Unmanned target drone flight path planning method and system

Abstract

The invention discloses an unmanned target aircraft flight path planning method and system. The method comprises the steps of obtaining dynamic battlefield environment data, generating an initial path node sequence by combining an A * algorithm with dynamic battlefield threat data, calculating a communication quality weight sequence by using a path loss model and a Monte Carlo method, and optimizing a path. The method comprises the following steps of: acquiring a path instruction sequence, fusing navigation data through Kalman filtering to evaluate deviation, correcting the path through quadratic programming, generating a smooth path by adopting B-spline curve fitting, evaluating the path execution probability through a Monte Carlo method, and finally generating a path instruction sequence containing speed and direction control signals. According to the method, intelligent path planning in a complex battlefield environment is realized, and the safety, the reliability and the execution efficiency of the path are improved.

Description

Technical Field

[0001] The present invention belongs to the field of path planning, and in particular relates to a flight path planning method and system for an unmanned target aircraft. Background Art

[0002] Unmanned drone flight path planning is a core technology in modern military training and testing, directly impacting the realism of combat simulations and training effectiveness. Its importance lies in improving the drone's mission execution capabilities and system resource utilization efficiency in complex environments. Currently, traditional path planning methods rely on static models or single optimization objectives, making them difficult to adapt to dynamic battlefield environments and multi-mission requirements. They suffer from issues such as insufficient real-time performance, poor path adaptability, and inefficient resource allocation. These limitations make it difficult for drones to respond flexibly to sudden threats or communication interruptions, limiting the complexity and practicality of training scenarios.

[0003] At the same time, the dynamic battlefield environment places higher demands on path planning, with situational awareness becoming the primary technical bottleneck. Target drones must acquire environmental data and perform threat analysis in real time using multiple sensors. However, existing systems struggle with data processing speed and accuracy in complex electromagnetic environments and terrain, making it difficult to generate a real-time optimal path. This creates a need for optimized communication quality, as path selection must not only consider threat avoidance but also ensure stable command transmission and control response. The uneven distribution of signal strength necessitates a dynamic balance between communication quality and mission objectives. Furthermore, path deviation management becomes a key constraint, with real-time deviation monitoring and correction required to strike a balance between tactical flexibility and safety. Excessive deviation can lead to mission failure or safety incidents. Finally, the smoothness and practicability of path fitting directly impact the dynamic performance of the target drone. Multi-segment spline curves must dynamically adjust between physical constraints and mission requirements. Existing methods lack fitting accuracy in highly maneuverable scenarios.

[0004] Therefore, how to integrate situational awareness, communication optimization, deviation management and path fitting technology to build an unmanned target drone system that can achieve real-time adaptive path planning in a complex dynamic environment has become the primary key issue that needs to be studied. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a method and system for planning the flight path of an unmanned target aircraft. The method comprises:

[0006] Acquire dynamic battlefield environment data, and generate a first path node sequence by assigning dynamic weights using an A* algorithm based on threat area coordinates in the dynamic battlefield environment data;

[0007] Calculating the signal strength of each node using a path loss model based on the first path node sequence, evaluating the signal attenuation probability using a Monte Carlo method, and generating a communication quality weight sequence;

[0008] If there are nodes in the communication quality weight sequence whose weights are lower than a preset threshold, optimizing the first path node sequence using a genetic algorithm to generate a second path node sequence;

[0009] According to the second path node sequence, calculating the Euclidean distance deviation by fusing the inertial navigation and global positioning data through Kalman filtering to generate a deviation data sequence;

[0010] If there is a deviation value exceeding a preset threshold in the deviation data sequence, a quadratic programming algorithm is used to locally correct the corresponding path segment to generate a third path node sequence;

[0011] According to the third path node sequence, a B-spline curve fitting algorithm is used in combination with motion constraints to optimize the control point positions and generate smooth path curve parameters;

[0012] According to the smooth path curve parameters, the path execution probability is evaluated in a dynamic battlefield simulation using the Monte Carlo method. If the execution probability is higher than a preset threshold, a final path instruction sequence including speed and direction control signals is generated.

[0013] Preferably, the process of acquiring dynamic battlefield environment data includes:

[0014] Collect dynamic battlefield environment data through radar, infrared and optical sensors to obtain multi-source sensor data sets;

[0015] Preprocessing the multi-source sensor data set using a multi-sensor fusion algorithm to obtain preliminary fusion data;

[0016] The Kalman filter algorithm is applied to the preliminary fusion data for optimization processing to obtain smooth target position, threat area coordinates and terrain height information;

[0017] If the distance between the target location and the coordinates of the threat area is less than a preset threshold, the high-risk targets are determined through coordinate information analysis and a high-risk target list is obtained;

[0018] Calculating the relative height of the target relative to the terrain based on the high-risk target list and terrain height information to obtain target terrain association data;

[0019] Using the target terrain association data, a clustering algorithm is used to spatially group the targets to obtain a target distribution pattern;

[0020] According to the target distribution pattern, real-time spatial data of the dynamic battlefield environment is generated to obtain battlefield situation information.

[0021] Preferably, the process of using the A* algorithm to assign dynamic weights to generate the first path node sequence includes:

[0022] Extracting threat area coordinates and threat level information based on the dynamic battlefield environment data, and determining a threat area division result;

[0023] Calculating the dynamic weights of the threat areas according to the threat level information by a linear mapping method to obtain a weight distribution table; wherein the dynamic weights are determined based on the linear mapping of the threat levels;

[0024] If the dynamic weight exceeds the preset threshold, the A* algorithm is used to generate the initial first path node sequence based on the weight distribution table to determine the initial path plan;

[0025] According to the initial path planning, the environmental data change trend in the path node sequence is obtained to determine whether the path passes through a high-threat area, and an optimization demand assessment is obtained;

[0026] If the optimization demand assessment shows that the path passes through a high-threat area, the path is recalculated using the Dijkstra algorithm, and the node sequence is adjusted based on the dynamic weight to generate an adjusted first path node sequence;

[0027] Obtain the environmental data of the adjusted first path node sequence, use data fusion technology to integrate the threat area coordinates and dynamic weights, and determine the final path plan;

[0028] Through the final path planning, the coordinate data of the path node sequence is generated, and the optimized first path node sequence is output.

[0029] Preferably, the process of generating a communication quality weight sequence includes:

[0030] By parsing the first path node sequence, the position distribution of each node and the signal propagation distance are obtained, and the initial signal strength is determined;

[0031] The path loss model is used in combination with environmental interference factors to calculate the signal strength of each node and obtain a signal strength sequence;

[0032] If the signal strength is lower than the preset threshold, the Monte Carlo method is used to simulate the signal attenuation probability and generate an attenuation probability distribution;

[0033] According to the attenuation probability distribution, the communication quality weight of each node is calculated to obtain the communication quality weight sequence;

[0034] Based on the weight sequence generation results, evaluate the communication quality and determine whether there are low-quality nodes;

[0035] If there are low-quality nodes, adjust the node position distribution and recalculate the signal strength sequence;

[0036] The final communication quality weight sequence is generated by iteratively optimizing the weight sequence.

[0037] Preferably, the process of generating the second path node sequence includes:

[0038] If there are nodes in the communication quality weight sequence whose values ​​are lower than the preset threshold, obtaining node identifiers of the nodes whose values ​​are lower than the preset threshold from the communication quality weight sequence to obtain a set of nodes to be optimized;

[0039] Initializing a population of a first path node sequence using a genetic algorithm according to the set of nodes to be optimized to generate an initial path node sequence set;

[0040] For the initial path node sequence set, calculating the weighted sum of the communication quality weight and the path length of each path to obtain a fitness function value set;

[0041] If there is a path in the fitness function value set that is lower than a preset fitness threshold, a new path node sequence set is generated through crossover and mutation operations of the genetic algorithm;

[0042] Recalculating the weighted sum of the communication quality weight and the path length according to the new set of path node sequences to obtain an updated set of fitness function values;

[0043] By comparing the updated fitness function value sets, the path node sequence with the highest fitness value is selected to generate a second path node sequence;

[0044] According to the second path node sequence, the node connection relationship of the communication network is adjusted to determine the optimized communication path configuration.

