Unmanned aerial vehicle flight path maintaining and autonomous positioning method in communication decline scene

Abstract

The invention discloses an unmanned aerial vehicle track maintenance and autonomous positioning method in a communication decline scene, and relates to the technical field of navigation maintenance positioning, and the method comprises the steps: carrying out the signal intensity monitoring and smoothing of signal quality and decline information collected in real time, carrying out the decline trend prediction through a long-short-term memory network, and outputting a signal decline report; in combination with multi-unmanned aerial vehicle sensor data, local sensor data is processed in real time through edge calculation, and shared information is fused through particle filtering; a cooperative positioning algorithm and a distributed positioning algorithm are used to correct the shared information of the multiple unmanned aerial vehicles and output the precision for autonomous positioning; and adjusting the unmanned aerial vehicle to an energy-saving flight mode by using an energy consumption model in combination with the signal recession report and the optimal path. According to the method, the flight path of the unmanned aerial vehicle is optimized by adopting deep reinforcement learning and the game theory, and adaptive flight path adjustment is realized in combination with a model prediction control algorithm, so that the unmanned aerial vehicle can dynamically avoid a low-signal area, and flight stability is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of navigation and positioning, and in particular to a method for maintaining the flight path and autonomous positioning of an unmanned aerial vehicle (UAV) in a communication degradation scenario. Background Art

[0002] In recent years, UAV technology has developed rapidly, and various technologies have penetrated into many fields such as aerial inspection, monitoring, and search and rescue. With the increasingly wide application of UAVs in complex environments, the problems of communication signal degradation and positioning error have gradually emerged, becoming important factors affecting the efficient operation of UAVs. Especially in the case of signal degradation or high-risk environments, UAVs become unstable, prone to unstable flight paths and positioning errors, affecting the task execution efficiency. To solve this problem, although a variety of flight path planning and positioning optimization methods have been proposed, using different algorithms such as Rapidly-Exploring Random Trees (RRT) and Particle Filter algorithms, to improve the autonomous navigation ability of UAVs through multi-sensor fusion.

[0003] However, the existing technologies still have some deficiencies in practical applications. Traditional flight path planning methods often ignore the real-time change of communication quality, resulting in the inability of UAVs to adjust the flight path in time when entering the signal degradation area. Moreover, the existing positioning correction technologies mostly rely on single-sensor data and cannot make full use of the advantages of group cooperation, easily resulting in large positioning errors. Therefore, how to ensure the stability of the communication link and the controllability of the flight path while improving the positioning accuracy remains a difficult point in current technologies. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for maintaining the flight path and autonomous positioning of an unmanned aerial vehicle in a communication degradation scenario to solve the problem of maintaining a stable flight path and high-precision positioning of the UAV in a communication degradation environment.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for maintaining the flight path and autonomous positioning of an unmanned aerial vehicle in a communication degradation scenario, which includes monitoring and smoothing the signal strength of the real-time collected signal quality and degradation information, predicting the degradation trend using a Long Short-Term Memory (LSTM) network, and outputting a signal degradation report;

[0008] Combining multi-UAV sensor data, real-time processing of local sensor data through edge computing, and fusing shared information using a particle filter;

[0009] Using collaborative positioning and distributed positioning algorithms to correct the shared information of multiple UAVs and output accurate autonomous positioning;

[0010] Adopt adaptive control and collaborative path optimization to adjust the UAV flight route and output the optimal path;

[0011] Combine the signal decay report with the optimal path, and use the energy consumption model to adjust the UAV to the energy-saving flight mode.

[0012] As a preferred solution of the UAV trajectory maintenance and autonomous positioning method in the communication decay scenario described in the present invention, wherein: for the signal quality and decay information collected in real time, perform signal strength monitoring and smoothing processing, and use the long short-term memory network for decay trend prediction to output a signal decay report. The specific steps are as follows:

[0013] The signal quality and decay information collected in real time includes signal strength, signal attenuation, signal error rate, signal delay, signal packet loss rate, signal spectrum, and temperature and humidity;

[0014] For the signal strength monitoring and smoothing processing to output a signal decay report, the specific steps are as follows:

[0015] Screen out abnormal information by monitoring the signal quality and decay information collected in real time;

[0016] Perform smoothing processing on the abnormal information to output signal decay abnormal data;

[0017] Use the long short-term memory network for decay trend prediction to output a signal abnormal decay report.

