A touch screen for a drone and a command decomposition method for the touch screen

Abstract

The application discloses a touch screen for unmanned aerial vehicle and a command decomposition method of the touch screen, and comprises the following steps: S1, standardizing task semantic data; S2, generating a complete unmanned aerial vehicle task command set; S3, generating an initial population solution according to the complete unmanned aerial vehicle task command set; S4, optimizing the initial population solution based on a Pudu optimization algorithm to generate an optimal task decomposition scheme; S5, generating an unmanned aerial vehicle executable subtask set; S6, collecting feedback data in a task execution process; S7, dynamically adjusting the task decomposition scheme by using the collected task execution feedback data, and when the feedback data indicates that there is an obstacle or deviation in the subtask execution, the Pudu optimization algorithm and a fuzzy logic reasoning module are called again to optimize the optimal task decomposition scheme to generate a new unmanned aerial vehicle executable subtask set. The application can dynamically respond to changes in a task scene, and has higher flexibility and execution efficiency in the execution of a multi-target task.

Description

Technical Field

[0001] This invention relates to the field of touch screen technology for drones, and more particularly to a touch screen for drones and a method for decomposing the instructions of the touch screen. Background Technology

[0002] As a crucial interface for human-computer interaction, the quality of the parsing and decomposition of input commands on a drone touchscreen directly determines the drone's mission execution performance. Currently, most drone touchscreen command parsing technologies rely on traditional syntax parsing and rule matching methods. While these methods are applicable to simple and explicit commands, they fall short when faced with uncertainties and ambiguities in user input. For example, user errors, ambiguous command expressions, or incomplete input can cause the system to struggle to accurately understand the user's intent, leading to mission parsing errors. Furthermore, existing command parsing technologies often lack the ability to semantically complete contextual information, resulting in some inputs not being effectively utilized by the system.

[0003] In terms of task decomposition, most existing technologies adopt static task decomposition strategies, which decompose complex tasks into several sub-tasks through predefined rules. Existing methods are relatively effective in handling low-complexity tasks, but they are prone to getting stuck in local optima and lack a global perspective when dealing with complex task scenarios where UAVs need to adapt dynamically. Traditional task decomposition methods also often ignore the dynamic nature of task execution priorities and resource allocation, resulting in a lack of flexibility and execution efficiency in task decomposition schemes. In addition, some optimization algorithms have problems such as slow convergence speed and poor adaptability when solving task decomposition problems, making it difficult to meet the requirements of real-time performance.

[0004] In summary, existing technologies for UAV touchscreen command parsing and task decomposition have the following significant shortcomings: parsing techniques cannot effectively handle uncertain inputs and contextual semantic completion; task decomposition methods lack global optimization capabilities and cannot dynamically adapt to complex scenarios; and traditional optimization algorithms are insufficient in terms of task decomposition efficiency and result quality. These problems directly limit the application effectiveness of UAVs in multi-target, dynamic task scenarios, and there is an urgent need for a new method that combines intelligent optimization algorithms with fuzzy logic reasoning to overcome the limitations of existing technologies. Summary of the Invention

[0005] One objective of this invention is to provide a touchscreen for unmanned aerial vehicles (UAVs) and a method for decomposing instructions from the touchscreen. This invention can dynamically respond to changes in the task scenario and exhibits higher flexibility and execution efficiency in the execution of multi-target tasks.

[0006] A method for decomposing instructions on a touchscreen for a drone according to an embodiment of the present invention includes the following steps:

[0007] S1. Receive the task instructions input by the user through the drone's touchscreen, convert the input task instructions into task semantic data for the drone, and perform standardized processing on the task semantic data;

[0008] S2. Use the fuzzy logic reasoning module to perform fuzzy analysis on the standardized task semantic data, and correct and supplement the uncertain information in the task semantic data according to the preset fuzzy rules to generate a complete set of UAV mission instructions.

[0009] S3. Initialize the population for the elk optimization algorithm, set the initial elk population size, population structure and fitness function, and generate the initial population solution based on the complete set of UAV mission instructions;

[0010] S4. Optimize the initial population solution based on the elk optimization algorithm to generate the optimal task decomposition scheme;

[0011] S5. Based on the optimal task decomposition scheme, the complete set of UAV task instructions is decomposed into multiple executable subtasks, and the executable subtasks are prioritized and resources are allocated to generate a set of executable UAV subtasks.

[0012] S6. Transmit the set of executable sub-tasks of the UAV to the UAV execution module, monitor the execution status of the sub-tasks in real time, and collect feedback data during the task execution process;

[0013] S7. Utilize the collected task execution feedback data to dynamically adjust the task decomposition scheme. When the feedback data indicates that there are obstacles or deviations in the execution of sub-tasks, call the elk optimization algorithm and fuzzy logic reasoning module again to optimize the optimal task decomposition scheme and generate a new set of executable sub-tasks for the UAV.

