Unmanned aerial vehicle control path optimization system and method

Abstract

The invention relates to an unmanned aerial vehicle control path optimization system and method, and relates to the technical field of unmanned aerial vehicles, and the method comprises the steps: converting a plurality of optimization targets into a plurality of single optimization targets, so as to obtain a plurality of single targets; acquiring flight environment information according to the plurality of single targets, and preprocessing the flight environment information to obtain preprocessed data; path planning is carried out according to the preprocessed data, each ant is regarded as a potential flight path explorer, and path searching is carried out to construct a solution space; performing ant search according to the solution space, and updating pheromones to obtain a flight path; iterating the flight path to obtain an iteration result of the ant colony; and according to an iteration result of the ant colony, evaluating ant walking paths of the plurality of optimization targets to obtain final flight paths of the plurality of optimization targets. According to the invention, the flight efficiency and safety of the unmanned aerial vehicle in a complex environment can be improved, and diversified task requirements can be met.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to a system and method for optimizing a control path of an unmanned aerial vehicle. Background Art

[0002] When performing missions, drones need to face complex flight environments and diverse mission requirements. How to optimize their flight paths and ensure efficient and safe flight has become a core research issue.

[0003] Some traditional UAV path planning methods only focus on a single optimization goal, such as pursuing the shortest flight time or the lowest energy consumption. However, in practical applications, UAVs usually need to consider multiple optimization goals at the same time, such as ensuring flight safety, shortening flight time, reducing energy consumption, and achieving effective coverage of waypoints. The complexity of this multi-objective optimization makes traditional path planning methods seem incapable of meeting the requirements. Summary of the invention

[0004] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art and provide a UAV control path optimization system and method, which can improve the flight efficiency and safety of the UAV in complex environments while meeting diverse mission requirements.

[0005] In order to solve the above technical problems, the basic concept of the technical solution adopted by the present invention is:

[0006] In a first aspect, a method for optimizing a control path of a UAV is provided, comprising:

[0007] Convert multiple optimization objectives into multiple single optimization objectives to obtain multiple single objectives;

[0008] Acquiring flight environment information according to multiple single targets, and preprocessing the flight environment information to obtain preprocessed data;

[0009] Perform path planning based on preprocessed data, consider each ant as a potential flight path explorer, and perform path search to construct a solution space;

[0010] Ants search the solution space and update pheromones to obtain the flight path;

[0011] Iterate the flight path to obtain the iteration result of the ant colony;

[0012] According to the iteration results of the ant colony, the paths that the ants walk are evaluated for multiple optimization objectives to obtain the final flight paths of multiple optimization objectives.

[0013] In a preferred embodiment of any of the above schemes, the flight environment information includes meteorological conditions, topography and airspace restrictions.

[0014] In any of the above schemes, a preferred embodiment performs path planning based on preprocessed data, regards each ant as a potential flight path explorer, and performs path search to construct a solution space, including:

[0015] Consider each ant as a potential flight path explorer to set the number of ants;

[0016] According to the number of ants, define pheromones and initialize the pheromone matrix to obtain initialization parameters;

[0017] According to the initialization parameters, the grid of the flight environment is constructed to obtain the solution space.

[0018] In any of the above schemes, a preferred embodiment performs ant search according to the solution space and updates pheromones to obtain a flight path, including:

[0019] According to the solution space, all ants are placed at the starting point. The ants choose the next moving position according to the pheromone concentration and heuristic information of the current position; each ant selects and moves to the next position according to the movement rule; when the ant moves to a new position, the pheromone concentration of the new position is updated;

[0020] After all ants have completed their local path search, the global pheromone matrix is ​​updated based on the quality of the local path found by each ant;

[0021] According to the global pheromone matrix, the final path is extracted and recorded as the flight path.

[0022] In any of the above schemes, a preferred embodiment evaluates the paths of ants walking according to the iteration results of the ant colony for multiple optimization objectives to obtain the final flight paths of multiple optimization objectives, including:

[0023] According to the iteration results of the ant colony, the path of the ants is optimized to obtain the optimization result;

[0024] According to the optimization result, the comprehensive objective function value of the flight path is evaluated to obtain an evaluation result;

[0025] Based on the analysis of the evaluation results, the final flight path of multiple optimization objectives is obtained.