[0018] As a preferred solution of the UAV trajectory maintenance and autonomous positioning method in the communication decay scenario described in the present invention, wherein: combine the multi-UAV sensor data, process the local sensor data in real time through edge computing, and use particle filtering to fuse the shared information. The specific steps are as follows:

[0019] Based on the signal abnormal report, the UAV processes the local sensor data in real time through edge computing to generate local state information;

[0020] Combine the local state information of multiple UAVs and use particle filtering to output shared information.

[0021] As a preferred solution of the UAV trajectory maintenance and autonomous positioning method in the communication decay scenario described in the present invention, wherein: use collaborative positioning and distributed positioning algorithms to correct the shared information of multiple UAVs and output accurate autonomous positioning. The specific steps are as follows:

[0022] Use blockchain for the shared information to output corrected shared information;

[0023] Use deep reinforcement learning and game theory to optimize the UAV flight path and dynamically adjust the flight strategy;

[0024] Autonomously position by adjusting the output accuracy of the real-time UAV positioning through the sensor fusion error correction method.

[0025] As a preferred solution of the UAV trajectory maintenance and autonomous positioning method in the communication degradation scenario described in the present invention, wherein: the adaptive control and collaborative path optimization are adopted to adjust the UAV flight route and output the optimal path. The specific steps are as follows.

[0026] Apply UAV dynamics to input the real-time data of the UAV and output the mathematical calculation for UAV path optimization.

[0027] Adopt the model predictive control algorithm to combine constraints such as path deviation, energy consumption, and obstacles to optimize the UAV flight path.

[0028] Utilize game theory to continuously optimize path planning, combine blockchain shared data for dynamic adjustment, and autonomously output the optimal path for multiple UAVs.

[0029] Combine real-time sensor data and apply the extended Kalman filter to perform real-time correction on the optimal path and output the real-time accuracy flight path.

[0030] Apply adaptive control and combine real-time signal anomaly reports for adaptive adjustment to output the optimal path.

[0031] As a preferred solution of the UAV trajectory maintenance and autonomous positioning method in the communication degradation scenario described in the present invention, wherein: combine the signal degradation report with the optimal path, and apply the energy consumption model to adjust the UAV to the energy-saving flight mode. The specific steps are as follows.

[0032] Combine the signal degradation report with environmental data and use the long short-term memory network for fusion analysis to output the basic information for planning.

[0033] Apply game theory and the model predictive control algorithm to combine the cooperative flight of multiple UAVs and the influence of signal degradation to generate the optimal path.

[0034] Construct an energy consumption model, combine the optimal path and the signal degradation report, and turn on the energy-saving flight mode.

[0035] As a preferred solution of the UAV trajectory maintenance and autonomous positioning method in the communication degradation scenario described in the present invention, wherein: apply game theory and the model predictive control algorithm to combine the cooperative flight of multiple UAVs and the influence of signal degradation to generate the optimal path. The specific steps are as follows.

[0036] Apply game theory to conduct a game on the UAV and output the basic decision for path optimization.

[0037] Utilize the model predictive control algorithm and the signal degradation report to output the preliminary optimized path.

[0038] Combine the extended Kalman filter with the shared information accuracy correction path to output the optimal path.

[0039] As a preferred solution of the method for maintaining the flight path and autonomous positioning of an unmanned aerial vehicle (UAV) in the communication degradation scenario described in the present invention, wherein: the use of deep reinforcement learning and game theory to optimize the flight path of the UAV and dynamically adjust the flight strategy, the specific steps are as follows.

[0040] Use blockchain to correct the shared data and output accurate autonomous positioning information of multiple UAVs.

[0041] Apply deep reinforcement learning to combine the flight path and environmental information of the UAV to output the flight strategy.

[0042] Apply the Nash equilibrium to combine the optimized path and signal anomaly report to optimize the flight strategy and output the flight strategy of multiple UAVs.

[0043] Utilize the dynamics, flight data, and optimized path of the UAV, and through the model predictive control algorithm, dynamically adjust the flight strategy in combination with path deviation, energy consumption, and obstacle constraints.

[0044] In a second aspect, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and wherein: when the computer program is executed by the processor, any step of the method for maintaining the flight path and autonomous positioning of an unmanned aerial vehicle in the communication degradation scenario as described in the first aspect of the present invention is implemented.

[0045] In a third aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and wherein: when the computer program is executed by the processor, any step of the method for maintaining the flight path and autonomous positioning of an unmanned aerial vehicle in the communication degradation scenario as described in the first aspect of the present invention is implemented.