[0045] Preferably, the process of generating the deviation data sequence includes:

[0046] Acquire inertial navigation data and global positioning data through the second path node sequence, perform preliminary fusion using Kalman filtering, and obtain initial fused data;

[0047] For the initial fusion data, calculate the Euclidean distance deviation between each node to generate a preliminary deviation data sequence;

[0048] If there are abnormal values ​​in the preliminary deviation data sequence, the abnormal values ​​are eliminated through a preset threshold judgment to obtain a corrected deviation data sequence;

[0049] According to the corrected deviation data sequence, a quadratic Kalman filter is used to optimize data smoothness to generate an optimized deviation data sequence;

[0050] Extracting deviation statistical features from the optimized deviation data sequence, calculating the deviation mean and variance, and obtaining deviation distribution characteristics;

[0051] According to the deviation distribution characteristics, the least square method is used to fit the deviation trend and construct a deviation trend model;

[0052] According to the deviation trend model, the deviation sequence of subsequent path nodes is predicted to obtain the deviation data sequence.

[0053] Preferably, the process of generating the third path node sequence includes:

[0054] If there is a deviation value exceeding a preset threshold value in the deviation data sequence, an abnormal deviation point is determined by threshold judgment to obtain an abnormal point set;

[0055] Analyze the correspondence between the set of outliers and the path segments, obtain the path segments to be optimized, and determine the set of segments to be optimized;

[0056] Using a quadratic programming algorithm to locally optimize the set of segments to be optimized, and generating a temporary path node sequence;

[0057] If the deviation between the temporary path node sequence and the original path segment still exceeds the preset threshold, the optimized path node sequence is obtained by iteratively adjusting the parameters of the quadratic programming algorithm;

[0058] According to the optimized path node sequence, obtaining the continuity characteristics of the node sequence and determining the smoothness of the sequence;

[0059] According to the smoothness judgment result, the spline interpolation algorithm is used to smooth the optimized path node sequence to generate the third path node sequence;

[0060] If the deviation value of the third path node sequence meets the preset threshold, the final path node sequence is generated through sequence integration.

[0061] Preferably, the process of generating smooth path curve parameters includes:

[0062] Based on the third path node sequence, extracting node coordinates and connection order through preprocessing to determine an initial path point set;

[0063] Using a B-spline curve fitting algorithm, the initial positions of the control points are calculated according to the initial path point set to obtain preliminary curve parameters;

[0064] If the preliminary curve parameters satisfy the motion constraints, retaining the control point position;

[0065] If not, the control points are adjusted according to the constraints to generate an optimized control point set;

[0066] Recalculating the B-spline curve through the optimized control point set to obtain smooth path curve parameters;

[0067] Analyzing the path smoothness according to the smooth path curve parameters, and if the smoothness is lower than a preset threshold, iteratively adjusting the control point positions to determine a final control point set;

[0068] generating a smooth path curve according to the final control point set, and outputting curve parameters and a path point sequence;

[0069] The path geometric features are extracted from the output curve parameters, the path description data is generated, and the final smooth path is determined.

[0070] Preferably, the process of evaluating the path execution probability in a dynamic battlefield simulation by a Monte Carlo method and generating a final path instruction sequence including speed and direction control signals if the execution probability is higher than a preset threshold comprises:

[0071] The probability distribution of the smooth path curve is obtained from the dynamic battlefield simulation through the Monte Carlo method to obtain the execution probability value;

[0072] Using a probability distribution model to analyze the comparison result between the execution probability value and a preset threshold value to determine the feasibility of the path;

[0073] If the path feasibility is determined to be executable, the speed control signal is extracted from the smooth path curve to generate a preliminary speed command set;

[0074] Extracting direction control signals from the smooth path curve to generate a preliminary direction instruction set;

[0075] Combining the preliminary speed instruction set and the preliminary direction instruction set through an instruction sequence optimization algorithm to obtain an optimized path instruction sequence;

[0076] For the optimized path instruction sequence, obtain battlefield environment parameters and judge the adaptability of the instruction sequence;

[0077] If the adaptability of the instruction sequence passes the judgment, the final path instruction sequence is output.

[0078] The present invention also provides an unmanned drone flight path planning system, comprising:

[0079] Data acquisition module, used to obtain dynamic battlefield environment data;

[0080] A path planning module, configured to generate a first path node sequence by assigning dynamic weights using an A* algorithm based on the threat area coordinates in the dynamic battlefield environment data;

[0081] a communication evaluation module, configured to calculate the signal strength of each node according to the first path node sequence using a path loss model, evaluate the signal attenuation probability using a Monte Carlo method, and generate a communication quality weight sequence;

[0082] A path optimization module, configured to optimize the first path node sequence using a genetic algorithm to generate a second path node sequence if there are nodes in the communication quality weight sequence whose weights are lower than a preset threshold;

[0083] a deviation calculation module, configured to calculate the Euclidean distance deviation by fusing inertial navigation and global positioning data through Kalman filtering according to the second path node sequence, and generate a deviation data sequence;

[0084] a local correction module, configured to use a quadratic programming algorithm to perform local correction on the corresponding path segment if a deviation value exceeding a preset threshold value exists in the deviation data sequence, so as to generate a third path node sequence;

[0085] a path smoothing module, configured to generate smooth path curve parameters by optimizing control point positions using a B-spline curve fitting algorithm combined with motion constraints according to the third path node sequence;

[0086] A path execution module is used to evaluate the path execution probability in a dynamic battlefield simulation using the Monte Carlo method based on the smooth path curve parameters, and to generate a final path instruction sequence including speed and direction control signals if the execution probability is higher than a preset threshold.

[0087] Compared with the prior art, the present invention has the following advantages and technical effects:

[0088] This invention discloses an intelligent path planning method for dynamic battlefield environments. This method acquires battlefield data through multi-sensor fusion, uses the A* algorithm to generate an initial path, and then optimizes it using a genetic algorithm combined with communication quality assessment. Kalman filtering and quadratic programming are then used to correct deviations, and finally, B-spline curve fitting is used to generate a smooth path. This method comprehensively considers multiple factors, including threat avoidance, communication quality, and navigation accuracy. Through multi-level optimization, it achieves intelligent path planning in complex battlefield environments, improving the safety, reliability, and execution efficiency of the path.

[0089] The present invention can provide effective decision support for the autonomous navigation of unmanned systems in dynamic confrontation environments and has important military application value.

[0090] The present invention realizes intelligent and adaptive path planning in dynamic battlefield environments, providing strong support for the autonomous maneuvering of equipment such as unmanned systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0092] Figure 1 Schematic diagram of a method flow in an embodiment of the present invention;

[0093] Figure 2 Schematic diagram of the system structure of an embodiment of the present invention. DETAILED DESCRIPTION

[0094] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0095] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0096] Example 1

[0097] like Figure 1 As shown, this embodiment provides a method for planning an unmanned target aircraft flight path, including:

[0098] Acquire dynamic battlefield environment data, and use the A* algorithm to assign dynamic weights based on the threat area coordinates in the dynamic battlefield environment data to generate a first path node sequence;

[0099] Based on the first path node sequence, the signal strength of each node is calculated using the path loss model, the signal attenuation probability is evaluated using the Monte Carlo method, and a communication quality weight sequence is generated;

[0100] If there are nodes in the communication quality weight sequence whose values ​​are lower than a preset threshold, a genetic algorithm is used to optimize the first path node sequence to generate a second path node sequence;

[0101] According to the second path node sequence, the Euclidean distance deviation is calculated by fusing the inertial navigation and global positioning data through Kalman filtering to generate a deviation data sequence;

[0102] If there is a deviation value exceeding a preset threshold in the deviation data sequence, a quadratic programming algorithm is used to locally correct the corresponding path segment to generate a third path node sequence;

[0103] According to the third path node sequence, the B-spline curve fitting algorithm is used in combination with motion constraints to optimize the control point positions and generate smooth path curve parameters;

[0104] According to the smooth path curve parameters, the Monte Carlo method is used to evaluate the path execution probability in a dynamic battlefield simulation. If the execution probability is higher than a preset threshold, the final path instruction sequence containing speed and direction control signals is generated.

