Intelligent control method and system for unmanned aerial vehicle for environmental monitoring task

Abstract

The application discloses a UAV intelligent control method and system for an environmental monitoring task, and relates to the technical field of UAVs, and comprises the following steps: acquiring at least one task environment state of an environmental monitoring task execution area; determining a state transition matrix between multiple task environment states of the environmental monitoring task execution area; evaluating the execution adaptation degree of a task parameter setting state of a UAV and all task environment states; constructing a real-time environment change matrix; predicting the next environment state of the environmental monitoring task execution area; and evaluating whether the UAV can meet the next task execution requirement, if yes, the UAV continues to execute the environmental monitoring task, and if not, the current task UAV returns to base. The application has the advantages that the pre-intelligent regulation and control of the UAV is carried out based on real-time monitoring results in the process of the environmental monitoring task of the UAV, the monitoring accuracy of the environmental monitoring task is effectively improved, and the damage caused by improper operation of the UAV is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle intelligent control method and system for environmental monitoring tasks. BACKGROUND

[0002] Environmental monitoring mainly collects environmental data of the to-be-measured region through various monitoring devices, comprehensively analyzes the collected environmental data, finds out possible environmental problems in the region, makes timely early warning, and takes measures to reduce or avoid the occurrence and expansion of environmental hazards. With the development of unmanned aerial vehicle technology, the unmanned aerial vehicle has the advantages of strong maneuverability and convenient environmental monitoring. The combination of unmanned aerial vehicles and environmental monitoring devices can effectively improve the efficiency and convenience of environmental monitoring, and also provides the possibility for environmental monitoring in complex terrain and rarely visited areas, realizing large-scale and dead-angle-free environmental monitoring. Therefore, it is of great significance to monitor the environment in a large range and without dead angle by combining unmanned aerial vehicles with environmental monitoring devices.

[0003] The setting of the unmanned aerial vehicle operation parameters including proportional parameters (P), integral parameters (I), and derivative parameters (D) has a close relationship with the task execution capability of the unmanned aerial vehicle. The task execution capability of the unmanned aerial vehicle in different task environments, including its stability, response speed, and precision, is greatly affected by the setting of its operation parameters. In the prior art, due to the lack of environmental prediction analysis of the environmental monitoring task execution area, the unmanned aerial vehicle for executing the environmental monitoring task can only respond after the environment changes. This control method has a delay in regulation and control, which easily leads to the execution of the task by the unmanned aerial vehicle with unsuitable operation parameters, on the one hand, which easily causes damage to the unmanned aerial vehicle, and on the other hand, which causes monitoring errors of the environmental monitoring task. SUMMARY

[0004] To solve the above technical problems, the present application provides an unmanned aerial vehicle intelligent control method and system for environmental monitoring tasks, which solves the problem of the prior art that the unmanned aerial vehicle for executing the environmental monitoring task can only respond after the environment changes due to the lack of environmental prediction analysis of the environmental monitoring task execution area. This control method has a delay in regulation and control, which easily leads to the execution of the task by the unmanned aerial vehicle with unsuitable operation parameters, on the one hand, which easily causes damage to the unmanned aerial vehicle, and on the other hand, which causes monitoring errors of the environmental monitoring task.

[0005] To achieve the above purposes, the technical scheme adopted by the present application is as follows:

[0006] An unmanned aerial vehicle intelligent control method for environmental monitoring tasks, comprising:

[0007] Based on the task execution log of the unmanned aerial vehicle, at least one task environment state of the environment monitoring task execution area is obtained;

[0008] A state transition matrix between a plurality of task environment states of the environment monitoring task execution area is determined;

[0009] The task parameter setting state of the unmanned aerial vehicle is obtained, and the execution adaptation degree of the task parameter setting state of the unmanned aerial vehicle to all task environment states is evaluated;

[0010] Based on the environment data of the environment monitoring task execution area collected by the unmanned aerial vehicle in real time, a real-time environment change matrix is constructed;

[0011] Based on the real-time environment change matrix and the state transition matrix between the task environment states, the next environment state of the environment monitoring task execution area is predicted;

[0012] Based on the next environment state of the environment monitoring task execution area and the execution adaptation degree of the task parameter setting state of the unmanned aerial vehicle to all task parameter setting states of the unmanned aerial vehicle, whether the unmanned aerial vehicle can meet the next task execution requirement is evaluated. If yes, the unmanned aerial vehicle continues to execute the environment monitoring task; if no, the current task unmanned aerial vehicle returns, and the task parameters of the unmanned aerial vehicle for executing the next task are set based on the next environment state of the environment monitoring task execution area.