[0046] The beneficial effects of the present invention are as follows: Through real-time signal monitoring and smoothing processing, combined with the particle filter and distributed cooperative positioning algorithm, the present invention improves the positioning accuracy of the UAV in the communication degradation scenario, thereby enhancing the flight path maintenance ability. In addition, deep reinforcement learning and game theory are used to optimize the flight path of the UAV, and combined with the model predictive control algorithm, an adaptive flight path adjustment is realized, enabling the UAV to dynamically avoid low-signal areas and ensuring flight stability. At the same time, the present invention applies an energy consumption model. On the premise of ensuring the optimal flight path, through the dynamic modeling of the UAV and the analysis of battery energy consumption, combined with the signal degradation report, the flight mode is adaptively adjusted to achieve energy consumption efficiency optimization. This solution not only improves the positioning accuracy and flight path control ability of the UAV under signal degradation, but also enhances the dynamic obstacle avoidance ability of the UAV, improving the reliability and endurance of task execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0048] Figure 1 It is a flowchart of the method for maintaining the UAV flight path and autonomous positioning in the communication degradation scenario in Embodiment 1.

[0049] Figure 2 It is a schematic diagram of dynamically adjusting the flight strategy in Embodiment 1. Specific Embodiments

[0050] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will provide a detailed description of the specific embodiments of the present invention with reference to the drawings in the specification.

[0051] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0052] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not all refer to the same embodiment, nor is it a separate or alternative embodiment that excludes other embodiments.

[0053] Embodiment 1, referring to Figure 1 and Figure 2 , is the first embodiment of the present invention. This embodiment provides a method for maintaining the UAV flight path and autonomous positioning in a communication degradation scenario, including the following steps:

[0054] S1. Monitor and smooth the signal strength of the real-time collected signal quality and degradation information, and use a long short-term memory network for degradation trend prediction to output a signal degradation report.

[0055] Furthermore, the real-time collected signal quality and degradation information include signal strength, signal attenuation, signal error rate, signal delay, signal packet loss rate, signal spectrum, and temperature and humidity;

[0056] It should be noted that by real-time monitoring of multiple parameters such as signal strength, signal attenuation, signal error rate, signal delay, signal packet loss rate, signal spectrum, temperature and humidity during the flight of the UAV, the health status of the communication link can be comprehensively understood, potential communication problems can be discovered in a timely manner, providing an accurate basis for subsequent flight path optimization and positioning correction, and ensuring the stable operation of the UAV in complex environments;

[0057] Screen out abnormal information by monitoring the signal quality and decay information collected in real time;

[0058] Specifically, screen by real-time monitoring of signal quality and signal decay information during the flight of the UAV, and extract abnormal data in the signal;

[0059] Perform smoothing processing on the abnormal information and output abnormal signal decay data;

[0060] Specifically, perform preliminary processing on the signal data collected in real time, use Gaussian filtering for denoising to remove random noise and high-frequency interference in the signal, improve the stability of the signal, and use Kalman filtering for trend extraction to retain the long-term change law of the signal and output abnormal signal decay data;

[0061] It should be noted that through smoothing processing, smooth and clearly trending abnormal signal decay data can be obtained, thus eliminating the influence of sporadic error data. The smoothed data provides a more reliable input for subsequent analysis and decision-making, improving robustness and accuracy;

[0062] Use a long short-term memory network for decay trend prediction and output an abnormal signal decay report;

[0063] Specifically, use a long short-term memory network to capture the long-term dependencies and change laws in the signal, predict the future signal decay trend, including changes in key indicators such as signal strength decline, error rate increase, and delay increase, and generate an abnormal signal decay report;

[0064] It should be noted that by using a long short-term memory network, the long-term trend and short-term fluctuations of signal decay can be effectively captured, the future signal decay situation can be predicted, the UAV can give early warnings of potential signal decay risks, take remedial measures in advance, and improve the overall reliability of the system;

[0065] Preferably, through real-time monitoring and processing of signal quality and decay information, the flight stability and positioning accuracy of the UAV in a communication decay scenario can be significantly improved. Through the prediction of the signal decay trend by a long short-term memory network, the path deviation caused by communication problems during flight is avoided, ensuring that the UAV can operate reliably in complex environments, significantly enhancing the robustness of the communication system, reducing the safety risks brought by signal instability, and improving the autonomous flight ability of the UAV.

[0066] S2. Combine the multi-UAV sensor data, process the local sensor data in real time through edge computing, and adopt particle filter to fuse and share information.