[0105] Furthermore, the process of obtaining dynamic battlefield environment data includes:

[0106] Dynamic battlefield environment data is collected through radar, infrared and optical sensors to obtain a multi-source sensor data set; a multi-sensor fusion algorithm is used to pre-process the multi-source sensor data set to obtain preliminary fused data;

[0107] The Kalman filter algorithm is applied to the preliminary fusion data for optimization processing to obtain smooth target position, threat area coordinates and terrain height information;

[0108] If the distance between the target location and the coordinates of the threat area is less than a preset threshold, the high-risk targets are determined through coordinate information analysis and a high-risk target list is obtained;

[0109] Based on the high-risk target list and terrain height information, the relative height of the target relative to the terrain is calculated to obtain target terrain correlation data;

[0110] Through the target terrain correlation data, a clustering algorithm is used to spatially group the targets to obtain the target distribution pattern; based on the target distribution pattern, real-time spatial data of the dynamic battlefield environment is generated to obtain battlefield situation information.

[0111] Specifically, in a dynamic battlefield environment, multi-source sensor data fusion is a core technology for achieving situational awareness. Radar, infrared, and optical sensors each capture target range, speed, thermal signature, and image information, forming a multi-source data set. For example, radar can provide target speed information within a range of 1000 meters, infrared sensors detect the target's thermal signature intensity, and optical sensors generate a two-dimensional image of the target. In the preprocessing stage, multi-sensor fusion algorithms, such as weighted averaging or Bayesian inference, are used to integrate this data into a preliminary fused set.

[0112] Specifically, the radar measures the target coordinates at (500, 300, 50), and the infrared confirms the thermal signature. This fusion generates unified target location data. This fusion improves data consistency and reduces the impact of individual sensor noise. A Kalman filter algorithm optimizes this initial fused data, generating smoothed target location, threat zone coordinates, and terrain height information.

[0113] For example, the initial position of a target is (510, 305, 55), which is corrected to (508, 302, 53) through Kalman filtering, combined with historical trajectory and sensor noise characteristics. At the same time, the threat area coordinates (600, 400, 60) and the terrain height of 50 meters are generated.

[0114] Preferably, this method can effectively filter out random errors, improve target tracking accuracy, and provide reliable data for subsequent analysis.

[0115] In one possible implementation, the distance between the target location and the threat area coordinates is calculated. If it is less than a preset threshold, such as 200 meters, it is determined to be a high-risk target.

[0116] For example, the target location (508,302,53) is about 141 meters away from the threat area (600,400,60), which is less than the threshold and is included in the high-risk target list.

[0117] It is understandable that this determination can quickly screen potential threats and assist in command decision-making. Based on the list of high-risk targets and terrain height information, the relative height of the target relative to the terrain is calculated to form target-terrain correlation data.

[0118] In one example, the target altitude is 53 meters, the terrain altitude is 50 meters, and the relative altitude is 3 meters, indicating that the target is likely a low-altitude aircraft. This correlation data can reveal target activity characteristics and enhance battlefield situational understanding. Using target-terrain correlation data, clustering algorithms such as K-means can be used to spatially group targets and generate target distribution patterns.

[0119] Specifically, the 10 high-risk targets were divided into three groups based on their location and relative height, located in the northwest, southeast and central areas of the battlefield.

[0120] It should be noted that this type of grouping can reveal the enemy's deployment patterns and facilitate the prediction of their operational intentions.

[0121] In one embodiment, real-time spatial data of the dynamic battlefield environment is generated based on target distribution patterns, forming battlefield situational information. For example, targets densely packed and relatively low in the northwest region may indicate a concentration of ground forces, while targets sparsely packed and high in the southeast region may indicate reconnaissance drones. This situational information provides commanders with an intuitive spatial situational picture, supporting tactical adjustments.

[0122] Optimally, the above technical process significantly improves the accuracy and real-time nature of battlefield situational awareness through multi-source data fusion, optimized processing, and pattern analysis, providing support for rapid decision-making. Each technical link supports each other, forming an efficient chain from data collection to situation generation, ensuring the comprehensiveness and reliability of battlefield information.

[0123] Furthermore, the process of using the A* algorithm to assign dynamic weights to generate the first path node sequence includes:

[0124] Extract threat area coordinates and threat level information based on dynamic battlefield environment data and determine threat area division results;

[0125] The dynamic weights of the threat areas are calculated based on the threat level information using a linear mapping method to obtain a weight distribution table. The dynamic weights are determined based on the linear mapping of the threat levels. If the dynamic weights exceed a preset threshold, the A* algorithm is used to generate an initial first path node sequence based on the weight distribution table to determine the initial path plan.

[0126] Based on the initial path planning, the environmental data change trend in the path node sequence is obtained to determine whether the path passes through a high-threat area and obtain an optimization demand assessment;

[0127] If the optimization demand assessment shows that the path passes through a high-threat area, the path is recalculated using the Dijkstra algorithm, and the node sequence is adjusted based on the dynamic weights to generate an adjusted first path node sequence;

[0128] Obtain the environmental data of the adjusted first path node sequence, use data fusion technology to integrate the threat area coordinates and dynamic weights, and determine the final path plan;

[0129] Through the final path planning, the coordinate data of the path node sequence is generated, and the optimized first path node sequence is output.

[0130] Specifically, in a dynamic battlefield environment, obtaining threat area coordinates and threat level information is the core of building battlefield situation awareness.

[0131] For example, suppose multi-sensor data fusion determines that the center coordinates of a certain area are (2000, 3000) and the threat level is high. Based on intelligence analysis and sensor detection, the threat area is divided into a circular area with a radius of 800 meters centered at these coordinates. Threat level information is typically derived from enemy target density detected by radar, heat signal strength captured by infrared sensors, and equipment type identified by optical sensors.

[0132] Specifically, a high threat level may correspond to a dense deployment of heavy enemy equipment, with thermal signatures indicating sustained activity. Using this data, the command system can clearly delineate the threat area, providing a basis for subsequent route planning.

[0133] Preferably, a linear mapping method is used when calculating the dynamic weight based on the threat level.

[0134] For example, the threat level can be categorized as low, medium, and high, and mapped to weights of 0.3, 0.6, and 0.9, respectively. For example, suppose the threat level in the area (2000, 3000) is high, with a weight of 0.9; the threat level in the area (2500, 3500) is medium, with a weight of 0.6. A weight distribution table records the coordinates of each area and its weight, forming a dynamic weight distribution. This method is simple and efficient, intuitively reflecting differences in threat levels and providing a quantitative basis for path planning.

[0135] In one possible implementation, if the dynamic weight of a region exceeds a threshold of 0.8, the A* algorithm is triggered to generate an initial path.

[0136] For example, when planning a path from the starting point (1000, 1000) to the end point (3000, 3000), the A* algorithm prioritizes nodes with lower weights based on the weight distribution table, generating a node sequence such as (1000, 1000), (1500, 1500), (2000, 2000), and (3000, 3000).

[0137] It should be noted that the A* algorithm uses heuristic search to comprehensively consider path length and threat weight to quickly generate feasible paths.