[0013] Preferably, the determination of the state transition matrix between a plurality of task environment states of the environment monitoring task execution area specifically comprises:

[0014] Based on the task execution log of the unmanned aerial vehicle, a standard environment parameter array corresponding to each task environment state of the environment monitoring task execution area is determined , , wherein, is the standard environment parameter array of the oth task environment state, is the standard environment parameter value of the i th environment parameter of the oth task environment state, is the total number of environment parameters; based on the task execution log of the unmanned aerial vehicle, the change trend of the standard environment parameter when the task environment state in the environment monitoring task execution area changes is determined, and the environment parameter change trend array of the environment monitoring task execution area is constructed , , wherein, is the environment parameter change trend array when the oth task environment state changes to the pth task environment state, is the environment parameter change trend standard environment parameter value of the i th environment parameter when the oth task environment state changes to the pth task environment state;

[0015] Based on the corresponding standard environment parameter array of each task environment state of the environment monitoring task execution area and the environment parameter change trend array of the environment monitoring task execution area, a state transition matrix between the task environment states is constructed , .

[0016] Preferably, the evaluation of the execution adaptation degree of the task parameter setting state of the unmanned aerial vehicle to all task environment states specifically includes:

[0017] Based on the task parameter setting state of the unmanned aerial vehicle, the task execution performance of the unmanned aerial vehicle is determined, which at least includes response speed, stability, running accuracy and maneuverability;

[0018] Based on the task execution experience of the unmanned aerial vehicle, the task execution performance requirement of the unmanned aerial vehicle in each task environment state is determined;

[0019] If all task execution performances of the unmanned aerial vehicle are higher than the task execution performance requirement of the unmanned aerial vehicle in the task environment state, the execution adaptation degree of the unmanned aerial vehicle to the task environment state is 1; if all task execution performances of the unmanned aerial vehicle are not higher than the task execution performance requirement of the unmanned aerial vehicle in the task environment state, the calculation formula of the execution adaptation degree of the unmanned aerial vehicle to the task environment state is:

[0020]

[0021] Among them, is the execution adaptation degree of the unmanned aerial vehicle to the oth task environment state in the state that all task execution performances of the unmanned aerial vehicle are not higher than the task execution performance requirement of the unmanned aerial vehicle in the oth task environment state, is the total number of task execution performances, is the performance value of the jth task execution performance of the unmanned aerial vehicle, is the jth task execution performance requirement in the oth task environment state, is the minimum value function.

[0022] Preferably, the construction of the real-time environment change matrix based on the environment data of the environment monitoring task execution area collected by the unmanned aerial vehicle in real time specifically includes:

[0023] Real-time collection of environment data of the task execution area, construction of an environment parameter array of the task execution area , Among them, is the environment parameter of the ith environment parameter of the task execution area; based on the real-time collected environment data of the task execution area, the change trend of each environment parameter of the task execution area is calculated, and a change trend array of the task execution area is constructed , wherein, is the change trend of the i-th environmental parameter of the task execution area;

[0024] constructing a real-time environmental change matrix based on the environmental parameter array of the task execution area and the change trend array of the task execution area , . Preferably, the predicting the next environmental state of the environmental monitoring task execution area based on the real-time environmental change matrix and the state transition matrix between the task environmental states specifically comprises:

[0025] the environmental parameter array of the task execution area the standard environmental parameter array of each task environmental state calculating the vector distance for comparison to determine the reference environmental state of the task execution area;

[0026] calculating the vector distance of the environmental parameter change trend array and the change trend array of the task execution area when the reference environmental state changes to each task environmental state;

[0027] calculating the probability of the next change of the task execution area to each task environmental state based on the conversion probability formula;

[0028] The conversion probability formula is specifically:

[0029] wherein, is the probability of the next change of the task execution area to the p-th task environmental state, is the vector distance of the environmental parameter change trend array and the change trend array of the task execution area when the reference environmental state changes to the p-th task environmental state, is the maximum value of all vector distances, is the minimum value of all vector distances, is the total number of task environmental states.