[0067] Furthermore, based on the signal anomaly report, the UAV processes the local sensor data in real time through edge computing, generates local state information, and outputs the shared information by using particle filter;

[0068] Specifically, the UAV processes the local sensor data in real time through edge computing, conducts data analysis and calculation to generate local state information, stores it in the local memory of the UAV, then uses particle filter to estimate the UAV state, generates high-precision local state information, takes the result of the particle filter as the shared information, and sends it to other UAVs through the communication network to output the shared information;

[0069] Preferably, edge computing reduces the need to upload data to the cloud, consumes low communication bandwidth, and can still operate stably in a signal-constrained environment. Particle filter can effectively handle the state estimation problem of nonlinear systems, improve the positioning robustness of UAVs in case of signal loss, reduce the impact of single sensor failure on positioning through multi-UAV shared information, and improve the overall reliability of the system.

[0070] S3. Apply collaborative positioning and distributed positioning algorithms to correct the shared information of multi-UAVs and output precise autonomous positioning.

[0071] Furthermore, use blockchain for the shared information to output corrected shared information;

[0072] Specifically, use the consensus mechanism to verify and upload the shared information to the chain, so that all UAVs can obtain consistent and real positioning data. Use the hash chain structure to verify whether the data has been tampered with for integrity verification, use digital signature to verify whether the source of the data is credible for source verification, and use the distributed storage of the blockchain ledger to verify whether the data is consistent with most nodes for consistency verification, and finally output the corrected shared information;

[0073] It should be noted that introducing blockchain in the UAV network makes the data consistent, improves the reliability and anti-tampering ability of the shared information, avoids positioning errors caused by transmission errors or malicious data, and improves the precision of multi-UAV collaborative positioning;

[0074] Apply deep reinforcement learning and game theory to optimize the flight path of UAVs and dynamically adjust the flight strategy;

[0075] Specifically, an intelligent flight strategy model is constructed by combining deep reinforcement learning, enabling the UAV to learn the optimal path planning scheme through trial and error in a dynamic environment. Through game theory, the cooperative relationship of the UAV swarm is analyzed, and the strategy selection of each UAV in the flight path adjustment is analyzed to form a global optimization scheme and dynamically adjust the flight strategy.

[0076] It should be noted that the long short-term memory network and game theory have a linkage. The long short-term memory network predicts the signal decay trend to trigger the game theory path optimization and generate the optimal path. The forward-looking prediction of the long short-term memory network provides real-time signal quality information for the game theory path optimization, making the path planning more adaptable.

[0077] Furthermore, blockchain is used to correct the shared data and output the accurate autonomous positioning information of multiple UAVs.

[0078] Specifically, blockchain is combined with shared data to correct the positioning error, and the credible correction and synchronization of data among multiple UAVs are carried out to ensure that the positioning information of all UAVs is consistent and to minimize the impact of communication decay on the positioning accuracy, and then output the accurate autonomous positioning information of multiple UAVs.

[0079] Apply deep reinforcement learning to combine the UAV flight path and environmental information to output the flight strategy.

[0080] Specifically, apply deep reinforcement learning, combine the flight path data and environmental information of the UAV, realize the autonomous flight decision-making of the UAV, enable it to dynamically adapt to environmental changes, and output the flight strategy.

[0081] Preferably, through deep reinforcement learning, the autonomous flight decision-making of the UAV is realized, enabling it to dynamically adapt to environmental changes, handle complex dynamic environments and optimize the flight path in real time, improving the autonomy and adaptability of the UAV. It can also dynamically adjust the strategy without human intervention, thereby improving the navigation performance of the UAV in complex environments.

[0082] Use Nash equilibrium to combine the optimized path and signal anomaly report to optimize the flight strategy and output the flight strategy of multiple UAVs.

[0083] Combining deep reinforcement learning and game theory, each UAV calculates its relative position with other UAVs, considers the signal anomaly report, and combines the use of Nash equilibrium to conduct game analysis among multiple UAVs. Each UAV adjusts its path according to the flight strategies of other UAVs to ensure that each UAV cannot obtain a better result by changing its strategy under the decisions of other UAVs, and then outputs the flight strategy of multiple UAVs.