[0138] Specifically, when analyzing environmental data trends along the initial path, the threat level and terrain information for each point in the node sequence are extracted. For example, node (2000, 2000) is near a high-threat area, with a threat weight of 0.85, exceeding the safety threshold. This indicates that the path may cross a high-threat area, triggering optimization. The optimization assessment, based on data fusion, integrates threat level, terrain height, and enemy activity intelligence to confirm that the path needs adjustment.

[0139] In one embodiment, the Dijkstra algorithm is used to replan the path, adjusting the node sequence based on dynamic weights. For example, the Dijkstra algorithm aims to minimize weight accumulation, avoids high-threat areas, and generates a second path node sequence such as (1000, 1000), (1200, 1300), (1800, 1800), and (3000, 3000). This method ensures higher path security through global search. The final path planning integrates the coordinates of the threat area and the dynamic weights, and outputs the optimized node sequence coordinate data, providing reliable support for command decision-making.

[0140] The advantage of this approach lies in its ability to dynamically adapt to changing battlefield conditions through multi-level data processing and algorithm optimization. Threat area demarcation and weight calculation provide precise situational awareness, while the combination of the A* and Dijkstra algorithms balances efficiency and security. The resulting path node sequence effectively avoids high-threat areas, improving mission success rates.

[0141] Furthermore, the process of generating the communication quality weight sequence includes:

[0142] By analyzing the first path node sequence, the location distribution of each node and the signal propagation distance are obtained to determine the initial signal strength;

[0143] The path loss model is used in combination with environmental interference factors to calculate the signal strength of each node and obtain a signal strength sequence;

[0144] If the signal strength is lower than the preset threshold, the Monte Carlo method is used to simulate the signal attenuation probability and generate an attenuation probability distribution;

[0145] According to the attenuation probability distribution, the communication quality weight of each node is calculated to obtain the communication quality weight sequence;

[0146] Based on the weight sequence generation results, evaluate the communication quality and determine whether there are low-quality nodes;

[0147] If there are low-quality nodes, adjust the node position distribution and recalculate the signal strength sequence;

[0148] The final communication quality weight sequence is generated by iteratively optimizing the weight sequence.

[0149] Specifically, in a dynamic battlefield environment, path planning and signal optimization of the communication system are crucial.

[0150] For example, path node sequences can be parsed by analyzing the spatial coordinates of each node to obtain the location distribution and signal propagation distance. For example, in a battlefield scenario, the node sequence is A(10,10), B(30,30), C(50,50), D(70,70), and E(90,90). By calculating the Euclidean distance between adjacent nodes, the propagation distance of each segment can be obtained, such as 28.28 units for segment AB and 28.28 units for segment BC. These distances provide the basis for subsequent signal strength calculations.

[0151] Specifically, the determination of the initial signal strength is based on the relationship between the transmission power and the distance.

[0152] In one embodiment, assuming the transmission power is 100 mW, combined with the free space path loss model, the signal strength of node A can be set as a baseline value, and the signal strength of other nodes is attenuated according to the distance.

[0153] For example, the signal strength of Node B is slightly attenuated due to a propagation distance of 28.28 units and is estimated to be 90 mW.

[0154] It should be noted that environmental interference factors such as terrain and electromagnetic noise need to be taken into consideration.

[0155] Preferably, an interference coefficient can be introduced. For example, if the interference coefficient for plain terrain is 0.8, the actual signal strength of node B is adjusted to 90mW × 0.8 = 72mW. Using a similar method, the signal strength sequence is calculated as: A (100mW), B (72mW), C (65mW), D (60mW), E (55mW). For example, if the preset signal strength threshold is 60mW, node E's 55mW is below the threshold, and its communication quality needs further analysis.

[0156] In one possible implementation, the Monte Carlo method is used to simulate signal attenuation probability. Multiple random sampling attempts are performed to simulate the attenuation of node E under different interference conditions, generating an attenuation probability distribution. Assuming that 500 out of 1000 simulations show attenuation exceeding 50%, the attenuation probability for node E is 50%. Based on this distribution, a communication quality weight is calculated.

[0157] For example, the weight of node E can be set to 1-0.5=0.5, and the weights of the remaining nodes are generated based on similar logic, resulting in a weight sequence: A(0.9), B(0.8), C(0.7), D(0.6), E(0.5).

[0158] It is understood that the weight sequence is used to evaluate the communication quality. The low weight of node E indicates that it is a low-quality node and needs to be optimized.

[0159] In one embodiment, the position of node E is adjusted to (85, 85), shortening the distance to node D. The signal strength is recalculated to 62 mW, meeting the threshold requirement. After iterative optimization, the weight sequence is updated to A (0.9), B (0.8), C (0.7), D (0.6), and E (0.7). This approach ensures the stability and reliability of the communication link through dynamic adjustment.

[0160] Preferably, the above solution can be expanded to multi-node collaborative optimization. For example, adding a backup node F(80,80) can share the communication pressure of E and further improve link quality. This logic, from core optimization to extended collaboration, ensures the integrity and diversity of the solution. The above method improves the robustness of battlefield communications through refined signal management.

[0161] Furthermore, the process of generating the second path node sequence includes:

[0162] If there are nodes in the communication quality weight sequence whose values ​​are lower than the preset threshold, the node identifiers of the nodes whose values ​​are lower than the preset threshold are obtained from the communication quality weight sequence to obtain a set of nodes to be optimized;

[0163] According to the node set to be optimized, a genetic algorithm is used to initialize the population of the first path node sequence to generate an initial path node sequence set;

[0164] For the initial path node sequence set, calculate the weighted sum of the communication quality weight and path length of each path to obtain the fitness function value set;

[0165] If there is a path in the fitness function value set that is lower than the preset fitness threshold, a new path node sequence set is generated through the crossover and mutation operations of the genetic algorithm;

[0166] According to the new set of path node sequences, the weighted sum of the communication quality weight and the path length is recalculated to obtain the updated set of fitness function values;

[0167] By comparing the updated fitness function value sets, the path node sequence with the highest fitness value is selected to generate a second path node sequence;

[0168] According to the second path node sequence, the node connection relationship of the communication network is adjusted to determine the optimized communication path configuration.

[0169] For example, the communication quality weight sequence reflects the communication reliability of each node in the network, and a preset threshold is used to filter out nodes with poor communication quality. Assuming the communication quality weight threshold is 0.6, and the weights of nodes A, B, C, and D in the sequence are 1.0, 0.8, 0.5, and 0.3, respectively, nodes C and D are below the threshold and constitute the set of nodes to be optimized. The key to this step is to accurately identify the nodes to be optimized, ensuring that subsequent optimization is highly targeted.

[0170] In one possible implementation, a genetic algorithm is used to initialize a population of path node sequences. For nodes C and D to be optimized, an initial set of multiple paths is generated, for example, path 1 is ABCD, path 2 is ACD, and path 3 is ABD. During population initialization, a variety of node connections are randomly generated to maintain path diversity. The advantage of genetic algorithms is that they mimic biological evolution, gradually selecting optimal path configurations.

[0171] Specifically, the fitness function value for the initial set of path node sequences must be calculated by comprehensively considering the communication quality weight and path length. The communication quality weight reflects signal stability, while path length affects transmission latency. Assume that the total length of path ABCD is 450 meters, with a weight sum of 2.6; the length of path ACD is 300 meters, with a weight sum of 1.8. The weighted sum is calculated using a linear combination of weight and length, with a higher weight being assigned to prioritize communication quality. Paths with low fitness values, such as ABCD, are marked for optimization due to their low weight.

[0172] Preferably, a new set of paths is generated through crossover and mutation operations in a genetic algorithm. The crossover operation swaps some nodes between two paths, for example, swapping ABCD with ACD to create ABD and ACBD. The mutation operation randomly reorders the nodes, for example, mutating ABD to ADB. This new set retains the advantages of the original path while introducing new possibilities.

[0173] It should be noted that the ratio of crossover and mutation needs to be controlled to avoid excessive randomization leading to slow convergence.

[0174] In one embodiment, the fitness value of the new path set is recalculated.