[0026] In a second aspect, a UAV control path optimization system is characterized by comprising:

[0027] The acquisition module is used to convert multiple optimization objectives into multiple single optimization objectives to obtain multiple single objectives; obtain flight environment information based on the multiple single objectives, and preprocess the flight environment information to obtain preprocessed data; perform path planning based on the preprocessed data, regard each ant as a potential flight path explorer, and perform path search to construct a solution space.

[0028] The processing module is used to perform ant search according to the solution space and update pheromones to obtain a flight path; iterate the flight path to obtain an iterative result of the ant colony; and evaluate the ant walking path for multiple optimization objectives according to the iterative result of the ant colony to obtain a final flight path of multiple optimization objectives.

[0029] After adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art:

[0030] By converting multiple optimization objectives into a single objective for processing, the complex multi-objective optimization problem is effectively simplified. By preprocessing the flight environment information and using the ant colony algorithm for path planning, the optimization efficiency of the UAV control path can be significantly improved. By comprehensively considering various factors of the flight environment, the UAV can better adapt to environmental changes in actual flight. Through iterative optimization and comprehensive evaluation, the quality of the flight path can be continuously improved to ensure that the UAV can fly along the optimal path. Multiple optimization objectives can be comprehensively considered so that the final flight path can meet the diverse needs in different scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. Some specific embodiments of the present application will be described in detail in an illustrative and non-restrictive manner with reference to the drawings. The same reference numerals in the drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the drawings:

[0032] Figure 1 It is a schematic diagram of the UAV control path optimization method of the present invention.

[0033] Figure 2 It is a schematic diagram of a control system of the unmanned aerial vehicle control path optimization method of the present invention.

[0034] It should be noted that these drawings and text descriptions are not intended to limit the conceptual scope of the present invention in any way, but to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. The elements in the drawings are schematic and not drawn to scale. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0036] The following embodiment of the present application takes the UAV control path optimization method as an example to explain the solution of the present application in detail, but this embodiment cannot limit the protection scope of the present application.

[0037] like Figure 1 As shown, the present invention provides a method for optimizing a control path of a UAV, comprising the following steps:

[0038] Step 11, converting the multiple optimization objectives into multiple single optimization objectives to obtain multiple single objectives;

[0039] Step 12, acquiring flight environment information according to the multiple single targets, and preprocessing the flight environment information to obtain preprocessed data, the flight environment information including meteorological conditions, topography and airspace restrictions;

[0040] Step 13, perform path planning based on the preprocessed data, regard each ant as a potential flight path explorer, and perform path search to construct a solution space;

[0041] Step 14, perform ant search according to the solution space and update pheromone to obtain the flight path;

[0042] Step 15, iterating the flight path to obtain the iteration result of the ant colony;

[0043] Step 16, based on the iteration result of the ant colony, the paths of the ants' walks are evaluated for multiple optimization targets to obtain the final flight paths of the multiple optimization targets.

[0044] In the embodiment of the present invention, step 11, by decomposing complex multiple goals into a single goal, it is easier to set specific optimization strategies and evaluation criteria for each goal, thereby reducing the complexity of the problem. Step 12, this step ensures that the planning of the UAV flight path is based on actual environmental conditions. Through detailed understanding and preprocessing of flight environment information, the accuracy and practicality of path planning can be improved, ensuring that the UAV can avoid adverse conditions such as bad weather, complex terrain or airspace restrictions during flight. Step 13, using the ant colony algorithm for path planning, it is possible to explore a variety of possible flight paths. Each ant represents a potential solution, and through their search behavior, a solution space containing a variety of possible paths can be constructed. Step 14, by simulating the pheromone update mechanism of ants, the optimal or approximately optimal flight path can be found among many potential paths. The update of pheromones reflects the quality of the path, making it easier for excellent paths to be selected by subsequent ants, thereby gradually converging to the optimal solution. Step 15, the iterative process helps to further optimize the flight path. Through multiple iterations, the ant colony algorithm can continuously approach the optimal solution and improve the quality and efficiency of path planning. Step 16, this step comprehensively considers multiple optimization objectives and comprehensively evaluates the flight path obtained after iteration. This ensures that the final flight path not only meets the requirements of a single optimization objective, but also achieves a balance between multiple objectives. Such a path has more practical application value and can meet the various needs of UAV flight.