[0084] It should be noted that by combining edge computing for local processing, particle filter for multi-UAV data fusion, blockchain for verifying and sharing information, and deep reinforcement learning for generating Nash equilibrium strategies, compared with the traditional single-UAV positioning framework, cross-UAV data trust is formed through blockchain, and group games combining particle filter and reinforcement learning are used to solve the problem of cumulative positioning errors in multi-UAV collaboration;

[0085] Preferably, the application of Nash equilibrium theory in multi-UAV systems can ensure that each UAV makes optimal decisions in cooperation with other UAVs. By analyzing the signal anomaly reports and flight paths of each UAV, the game process can optimize the flight strategies of each UAV, avoid path conflicts, and ensure flight efficiency, effectively improving the cooperative combat ability of multi-UAV systems. Especially in the case of communication decline or signal loss, it can dynamically adjust strategies to maintain the stability and safety of global flight;

[0086] It should be noted that the game formula is as follows:

[0087]

[0088] where \(A_i\) is the optimal path strategy of UAV \(i\), \(w\) ij is the collaborative influence weight of UAV \(j\) on UAV \(i\), and the value range: \(0\leq w\) ij \(\leq1\) represents the influence degree of UAV \(j\) on \(i\), \(w\) ij \( = 0\) means no influence, \(w\) ij \( = 1\) means the maximum influence, \(Q\) j is the path strategy payoff selected by UAV \(j\), \(Q\) j \(\geq0\), indicating the utility value of the path selected by UAV \(j\). The larger the value, the higher the benefit of the path selection. \(N\) is the total number of UAVs participating in the game.

[0089] Utilize UAV dynamics, flight data, and optimized paths to dynamically adjust flight strategies through model predictive control algorithms in combination with path deviation, energy consumption, and obstacle constraints;

[0090] Specifically, establish UAV dynamics using UAV dynamics characteristics, flight data, and optimized paths. Through model predictive control algorithms, combine the real-time monitoring of the positions of obstacles by sensors and use them as constraint conditions in the optimization problem to ensure that the flight path does not intersect with obstacles, dynamically adjust the flight path, and at the same time add energy consumption as a constraint. Combine the battery status of the UAV to dynamically adjust the flight strategy, enabling the UAV to follow the optimal path during flight, reduce energy waste, and lower the risk of collision, precisely control the flight behavior of the UAV, and output the dynamically adjusted flight strategy;

[0091] It should be noted that the model predictive control algorithm predicts the signal decay trend through a long short-term memory network and dynamically adjusts the flight path to make the flight track stable. It does not solely use the model predictive algorithm but combines the two to jointly adjust the flight path;

[0092] Preferably, deep reinforcement learning enables the UAV to autonomously learn the optimal path decision during the continuous exploration of the environment, improving the robustness of the flight track. Game theory modeling can further enhance the overall optimization ability of the UAV swarm. Each UAV can autonomously adjust its path when interacting with other UAVs to achieve the goal of optimal communication quality or lowest energy consumption. This method can effectively reduce the flight risk in the communication decay area and ensure the task execution efficiency of the multi-UAV system in a complex environment;

[0093] Autonomous positioning is achieved by adjusting the output accuracy of the real-time UAV positioning through the sensor fusion error correction method;

[0094] Specifically, multi-sensor fusion is used for real-time error correction. By utilizing the complementarity of different sensors, the sensor data is weighted to reduce the impact of abnormal data from a single sensor on the positioning result, thereby improving the autonomous positioning accuracy of the UAV in a communication decay environment.

[0095] S4. Adaptive control and cooperative path optimization are adopted to adjust the UAV flight route and output the optimal path.

[0096] Furthermore, the UAV dynamics is used to input the real-time UAV data to output the mathematical calculation for UAV path optimization;

[0097] Specifically, through the UAV dynamics, combined with the real-time flight data, the mathematical calculation for UAV path optimization is output, which can efficiently describe the flight performance of the UAV and make the mathematical calculation of path optimization consistent with the actual motion ability of the UAV;

[0098] The model predictive control algorithm is combined with path deviation, energy consumption, and obstacle constraints to optimize the UAV flight path;

[0099] Specifically, by combining path deviation, energy consumption, and obstacle constraints and applying the model predictive control algorithm for flight path optimization, obstacles can be effectively avoided, while maximizing energy efficiency and making real-time adjustments according to changes in the environment;

[0100] Game theory is used to continuously optimize the path planning, combined with blockchain shared data for dynamic adjustment, and the multi-UAV optimized path is autonomously output;

[0101] Specifically, game theory is used to model the states of each drone and their mutual influences as a game model. Through information sharing and cooperative control among multiple drones, conflicts are avoided and paths are optimized. During the cooperative flight of multiple drones, the flight paths of each drone are dynamically adjusted through the game theory model to output the optimized paths of each drone.

[0102] Preferably, game theory can achieve cooperation and conflict avoidance among multiple drones. By optimizing the paths of each drone through the game model, task conflicts are minimized, the group efficiency is improved, dynamic path adjustment is realized, resource waste is reduced, and the overall efficiency is enhanced.