[0175] For example, ABD, with a weight sum of 2.3 and a length of 350 meters, has a higher fitness value than ACBD, with a weight sum of 1.5 and a length of 400 meters. After comparison, ABD, with the highest fitness, is selected as the second path node sequence. This step ensures that the path balances communication quality and transmission efficiency.

[0176] It's understandable that adjusting network connectivity based on the second path node sequence requires reconfiguring inter-node communication links. For example, connecting nodes B and D directly, bypassing node C, reduces signal attenuation. This optimized path configuration improves overall network reliability, effectively reducing packet loss in high-load scenarios.

[0177] For example, in actual deployments, the optimized path ABD improved signal transmission stability and increased the communication quality weight of node D from 0.3 to 0.7. This improvement was achieved thanks to the genetic algorithm's global path search capability and its comprehensive consideration of communication quality and path length. Through multiple rounds of iteration, the network configuration gradually converged to the optimal one, significantly improving communication efficiency.

[0178] Furthermore, the process of generating the deviation data sequence includes:

[0179] Obtain inertial navigation data and global positioning data through the second path node sequence, perform preliminary fusion using Kalman filtering to obtain initial fusion data; calculate the Euclidean distance deviation between each node based on the initial fusion data to generate a preliminary deviation data sequence;

[0180] If there are outliers in the preliminary deviation data sequence, the outliers are eliminated through the preset threshold judgment to obtain a corrected deviation data sequence; based on the corrected deviation data sequence, the quadratic Kalman filter is used to optimize the data smoothness to generate an optimized deviation data sequence;

[0181] Deviation statistical features are extracted from the optimized deviation data sequence, and the deviation mean and variance are calculated to obtain the deviation distribution characteristics. Based on the deviation distribution characteristics, the least squares method is used to fit the deviation trend and construct a deviation trend model. Based on the deviation trend model, the deviation sequence of subsequent path nodes is predicted to obtain the deviation data sequence.

[0182] In one possible implementation, the process of acquiring inertial navigation data and global positioning data typically involves sensor data acquisition. Inertial navigation systems use accelerometers and gyroscopes to record the device's motion trajectory, providing high-frequency but drift-prone position data.

[0183] For example, when a drone cruises along an AFCGE path, its inertial navigation system collects acceleration and angular velocity data 100 times per second, while the Global Positioning System provides low-frequency but high-precision absolute position data via satellite signals.

[0184] For example, a drone acquires global positioning coordinates every 5 seconds with an accuracy of approximately 2 meters. After the two are aligned using timestamps, they are fed into a Kalman filter for preliminary fusion. The Kalman filter utilizes state predictions and observation updates to balance the error characteristics of the two types of data, generating the initial fused data.

[0185] Preferably, the fused data can reflect the position of the UAV at a higher frequency while maintaining good accuracy.

[0186] Specifically, when calculating the Euclidean distance deviation based on the initial fusion data, it is necessary to compare the geometric distance between the fusion position and the actual path between adjacent nodes.

[0187] For example, the fused position of a drone traveling from node A to node F displays a distance of 500 meters, while the actual path is 510 meters, a deviation of 10 meters. The deviations of AF, FC, CG, and GE are calculated sequentially to form a preliminary deviation data sequence, such as [10, 8, 15, 12]. If there are outliers in the sequence, such as a 15-meter deviation between CGs that far exceeds the mean, a threshold of the mean plus two standard deviations can be set. After removing the outliers, a corrected deviation data sequence can be obtained, such as [10, 8, 12]. This elimination method effectively reduces the impact of sensor noise or environmental interference.

[0188] In one embodiment, a secondary Kalman filter is used to optimize the smoothness of the corrected deviation data sequence. Compared to the primary fusion, the secondary filter focuses on the dynamic characteristics of the deviation data and reduces random fluctuations.

[0189] For example, after filtering, the deviation sequence may become [9.8, 8.2, 11.9], which makes the data smoother and more suitable for subsequent analysis.

[0190] It should be noted that improved smoothness helps accurately extract the statistical characteristics of deviations. The calculated mean deviation is approximately 9.97 meters, and the variance is approximately 2.25, reflecting the concentration and dispersion of the deviations. These characteristics provide a quantitative basis for the distribution characteristics of the deviations.

[0191] For example, deviation trend fitting uses the least squares method to construct a linear or polynomial model based on the optimized deviation data sequence. Suppose the fitting results show a slowly increasing deviation trend with each path node, such as gradually increasing to 12 meters from A to E. This trend may be related to the accumulated error of the drone's navigation system. The deviation trend model provides a basis for predicting deviations at subsequent nodes.

[0192] Preferably, the prediction deviation data series can be generated by model extrapolation.

[0193] For example, the predicted deviation from the subsequent node E to the new node H is about 12.5 meters. This prediction result can be used to adjust navigation parameters in advance to reduce positioning errors.

[0194] It is understandable that the above method gradually optimizes the reliability of navigation data through multi-level data processing. The implementation methods of each technical theme support each other, forming a complete chain from data collection to deviation prediction.

[0195] For example, initial fusion ensures data accuracy, secondary filtering improves smoothness, and trend fitting and prediction provide the basis for dynamic adjustments. This progressive logic effectively improves the robustness of path planning, especially in complex environments.

[0196] Furthermore, the process of generating the third path node sequence includes:

[0197] If there is a deviation value exceeding the preset threshold in the deviation data sequence, the abnormal deviation point is determined by threshold judgment to obtain an abnormal point set;

[0198] Analyze the correspondence between the set of outliers and the path segments, obtain the path segments to be optimized, and determine the set of segments to be optimized;

[0199] The quadratic programming algorithm is used to perform local optimization on the set of segments to be optimized and generate a temporary path node sequence;

[0200] If the deviation between the temporary path node sequence and the original path segment still exceeds the preset threshold, the optimized path node sequence is obtained by iteratively adjusting the parameters of the quadratic programming algorithm;

[0201] According to the optimized path node sequence, the continuity characteristics of the node sequence are obtained and the smoothness of the sequence is determined;

[0202] According to the smoothness judgment result, the spline interpolation algorithm is used to smooth the optimized path node sequence to generate the third path node sequence;

[0203] If the deviation value of the third path node sequence meets the preset threshold, the final path node sequence is generated through sequence integration.

[0204] For example, processing a deviation data sequence requires first identifying anomalous deviation points. Suppose the deviation data sequence for a path node is [0.2, 0.3, 0.9, 0.4, 0.7] m, with a preset threshold of 0.5 m. Based on the threshold, deviation values ​​of 0.9 m and 0.7 m exceed the threshold and are marked as outliers, forming an outlier set. When analyzing the correspondence between outliers and path segments, the outlier segments can be identified by associating them using timestamps or node numbers.

[0205] For example, a deviation of 0.9m corresponds to the third node, located in path segment S1; a deviation of 0.7m corresponds to the fifth node, located in path segment S2, thus obtaining the set of segments to be optimized {S1, S2}.

[0206] In one possible implementation, a quadratic programming algorithm is used to locally optimize S1 and S2. Quadratic programming adjusts node coordinates by setting an objective function to minimize path deviation while maintaining path continuity. Assuming S1 contains node coordinates [100, 50] and [102, 52], a temporary path node sequence is generated after optimization, adjusted to [101, 51], etc. The temporary path deviation is checked. If it still exceeds the threshold, the quadratic programming weight parameters can be iteratively adjusted, for example, by increasing the smoothness weight to generate an optimized path node sequence, such as [100.8, 50.9]. This process ensures that the path closely follows the reference trajectory.

[0207] Specifically, the continuity characteristics of the optimized path node sequence are determined by calculating the distance and angle changes between nodes.

[0208] For example, if the distance between nodes is stable within 2 meters and the angle variation is less than 15 degrees, the sequence continuity is good. If the continuity is insufficient, spline interpolation can be used for smoothing. Spline interpolation generates a smooth third path node sequence by fitting a cubic polynomial.