[0030] Preferably, the evaluating whether the UAV can meet the next task execution requirement based on the next environmental state of the environmental monitoring task execution area and the task parameter setting state of the UAV and the execution adaptation degree of all UAVs' task parameter setting states specifically comprises:

[0031] calculating the next task execution capability index of the UAV based on the probability of the next change of the task execution area to each task environmental state and the execution adaptation degree of the task parameter setting state of the UAV and all task environmental states using the prediction fitting formula;

[0032] determining whether the next task execution capability index of the UAV is greater than a preset value, if yes, determining that the UAV can meet the next task execution requirement, if no, determining that the UAV cannot meet the next task execution requirement; wherein the prediction fitting formula is specifically:

[0033]

[0034] the next task execution capability index of the UAV, is the execution adaptation degree of the UAV and the pth task environment state. Preferably, the next environment state of the environment monitoring task execution area is set to determine the task parameters of the UAV for executing the next task, specifically including:

[0035] determining the task execution performance of the UAV in the limited task parameter setting mode;

[0036] and calculating the next task execution capability index of the UAV in each task parameter setting mode, screening out the task parameter setting mode corresponding to the maximum task execution capability index, and setting the task parameters of the UAV for executing the next task.

[0037] Further, a UAV intelligent control system for an environment monitoring task is proposed, which is used to realize the UAV intelligent control method for an environment monitoring task as described above, comprising:

[0038] a task environment module, the task environment module is used to obtain at least one task environment state of the environment monitoring task execution area based on the task execution log of the UAV, and determine the state transition matrix between the multiple task environment states of the environment monitoring task execution area;

[0039] a mode adaptation analysis module, the mode adaptation analysis module is electrically connected with the task environment module, and the mode adaptation analysis module is used to obtain the task parameter setting state of the UAV, and evaluate the execution adaptation degree of the task parameter setting state of the UAV and all task environment states;

[0040] a change analysis module, the change analysis module is electrically connected with the task environment module, the change analysis module is used to construct a real-time environment change matrix based on the environment data of the environment monitoring task execution area collected by the UAV in real time, and predict the next environment state of the environment monitoring task execution area based on the real-time environment change matrix and the state transition matrix between the task environment states;

[0041] The intelligent control module is electrically connected with the change analysis module and the mode adaptation analysis module, and is used for performing adaptation degree based on the next environmental state of the environmental monitoring task execution area and the task parameter setting state of the unmanned aerial vehicle and the task parameter setting state of all unmanned aerial vehicles, evaluating whether the unmanned aerial vehicle can meet the next task execution requirement, if yes, the unmanned aerial vehicle continues to execute the environmental monitoring task, if not, the current task unmanned aerial vehicle returns, and the task parameters of the unmanned aerial vehicle for executing the next task are set based on the next environmental state of the environmental monitoring task execution area.

[0042] Compared with the prior art, the beneficial effects of the present application are that: the present application proposes an unmanned aerial vehicle intelligent control scheme for environmental monitoring tasks, through real-time environmental change analysis during unmanned aerial vehicle task execution, intelligent prediction analysis of the execution ability of the unmanned aerial vehicle in the next environmental monitoring task is carried out in combination with the parameter setting state of the unmanned aerial vehicle, and intelligent control of the unmanned aerial vehicle to continue to execute the task or return is carried out based on the analysis result, in this way, the adaptation degree of the unmanned aerial vehicle to the environment of the execution area during execution of the environmental monitoring task is greatly guaranteed, pre-intelligent regulation and control of the unmanned aerial vehicle is realized, damage is effectively reduced, and the monitoring accuracy of the environmental monitoring task is improved. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 A flow chart of the unmanned aerial vehicle intelligent control method for environmental monitoring tasks proposed in the present scheme is shown in the figure;

[0044] Figure 2 A flow chart of the method for determining the state transition matrix in the present scheme is shown in the figure;

[0045] Figure 3 A flow chart of the method for evaluating the execution adaptation degree of the unmanned aerial vehicle in the present scheme is shown in the figure;

[0046] Figure 4 A flow chart of the method for constructing the real-time environmental change matrix in the present scheme is shown in the figure;

[0047] Figure 5 A flow chart of the method for predicting the next environmental state of the environmental monitoring task execution area in the present scheme is shown in the figure;

[0048] Figure 6 A flow chart of the method for evaluating whether the unmanned aerial vehicle can meet the next task execution requirement in the present scheme is shown in the figure;

[0049] Figure 7 A flow chart of the method for setting the task parameters of the unmanned aerial vehicle for executing the next task in the present scheme is shown in the figure. DETAILED DESCRIPTION

[0050] The following description is used to disclose the present application to enable a person skilled in the art to implement the present application. The preferred embodiments in the following description are only as examples, and other obvious modifications can be conceived by those skilled in the art.