[0103] The optimized path is corrected in real time by using the extended Kalman filter in combination with real-time sensor data to output the real-time accurate flight path.

[0104] Specifically, the sensor data of the drone is obtained in real time, and these data are used to compensate for sensor noise and measurement errors by using the extended Kalman filter to output the real-time accurate flight path.

[0105] Preferably, this solution can combine real-time sensor data to accurately correct the path, thereby improving the positioning accuracy of the drone in a dynamic environment, overcoming the errors caused by sensor noise, and ensuring that the drone can accurately correct its flight path and maintain a high-precision flight state during flight to adapt to environmental changes.

[0106] Adaptive control is used in combination with real-time signal anomaly reports for adaptive adjustment to output the real-time optimized path.

[0107] Specifically, when signal decay or anomaly is detected, the adaptive control system dynamically adjusts the flight path of the drone according to the information in the report to avoid entering the communication decay area or the low-signal area. In an abnormal communication environment, the flight path of the drone is automatically adjusted according to the real-time signal anomaly report to ensure stable communication quality and avoid the impact of the signal decay area on flight safety.

[0108] S5. Combine the signal decay report with the real-time optimized path and use the energy consumption model to adjust the drone to the energy-saving flight mode.

[0109] Furthermore, the long short-term memory network is used for fusion analysis by combining the signal decay report with environmental data to output the basic information for planning.

[0110] Specifically, the long short-term memory network is used to perform time series analysis on the collected signal decay data and environmental information, capture the long-term dependence relationship of signal changes, process the signal fluctuations caused by environmental factor changes, and output the basic information for planning. The prediction result of the long short-term memory network provides signal quality information for the energy consumption model to ensure the dynamic adaptation of the energy-saving mode.

[0111] Preferably, the subsequent path optimization and flight control using long short-term memory networks provide high-quality data support, which can effectively avoid positioning errors caused by communication decay areas, ensure that the unmanned aerial vehicle (UAV) maintains an accurate flight path during flight, and improve the safety and reliability of flight missions;

[0112] Apply game theory and model predictive control algorithms to combine multi-UAV cooperative flight and signal decay effects to generate an optimal path;

[0113] Specifically, using a game theory model, game out the best flight strategy for each UAV, apply model predictive control algorithms combined with real-time data to predict the future flight state of the UAV, and adjust the flight path according to the real-time prediction results;

[0114] Preferably, game theory can dynamically adjust the flight strategy of each UAV by considering the cooperation and competition relationships between multiple UAVs, avoiding situations of mutual interference or path conflicts. The model predictive control algorithm can calculate the optimal path in real time, ensure the coordination of each UAV during flight, and flexibly adjust the flight path according to the real-time signal decay situation;

[0115] It should be noted that applying game theory and model predictive control algorithms to combine multi-UAV cooperative flight and signal decay effects to generate an optimal path, the specific steps are as follows;

[0116] Furthermore, apply game theory to the UAV to game out the basic decision for path optimization;

[0117] Specifically, applying game theory, each UAV will consider its interaction with other UAVs and continuously adjust its decision according to the changes in its goals and environment, and output the path optimization decision;

[0118] Preferably, the application of game theory in UAV path optimization can help each UAV select the optimal flight path by analyzing the flight strategies, cooperation and competition relationships of multiple UAVs. In the communication decay scenario, game theory can consider the impact of signal quality changes on UAV flight decisions, avoid further signal quality decay caused by path selection, and the process can reduce conflicts during flight, improve flight safety and mission execution efficiency;

[0119] Use model predictive control algorithms and signal decay reports to output a preliminary optimized path;

[0120] Preferably, through the model predictive control algorithm combined with real-time signal decay reports, it can predict the dynamically changing communication environment during flight and adjust the flight path in real time, output a preliminary path optimization plan, and can make a judgment based on the future system state, effectively avoiding the UAV from entering the communication decay area, ensuring the continuity and stability during flight, and improving the adaptability of the system to environmental changes;

[0121] Combine the extended Kalman filter with the shared information precision correction path to output the optimal path;

[0122] Specifically, predict the UAV state by combining the current flight state and real-time information, compare the predicted state with the observed data, adjust the predicted state and observed data according to the uncertainty of the observation noise, correct the state, and further improve the positioning accuracy by combining the shared information and the extended Kalman for structural correction. By avoiding communication degradation areas, selecting paths with better signal quality, and considering energy consumption and obstacles, plan the flight path of the UAV to output the optimal path;