[0209] For example, after interpolation, the original node sequences [100,50] and [102,52] are added with the intermediate node [101,51], making the path smoother.

[0210] Preferably, the third path node sequence is re-verified to see if the deviation meets the threshold. Assuming the verified deviations are [0.3, 0.4, 0.2], all below 0.5m, the final path node sequence is generated through sequence integration. During integration, adjacent nodes can be merged to reduce redundancy. For example, the nearby nodes [100.8, 50.9] and [101, 51] can be merged into [100.9, 51]. This final path node sequence is more efficient and suitable for use with navigation devices.

[0211] It should be noted that the above method forms a complete optimization process through outlier identification, path segment optimization, and smoothing. Each step supports each other to ensure path accuracy and continuity.

[0212] For example, outlier identification provides precise targets for subsequent optimization, while quadratic programming and spline interpolation improve path quality at different levels. This multi-step collaborative optimization approach effectively improves the practicality of navigation paths.

[0213] Furthermore, the process of generating smooth path curve parameters includes:

[0214] Based on the third path node sequence, node coordinates and connection order are extracted through preprocessing to determine the initial path point set;

[0215] The B-spline curve fitting algorithm is used to calculate the initial positions of the control points based on the initial path point set to obtain the preliminary curve parameters;

[0216] If the preliminary curve parameters satisfy the motion constraints, the control point positions are retained;

[0217] If not, the control points are adjusted according to the constraints to generate an optimized control point set;

[0218] By optimizing the control point set, the B-spline curve is recalculated to obtain the smooth path curve parameters;

[0219] According to the smooth path curve parameters, the path smoothness is analyzed. If the smoothness is lower than the preset threshold, the control point positions are iteratively adjusted to determine the final control point set.

[0220] Generate a smooth path curve based on the final control point set, and output the curve parameters and path point sequence;

[0221] The path geometric features are extracted from the output curve parameters, the path description data is generated, and the final smooth path is determined.

[0222] Specifically, in the field of path planning, generating a smooth path is the key to ensuring efficiency and accuracy. To obtain the third path node sequence, the node coordinates and connection order must first be extracted through preprocessing.

[0223] For example, the initial pathpoint set might contain a series of node coordinates, such as (1,2), (2,3), and (4,4). These nodes are connected by timestamps or path sequence to form a preliminary path. During preprocessing, the system analyzes the distance and direction changes between nodes to ensure the continuity of the point set.

[0224] Preferably, if it is detected that the node spacing is too large, such as a distance of more than 2 units, the system will insert intermediate points to improve the path resolution. When using the B-spline curve fitting algorithm, the initial positions of the control points are calculated based on the initial path point set.

[0225] It is understandable that the advantage of B-spline curves lies in their local adjustment capabilities, where the movement of a single control point only affects the local area of ​​the curve.

[0226] For example, if the initial path point set contains five nodes, the system will generate a set of control points, such as (0.8, 1.8), (2.2, 3.1), and (4.1, 4.2), to initially form a curve. If the initial curve parameters meet the motion constraints, such as a curvature radius of at least 0.5, the control point positions are retained. Otherwise, the control point positions need to be adjusted.

[0227] For example, if the curvature of a certain section is too small, the system will use an optimization algorithm to offset the control points outward, such as adjusting (2.2, 3.1) to (2.4, 3.3), to generate an optimized control point set.

[0228] In one possible implementation, the B-spline curve is recalculated by optimizing the control point set to obtain smooth path curve parameters. The system will analyze the path smoothness.

[0229] Specifically, smoothness can be evaluated by the curvature change rate. If the change rate exceeds a preset threshold, such as 0.3, the system will iteratively adjust the control points.

[0230] For example, a control point might be fine-tuned from (4.1, 4.2) to (4.0, 4.3) until smoothness is achieved. The final set of control points generates a smooth path curve, outputting curve parameters and a path point sequence such as (1, 2), (1.5, 2.5), (2, 3), and (4, 4). To extract the path's geometric features, the system analyzes the curve's length, curvature, and directional changes.

[0231] For example, the total length of a path may be 10 units, with the maximum curvature occurring near (2, 3). When generating path description data, the system records these features to form structured data for subsequent path optimization or navigation applications.

[0232] It should be noted that the integrity of path description data directly affects planning efficiency.

[0233] For example, a navigation system can adjust speed in advance based on curvature data to ensure smooth operation.

[0234] In one embodiment, the smooth path generation process embodies high flexibility and adaptability.

[0235] For example, if the initial set of path points needs to be temporarily adjusted due to environmental changes, such as a new obstacle causing path point offsets, the B-spline algorithm can quickly recalculate the control points and generate a new path. The advantage of this method is that it does not require reconstructing the entire path; only local adjustments can satisfy the constraints.

[0236] Preferably, the system can also iteratively optimize based on real-time feedback to ensure that the path always meets dynamic requirements.

[0237] Specifically, the above process, through multi-level analysis and adjustment, forms a complete chain from the initial set of points to the final smooth path. The implementation of each technical theme revolves around path smoothness and constraint satisfaction, with rigorous logic and mutual support.

[0238] For example, control point adjustment and smoothness analysis complement each other to ensure path quality. The resulting path description data provides a reliable foundation for subsequent applications, demonstrating the practicality and efficiency of the technology.

[0239] Furthermore, the Monte Carlo method is used to evaluate the path execution probability in a dynamic battlefield simulation. If the execution probability is higher than a preset threshold, the process of generating a final path instruction sequence including speed and direction control signals includes:

[0240] The probability distribution of the smooth path curve is obtained from the dynamic battlefield simulation through the Monte Carlo method to obtain the execution probability value;

[0241] Use the probability distribution model to analyze the comparison results between the execution probability value and the preset threshold to determine the feasibility of the path;

[0242] If the path feasibility is determined to be executable, the speed control signal is extracted from the smooth path curve to generate a preliminary speed command set;

[0243] Extracting direction control signals from the smooth path curve to generate a preliminary direction instruction set;

[0244] The initial speed instruction set and the initial direction instruction set are combined through the instruction sequence optimization algorithm to obtain the optimized path instruction sequence;

[0245] For the optimized path instruction sequence, obtain battlefield environment parameters and judge the adaptability of the instruction sequence;

[0246] If the adaptability of the instruction sequence passes the judgment, the final path instruction sequence is output.

[0247] More specifically, the probability distribution of the smooth path curve is obtained from the dynamic battlefield simulation through the Monte Carlo method. When obtaining the execution probability value, the dynamic battlefield simulation is constructed based on the battlefield environment parameters. The Monte Carlo method performs random sampling through the number of simulation iterations to generate a probability distribution model and calculate the execution probability value of the smooth path curve.

[0248] A probability distribution model is used to analyze the comparison results between the execution probability value and the preset threshold. When determining the feasibility of a path, the probability distribution model generates a statistical distribution based on the execution probability value. If the execution probability value is higher than the preset threshold, the path is determined to be feasible and a feasibility result is output;

[0249] If the path feasibility is determined to be executable, the speed control signal is extracted from the smooth path curve. When generating the preliminary speed instruction set, the speed-related parameters are parsed from the smooth path curve, and the preliminary speed instruction set is generated through a mapping function, which includes a timestamp and a speed value.

[0250] When extracting the direction control signal from the smooth path curve and generating the preliminary direction instruction set, the direction-related parameters are parsed from the smooth path curve and the preliminary direction instruction set is generated through vector transformation, including the timestamp and direction angle;

[0251] The instruction sequence optimization algorithm combines the preliminary speed instruction set and the preliminary direction instruction set to obtain the optimized path instruction sequence; the instruction sequence optimization algorithm adopts a dynamic programming algorithm to fuse the speed instruction set and the direction instruction set to generate a time-synchronized optimized path instruction sequence;

[0252] To optimize the path instruction sequence, obtain battlefield environment parameters and judge the adaptability of the instruction sequence, including:

[0253] Extract battlefield environment parameters from dynamic battlefield simulation. If the optimized path instruction sequence matches the environment parameters, the instruction sequence is deemed to be adaptable.