[0014] Optionally, step S1 includes:

[0015] S11. Receive task commands input by the user via the drone's touchscreen. input The input content can be an explicit instruction or a vague description;

[0016] S12. Transfer the task instruction I input Transform into mission semantic data for UAVs D semantic The task semantics are generated based on the context of the input task instructions and include the following parameters:

[0017] Unmanned aerial vehicle (UAV) mission target T goal This indicates the specific operational objective that the drone needs to accomplish;

[0018] Unmanned Aerial Vehicle Mission Area A region This indicates the geographical area within which the drone needs to perform its mission;

[0019] Unmanned aerial vehicle (UAV) mission constraints C constraint These include time limits for task execution, energy consumption limits, and path obstacle limits;

[0020] S13. Based on the preset mission parameter range, target the UAV mission T. goal To express in a formatted way, the UAV mission area A region Perform geographic coordinate system transformation to generate standardized geographic location information A. region,norm Constraints C for unmanned aerial vehicle (UAV) missions constraint Constraint parameters are analyzed to transform fuzzy restrictions into defined numerical ranges, generating standardized UAV mission constraints C. constraint,norm And combine them to generate a complete task semantic dataset D for UAVs. semantic,norm .

[0021] Optionally, step S2 includes:

[0022] S21. Perform semantic fuzzification analysis on the fuzzy or incomplete parts of the UAV mission semantic data, using the fuzzy membership function μ. T (x) represents the adaptability of the UAV mission objective, using the fuzzy membership function μ. A Fuzzy analysis is performed on the UAV mission area (x, y) to indicate whether a coordinate point (x, y) within the area belongs to the mission area, using the fuzzy membership function μ. C (z) The constraints of the UAV mission are represented in a fuzzy manner, where z is the constraint value, reflecting the tightness of the mission constraints;

[0023] S22. Targeting the UAV mission objective T goal,norm Based on the input semantics and contextual information, the task objective is completed:

[0024]

[0025] Among them, T i Complete the candidate options for the task objective, where i∈N, N is the set of candidate tasks, and μ T (T i ) represents the membership value of the task objective, indicating that T i Adaptability, w i d represents the task priority weight. i The relevance distance of the context information is smaller, indicating a better match between the task objective and the context. α is an adjustment parameter used to balance the weights of membership degree and context matching degree.

[0026] For drone mission area A region,norm The range of the region to be completed based on fuzzy reasoning:

[0027] Areg i on,comp l e t e =∪ j∈M [μ A (x j ,y j )·ψ(x j ,y j )];

[0028] Among them, (x j ,y j Let be the coordinates of a point within the region, j∈M, where M is the set of candidate region points, and μ A (x j ,y j ψ(x) represents the membership value of a coordinate point, indicating whether the point belongs to the target region. j ,y j ) is the completion factor, defined based on context information as:

[0029]

[0030] Where r represents the distance threshold between the reference point and the current point, and β is the expansion speed of the control area;

[0031] Regarding the constraints of drone mission C constraint,norm New constraint completion values ​​are generated using fuzzy reasoning:

[0032] C constraint,complete =∫ z∈L μ C (z)·g(z)dz;

[0033] Where z is the value of the constraint, L is the domain of the constraint, and μ C (z) represents the membership value of the constraint, indicating the fitness of z. g(z) is the completion function, which is dynamically adjusted based on the environmental parameters of the task execution and is defined as follows:

[0034]

[0035] Where z0 is the current optimal value of the constraint, k is the steepness of the function, and γ is the complement strength coefficient;

[0036] S23. Based on the semantically completed UAV mission objective T goal,complete UAV mission area A region,complete And drone mission constraints C constraint,complete Generate a complete set of UAV mission instructions D instruction ;

[0037] S24. Deblur the UAV mission instruction set and output the complete deblurred UAV mission instruction set.

[0038] Optionally, step S24 includes:

[0039] S241. Defuzzify the semantic description of the UAV mission objective, and select the best semantic description of the mission objective using the maximum value method of the membership function:

[0040]

[0041] Among them, T goal,final The final task objective after deblurring;

[0042] S242. Deblur the UAV mission area and determine the center range of the mission area based on the optimal path planning algorithm within the fuzzy area:

[0043]

[0044] Among them, (x k ,y k Let μ be the candidate coordinates of the center point of the region, k∈K, where K is the candidate set of center points. A (x j ,y j P represents the membership degree of a coordinate point within the region, indicating its suitability for the task region. optimal This represents the set of optimal path center points for the defuzzified region.

[0045] S243. Defuzzify the constraints of the UAV mission and use the maximum membership degree method of the constraints to clarify the resource and time allocation scheme:

[0046]

[0047] Where z is a candidate value of the constraint, L is the domain of the constraint, and C constraint,final The final constraint values ​​after deblurring include time allocation and resource allocation;

[0048] S244. Based on the deblurred UAV mission objective T goal,final Task area center range P optimal and task constraints C constraint,final Generate a complete set of drone mission instructions:

[0049] D instruction,complete ={T goal,final ,P optimal C constraint,final}

[0050] Optionally, step S4 includes:

[0051] S41. Based on the complete set of UAV mission instructions D instruction,complete Initialize the population, where each individual represents a drone mission decomposition scheme;

[0052] Define population size N population The total number of task decomposition schemes that can be generated is N, which divides the population into several families, with each family containing N individuals. family The number of leaders is N. leader The leader represents a high-priority task decomposition plan;

[0053] Define the fitness function f fitness Evaluate the performance of the task decomposition scheme in UAV missions:

[0054] f fitness (x)=w1·f priority (x)+w2·f resource (x)+w3·f time (x);

[0055] Where x represents the task decomposition scheme, including the task objective, task area, and task constraints, and f priority (x) represents the rationality of task priority allocation in the task decomposition scheme, f resource (x) represents the efficiency of resource allocation, f time (x) represents the rationality of task time allocation, where w1, w2, and w3 are weight parameters that are dynamically adjusted according to task requirements;