[0051] Referring to Figure 1 As shown in the figure, an unmanned aerial vehicle intelligent control method for an environmental monitoring task comprises:

[0052] Based on the task execution log of the unmanned aerial vehicle, at least one task environment state of the environmental monitoring task execution area is obtained; a state transition matrix between multiple task environment states of the environmental monitoring task execution area is determined;

[0053] The task parameter setting state of the unmanned aerial vehicle is obtained, and the execution adaptation degree of the task parameter setting state of the unmanned aerial vehicle and all task environment states is evaluated;

[0054] Based on the environmental data of the environmental monitoring task execution area collected by the unmanned aerial vehicle in real time, a real-time environmental change matrix is constructed;

[0055] Based on the real-time environmental change matrix and the state transition matrix between the task environment states, the next environmental state of the environmental monitoring task execution area is predicted;

[0056] Based on the next environmental state of the environmental monitoring task execution area and the execution adaptation degree of the task parameter setting state of the unmanned aerial vehicle and all task parameter setting states of the unmanned aerial vehicle, it is evaluated whether the unmanned aerial vehicle can meet the next task execution requirement, if yes, the unmanned aerial vehicle continues to execute the environmental monitoring task, if not, the current task unmanned aerial vehicle returns, and based on the next environmental state of the environmental monitoring task execution area, the task parameters of the unmanned aerial vehicle for executing the next task are set.

[0057] The present scheme analyzes the real-time environmental change during the task execution of the unmanned aerial vehicle, and intelligently predicts by combining the parameter setting state of the unmanned aerial vehicle, so as to evaluate the execution capability of the unmanned aerial vehicle in the subsequent environmental monitoring task. According to the analysis result, the intelligent control of the unmanned aerial vehicle is realized, and it is determined whether to continue to execute the task or to return. By this way, the adaptation degree of the unmanned aerial vehicle to the environmental area during the execution of the environmental monitoring task can be greatly improved, the pre-intelligent regulation of the unmanned aerial vehicle is achieved, the damage is effectively reduced, and the monitoring accuracy of the environmental monitoring task is improved.

[0058] Referring to Figure 2 As shown in the figure, the state transition matrix between multiple task environment states of the environmental monitoring task execution area comprises:

[0059] Based on the task execution log of the unmanned aerial vehicle, the standard environmental parameter array corresponding to each task environment state of the environmental monitoring task execution area is determined , wherein, is a standard environment parameter array of the oth task environment state, is a standard environment parameter value of the i th environment parameter of the oth task environment state, is a total number of environment parameters, wherein the standard environment parameter value can be a specific standard value, for example, obtained by averaging a plurality of environment parameters of the task environment state, or a standard value range interval representing the change range of the environment parameter under the task environment state; based on the task execution log of the unmanned aerial vehicle, the change trend of the standard environment parameter when the task environment state in the environment monitoring task execution area changes is determined, and an environment parameter change trend array of the environment monitoring task execution area is formed , wherein, is an environment parameter change trend array when the oth task environment state changes to the pth task environment state, is an environment parameter change trend standard environment parameter value of the i th environment parameter when the oth task environment state changes to the pth task environment state;

[0060] Based on the standard environment parameter array corresponding to each task environment state of the environment monitoring task execution area and the environment parameter change trend array of the environment monitoring task execution area, a state transition matrix between task environment states is constructed , Since the environment parameter will change when the environment state changes, for example, when the weather changes from sunny to rainy, the environment parameter will change significantly, including the decrease of air pressure, the decrease of temperature, the increase of humidity, and the decrease of light, in the present scheme, the state transition matrix is constructed, the standard environment parameter array of the task environment state is taken as the judgment basis of the current environment state, the environment parameter change trend array is taken as the parameter change attribute when the environment state changes, and the state transition matrix between the task environment states is constructed by combining the two, which is used to reflect the environment state change.