[0254] If the adaptability of the instruction sequence passes the judgment, the final path instruction sequence is output;

[0255] The optimized path instruction sequence is formatted into a standard instruction format, and the final path instruction sequence is output, including speed and direction control signals.

[0256] For example, in dynamic battlefield simulations, the Monte Carlo method generates a probability distribution of smooth path curves through random sampling. The core of the Monte Carlo method is to simulate the uncertainty of the battlefield environment, such as terrain changes or enemy movements, through a large number of random iterations.

[0257] In one embodiment, a battlefield simulation is set up for 10,000 iterations, with pathpoint coordinates randomly sampled each time to generate a probability distribution model for the path curve. A path execution probability value, such as 0.85, indicates that the path successfully traverses obstacles in 85% of simulations. If the preset threshold is 0.8, the path is deemed feasible. This method offers the advantage of quantifying the reliability of the path in complex environments.

[0258] Specifically, when the probability distribution model analyzes the execution probability value, the feasibility of the path can be judged based on the statistical distribution.

[0259] In one possible implementation, the probability distribution model uses a normal distribution with a mean of 0.85 and a standard deviation of 0.05. If the execution probability value is higher than a threshold of 0.8, the path feasibility is passed.

[0260] For example, the probability value of a certain path is 0.9, which is significantly higher than the threshold, indicating that it has high stability in a dynamic environment. The advantage of this analysis method is that it intuitively reflects the robustness of the path through statistical means.

[0261] In one embodiment, when extracting the speed control signal from the smooth path curve, the geometric characteristics of the path curve may be analyzed.

[0262] For example, if a certain segment of a path curve has low curvature, this is mapped to a speed value of 10 m / s. A command with a timestamp of 1 second and a speed of 10 m / s is generated. This creates a preliminary set of speed commands covering the entire path segment. The advantage of this approach is that it ensures that the speed commands are consistent with the path geometry, improving execution accuracy.

[0263] Preferably, the extraction of the direction control signal depends on the tangent vector of the path curve.

[0264] For example, if the tangent vector at a certain point on a path has a heading angle of 30 degrees, vector transformation generates a heading instruction with a timestamp of 1 second and a heading angle of 30 degrees. This generates a preliminary heading instruction set, ensuring the continuity of the path direction. The advantage of this approach is that the heading instructions closely match the path geometry, minimizing deviations.

[0265] For example, the instruction sequence optimization algorithm uses dynamic programming to fuse speed and direction instruction sets.

[0266] In one possible implementation, a dynamic programming algorithm uses time synchronization as the goal, combining a speed command of 10 meters per second with a direction command of 30 degrees to generate an optimized path command sequence. This approach has the advantage of ensuring temporal consistency in the command sequence, avoiding execution conflicts.

[0267] It's understandable that judging the adaptability of a command sequence requires obtaining battlefield environmental parameters, such as a wind speed of 5 meters per second or a terrain slope of 10 degrees. If the speed and direction instructions of the optimized path command sequence meet these parameters, for example, if the speed does not exceed the terrain limits, then the adaptability is determined to be passed. This judgment method has the advantage of ensuring that the command sequence is compatible with the actual environment.

[0268] It should be noted that the output of the final path instruction sequence must be formatted in a standard instruction format.

[0269] For example, a command sequence containing a timestamp of 1 second, a speed of 10 meters per second, and a direction angle of 30 degrees is formatted as a JSON structure. This formatting method facilitates system parsing and execution, improving command transmission efficiency.

[0270] Example 2

[0271] like Figure 2 As shown, based on the same inventive concept, this embodiment also provides an unmanned target aircraft flight path planning system, including:

[0272] Data acquisition module, used to obtain dynamic battlefield environment data;

[0273] A path planning module is used to generate a first path node sequence by assigning dynamic weights using an A* algorithm based on the threat area coordinates in the dynamic battlefield environment data;

[0274] a communication evaluation module, configured to calculate the signal strength of each node according to the first path node sequence using a path loss model, evaluate the signal attenuation probability using a Monte Carlo method, and generate a communication quality weight sequence;

[0275] A path optimization module is configured to use a genetic algorithm to optimize the first path node sequence and generate a second path node sequence if there are nodes in the communication quality weight sequence that are lower than a preset threshold;

[0276] a deviation calculation module, configured to calculate the Euclidean distance deviation by fusing the inertial navigation and global positioning data through Kalman filtering according to the second path node sequence, and generate a deviation data sequence;

[0277] A local correction module is configured to use a quadratic programming algorithm to perform local correction on the corresponding path segment if a deviation value exceeding a preset threshold value exists in the deviation data sequence, thereby generating a third path node sequence;

[0278] A path smoothing module is used to generate smooth path curve parameters by optimizing the control point positions using a B-spline curve fitting algorithm combined with motion constraints according to the third path node sequence;

[0279] The path execution module is used to evaluate the path execution probability in a dynamic battlefield simulation using the Monte Carlo method based on the smooth path curve parameters. If the execution probability is higher than a preset threshold, a final path instruction sequence containing speed and direction control signals is generated.

[0280] The unmanned drone flight path planning system provided in this embodiment has all the advantages of the unmanned drone flight path planning method provided in the first embodiment.

[0281] The above are merely preferred embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for planning a flight path of an unmanned target aircraft, characterized in that: include: Acquire dynamic battlefield environment data, and generate a first path node sequence by assigning dynamic weights using an A* algorithm based on threat area coordinates in the dynamic battlefield environment data; Calculating the signal strength of each node using a path loss model based on the first path node sequence, evaluating the signal attenuation probability using a Monte Carlo method, and generating a communication quality weight sequence; If there are nodes in the communication quality weight sequence whose weights are lower than a preset threshold, optimizing the first path node sequence using a genetic algorithm to generate a second path node sequence; According to the second path node sequence, calculating the Euclidean distance deviation by fusing the inertial navigation and global positioning data through Kalman filtering to generate a deviation data sequence; If there is a deviation value exceeding a preset threshold in the deviation data sequence, a quadratic programming algorithm is used to locally correct the corresponding path segment to generate a third path node sequence; According to the third path node sequence, a B-spline curve fitting algorithm is used in combination with motion constraints to optimize the control point positions and generate smooth path curve parameters; According to the smooth path curve parameters, the path execution probability is evaluated in a dynamic battlefield simulation using the Monte Carlo method. If the execution probability is higher than a preset threshold, a final path instruction sequence including speed and direction control signals is generated.

2. The method according to claim 1, characterized in that The process of obtaining dynamic battlefield environment data includes: Collect dynamic battlefield environment data through radar, infrared and optical sensors to obtain multi-source sensor data sets; Preprocessing the multi-source sensor data set using a multi-sensor fusion algorithm to obtain preliminary fusion data; The Kalman filter algorithm is applied to the preliminary fusion data for optimization processing to obtain smooth target position, threat area coordinates and terrain height information; If the distance between the target location and the coordinates of the threat area is less than a preset threshold, the high-risk targets are determined through coordinate information analysis and a high-risk target list is obtained; Calculating the relative height of the target relative to the terrain based on the high-risk target list and terrain height information to obtain target terrain association data; Using the target terrain association data, a clustering algorithm is used to spatially group the targets to obtain a target distribution pattern; According to the target distribution pattern, real-time spatial data of the dynamic battlefield environment is generated to obtain battlefield situation information.