[0056] S42. Generate an optimized drone task decomposition scheme based on the collaborative behavior of the leader and followers of the elk herd, and assign a task to the leader L of each herd. i Using the fitness value f of the task decomposition scheme fitness (L i Determine their influence; the leader plan represents the current optimal task decomposition strategy for each family's followers F. j Update the task breakdown scheme:

[0057]

[0058] in, For the task decomposition scheme of the followers in generation t, The task decomposition scheme for the leader in generation t reflects the current optimal instruction decomposition method. λ is the step size parameter, controlling the adjustment range of the task decomposition scheme. A new set of candidate UAV task decomposition schemes S is generated by updating this scheme. candidate ;

[0059] S43. Generate new task decomposition schemes based on the interaction behavior between leaders and followers, optimize the task instruction decomposition of drones, and in each family, based on the leader L i and followers F j The interaction generates a new task decomposition scheme x new :

[0060]

[0061] Where, x new This represents the newly generated task decomposition scheme, where η1 is the interaction factor, representing the degree of innovation of the task scheme;

[0062] The newly generated task decomposition scheme is optimized based on the actual operational needs of the UAV and added to the candidate task decomposition scheme set S. candidate ;

[0063] S44. Select a set of candidate task decomposition schemes S based on the specific requirements of the UAV mission. candidate Select the optimal solution with the highest fitness:

[0064]

[0065] Where, x optimal The optimal task decomposition scheme includes task objective priority, resource allocation, and path planning. Candidate schemes are selected based on fitness values, and the selected scheme is suitable for the current task scenario of the UAV.

[0066] S45. Decompose the optimal task into schemes x optimal The output is sent to the UAV mission execution module to guide the UAV to perform operations according to the decomposed mission plan.

[0067] Optionally, step S5 includes:

[0068] S51. Based on the optimal task decomposition scheme x optimal For the complete set of UAV mission instructions D instruction,complete The task is decomposed by extracting the task objective, task area, and task constraints from the optimal task decomposition scheme. The task objective is then broken down into several independent sub-objectives, which are further divided according to their priority and area scope. Each sub-objective... Includes specific task operations, execution areas, and constraints, generating a set of multiple executable subtasks:

[0069]

[0070] S52. Prioritize the set of executable subtasks and process high-priority subtasks first:

[0071]

[0072] in, For the i-th subtask, This represents the degree of membership in the subtask objective, indicating its suitability. Indicates the urgency of the subtask. This indicates the degree of dependence of a subtask on other tasks. w4, w5, and w6 are priority ranking weights that are dynamically adjusted according to task requirements.

[0073] S53. Allocate resources to the set of executable subtasks, calculate the resource allocation scheme based on the current resource status of the UAV, and allocate specific resources to each subtask based on the calculation results:

[0074]

[0075] in, To assign to subtasks Resources, R available ρ represents the total amount of resources currently available to the drone. i For subtasks The resource requirement weights are determined by task complexity and area range, where n is the total number of subtasks, and the current resource status includes power, flight time, and payload capacity.

[0076] S54. Integrate the priority ranking and resource allocation results into a set of executable subtasks for the UAV, D. subtasks :

[0077]

[0078] Each subtask includes a task objective, priority, and resource allocation plan.

[0079] A touchscreen for drones includes an internally embedded memory, a processor, and a computer program stored in the memory and executable on the processor. The processor, when executing the computer program, implements a method for decomposing instructions for the touchscreen.

[0080] The beneficial effects of this invention are:

[0081] (1) This invention introduces the elk optimization algorithm, which applies the estrus, calving and selection mechanisms of elk group behavior to the optimization of UAV task decomposition. Compared with traditional optimization algorithms, the elk optimization algorithm can better balance the ability of global search and local search in the process of population initialization, individual update and solution selection, and avoid getting trapped in local optima. During the estrus stage, it uses the behavior of leaders and followers to generate high fitness solutions. During the calving stage, it generates innovative solutions through interaction. During the selection stage, it selects the optimal solution through global evaluation, so that the task decomposition achieves the global optimal effect in terms of priority, resource allocation and path planning.

[0082] (2) This invention effectively addresses the fuzziness and uncertainty issues in UAV touchscreen input through a fuzzy logic reasoning module. By constructing fuzzy membership functions, fuzzy reasoning rules, and semantic completion mechanisms, the task objectives, task regions, and constraints are dynamically adjusted and completed. In the fuzzification of the task region, the precise task range is calculated through fuzzy membership functions and region completion factors, ensuring the completeness and accuracy of task parsing.

[0083] (3) This invention prioritizes and allocates resources to the set of executable subtasks generated by the optimal task decomposition scheme by combining the dynamic characteristics of UAV tasks, forming a set of executable UAV subtasks. The priority ranking method comprehensively considers the adaptability of task objectives, urgency and task dependence, and realizes real-time optimization of task priorities by dynamically adjusting weights. The resource allocation method calculates the resource allocation scheme in combination with the real-time status of the UAV to ensure the efficiency of task execution. Compared with the traditional static task decomposition method, this invention can dynamically respond to changes in task scenarios and shows higher flexibility and execution efficiency in the execution of multi-objective tasks. Attached Figure Description

[0084] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0085] Figure 1 This is a flowchart of a touch screen for unmanned aerial vehicles and a method for decomposing instructions from the touch screen, as proposed in this invention. Detailed Implementation

[0086] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0087] refer to Figure 1 A method for decomposing instructions on a touchscreen for a drone includes the following steps:

[0088] S1. Receive the task instructions input by the user through the drone's touchscreen, convert the input task instructions into task semantic data for the drone, and perform standardized processing on the task semantic data;

[0089] S2. Use the fuzzy logic reasoning module to perform fuzzy analysis on the standardized task semantic data, and correct and supplement the uncertain information in the task semantic data according to the preset fuzzy rules to generate a complete set of UAV mission instructions.