[0045] When applied specifically, the following steps are included:

[0046] Step 11. In the path planning of the UAV, there may be multiple optimization objectives, such as minimizing flight time, minimizing energy consumption, maximizing flight safety, etc. Decompose these multiple optimization objectives into single independent optimization objectives. For example, "minimizing flight time" can be used as a single objective, "minimizing energy consumption" can be used as another single objective, and so on. For each single objective, a quantitative standard or indicator needs to be determined to measure its achievement. For example, flight time can be measured by total flight time, and energy consumption can be measured by total power consumption or fuel consumption. According to the actual situation, these single objectives can be prioritized so that they can be focused in the subsequent optimization process.

[0047] Step 12, using the sensors carried by the drone or other external data sources, collect information related to the flight environment, such as meteorological conditions (wind speed, wind direction, temperature, humidity, etc.), topography (altitude, slope, obstacle distribution, etc.) and airspace restrictions (no-fly zones, restricted-fly zones, etc.); clean the collected raw data, remove erroneous or invalid data, and then organize and format it; pre-process the cleaned data according to the needs of each single goal. For example, for the goal of "minimizing flight time", it may be necessary to extract meteorological conditions that affect flight speed; for the goal of "minimizing energy consumption", it may be necessary to analyze topographic data to predict energy consumption during flight. Convert the pre-processed data into a unified format and standard for use in subsequent path planning algorithms.

[0048] When applied specifically, the following steps are included:

[0049] Suppose a drone company needs to design an optimal flight path for its drone from point A to point B. Considering the three optimization goals of flight time, energy consumption, and flight safety, the following steps can be followed:

[0050] Step 11: Consider the three optimization goals of "minimizing flight time", "minimizing energy consumption" and "maximizing flight safety" as single objectives respectively; for each single objective, set corresponding quantitative indicators. For example, flight time can be measured by the total time from A to B; energy consumption can be measured by the total power consumption of this flight; flight safety can be evaluated by avoiding obstacles and dangerous areas during the flight.

[0051] Step 12, use the sensors on the drone to collect flight environment information, including wind speed, wind direction, temperature, terrain height, obstacle distribution, and no-fly zones; clean and organize the collected data to remove invalid or erroneous data. Perform preprocessing according to each single goal. For example, in order to minimize flight time, it is necessary to analyze the impact of meteorological conditions on flight speed; in order to minimize energy consumption, it is necessary to analyze the impact of terrain and wind speed on energy consumption; in order to maximize flight safety, obstacles and no-fly zones need to be identified and avoided. Convert the preprocessed data into a unified format for use in the path planning algorithm.

[0052] In a preferred embodiment of the present invention, the above step 13, performing path planning according to the preprocessed data, treating each ant as a potential flight path explorer, and performing path search to construct a solution space, may include:

[0053] Step 131, treating each ant as a potential flight path explorer to set the number of ants;

[0054] Step 132, defining pheromones according to the number of ants, and initializing the pheromone matrix to obtain initialization parameters;

[0055] Step 133, constructing a grid of the flight environment according to the initialization parameters to obtain a solution space.

[0056] In the embodiment of the present invention, step 13, by simulating the foraging behavior of ants, each ant independently performs path search, thereby realizing parallel processing and improving search efficiency. The ant colony algorithm can adaptively adjust the search direction according to the update of pheromones and gradually approach the optimal solution. Since multiple ants are used for parallel search, the algorithm has a low dependence on the initial solution and has strong robustness.

[0057] Step 131, by setting the number of ants, the search breadth and depth of the algorithm can be controlled to adapt to different optimization requirements and computing resources. Each ant represents a potential flight path explorer, which increases the diversity of solutions in the search process and helps avoid falling into local optimality. Step 132, pheromones, as a medium for indirect communication between ants, can guide the ant colony to search for a better path and improve search efficiency. Reasonable initialization of the pheromone matrix can lay a good foundation for the subsequent search process and accelerate the convergence of the algorithm. Step 133, by gridding the flight environment, the continuous path planning problem can be discretized, simplifying the complexity of the problem. The gridded environment model is easier to visualize and analyze data, which helps to understand and explain the operation process and results of the algorithm. The gridded environment provides ants with clear movement rules and search space, so that each ant can effectively explore paths within a limited solution space.

[0058] When applied specifically, the following steps are specifically included:

[0059] Step 131, according to the complexity of the problem and the computing resources, set an appropriate number of ants. A larger number of ants can increase the diversity of the search, but it will also increase the computing burden. Each ant is assigned a starting position, which is usually random or selected according to a specific strategy. Each ant will start its path exploration from this starting position.