3. The method according to claim 1, characterized in that The process of using the A* algorithm to assign dynamic weights to generate the first path node sequence includes: Extracting threat area coordinates and threat level information based on the dynamic battlefield environment data, and determining a threat area division result; Calculating the dynamic weights of the threat areas according to the threat level information by a linear mapping method to obtain a weight distribution table; wherein the dynamic weights are determined based on the linear mapping of the threat levels; If the dynamic weight exceeds the preset threshold, the A* algorithm is used to generate the initial first path node sequence based on the weight distribution table to determine the initial path plan; According to the initial path planning, the environmental data change trend in the path node sequence is obtained to determine whether the path passes through a high-threat area, and an optimization demand assessment is obtained; If the optimization demand assessment shows that the path passes through a high-threat area, the path is recalculated using the Dijkstra algorithm, and the node sequence is adjusted based on the dynamic weight to generate an adjusted first path node sequence; Obtain the environmental data of the adjusted first path node sequence, use data fusion technology to integrate the threat area coordinates and dynamic weights, and determine the final path plan; Through the final path planning, the coordinate data of the path node sequence is generated, and the optimized first path node sequence is output.

4. The method according to claim 1, wherein The process of generating a communication quality weight sequence includes: By parsing the first path node sequence, the position distribution of each node and the signal propagation distance are obtained, and the initial signal strength is determined; The path loss model is used in combination with environmental interference factors to calculate the signal strength of each node and obtain a signal strength sequence; If the signal strength is lower than the preset threshold, the Monte Carlo method is used to simulate the signal attenuation probability and generate an attenuation probability distribution; According to the attenuation probability distribution, the communication quality weight of each node is calculated to obtain the communication quality weight sequence; Based on the weight sequence generation results, evaluate the communication quality and determine whether there are low-quality nodes; If there are low-quality nodes, adjust the node position distribution and recalculate the signal strength sequence; The final communication quality weight sequence is generated by iteratively optimizing the weight sequence.

5. The method according to claim 1, wherein The process of generating the second path node sequence includes: If there are nodes in the communication quality weight sequence whose values ​​are lower than the preset threshold, obtaining node identifiers of the nodes whose values ​​are lower than the preset threshold from the communication quality weight sequence to obtain a set of nodes to be optimized; Initializing a population of a first path node sequence using a genetic algorithm according to the set of nodes to be optimized to generate an initial path node sequence set; For the initial path node sequence set, calculating the weighted sum of the communication quality weight and the path length of each path to obtain a fitness function value set; If there is a path in the fitness function value set that is lower than a preset fitness threshold, a new path node sequence set is generated through crossover and mutation operations of the genetic algorithm; Recalculating the weighted sum of the communication quality weight and the path length according to the new set of path node sequences to obtain an updated set of fitness function values; By comparing the updated fitness function value sets, the path node sequence with the highest fitness value is selected to generate a second path node sequence; According to the second path node sequence, the node connection relationship of the communication network is adjusted to determine the optimized communication path configuration.

6. The method according to claim 1, characterized in that The process of generating a deviation data series includes: Acquire inertial navigation data and global positioning data through the second path node sequence, perform preliminary fusion using Kalman filtering, and obtain initial fused data; For the initial fusion data, calculate the Euclidean distance deviation between each node to generate a preliminary deviation data sequence; If there are abnormal values ​​in the preliminary deviation data sequence, the abnormal values ​​are eliminated through a preset threshold judgment to obtain a corrected deviation data sequence; According to the corrected deviation data sequence, a quadratic Kalman filter is used to optimize data smoothness to generate an optimized deviation data sequence; Extracting deviation statistical features from the optimized deviation data sequence, calculating the deviation mean and variance, and obtaining deviation distribution characteristics; According to the deviation distribution characteristics, the least square method is used to fit the deviation trend and construct a deviation trend model; According to the deviation trend model, the deviation sequence of subsequent path nodes is predicted to obtain the deviation data sequence.

7. The method according to claim 1, characterized in that The process of generating the third path node sequence includes: If there is a deviation value exceeding a preset threshold value in the deviation data sequence, an abnormal deviation point is determined by threshold judgment to obtain an abnormal point set; Analyze the correspondence between the set of outliers and the path segments, obtain the path segments to be optimized, and determine the set of segments to be optimized; Using a quadratic programming algorithm to locally optimize the set of segments to be optimized, and generating a temporary path node sequence; If the deviation between the temporary path node sequence and the original path segment still exceeds the preset threshold, the optimized path node sequence is obtained by iteratively adjusting the parameters of the quadratic programming algorithm; According to the optimized path node sequence, obtaining the continuity characteristics of the node sequence and determining the smoothness of the sequence; According to the smoothness judgment result, the spline interpolation algorithm is used to smooth the optimized path node sequence to generate the third path node sequence; If the deviation value of the third path node sequence meets the preset threshold, the final path node sequence is generated through sequence integration.

8. The method according to claim 1, characterized in that The process of generating smooth path curve parameters includes: Based on the third path node sequence, extracting node coordinates and connection order through preprocessing to determine an initial path point set; Using a B-spline curve fitting algorithm, the initial positions of the control points are calculated according to the initial path point set to obtain preliminary curve parameters; If the preliminary curve parameters satisfy the motion constraints, retaining the control point position; If not, the control points are adjusted according to the constraints to generate an optimized control point set; Recalculating the B-spline curve through the optimized control point set to obtain smooth path curve parameters; Analyzing the path smoothness according to the smooth path curve parameters, and if the smoothness is lower than a preset threshold, iteratively adjusting the control point positions to determine a final control point set; generating a smooth path curve according to the final control point set, and outputting curve parameters and a path point sequence; The path geometric features are extracted from the output curve parameters, the path description data is generated, and the final smooth path is determined.

9. The method according to claim 1, characterized in that The process of evaluating the path execution probability in a dynamic battlefield simulation using a Monte Carlo method and generating a final path instruction sequence including speed and direction control signals if the execution probability is higher than a preset threshold includes: The probability distribution of the smooth path curve is obtained from the dynamic battlefield simulation through the Monte Carlo method to obtain the execution probability value; Using a probability distribution model to analyze the comparison result between the execution probability value and a preset threshold value to determine the feasibility of the path; If the path feasibility is determined to be executable, the speed control signal is extracted from the smooth path curve to generate a preliminary speed command set; Extracting direction control signals from the smooth path curve to generate a preliminary direction instruction set; Combining the preliminary speed instruction set and the preliminary direction instruction set through an instruction sequence optimization algorithm to obtain an optimized path instruction sequence; For the optimized path instruction sequence, obtain battlefield environment parameters and judge the adaptability of the instruction sequence; If the adaptability of the instruction sequence passes the judgment, the final path instruction sequence is output.

10. An unmanned target aircraft flight path planning system, characterized in that: include: Data acquisition module, used to obtain dynamic battlefield environment data; A path planning module, configured to generate a first path node sequence by assigning dynamic weights using an A* algorithm based on the threat area coordinates in the dynamic battlefield environment data; a communication evaluation module, configured to calculate the signal strength of each node according to the first path node sequence using a path loss model, evaluate the signal attenuation probability using a Monte Carlo method, and generate a communication quality weight sequence; A path optimization module, configured to optimize the first path node sequence using a genetic algorithm to generate a second path node sequence if there are nodes in the communication quality weight sequence whose weights are lower than a preset threshold; a deviation calculation module, configured to calculate the Euclidean distance deviation by fusing inertial navigation and global positioning data through Kalman filtering according to the second path node sequence, and generate a deviation data sequence; a local correction module, configured to use a quadratic programming algorithm to perform local correction on the corresponding path segment if a deviation value exceeding a preset threshold value exists in the deviation data sequence, so as to generate a third path node sequence; a path smoothing module, configured to generate smooth path curve parameters by optimizing control point positions using a B-spline curve fitting algorithm combined with motion constraints according to the third path node sequence; A path execution module is used to evaluate the path execution probability in a dynamic battlefield simulation using the Monte Carlo method based on the smooth path curve parameters, and to generate a final path instruction sequence including speed and direction control signals if the execution probability is higher than a preset threshold.

Images