[0090] S3. Initialize the population for the elk optimization algorithm, set the initial elk population size, population structure and fitness function, and generate the initial population solution based on the complete set of UAV mission instructions;

[0091] S4. Optimize the initial population solution based on the elk optimization algorithm to generate the optimal task decomposition scheme;

[0092] S5. Based on the optimal task decomposition scheme, the complete set of UAV task instructions is decomposed into multiple executable subtasks, and the executable subtasks are prioritized and resources are allocated to generate a set of executable UAV subtasks.

[0093] S6. Transmit the set of executable sub-tasks of the UAV to the UAV execution module, monitor the execution status of the sub-tasks in real time, and collect feedback data during the task execution process;

[0094] S7. Utilize the collected task execution feedback data to dynamically adjust the task decomposition scheme. When the feedback data indicates that there are obstacles or deviations in the execution of sub-tasks, call the elk optimization algorithm and fuzzy logic reasoning module again to optimize the optimal task decomposition scheme and generate a new set of executable sub-tasks for the UAV.

[0095] In this embodiment, step S1 includes:

[0096] S11. Receive task commands input by the user via the drone's touchscreen. input The input content can be an explicit instruction or a vague description;

[0097] S12. Transfer task instruction I input Transform into mission semantic data for UAVs D semantic The task semantics are generated based on the context of the input task instructions and include the following parameters:

[0098] Unmanned aerial vehicle (UAV) mission target T goal This indicates the specific operational objective that the drone needs to accomplish;

[0099] Unmanned Aerial Vehicle Mission Area A region This indicates the geographical area within which the drone needs to perform its mission;

[0100] Unmanned aerial vehicle (UAV) mission constraints C constraint These include time limits for task execution, energy consumption limits, and path obstacle limits;

[0101] S13. Based on the preset mission parameter range, target the UAV mission T. goal To express in a formatted way, the UAV mission area A region Perform geographic coordinate system transformation to generate standardized geographic location information A. region,norm Constraints C for unmanned aerial vehicle (UAV) missions constraint Constraint parameters are analyzed to transform fuzzy restrictions into defined numerical ranges, generating standardized UAV mission constraints C. constraint,norm And combine them to generate a complete task semantic dataset D for UAVs. semantic,norm .

[0102] In this embodiment, step S2 includes:

[0103] S21. Perform semantic fuzzification analysis on the fuzzy or incomplete parts of the UAV mission semantic data, using the fuzzy membership function μ. T (x) represents the adaptability of the UAV mission objective, using the fuzzy membership function μ. A Fuzzy analysis is performed on the UAV mission area (x, y) to indicate whether a coordinate point (x, y) within the area belongs to the mission area, using the fuzzy membership function μ. C (z) The constraints of the UAV mission are represented in a fuzzy manner, where z is the constraint value, reflecting the tightness of the mission constraints;

[0104] S22. Targeting the UAV mission objective T goal,norm Based on the input semantics and contextual information, the task objective is completed:

[0105]

[0106] Among them, T i Complete the candidate options for the task objective, where i∈N, N is the set of candidate tasks, and μ T (T i ) represents the membership value of the task objective, indicating that T i Adaptability, w i d represents the task priority weight. i The relevance distance of the context information is smaller, indicating a better match between the task objective and the context. α is an adjustment parameter used to balance the weights of membership degree and context matching degree.

[0107] For drone mission area A region,norm The range of the region to be completed based on fuzzy reasoning:

[0108] Aregion,complete =∪ j∈M [μ A (x j ,y j )·ψ(x j ,y j )];

[0109] Among them, (x j ,y j Let be the coordinates of a point within the region, j∈M, where M is the set of candidate region points, and μ A (x j ,y j ψ(x) represents the membership value of a coordinate point, indicating whether the point belongs to the target region. j ,y j ) is the completion factor, defined based on context information as:

[0110]

[0111] Where r represents the distance threshold between the reference point and the current point, and β is the expansion speed of the control area;

[0112] Regarding the constraints of drone mission C constraint,norm New constraint completion values ​​are generated using fuzzy reasoning:

[0113] C constraint,complete =∫ z∈L μ C (z)·g(z)dz;

[0114] Where z is the value of the constraint, L is the domain of the constraint, and μ C (z) represents the membership value of the constraint, indicating the fitness of z. g(z) is the completion function, which is dynamically adjusted based on the environmental parameters of the task execution and is defined as follows:

[0115]

[0116] Where z0 is the current optimal value of the constraint, k is the steepness of the function, and γ is the complement strength coefficient;

[0117] S23. Based on the semantically completed UAV mission objective T goal,complete UAV mission area A region,complete And drone mission constraints C constraint,complete Generate a complete set of UAV mission instructions D instruction ;

[0118] S24. Deblur the UAV mission instruction set and output the complete deblurred UAV mission instruction set.