[0123] It should be noted that the extended Kalman filter improves the positioning accuracy of the UAV in complex environments through multi-source information fusion, can update the state estimation value in real time, adapt to the dynamically changing flight environment, make the flight mission continuous and stable, can handle the uncertainty in nonlinear systems, enhance the robustness of the UAV in communication degradation scenarios, and improve the limitations of the traditional Kalman filter in nonlinear systems;

[0124] Construct an energy consumption model, combine the optimal path with the signal degradation report, and turn on the energy-saving flight mode;

[0125] Specifically, calculate the energy consumption of each path segment of each UAV during flight through the energy consumption model, and associate the flight path in the signal degradation area with the energy consumption. When the energy consumption is serious, the model will automatically adjust the flight speed, altitude, etc., so that the UAV can reduce energy consumption and enter the energy-saving flight mode;

[0126] It should be noted that the energy consumption formula is as follows,

[0127] E = C1·v 2 + C2·h;

[0128] where E is the total energy consumption, representing the total energy consumed during the flight of the UAV, C1 is the energy consumption coefficient related to the flight speed v, reflecting the influence degree of the speed on the total energy consumption, v 2 is the square of the flight speed v, representing the influence of the speed on the energy consumption, C2 is the energy consumption coefficient related to the flight height h, representing the influence degree of the height on the total energy consumption, and h is the flight height, representing the height of the UAV during flight.

[0129] Preferably, signal prediction provides forward-looking input for path planning. Game theory is used to balance multi-aircraft cooperation and energy consumption constraints. The model predictive control algorithm combines with the extended Kalman filter to ensure positioning accuracy and real-time feedback. Through the mutual combination and linkage of modules, a comprehensive method for maintaining the UAV flight path and autonomous positioning is formed. A solution is formed through the time-series dependence relationship, solving the problems of unstable flight path, cumulative positioning error, and excessive energy consumption in the communication degradation scenario;

[0130] It should be noted that the long short-term memory network predicts the signal degradation trend in real time, dynamically triggers the game theory path optimization, the model predictive control combines with the real-time anomaly report, adaptively adjusts the flight path, and the extended Kalman and blockchain cooperate to correct the positioning error, forming a dynamic closed-loop linkage mechanism of "signal prediction, path decision-making, and flight path control". Through the forward-looking nature of signal prediction, the game nature of path decision-making, and the real-time nature of flight path control, the ability to solve the disconnection between signal processing and path planning and the cumulative positioning error is improved.

[0131] This embodiment also provides a computer device, which is applicable to the situation of the UAV flight path maintenance and autonomous positioning method in the communication degradation scenario, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the UAV flight path maintenance and autonomous positioning method in the communication degradation scenario proposed in the above embodiment.

[0132] This computer device can be a terminal. This computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of this computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (near field communication), or other technologies. The display screen of this computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of this computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0133] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the method for maintaining the flight path and autonomous positioning of an unmanned aerial vehicle (UAV) in a communication degradation scenario as proposed in the above embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0134] In summary, the present invention improves the positioning accuracy of the UAV in a communication degradation scenario and thus enhances the flight path maintenance ability by: real-time signal monitoring and smoothing processing, combined with a particle filter and a distributed cooperative positioning algorithm. In addition, deep reinforcement learning and game theory are used to optimize the flight path of the UAV, and combined with a model predictive control algorithm, an adaptive flight path adjustment is achieved, enabling the UAV to dynamically avoid low-signal areas and ensuring flight stability. Meanwhile, an energy consumption model is introduced in the present invention. On the premise of ensuring the optimal flight path, through UAV dynamics modeling and battery energy consumption analysis, combined with a signal degradation report, the flight mode is adaptively adjusted to achieve energy consumption efficiency optimization. This solution not only improves the positioning accuracy and flight path control ability of the UAV under signal degradation, but also enhances the UAV's dynamic obstacle avoidance ability, improving the reliability and endurance of task execution.

[0135] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A method for maintaining the flight path and autonomous positioning of an unmanned aerial vehicle in a communication degradation scenario, characterized in that: Including, Monitoring the signal strength and performing smoothing processing on the signal quality and decay information collected in real time, using a long short-term memory network for decay trend prediction, and outputting a signal decay report; Combining multi-UAV sensor data, processing local sensor data in real time through edge computing, and using particle filtering to fuse shared information; Using cooperative positioning and distributed positioning algorithms to correct the shared information of multiple UAVs and output accurate autonomous positioning; Adopting adaptive control and cooperative path optimization to adjust the UAV flight route and output the optimal path; Combining the signal decay report with the optimal path and using an energy consumption model to adjust the UAV to an energy-saving flight mode.