[0061] Referring to Figure 3 , the execution adaptation degree of the task parameter setting state of the unmanned aerial vehicle to all task environment states specifically includes:

[0062] Based on the task parameter setting state of the unmanned aerial vehicle, the task execution performance of the unmanned aerial vehicle is determined, and the task execution performance of the unmanned aerial vehicle at least includes: response speed, stability, running accuracy and maneuverability;

[0063] Based on the task execution experience of the unmanned aerial vehicle, the task execution performance requirement of the unmanned aerial vehicle in each task environment state is determined;

[0064] If all the task execution performances of the UAV are higher than the task execution performance requirements of the UAV in the task environment state, the execution adaptation degree of the UAV and the task environment state is 1.

[0065] If all the task execution performances of the UAV are not higher than the task execution performance requirements of the UAV in the task environment state, the calculation formula of the execution adaptation degree of the UAV and the task environment state is:

[0066] wherein, is the execution adaptation degree of the UAV and the oth task environment state in the state that all the task execution performances of the UAV are not higher than the task execution performance requirements of the UAV in the oth task environment state, is the total number of task execution performance types, is the performance value of the jth task execution performance of the UAV, is the jth task execution performance requirement in the oth task environment state, is a minimum value function.

[0067] It can be understood that different parameter settings of the UAV will affect the task execution performance of the UAV. For example, the adjustment of the proportional parameter (P) can affect the degree of response of the UAV to the control input. If the P value is too high, the UAV may react too violently, and if the P value is too low, the UAV may respond slowly. The adjustment of the integral parameter (I) can affect the cumulative response of the UAV under long-time control input. If the I value is too high, the UAV may produce a large overshoot when approaching the target, and if the I value is too low, the UAV may not be able to accurately reach the target. The adjustment of the derivative parameter (D) can affect the reaction speed of the UAV to the change of the control input. If the D value is too high, the UAV may produce oscillation in a rapidly changing environment, and if the D value is too low, the UAV may not be able to respond to the change of the environment in time. Different environment states require the UAV to have different performances. For example, in the wind and rain state, the UAV needs to have higher stability. In the present scheme, the task execution ability of the UAV in different parameter setting modes in different environment states is evaluated by comprehensively evaluating the task execution adaptation degree of the UAV based on the UAV performance in multiple different parameter setting modes and the task execution performance requirements in different environment states.

[0068] Referring to FIG. 1, Figure 4 based on the environment data of the task execution area collected by the UAV in real time, the real-time environment change matrix is constructed. Specifically, the real-time environment change matrix is constructed by:

[0069] collecting the environment data of the task execution area in real time to construct the environment parameter array of the task execution area , wherein, Let i be the environmental parameter of the i-th environmental parameter in the task execution area; based on the real-time collected environmental data of the task execution area, calculate the changing trend of each environmental parameter in the task execution area, and construct a changing trend array of the task execution area. , ,in, The changing trend of the i-th environmental parameter in the task execution area;

[0070] Construct a real-time environmental change matrix based on the environmental parameter array and the change trend array of the task execution area. , .

[0071] Reference Figure 5 As shown, based on the real-time environmental change matrix and the state transition matrix between the task environment states, the predicted environmental state of the execution area for the environmental monitoring task includes:

[0072] Environmental parameter array based on task execution region Standard environment parameter array for each task environment state Calculate and compare vector distances to determine the baseline environmental state of the task execution area;

[0073] Calculate the vector distance between the array of environmental parameter change trends and the array of task execution region change trends as the baseline environment state changes to each task environment state;

[0074] Based on the transformation probability formula, calculate the probability that the next change in the task execution area will be each task environment state;

[0075] The specific formula for the transition probability is as follows:

[0076] In the formula, Let p be the probability that the next change in the task execution area will be the p-th task environment state. This is the vector distance between the array of environmental parameter change trends and the array of task execution region change trends as the baseline environment state changes to the p-th task environment state. It is the maximum value among all vector distances. It is the minimum value among all vector distances. This represents the total number of types of task environment states.

[0077] The trend of change can be represented by the slope of the tangent line on the curve of the parameter changing over time. In a preferred embodiment, the trend of change can also be represented by the slope of the linear regression equation of the parameter over time.

[0078] In the scheme, the vector distance is calculated between the parameter change trend of the actual environment and the standard change trend in the standard state conversion process, the smaller the vector distance, the closer the parameter change trend of the actual environment and the standard change trend in the standard state conversion process, the greater the probability of the next change of the state, based on this, the conversion probability formula is used to convert the vector distance between the parameter change trend of the actual environment and the standard change trend in the standard state conversion process into the probability of the next change of the task execution area to the task environment state.