[0119] In this embodiment, step S24 includes:

[0120] S241. Defuzzify the semantic description of the UAV mission objective, and select the best semantic description of the mission objective using the maximum value method of the membership function:

[0121]

[0122] Among them, T goal,final The final task objective after deblurring;

[0123] S242. Deblur the UAV mission area and determine the center range of the mission area based on the optimal path planning algorithm within the fuzzy area:

[0124]

[0125] Among them, (x k ,y k Let μ be the candidate coordinates of the center point of the region, k∈K, where K is the candidate set of center points. A (x j ,y j P represents the membership degree of a coordinate point within the region, indicating its suitability for the task region. optimal This represents the set of optimal path center points for the defuzzified region.

[0126] S243. Defuzzify the constraints of the UAV mission and use the maximum membership degree method of the constraints to clarify the resource and time allocation scheme:

[0127]

[0128] Where z is a candidate value of the constraint, L is the domain of the constraint, and C constraint,final The final constraint values ​​after deblurring include time allocation and resource allocation;

[0129] S244. Based on the deblurred UAV mission objective T goal,final Task area center range P optimal and task constraints C constraint,final Generate a complete set of drone mission instructions:

[0130] D instruction,complete ={T goal,final ,P optimal C constraint,final}

[0131] In this embodiment, step S4 includes:

[0132] S41. Based on the complete set of UAV mission instructions Dinstruction,complete Initialize the population, where each individual represents a drone mission decomposition scheme;

[0133] Define population size N population The total number of task decomposition schemes that can be generated is N, which divides the population into several families, with each family containing N individuals. family The number of leaders is N. leader The leader represents a high-priority task decomposition plan;

[0134] Define the fitness function f fitness Evaluate the performance of the task decomposition scheme in UAV missions:

[0135] f fitness (x)=w1·f priority (x)+w2·f resource (x)+w3·f time (x);

[0136] Where x represents the task decomposition scheme, including the task objective, task area, and task constraints, and f priority (x) represents the rationality of task priority allocation in the task decomposition scheme, f resource (x) represents the efficiency of resource allocation, f time (x) represents the rationality of task time allocation, where w1, w2, and w3 are weight parameters that are dynamically adjusted according to task requirements;

[0137] S42. Generate an optimized drone task decomposition scheme based on the collaborative behavior of the leader and followers of the elk herd, and assign a task to the leader L of each herd. i Using the fitness value f of the task decomposition scheme fitness (L i Determine their influence; the leader plan represents the current optimal task decomposition strategy for each family's followers F. j Update the task breakdown scheme:

[0138]

[0139] in, For the task decomposition scheme of the followers in generation t, The task decomposition scheme for the leader in generation t reflects the current optimal instruction decomposition method. λ is the step size parameter, controlling the adjustment range of the task decomposition scheme. A new set of candidate UAV task decomposition schemes S is generated by updating this scheme. candidate ;

[0140] S43. Generate new task decomposition schemes based on the interaction behavior between leaders and followers, optimize the task instruction decomposition of drones, and in each family, based on the leader Li and followers F j The interaction generates a new task decomposition scheme x new :

[0141]

[0142] Where, x new This represents the newly generated task decomposition scheme, where η1 is the interaction factor, representing the degree of innovation of the task scheme;

[0143] The newly generated task decomposition scheme is optimized based on the actual operational needs of the UAV and added to the candidate task decomposition scheme set S. candidate ;

[0144] S44. Select a set of candidate task decomposition schemes S based on the specific requirements of the UAV mission. candidate Select the optimal solution with the highest fitness:

[0145]

[0146] Where, x optimal The optimal task decomposition scheme includes task objective priority, resource allocation, and path planning. Candidate schemes are selected based on fitness values, and the selected scheme is suitable for the current task scenario of the UAV.

[0147] S45. Decompose the optimal task into schemes x optimal The output is sent to the UAV mission execution module to guide the UAV to perform operations according to the decomposed mission plan.

[0148] In this embodiment, step S5 includes:

[0149] S51. Based on the optimal task decomposition scheme x optimal For the complete set of UAV mission instructions D instruction,complete The task is decomposed by extracting the task objective, task area, and task constraints from the optimal task decomposition scheme. The task objective is then broken down into several independent sub-objectives, which are further divided according to their priority and area scope. Each sub-objective... Includes specific task operations, execution areas, and constraints, generating a set of multiple executable subtasks:

[0150]

[0151] S52. Prioritize the set of executable subtasks and process high-priority subtasks first:

[0152]

[0153] in, For the i-th subtask, This represents the degree of membership in the subtask objective, indicating its suitability. Indicates the urgency of the subtask. This indicates the degree of dependence of a subtask on other tasks. w4, w5, and w6 are priority ranking weights that are dynamically adjusted according to task requirements.

[0154] S53. Allocate resources to the set of executable subtasks, calculate the resource allocation scheme based on the current resource status of the UAV, and allocate specific resources to each subtask based on the calculation results:

[0155]

[0156] in, To assign to subtasks Resources, R available ρ represents the total amount of resources currently available to the drone. i For subtasks The resource requirement weights are determined by task complexity and area range, where n is the total number of subtasks, and the current resource status includes power, flight time, and payload capacity.

[0157] S54. Integrate the priority ranking and resource allocation results into a set of executable subtasks for the UAV, D. subtasks :

[0158]

[0159] Each subtask includes a task objective, priority, and resource allocation plan.

[0160] A touchscreen for drones includes an internally embedded memory, a processor, and a computer program stored in the memory and executable on the processor. The feature is that the processor executes the computer program to implement an instruction decomposition method for the touchscreen for drones.