2. The method for maintaining the flight path and autonomous positioning of an unmanned aerial vehicle in a communication degradation scenario according to claim 1, characterized in that: The signal quality and decay information collected in real time includes signal strength, signal attenuation, signal error rate, signal delay, signal packet loss rate, signal spectrum, and temperature and humidity; The steps for monitoring the signal strength and performing smoothing processing to output a signal decay report are as follows: Screening out abnormal information by monitoring the signal quality and decay information collected in real time; Performing smoothing processing on the abnormal information to output signal decay abnormal data; Using a long short-term memory network for decay trend prediction to output a signal abnormal decay report.

3. The method for maintaining the flight path and autonomous positioning of an unmanned aerial vehicle in a communication degradation scenario according to claim 2, wherein: The steps for combining multi-UAV sensor data, processing local sensor data in real time through edge computing, and using particle filtering to fuse shared information are as follows: Based on the signal abnormal report, the UAV processes local sensor data in real time through edge computing to generate local state information, and uses particle filtering to output shared information.

4. The method for maintaining the flight path and autonomous positioning of an unmanned aerial vehicle in a communication degradation scenario according to claim 3, wherein: The steps for using cooperative positioning and distributed positioning algorithms to correct the shared information of multiple UAVs and output accurate autonomous positioning are as follows: Using blockchain for the shared information to output corrected shared information; Using deep reinforcement learning and game theory to optimize the UAV flight path and dynamically adjust the flight strategy; Adjusting the real-time UAV positioning accuracy through sensor fusion error correction method to output accurate autonomous positioning.

5. The method for maintaining the flight path and autonomous positioning of an unmanned aerial vehicle in a communication degradation scenario according to claim 4, wherein: The steps for adopting adaptive control and cooperative path optimization to adjust the UAV flight route and output the optimal path are as follows: Using UAV dynamics to bring in UAV real-time data to output UAV path optimization mathematical calculations; Adopting a model predictive control algorithm combined with path deviation, energy consumption, and obstacle constraints to optimize the UAV flight path; Continuously optimizing the path planning using game theory, dynamically adjusting in combination with blockchain shared data, and autonomously outputting the optimized path of multiple UAVs; Combining real-time sensor data and using an extended Kalman filter to perform real-time correction on the optimized path and output a real-time accurate flight path; Using adaptive control in combination with a real-time signal abnormal report for adaptive adjustment to output a real-time optimized path.

6. The method for maintaining the flight path and autonomous positioning of a drone in a communication degradation scenario according to claim 5, wherein: The steps for combining the signal decay report with the optimal path and using an energy consumption model to adjust the UAV to an energy-saving flight mode are as follows: Combining the signal decay report with environmental data and using a long short-term memory network for fusion analysis to output planning basic information; Using game theory and a model predictive control algorithm to generate an optimal path in combination with multi-UAV cooperative flight and signal decay effects; Constructing an energy consumption model in combination with the optimal path and the signal decay report to turn on the energy-saving flight mode.

7. The method for maintaining the flight path and autonomous positioning of an unmanned aerial vehicle in a communication degradation scenario according to claim 6, characterized in that: The optimal path is generated by combining game theory and model predictive control algorithms with multi-UAV cooperative flight and signal decay effects. The specific steps are as follows: Use game theory to perform game on the UAVs and output the basic decision for path optimization; Use the model predictive control algorithm and the signal decay report to output the preliminary optimized path; Combine the extended Kalman filter and the shared information accuracy to correct the path and output the optimal path.

8. The method for maintaining the flight path and autonomous positioning of a drone in a communication degradation scenario according to claim 7, characterized in that: The flight path of the UAVs is optimized by using deep reinforcement learning and game theory, and the flight strategy is dynamically adjusted. The specific steps are as follows: Use the blockchain method to correct the shared data and output the accurate autonomous positioning information of multiple UAVs; Apply deep reinforcement learning to combine the UAV flight path and environmental information to output the flight strategy; Use the Nash equilibrium to combine the optimized path and the signal anomaly report to optimize the flight strategy and output the multi-UAV flight strategy; Use the UAV dynamics, flight data, and optimized path to dynamically adjust the flight strategy through the model predictive control algorithm in combination with path deviation, energy consumption, and obstacle constraints.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, the steps of the method for maintaining the UAV trajectory and autonomous positioning in the communication decay scenario according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the method for maintaining the UAV trajectory and autonomous positioning in the communication decay scenario according to any one of claims 1 to 8 are implemented.

Images