[0079] Referring to Figure 6 As shown in the figure, the execution adaptation degree of the next environment state of the environment monitoring task execution area and the task parameter setting state of the unmanned aerial vehicle with all task parameter setting states of the unmanned aerial vehicle is performed to evaluate whether the unmanned aerial vehicle can meet the next task execution requirement, which specifically includes:

[0080] Based on the probability of the next change of each task environment state of the task execution area and the execution adaptation degree of the task parameter setting state of the unmanned aerial vehicle with all task environment states, the prediction fitting formula is used to calculate the next task execution capability index of the unmanned aerial vehicle; it is judged whether the next task execution capability index of the unmanned aerial vehicle is greater than the preset value, if yes, it is determined that the unmanned aerial vehicle can meet the next task execution requirement, if not, it is determined that the unmanned aerial vehicle cannot meet the next task execution requirement;

[0081] The prediction fitting formula is specifically:

[0082]

[0083] The next task execution capability index of the unmanned aerial vehicle, is the execution adaptation degree of the unmanned aerial vehicle and the pth task environment state. Referring to Figure 7 As shown in the figure, based on the next environment state of the environment monitoring task execution area, the task parameters of the unmanned aerial vehicle performing the next task are set, which specifically includes:

[0084] The task execution performance of the unmanned aerial vehicle in the limited task parameter setting mode is determined;

[0085] The next task execution capability index of the unmanned aerial vehicle in each task parameter setting mode is calculated, the task parameter setting mode corresponding to the maximum task execution capability index is screened out, and the task parameters of the unmanned aerial vehicle performing the next task are set.

[0086] Because the unmanned aerial vehicle needs to have different performances in different environment states, for example, in the wind and rain state, the unmanned aerial vehicle needs to have higher stability, so when the current parameter setting state of the unmanned aerial vehicle does not meet the next environment requirement of the unmanned aerial vehicle, the running state of the unmanned aerial vehicle needs to be adjusted in time.

[0087] Further, based on the same inventive concept as the above unmanned aerial vehicle intelligent control method for environmental monitoring tasks, the present scheme also proposes an unmanned aerial vehicle intelligent control system for environmental monitoring tasks, comprising:

[0088] A task environment module, the task environment module is used to obtain at least one task environment state of the environmental monitoring task execution area based on the task execution log of the unmanned aerial vehicle, and determine the state transition matrix between multiple task environment states of the environmental monitoring task execution area;

[0089] A mode adaptation analysis module, the mode adaptation analysis module is electrically connected with the task environment module, and the mode adaptation analysis module is used to obtain the task parameter setting state of the unmanned aerial vehicle, and evaluate the execution adaptation degree of the task parameter setting state of the unmanned aerial vehicle and all task environment states;

[0090] A change analysis module, the change analysis module is electrically connected with the task environment module, and the change analysis module is used to construct a real-time environmental change matrix based on the environmental data of the environmental monitoring task execution area collected by the unmanned aerial vehicle in real time, and predict the next environmental state of the environmental monitoring task execution area based on the real-time environmental change matrix and the state transition matrix between the task environment states;

[0091] An intelligent control module, the intelligent control module is electrically connected with the change analysis module and the mode adaptation analysis module, and the intelligent control module is used to evaluate whether the unmanned aerial vehicle can meet the next task execution demand based on the next environmental state of the environmental monitoring task execution area and the execution adaptation degree of the task parameter setting state of the unmanned aerial vehicle and all task parameter setting states of the unmanned aerial vehicle, if yes, the unmanned aerial vehicle continues to execute the environmental monitoring task, if not, the current task unmanned aerial vehicle returns, and sets the task parameters of the unmanned aerial vehicle for executing the next task based on the next environmental state of the environmental monitoring task execution area.