[0161] Example 1:

[0162] In an example, at 3 PM on August 15, 2024, an earthquake caused the collapse of multiple buildings in the city center of H. The rescue team quickly deployed drones to carry out post-disaster search and rescue missions. Due to the complex on-site environment, the command center operator rapidly input instructions via a touchscreen: "Search affected areas A and B, prioritizing areas with large populations, and upload real-time photos as soon as possible." The input instructions contained vague descriptions (such as "priority" and "as soon as possible") and incomplete area definitions (such as the specific boundaries of areas A and B being unclear). The command center needed to parse the vague touchscreen input into complete mission instructions and decompose and optimize the drone mission.

[0163] At 3:05 PM, the drone received the mission instructions input from the command center via its built-in computer program on the touchscreen and began parsing them. Because the instructions contained vague terms like "priority" and "as soon as possible," the system performed semantic analysis using a fuzzy logic reasoning module.

[0164] The real-time disaster rating for Zone A is 87, and for Zone B it is 75. The system determines that Zone A should be searched first.

[0165] The requirement of "as soon as possible" is transformed into an actual time requirement through a fuzzy time membership function, and is defined as completing the search for the population gathering place in area A within 5 minutes.

[0166] The boundary between Zone A and Zone B was completed with specific coordinates using historical drone images and real-time disaster data.

[0167] At 3:08 PM, after parsing was completed, the system generated a complete set of drone mission instructions:

[0168] 1. Drone 1: Search for a densely populated area in the northern part of Area A, take photos and upload them;

[0169] 2. Drone 2: Search for densely populated areas in the southern part of Area A and drop emergency supplies;

[0170] 3. Drone 3: Real-time monitoring of the southeast area of ​​Zone B, transmitting video footage.

[0171] At 3:10 PM, the system decomposed the task instruction set based on the elk optimization algorithm.

[0172] Initialize the population: Generate 30 task decomposition schemes, each of which includes the UAV mission objective, mission area, and resource allocation.

[0173] During the mating season: The leader (current optimal solution) and followers work together to update the task objectives. Solutions with no significant fitness differences are eliminated, while solutions with high fitness enter the next stage.

[0174] The calving stage: Innovative solutions are generated through interaction. In the original solution, drone 2 was responsible for the northern part of area A, but due to unreasonable resource allocation (insufficient power to complete the task), the system updated the solution to transfer the task to drone 1.

[0175] Selection phase: The system evaluates candidate schemes and finally selects the optimal task decomposition scheme, which improves the task area coverage by 15% and the power allocation utilization rate reaches 92%.

[0176] At 3:15 PM, the drone began its mission:

[0177] Drone 1 entered the northern part of Zone A, scanned multiple locations of heat sources in the ruins, located the possible locations of trapped personnel, and took three high-resolution photos (filenames photo1.jpg, photo2.jpg, and photo3.jpg) which were then uploaded to the command center.

[0178] Drone 2 successfully delivered 5 kg of emergency supplies in the southern part of Zone A. At the same time, it detected thick smoke in the area and reported its location information to the command center in real time, suggesting adjustments to the search strategy.

[0179] Drone 3 was shooting real-time video in the southeast of Zone B, but due to signal interference, some of the footage was blurry. The system switched the task to Drone 2 and completed the video transmission through the backup channel.

[0180] After the task was completed, the command center compared the data from the method of this invention with that from the traditional task decomposition method. The results are shown in Table 1 below:

[0181] Table 1. Performance of traditional methods and the method of this invention in task execution.

[0182] index Traditional methods Method of the present invention Average task parsing time (seconds) 15 5 Task decomposition success rate 80％ 97％ Average task completion time (minutes) 35 18 Regional coverage 70％ 85％ Resource utilization rate (electricity allocation efficiency) 75％ 92％ Fuzzy command parsing success rate 60％ 94％

[0183] In a specific case, Drone 1 completed the search mission in the northern part of Area A at 3:20, accurately locating the positions of three potentially trapped people. Drone 2 completed the task of delivering supplies in the southern part of Area A. Due to interference from dense smoke, the system quickly adjusted the mission plan. Drone 3 successfully transmitted real-time images, helping the command center to understand the dynamic situation in the southeastern part of the disaster area in real time.

[0184] This embodiment demonstrates the advantages of the method of the present invention in complex task decomposition through a post-earthquake disaster relief scenario. The ability to parse fuzzy instructions improves the efficiency of UAV mission execution by nearly 50%, significantly enhances mission area coverage and resource utilization, and provides an efficient solution for UAV scheduling in complex scenarios.

[0185] This invention introduces the Père David's deer optimization algorithm, applying the estrus, calving, and selection phase mechanisms of Père David's deer group behavior to the optimization of UAV task decomposition. Compared with traditional optimization algorithms, the Père David's deer optimization algorithm can better balance global search and local search capabilities during population initialization, individual update, and solution selection, avoiding getting trapped in local optima. During the estrus phase, it utilizes the behavior of leaders and followers to generate high-fitness solutions. During the calving phase, it generates innovative solutions through interaction. During the selection phase, it selects the optimal solution through global evaluation, enabling the task decomposition to achieve globally optimal results in terms of priority, resource allocation, and path planning.

[0186] This invention effectively addresses the fuzziness and uncertainty issues in UAV touchscreen input through a fuzzy logic reasoning module. By constructing fuzzy membership functions, fuzzy reasoning rules, and semantic completion mechanisms, it dynamically adjusts and completes the task objectives, task regions, and constraints. In the fuzzification of the task region, the precise task range is calculated through fuzzy membership functions and region completion factors, ensuring the completeness and accuracy of task parsing.