[0060] Step 132, pheromone is a key element in the ant colony algorithm, which simulates the chemical substances released by real ants in the process of searching for food. In the algorithm, pheromones are used to guide the search direction of ants. According to the grid size of the flight environment, a pheromone matrix corresponding to the grid is created. Each grid cell has a corresponding pheromone value. Initially, these values ​​can be set to the same constant or initialized according to a certain strategy.

[0061] Step 133, abstract the flight environment into a grid model, where each grid unit represents a feasible flight area. The size and resolution of the grid are determined according to actual needs and environmental characteristics. Obstacles, no-fly zones and other unreachable areas, as well as the starting point and target point of the flight are marked in the grid. The solution space is a set of all possible flight paths. In the ant colony algorithm, each ant moves on the grid and explores different paths to construct this solution space.

[0062] For example, suppose a drone needs to fly from point A to point B, and there are some obstacles and no-fly zones in the flight environment. The ant colony algorithm can be used for path planning. Step 131: Set the number of ants to 10, and each ant starts its path exploration from point A. Step 132: Define a 10x10 pheromone matrix, and initially, the pheromone value of each grid cell is set to 1. Step 133: Model the flight environment as a 10x10 grid, where some grids are marked as obstacles or no-fly zones. Point A is located in the upper left corner of the grid, and point B is located in the lower right corner of the grid. Each ant will move on this grid, trying to find the optimal path from A to B. As the algorithm runs, each ant will choose the next grid cell to move to based on pheromone and heuristic information. When all ants have completed a path exploration, the pheromone matrix will be updated to guide the ants' search direction in the next iteration. After multiple iterations, the algorithm will converge to an optimal or nearly optimal flight path.

[0063] In a preferred embodiment of the present invention, the above step 14, performing ant search according to the solution space and updating pheromones to obtain a flight path, includes:

[0064] Step 141, according to the solution space, all ants are placed at the starting point, and the ants select the next moving position according to the pheromone concentration and heuristic information of the current position; each ant selects and moves to the next position according to the movement rule; when the ant moves to a new position, the pheromone concentration of the new position is updated;

[0065] Step 142, after all ants have completed the local path search, the global pheromone matrix is ​​updated according to the quality of the local path found by each ant;

[0066] Step 143, extracting and recording the final path as the flight path according to the global pheromone matrix.

[0067] In the embodiment of the present invention, through the search of ants in the solution space and the update of pheromones, the algorithm can adaptively adjust the search strategy and gradually focus on a better path. Multiple ants search at the same time, which increases the parallelism of the search and helps to find a better solution in a shorter time. Through the volatilization and update mechanism of pheromones, the algorithm can avoid falling into the local optimum to a certain extent and continue to explore better solutions.

[0068] In step 141, when the ants select the next location, they not only rely on the pheromone concentration, but also combine heuristic information (such as distance, visibility, etc.), which helps guide the ants to move in the target direction and improve the search efficiency. Every time the ants move to a new location, they update the pheromone at that location. This local update strategy can reflect the quality of the path in real time and provide useful guidance for the subsequent ant searches.

[0069] Step 142, after all ants have completed the local search, the global pheromone matrix is ​​updated according to the quality of the local path found by each ant, which realizes the global fusion of local information and helps the algorithm to quickly converge to a better solution. The pheromone is updated by evaluating the path quality, so that high-quality paths are marked more and the pheromone of poor-quality paths is gradually reduced, thereby guiding subsequent searches to be more accurate. Step 143, extracting the final path according to the global pheromone matrix ensures that the selected path is the optimal or approximately optimal solution found in the current search process. Extracting and recording the final flight path not only facilitates subsequent analysis and optimization, but also provides clear guidance for actual flight. In summary, step 14 and its sub-steps achieve beneficial effects such as self-adaptation, parallel search and avoidance of local optimality in path planning by simulating the foraging behavior of ant colonies, providing an effective solution for the optimization of drone control paths.

[0070] For example, a solution space is constructed based on preprocessed terrain and meteorological data and divided into a grid map. Each grid contains terrain height, obstacle information, and initial pheromone concentration. Then, a certain number of ants (for example, 10) are placed at the starting point A. Each ant will choose the next grid position to move to based on the pheromone concentration and heuristic information (such as the straight-line distance from the target point) at the current position. The ants move gradually toward the target point B according to the set movement rules (such as selecting the direction with the largest weighted sum of pheromone concentration and heuristic information). Whenever the ant moves to a new grid position, the pheromone concentration of that position will be updated according to certain rules, such as adding a certain amount of pheromone.