[0092] The working process of the above system is as follows: step one: the task environment module obtains at least one task environment state of the environmental monitoring task execution area based on the task execution log of the unmanned aerial vehicle, and determines the state transition matrix between multiple task environment states of the environmental monitoring task execution area;

[0093] Step two: the mode adaptation analysis module is used to obtain the task parameter setting state of the unmanned aerial vehicle, and evaluate the execution adaptation degree of the task parameter setting state of the unmanned aerial vehicle and all task environment states;

[0094] Step three: the change analysis module constructs a real-time environmental change matrix based on the environmental data of the environmental monitoring task execution area collected by the unmanned aerial vehicle in real time, and predicts the next environmental state of the environmental monitoring task execution area based on the real-time environmental change matrix and the state transition matrix between the task environment states;

[0095] Step four: the intelligent control module performs the adaptability of the next environment state of the environment monitoring task execution area and the task parameter setting state of the unmanned aerial vehicle with the task parameter setting state of all unmanned aerial vehicles, evaluates whether the unmanned aerial vehicle can meet the next task execution requirement, if yes, the unmanned aerial vehicle continues to execute the environment monitoring task, if not, the current task unmanned aerial vehicle returns, and based on the next environment state of the environment monitoring task execution area, the task parameters of the unmanned aerial vehicle for executing the next task are set.

[0096] In summary, the advantages of the present application are that the real-time monitoring results in the process of the unmanned aerial vehicle environment monitoring task are used for the pre-intelligent control of the unmanned aerial vehicle, the monitoring accuracy of the environment monitoring task is effectively improved, and the damage caused by the improper operation of the unmanned aerial vehicle is reduced.

[0097] The basic principles, main features and advantages of the present application are shown and described above. It should be understood by those skilled in the art that the present application is not limited by the above examples, and the above examples and descriptions in the specification are only the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection required by the present application is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent control of unmanned aerial vehicles (UAVs) for environmental monitoring tasks, characterized in that, include: Based on the mission execution logs of the UAV, obtain at least one mission environmental status of the environmental monitoring mission execution area; Determine the state transition matrix between multiple environmental states in the environmental monitoring task execution area. , ,in, This is the standard environment parameter array for the o-th task's environment state. This is an array of environmental parameter change trends as the 0th task environment state changes to the pth task environment state; the task parameter setting state of the UAV is obtained, and the execution adaptability of the UAV's task parameter setting state with all task environment states is evaluated; Real-time acquisition of environmental data in the task execution area to construct an array of environmental parameters for the task execution area. , ,in, The environment parameter of the i-th environment parameter of the task execution region; Based on real-time collected environmental data of the task execution area, the changing trend of each environmental parameter in the task execution area is calculated, and an array of changing trends of the task execution area is constructed. , ,in, The changing trend of the i-th environmental parameter in the task execution area; Construct a real-time environmental change matrix based on the environmental parameter array and the change trend array of the task execution area. , ; An array of environmental parameters based on the task execution region Standard environment parameter array for each task environment state Calculate the vector distance for comparison to determine the baseline environmental state of the task execution area; calculate the vector distance between the environmental parameter change trend array and the task execution area change trend array when the baseline environmental state changes to each task environmental state; Based on the transition probability formula, the probability of the next change in the task execution area becoming each task environment state is calculated. Based on the probability of the next change in the task execution area becoming each task environment state and the adaptation of the UAV's task parameter settings to the task parameter settings of all UAVs, the system assesses whether the UAV can meet the requirements of the next task execution. If so, the UAV continues to perform the environmental monitoring task; otherwise, the current task UAV returns to base, and the task parameters of the UAV performing the next task are set based on the next environmental state of the environmental monitoring task execution area. The transition probability formula is as follows: In the formula, Let p be the probability that the next change in the task execution area will be the p-th task environment state. This is the vector distance between the array of environmental parameter change trends and the array of task execution region change trends as the baseline environment state changes to the p-th task environment state. It is the maximum value among all vector distances. It is the minimum value among all vector distances. This represents the total number of types of task environment states.

2. The intelligent control method for unmanned aerial vehicles (UAVs) for environmental monitoring tasks according to claim 1, characterized in that, The state transition matrix between multiple task environmental states in the environmental monitoring task execution area specifically includes: Based on the drone's mission execution logs, determine the standard environmental parameter array corresponding to the environmental state of each mission in the environmental monitoring mission execution area. , ,in, Let i be the standard environmental parameter value for the i-th environmental parameter under the o-th task environment state. This represents the total number of environmental parameters. Based on the UAV's mission logs, the changing trends of standard environmental parameters are determined when the environmental state in the environmental monitoring mission area changes, and these trends are compiled into an array representing the environmental parameter change trends in the environmental monitoring mission area. , ,in, The standard environmental parameter value represents the trend of environmental parameter change of the i-th environmental parameter when the environmental state of the 0-th task changes to the environmental state of the p-th task. Based on the standard environmental parameter array corresponding to each task environmental state in the environmental monitoring task execution area and the environmental parameter change trend array in the environmental monitoring task execution area, a state transition matrix between task environmental states is constructed. , .