[0187] This invention prioritizes and allocates resources to the set of executable subtasks generated by the optimal task decomposition scheme, taking into account the dynamic characteristics of UAV missions. This forms a set of executable UAV subtasks. The priority ranking method comprehensively considers the adaptability of the task objectives, urgency, and task dependencies, and achieves real-time optimization of task priorities by dynamically adjusting weights. The resource allocation method calculates the resource allocation scheme based on the real-time status of the UAV, ensuring the high efficiency of task execution. Compared with traditional static task decomposition methods, this invention can dynamically respond to changes in the task scenario and exhibits higher flexibility and execution efficiency in the execution of multi-objective tasks.

[0188] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for decomposing instructions on a touchscreen for a drone, characterized in that, Includes the following steps: S1. Receive the task instructions input by the user through the drone's touchscreen, convert the input task instructions into task semantic data for the drone, and perform standardized processing on the task semantic data; S2. Use the fuzzy logic reasoning module to perform fuzzy analysis on the standardized task semantic data, and correct and supplement the uncertain information in the task semantic data according to the preset fuzzy rules to generate a complete set of UAV mission instructions. S3. Initialize the population for the elk optimization algorithm, set the initial elk population size, population structure and fitness function, and generate the initial population solution based on the complete set of UAV mission instructions; S4. Optimize the initial population solution based on the elk optimization algorithm to generate the optimal task decomposition scheme; S5. Based on the optimal task decomposition scheme, the complete set of UAV task instructions is decomposed into multiple executable subtasks, and the executable subtasks are prioritized and resources are allocated to generate a set of executable UAV subtasks. S6. Transmit the set of executable sub-tasks of the UAV to the UAV execution module, monitor the execution status of the sub-tasks in real time, and collect feedback data during the task execution process; S7. The task decomposition scheme is dynamically adjusted using the collected task execution feedback data. When the feedback data indicates that there are obstacles or deviations in the execution of sub-tasks, the elk optimization algorithm and fuzzy logic reasoning module are called again to optimize the optimal task decomposition scheme and generate a new set of executable sub-tasks for the UAV. Step S2 includes: S21. Perform semantic fuzzification analysis on the fuzzy or incomplete parts of the UAV mission semantic data, using the fuzzy membership function μ. T (x) represents the adaptability of the UAV mission objective, using the fuzzy membership function μ. A Fuzzy analysis is performed on the UAV mission area (x, y) to indicate whether a coordinate point (x, y) within the area belongs to the mission area, using the fuzzy membership function μ. C (z) The constraints of the UAV mission are represented in a fuzzy manner, where z is the constraint value, reflecting the tightness of the mission constraints; S22. Targeting the UAV mission objective T goal,norm Based on the input semantics and contextual information, the task objective is completed: Among them, T i Complete the candidate options for the task objective, where i∈N, N is the set of candidate tasks, and μ T (T i ) represents the membership value of the task objective, indicating that T i Adaptability, w i d represents the task priority weight. i The relevance distance of the context information is smaller, indicating a better match between the task objective and the context. α is an adjustment parameter used to balance the weights of membership degree and context matching degree. For drone mission area A region,norm The range of the region to be completed based on fuzzy reasoning: A region,complete =∪ j∈M [m A (x j ,y j )·ψ(x j ,y j )]; Among them, (x j ,y j Let be the coordinates of a point within the region, j∈M, where M is the set of candidate region points, and μ A (x j ,y j ψ(x) represents the membership value of a coordinate point, indicating whether the point belongs to the target region. j ,y j ) is the completion factor, defined based on context information as: Where r represents the distance threshold between the reference point and the current point, and β is the expansion speed of the control area; Regarding the constraints of drone mission C constraint,norm New constraint completion values ​​are generated using fuzzy reasoning: C constraint,complete =∫ z∈L μ C (z)·g(z)dz; Where z is the value of the constraint, L is the domain of the constraint, and μ C (z) represents the membership value of the constraint, indicating the fitness of z. g(z) is the completion function, which is dynamically adjusted based on the environmental parameters of the task execution and is defined as follows: Where z0 is the current optimal value of the constraint, k is the steepness of the function, and γ is the complement strength coefficient; S23. Based on the semantically completed UAV mission objective T goal,complete UAV mission area A region,complete And drone mission constraints C constraint,complete Generate a complete set of UAV mission instructions D instruction ; S24. Deblur the UAV mission instruction set and output the complete deblurred UAV mission instruction set; Step S24 includes: S241. Defuzzify the semantic description of the UAV mission objective, and select the best semantic description of the mission objective using the maximum value method of the membership function: Among them, T goal,final The final task objective after deblurring; S242. Deblur the UAV mission area and determine the center range of the mission area based on the optimal path planning algorithm within the fuzzy area: Among them, (x k ,y k Let μ be the candidate coordinates of the center point of the region, k∈K, where K is the candidate set of center points. A (x j ,y j P represents the membership degree of a coordinate point within the region, indicating its suitability for the task region. optimal This represents the set of optimal path center points for the defuzzified region. S243. Defuzzify the constraints of the UAV mission and use the maximum membership degree method of the constraints to clarify the resource and time allocation scheme: Where z is a candidate value of the constraint, L is the domain of the constraint, and C constraint,final The final constraint values ​​after deblurring include time allocation and resource allocation; S244. Based on the deblurred UAV mission objective T goal,final Task area center range P optimal and task constraints C constraint,final Generate a complete set of drone mission instructions: D instruction,complete ={T goal,final ,P optimal ,C constraint,final }; The S4 step includes: S41. Based on the complete set of UAV mission instructions D instruction,complete Initialize the population, where each individual represents a drone mission decomposition scheme; Define population size N population The total number of task decomposition schemes that can be generated is N, which divides the population into several families, with each family containing N individuals. family The number of leaders is N. leader The leader represents a high-priority task decomposition plan; Define the fitness function f fitness Evaluate the performance of the task decomposition scheme in UAV missions: f fitness (x)=w1·f priority (x)+w2·f resource (x)+w3·f time (x); Where x represents the task decomposition scheme, including the task objective, task area, and task constraints, and f priority (x) represents the rationality of task priority allocation in the task decomposition scheme, f resource (x) represents the efficiency of resource allocation, f time (x) represents the rationality of task time allocation, where w1, w2, and w3 are weight parameters that are dynamically adjusted according to task requirements; S42. Generate an optimized drone task decomposition scheme based on the collaborative behavior of the leader and followers of the elk herd, and assign a task to the leader L of each herd. i Using the fitness value f of the task decomposition scheme fitness (L i Determine their influence; the leader plan represents the current optimal task decomposition strategy for each family's followers F. j Update the task breakdown scheme: in, For the task decomposition scheme of the followers in generation t, The task decomposition scheme for the leader in generation t reflects the current optimal instruction decomposition method. λ is the step size parameter, controlling the adjustment range of the task decomposition scheme. A new set of candidate UAV task decomposition schemes S is generated by updating this scheme. candidate ; S43. Generate new task decomposition schemes based on the interaction behavior between leaders and followers, optimize the task instruction decomposition of drones, and in each family, based on the leader L i and followers F j The interaction generates a new task decomposition scheme x new : Where, x new This represents the newly generated task decomposition scheme, where η1 is the interaction factor, representing the degree of innovation of the task scheme; The newly generated task decomposition scheme is optimized based on the actual operational needs of the UAV and added to the candidate task decomposition scheme set S. candidate ; S44. Select a set of candidate task decomposition schemes S based on the specific requirements of the UAV mission. candidate Select the optimal solution with the highest fitness: Where, x optimal The optimal task decomposition scheme includes task objective priority, resource allocation, and path planning. Candidate schemes are selected based on fitness values, and the selected scheme is suitable for the current task scenario of the UAV. S45. Decompose the optimal task into schemes x optimal The output is sent to the UAV mission execution module to guide the UAV to perform operations according to the decomposed mission plan.