[0071] When all ants have completed the local path search from the starting point A to the target point B, the quality of the path found by each ant is evaluated. The evaluation of path quality can be based on multiple factors, such as the total length of the path, safety (the degree of avoiding obstacles), etc. Next, the global pheromone matrix is ​​updated according to the quality of the local path found by each ant. For paths with higher quality, the pheromone concentration on it will be increased; for paths with lower quality, the pheromone concentration may be reduced or remain unchanged. After multiple iterations (i.e., multiple rounds of ant searches and pheromone updates), the global pheromone matrix will gradually converge to reflect the optimal or nearly optimal flight path. Finally, the path with the highest pheromone concentration is extracted according to the global pheromone matrix, which is the optimal flight path for the drone from the distribution center to the remote village. This path is recorded and used to guide the actual flight of the drone.

[0072] In a preferred embodiment of the present invention, the formula for updating the pheromone concentration at a new location is:

[0073]

[0074] Among them, τ ij (t+1) represents the pheromone concentration on path (i, j) at time t+1, τ ij (t) represents the pheromone concentration on the path (i, j) at the current time t, ρ represents the pheromone evaporation rate, Q represents the pheromone constant, which is used to control the total amount of pheromone released by ants, and L k represents the total length of the path traveled by the kth ant in this iteration, m represents the total number of ants; δ ij k(t) is an indicator function used to determine whether the kth ant has moved from one location i to another location j at the current time t. If so, the value is 1; otherwise, the value is 0; k is an iteration variable that traverses all ants, and t represents the current time.

[0075] In an embodiment of the present invention, by introducing the pheromone evaporation coefficient, the volatilization process of pheromones in the real world can be simulated, which helps to prevent excessive accumulation of old pheromones and cause the algorithm to converge to a non-optimal solution prematurely. The evaporation of pheromones prompts ants to continue exploring new paths instead of relying solely on already marked high-pheromone paths, thereby increasing the possibility of finding a global optimal solution. Controlling the total amount of pheromones is used to adjust the total amount of pheromones released by ants during movement, which helps to balance the exploration and development capabilities of the algorithm. Using the total length of the path traversed by the kth ant as the denominator means that shorter paths will get more pheromone increments. This encourages ants to find shorter paths, thereby improving the optimization performance of the algorithm. By using the indicator function δ ijk(t) ensures that only the pheromones on the paths actually walked by the ants are updated. This precise update mechanism avoids unnecessary pheromone changes and makes the algorithm more efficient and accurate. By searching in parallel with multiple ants m and updating the pheromone based on the path selection of each ant, the diversity of search and global search capability are increased. The iteration variable k ensures that the contributions of all ants are taken into account, resulting in a more comprehensive pheromone update. In summary, this formula achieves the efficiency and accuracy of the ant colony algorithm in path planning by comprehensively considering pheromone evaporation, total pheromone control, path quality feedback, precise update, and parallel search. These beneficial effects jointly promote the performance improvement of the algorithm in finding the optimal or approximately optimal path.

[0076] In a preferred embodiment of the present invention, the above step 16, based on the iteration result of the ant colony, evaluates the paths of the ants walking for multiple optimization objectives to obtain the final flight paths of the multiple optimization objectives, including:

[0077] Step 161, optimizing the path of the ants according to the iteration result of the ant colony to obtain an optimization result;

[0078] Step 162, evaluating the comprehensive objective function value of the flight path according to the optimization result to obtain an evaluation result;

[0079] Step 163, based on the analysis of the evaluation results, a final flight path of multiple optimization objectives is obtained.