3. The intelligent control method for unmanned aerial vehicles (UAVs) used for environmental monitoring tasks according to claim 2, characterized in that, The evaluation of the UAV's mission parameter setting state and the execution adaptability of all mission environment states specifically includes: determining the UAV's mission execution performance based on the UAV's mission parameter setting state, wherein the UAV's mission execution performance includes at least: response speed, stability, operational accuracy, and maneuverability; Based on the mission execution experience of UAVs, determine the mission execution performance requirements of UAVs in each mission environment. If the performance of all tasks performed by the drone is higher than the performance requirements of the drone in the task environment, then the performance fit between the drone and the task environment is 1. If the performance of all tasks performed by the drone is not higher than the performance requirements of the drone under the task environment, then the formula for calculating the drone's performance adaptability to the task environment is: in, To determine the performance adaptability of the UAV to the o-th task environment state, assuming that the performance of all tasks performed by the human-machine interface is not higher than the performance requirements of the UAV in the o-th task environment state. The total number of types of task execution performance. Let be the performance value of the human-machine interface for executing the j-th task. The performance requirements for executing task j in the 0th task environment state are as follows: This is a function that takes the minimum value.

4. The intelligent control method for unmanned aerial vehicles (UAVs) used for environmental monitoring tasks according to claim 3, characterized in that, The next changes in the task execution area are the probability of each task environment state and the execution adaptability of the UAV's task parameter setting state with the task parameter setting state of all UAVs. The evaluation of whether the UAV can meet the next task execution requirements specifically includes: based on the probability of the next changes in the task execution area being each task environment state and the execution adaptability of the UAV's task parameter setting state with the task environment state of all task environments, a prediction fitting formula is used to calculate the UAV's next task execution capability index. Determine whether the drone's next task execution capability index is greater than the preset value. If it is, then the drone can meet the next task execution requirements; otherwise, the drone cannot meet the next task execution requirements. The prediction fitting formula is specifically as follows: The drone's next mission execution capability indicators The execution adaptability of the UAV to the p-th mission environment state.

5. The intelligent control method for unmanned aerial vehicles (UAVs) used for environmental monitoring tasks according to claim 4, characterized in that, The process of setting the mission parameters for the UAV to perform the next mission based on the subsequent environmental state of the environmental monitoring task execution area specifically includes: Determine the mission performance of the UAV under limited mission parameter setting modes; It calculates the drone's next task execution capability index under each task parameter setting mode, filters out the task parameter setting mode corresponding to the maximum value of the task execution capability index, and sets the task parameters of the drone to perform the next task.

6. An intelligent control system for unmanned aerial vehicles (UAVs) used for environmental monitoring tasks, characterized in that: The intelligent control method for an unmanned aerial vehicle (UAV) for an environmental monitoring task as described in any one of claims 1-5 includes: The task environment module is used to obtain at least one task environment state of the environmental monitoring task execution area based on the UAV's task execution log, and to determine the state transition matrix between multiple task environment states of the environmental monitoring task execution area. The mode adaptation analysis module is electrically connected to the task environment module. The mode adaptation analysis module is used to obtain the task parameter setting status of the UAV and evaluate the execution adaptation degree between the UAV's task parameter setting status and all task environment statuses. The change analysis module is electrically connected to the task environment module. The change analysis module is used to construct a real-time environmental change matrix based on the environmental data of the environmental monitoring task execution area collected in real time by the UAV, and to predict the next environmental state of the environmental monitoring task execution area based on the state transition matrix between the real-time environmental change matrix and the task environment state. The intelligent control module is electrically connected to the change analysis module and the mode adaptation analysis module. The intelligent control module is used to evaluate whether the UAV can meet the requirements of the next task execution based on the next environmental state of the environmental monitoring task execution area and the execution adaptation of the UAV's task parameter setting state with the task parameter setting states of all UAVs. If yes, the UAV continues to execute the environmental monitoring task; if not, the UAV currently performing the task returns to home. Based on the next environmental state of the environmental monitoring task execution area, the module sets the task parameters of the UAV that will perform the next task.

Images