2. The method for decomposing instructions on a touchscreen for a drone according to claim 1, characterized in that, Step S1 includes: S11. Receive task commands input by the user via the drone's touchscreen. input The input content can be an explicit instruction or a vague description; S12. Transfer the task instruction I input Transform into mission semantic data for UAVs D semantic The task semantics are generated based on the context of the input task instructions and include the following parameters: Unmanned aerial vehicle (UAV) mission target T goal This indicates the specific operational objective that the drone needs to accomplish; Unmanned Aerial Vehicle Mission Area A region This indicates the geographical area within which the drone needs to perform its mission; Unmanned aerial vehicle (UAV) mission constraints C constraint These include time limits for task execution, energy consumption limits, and path obstacle limits; S13. Based on the preset mission parameter range, target the UAV mission T. goal To express in a formatted way, the UAV mission area A region Perform geographic coordinate system transformation to generate standardized geographic location information A. region,norm Constraints C for unmanned aerial vehicle (UAV) missions constraint Constraint parameters are analyzed to transform fuzzy restrictions into defined numerical ranges, generating standardized UAV mission constraints C. constraint,norm And combine them to generate a complete task semantic dataset D for UAVs. semantic,norm .

3. The method for decomposing instructions on a touchscreen for a drone according to claim 1, characterized in that, Step S5 includes: S51. Based on the optimal task decomposition scheme x optimal For the complete set of UAV mission instructions D instruction,complete The task is decomposed by extracting the task objective, task area, and task constraints from the optimal task decomposition scheme. The task objective is then broken down into several independent sub-objectives, which are further divided according to their priority and area scope. Each sub-objective... Includes specific task operations, execution areas, and constraints, generating a set of multiple executable subtasks: S52. Prioritize the set of executable subtasks and process high-priority subtasks first: in, For the i-th subtask, This represents the degree of membership in the subtask objective, indicating its suitability. Indicates the urgency of the subtask. This indicates the degree of dependence of a subtask on other tasks. w4, w5, and w6 are priority ranking weights that are dynamically adjusted according to task requirements. S53. Allocate resources to the set of executable subtasks, calculate the resource allocation scheme based on the current resource status of the UAV, and allocate specific resources to each subtask based on the calculation results: in, To assign to subtasks Resources, R available ρ represents the total amount of resources currently available to the drone. i For subtasks The resource requirement weights are determined by task complexity and area range, where n is the total number of subtasks, and the current resource status includes power, flight time, and payload capacity. S54. Integrate the priority ranking and resource allocation results into a set of executable subtasks for the UAV, D. subtasks : Each subtask includes a task objective, priority, and resource allocation plan.

4. A touchscreen for a drone, comprising an internally embedded memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the instruction decomposition method for a touch screen for a drone as described in any one of claims 1-3.

Images