[0080] In an embodiment of the present invention, by optimizing the path of ants walking, unnecessary detours and redundancy can be eliminated, making the flight path more direct and efficient, helping to reduce flight time and energy consumption, and improving the operating efficiency of the drone. Step 16 takes into account multiple optimization objectives, such as path length, safety, flight time, etc. By comprehensively evaluating these objectives, a flight path that performs well in many aspects can be obtained. This multi-objective optimization method makes the algorithm more flexible and practical, and can adapt to different scenarios and needs. By evaluating the comprehensive objective function value of the flight path, the algorithm can automatically adjust the search strategy to adapt to different environments and task requirements. This adaptability enables the algorithm to find the optimal or approximately optimal flight path in various complex situations. The evaluation results provide a quantitative basis for decision makers, helping them to choose the most appropriate flight path according to actual needs, which is particularly important for situations where quick decisions need to be made, such as emergency rescue, material transportation, etc. By evaluating and analyzing the optimization results, deviations in the search process can be discovered and corrected in a timely manner, thereby accelerating the convergence speed of the algorithm. This helps to improve the operating efficiency and solution quality of the algorithm. In summary, step 16 and its sub-steps achieve beneficial effects such as improving path quality, multi-objective optimization, enhancing algorithm adaptability, providing decision support, and promoting algorithm convergence by optimizing the path of ants, evaluating the comprehensive objective function value of the flight path, and analyzing the evaluation results. These effects jointly improve the practicality and performance of the ant colony algorithm in UAV path planning.

[0081] In the specific implementation process of the present invention, step 161 collects the path information of all ants obtained after multiple iterations of the ant colony algorithm, and selects a part of the paths with better performance from these paths. Usually, based on factors such as the length, safety, and obstacle avoidance of the path, an optimization algorithm such as local search and simulated annealing is applied to the selected paths to further improve the quality of the paths. After optimization, a group of paths that perform well on multiple optimization targets are output as optimization results. Step 162 defines one or more objective functions, such as path length, flight time, energy consumption, safety, etc., according to actual needs; for each optimized path output in step 161, calculate its corresponding comprehensive objective function value; because different objective functions may have different units and magnitudes, it is necessary to normalize these objective function values ​​for unified evaluation, and output the normalized comprehensive objective function value as the evaluation result. Step 163, conduct a detailed analysis of the evaluation results output in step 162, find out the paths that perform well on multiple optimization objectives, select one or more final flight paths based on the evaluation results, conduct actual verification or simulation verification on the selected flight paths to ensure their feasibility in actual applications, and after verification, output the final flight path.

[0082] For example, suppose we are carrying out a drone express delivery mission and need to plan the optimal flight path from the starting point to the end point. We can use the ant colony algorithm for path planning and obtain the final flight path through the above step 16. Step 161, through multiple iterations of the ant colony algorithm, a large number of paths walked by ants are collected. From these paths, select paths with shorter length, avoiding obstacles and higher safety. Then apply the local search algorithm to further optimize these paths to obtain a set of optimized candidate paths. Step 162, define a comprehensive objective function, including path length, flight time and safety. For each candidate path, calculate its corresponding comprehensive objective function value. For example, the length of a path is 10km, the estimated flight time is 15 minutes, and the safety score is 0.9 (1 is the highest safety). These objective function values ​​are normalized to obtain the comprehensive evaluation result of the path. Step 163, analyze the comprehensive evaluation results of all candidate paths, and select the path that performs well in terms of length, flight time and safety as the final flight path. For example, a path may not be the shortest in length, but it has a shorter flight time and is very safe, so it is selected as the final flight path. Finally, the feasibility of the path is ensured through actual flight or simulation verification.

[0083] In a preferred embodiment of the present invention, the calculation formula of the comprehensive objective function value is:

[0084]

[0085] Where L(P) is the length of path P, V is the average flight speed of the UAV, k1 is the performance constant of the UAV; m c∈ P d is the minimum distance between the path and the obstacle, ∑ g I(g∈P) is the indicator function of the number of preset waypoints, g is the waypoint, P is the path, w T 、w E 、w S 、w C They are the weights of flight time, energy consumption, safety, and waypoint coverage, and F(P) is the calculation formula for the comprehensive objective function value.

[0086] In an embodiment of the present invention, the formula comprehensively considers multiple factors such as flight time, energy consumption, safety, and waypoint coverage, ensuring that path planning not only focuses on a single optimization goal, but also weighs and optimizes multiple key factors, which helps to find a flight path that performs well in multiple dimensions. By adjusting the weight coefficient, decision makers can emphasize or downplay certain optimization goals based on actual needs and mission characteristics. For example, in an emergency rescue mission, the weight of flight time can be increased to ensure that path planning focuses more on reducing flight time. This formula provides a quantitative evaluation standard for path planning, making the comparison between different paths more objective and accurate. By calculating the comprehensive objective function value of each path, the comprehensive performance of each path on multiple optimization goals can be intuitively understood.

