system according to claim 1, characterized in that: The node analysis module is used to analyze the control instruction propagation impact category of each switching time node, including If the instruction difference characterization parameter is greater than or equal to the instruction difference characterization parameter threshold, the control instruction propagation of the switching time node is determined to be a high-impact category; If the instruction difference characterization parameter is less than the instruction difference characterization parameter threshold, the control instruction propagation of the switching time node is determined to be a low impact category.

5. The drone swarm collaborative operation system according to claim 4, characterized in that: The processing module is used to process the control instruction based on the control instruction propagation impact category of the switching time node, include, If the control instruction propagation of the switching time node is a high-impact category, the buffering duration is determined based on the instruction difference characterization parameter, the control instruction segment corresponding to the buffering duration after the switching time node is determined, the preloading time is determined, and the control instruction segment is preloaded to the corresponding drone node at the corresponding preloading time; If the control instruction propagation of the switching time node is of the low impact category, the control instruction is transmitted to the drone node according to the pre-set control instruction sequence.

6. The drone swarm collaborative operation system according to claim 1, characterized in that: The processing module is used to determine the buffering time length based on the instruction difference characterization parameter, include, The buffering time is positively correlated with the instruction difference characterization parameter.

7. The drone swarm collaborative operation system according to claim 1, characterized in that: The processing module is used to determine the control instruction fragment corresponding to the buffering time length after the switching time node, including: for delaying the switching time node by the buffering time on the time axis to determine the corresponding buffering moment after the extension; Used to determine the control instruction segment corresponding to the switching time node to the buffering time.

8. The drone swarm collaborative operation system according to claim 7, characterized in that: The processing module is used to determine the preloading time, including: Used to determine the transmission speed of the current control instruction; to determine the transmission time required to transmit the control instruction fragment after reducing the current control instruction transmission speed; It is used to extend the transmission duration of the switching time node forward on the time axis, and determine the time corresponding to the extended transmission duration as the preloading time.

9. The drone swarm collaborative operation system according to claim 1, characterized in that: The processing module is also used to determine the previous control instruction segment of the preloaded control instruction segment, and control the drone node to execute the previous control instruction segment and then execute the preloaded control instruction segment in sequence.

10. The drone swarm collaborative operation system according to claim 1, characterized in that: The processing module is used to transmit the control instructions to the drone node according to a preset control instruction sequence, including: Used to divide the control instruction into a plurality of control instruction fragments and set a transmission order for the control instruction fragments; The control instruction segments are transmitted according to the transmission sequence.

Images