[0087] Among them, the indicator function of the number of preset waypoints ∑ g The specific calculation process of I(g∈P) is as follows:

[0088] According to the mission requirements and the characteristics of the flight area, all preset waypoints are determined. These waypoints are key locations that must be visited in the mission, such as charging stations, target areas, etc. For a given path P, analyze whether it contains these preset waypoints, which can be achieved by checking the coordinate points of path P or the identifiers associated with the waypoints; for each preset waypoint, calculate the indicator function, if the preset waypoint is on path P, the indicator function is 1; otherwise, the indicator function is 0; add up the values ​​of all indicator functions to get the total number of preset waypoints included in path P.

[0089] A UAV control path optimization system, comprising:

[0090] The acquisition module is used to convert multiple optimization objectives into multiple single optimization objectives to obtain multiple single objectives; obtain flight environment information based on the multiple single objectives, and preprocess the flight environment information to obtain preprocessed data; perform path planning based on the preprocessed data, regard each ant as a potential flight path explorer, and perform path search to construct a solution space.

[0091] The processing module is used to perform ant search according to the solution space and update pheromones to obtain a flight path; iterate the flight path to obtain an iterative result of the ant colony; and evaluate the ant walking path for multiple optimization objectives according to the iterative result of the ant colony to obtain a final flight path of multiple optimization objectives.

[0092] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0093] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0094] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

Claims

1. A method for optimizing a drone control path, characterized in that: include: Convert multiple optimization objectives into multiple single optimization objectives to obtain multiple single objectives; Acquiring flight environment information according to multiple single targets, and preprocessing the flight environment information to obtain preprocessed data; Perform path planning based on preprocessed data, consider each ant as a potential flight path explorer, and perform path search to construct a solution space; Ants search the solution space and update pheromones to obtain the flight path; Iterate the flight path to obtain the iteration result of the ant colony; According to the iteration results of the ant colony, the paths that the ants walk are evaluated for multiple optimization objectives to obtain the final flight paths of multiple optimization objectives.

2. The method for optimizing the control path of a UAV according to claim 1, characterized in that: Flight environment information includes meteorological conditions, topography and airspace restrictions.

3. The method for optimizing the control path of a UAV according to claim 2, characterized in that: Path planning is performed based on the preprocessed data, each ant is considered as a potential flight path explorer, and path search is performed to construct a solution space, including: Consider each ant as a potential flight path explorer to set the number of ants; According to the number of ants, define pheromones and initialize the pheromone matrix to obtain initialization parameters; According to the initialization parameters, the grid of the flight environment is constructed to obtain the solution space.

4. The method for optimizing the control path of a UAV according to claim 3, characterized in that: Ants search the solution space and update pheromones to obtain the flight path, including: According to the solution space, all ants are placed at the starting point. The ants choose the next moving position according to the pheromone concentration and heuristic information of the current position; each ant selects and moves to the next position according to the movement rule; when the ant moves to a new position, the pheromone concentration of the new position is updated; After all ants have completed their local path search, the global pheromone matrix is ​​updated based on the quality of the local path found by each ant; According to the global pheromone matrix, the final path is extracted and recorded as the flight path.

5. The method for optimizing the control path of a UAV according to claim 4, characterized in that: According to the iteration results of the ant colony, the paths of the ants are evaluated for multiple optimization objectives to obtain the final flight paths of multiple optimization objectives, including: According to the iteration results of the ant colony, the path of the ants is optimized to obtain the optimization result; According to the optimization result, the comprehensive objective function value of the flight path is evaluated to obtain an evaluation result; Based on the analysis of the evaluation results, the final flight path of multiple optimization objectives is obtained.

6. A UAV control path optimization system, the system implementing the method as claimed in claim 1, characterized in that: include: An acquisition module, used for converting multiple optimization objectives into multiple single optimization objectives to obtain multiple single objectives; Acquiring flight environment information according to multiple single targets, and preprocessing the flight environment information to obtain preprocessed data; Perform path planning based on preprocessed data, consider each ant as a potential flight path explorer, and perform path search to construct a solution space; The processing module is used to perform ant search according to the solution space and update pheromones to obtain the flight path; Iterate the flight path to obtain the iteration result of the ant colony; According to the iteration results of the ant colony, the paths that the ants walk are evaluated for multiple optimization objectives to obtain the final flight paths of multiple optimization objectives.

7. A computing device, characterized in that include: one or more processors; A storage device, used for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images