Particle swarm optimization flight path planning method for unmanned aerial vehicle formation cooperative combat

Abstract

The invention provides a particle swarm optimization flight path planning method for unmanned aerial vehicle formation cooperative combat, and the method comprises the following steps: S1, initialization: randomly generating an initial particle swarm, each particle representing a possible unmanned aerial vehicle flight path; s2, evaluation: calculating a fitness value of each particle according to a predefined objective function; s3, updating: updating the speed and position of each particle according to the optimal position of the current particle, the global optimal position of the group and an adjustment strategy; s4, stopping conditions are checked, and if the preset maximum number of iterations is reached or other stopping standards are met, stopping is carried out; otherwise, returning to S2; and S5, result extraction: selecting an optimal solution from the final particle swarm as a cooperative flight path planning scheme of the multiple unmanned aerial vehicles. According to the particle swarm optimization flight path planning method for the unmanned aerial vehicle formation cooperative combat, the optimal or approximately optimal flight path meeting the actual combat requirement can be effectively planned, and the efficiency and the success rate of the unmanned aerial vehicle formation cooperative combat are improved.

Description

Technical Field

[0001] The present invention relates to unmanned aerial vehicle (UAV) formation cooperative operation and particle swarm optimization algorithm, and specifically to a particle swarm optimization trajectory planning method for UAV formation cooperative operation. Background Art

[0002] UAVs, due to their unique combat advantages, have been widely used in various military tasks such as reconnaissance, surveillance, and strike. When performing tasks, they can significantly improve the efficiency and success rate of task execution through formation cooperative operation. Through the mutual cooperation between multiple UAVs, rapid strikes and effective suppression of enemy targets can be achieved, thus gaining an advantage on the battlefield.

[0003] However, UAV formation cooperative operation also faces many challenges, among which trajectory planning is a key issue. Trajectory planning needs to be carried out under a series of constraints, including flight altitude, speed, fuel consumption, threat area avoidance, etc. Under these conditions, planning an optimal or near-optimal flight path for a UAV formation is a complex task. Traditional trajectory planning methods often struggle with the complexity and dynamic changes when dealing with multi-UAV cooperative operation, resulting in low planning efficiency and difficulty in meeting actual combat requirements.

[0004] Particle Swarm Optimization (PSO) is an optimization technique based on swarm intelligence. It solves optimization problems by simulating the social behavior of bird flocks or fish schools. Due to its simplicity, easy implementation, fast convergence speed, etc., the PSO algorithm performs well in solving continuous space optimization problems. In recent years, the PSO algorithm has been widely applied to the field of UAV path planning. By continuously optimizing the position and velocity of particles, it can quickly find the optimal path that meets the constraint conditions.

[0005] However, the traditional PSO algorithm still has limitations in dealing with complex constraint conditions and multi-objective optimization problems. For example, in UAV formation cooperative operation, multiple objectives such as the cooperative flight of multiple UAVs, threat avoidance, and energy consumption need to be considered simultaneously, and the traditional PSO algorithm is difficult to meet these complex requirements at the same time.

[0006] Therefore, the present invention proposes a UAV formation cooperative operation method based on an optimized particle swarm algorithm, aiming to improve its performance in dealing with complex constraint conditions and multi-objective optimization problems by improving the PSO algorithm, thereby effectively enhancing the efficiency and success rate of UAV formation cooperative operation. Summary of the Invention

[0007] The objective of the present invention is to provide a particle swarm optimization trajectory planning method for cooperative operation of UAV formations, so as to solve the problems of real-time path planning, safety and efficiency of control, and optimal path planning during the flight of UAV formations in a real environment in the prior art.

[0008] To achieve the above objective, the present invention provides the following technical solutions: The present invention provides a particle swarm optimization trajectory planning method for cooperative operation of UAV formations, including the following steps:

[0009] S1. Initialization: Randomly generate an initial particle swarm, and each particle represents a possible UAV trajectory.

[0010] S2. Evaluation: Calculate the fitness value of each particle according to a predefined objective function.

[0011] S3. Update: Update the velocity and position of each particle based on the best position of the current particle, the global best position of the group, and an adjustment strategy.

[0012] S4. Check the stop condition: If the preset maximum number of iterations is reached or other termination criteria are met, stop; otherwise, return to S2.

[0013] S5. Result extraction: Select the best solution from the final particle swarm as the cooperative trajectory planning scheme for multiple UAVs.

[0014] Preferably, in S1, it includes adaptive adjustment parameters, constraint handling, and multi-objective optimization. The adaptive adjustment parameters include dynamically adjusting the inertia weight, cognitive coefficient, social coefficient, etc., to adapt to different search stages or environmental changes.

[0015] The constraint handling of the aircraft includes dynamic limitations, obstacle avoidance rules, and flight airspace limitations. Improve the algorithm and introduce a penalty function or directly embed a constraint handling strategy in the particle update mechanism to ensure that the generated trajectory is both optimized and feasible.

[0016] The multi-objective optimization uses NSGA-II, MOEA / D to find the Pareto optimal solution set.

[0017] Preferably, in S2, the objective function is one or more of the total flight distance, energy consumption, and task completion efficiency.

[0018] Preferably, in S3, the adjustment strategy includes dynamically adjusting the inertia weight, cognitive coefficient, and social coefficient to adapt to different search stages or environmental changes.

[0019] Preferably, in S4, the other termination criteria include the degree of swarm convergence, the stability of the best solution, etc., to ensure that the algorithm can find a high-quality solution within a reasonable time. During the iteration process, each particle continuously adjusts its flight direction and speed according to its own historical experience and the experience of the entire swarm to search for a better flight path.

[0020] Preferably, in S5, the selection of the best solution is based on multiple metrics, such as the shortest total flight time, the lowest energy consumption, or the highest task completion efficiency, to ensure the effectiveness and reliability of the selected flight path plan in the actual combat environment.

[0021] The present invention has at least the following beneficial effects:

[0022] A particle swarm optimization flight path planning method for unmanned aerial vehicle formation cooperative combat provided by the present invention can quickly find the optimal or approximate optimal path that meets complex constraint conditions through the improvement of the particle swarm optimization algorithm, thereby improving the efficiency and success rate of the unmanned aerial vehicle formation in performing tasks.

[0023] By dynamically adjusting parameters such as the inertia weight, cognitive coefficient, and social coefficient, the algorithm can adapt to different search stages or environmental changes, and improve the adaptability to complex environments.

[0024] By adopting multi-objective optimization algorithms such as NSGA-II and MOEA / D, multiple objectives (such as total flight distance, energy consumption, task completion efficiency, etc.) can be considered simultaneously, and the Pareto optimal solution set can be found to meet various requirements in actual combat.

[0025] By introducing constraint handling strategies, such as penalty functions or directly embedding constraint handling in the particle update mechanism, it is ensured that the generated flight path is both optimized and feasible, avoiding the vehicle from violating dynamic limitations, obstacle avoidance rules, and flight airspace limitations.

[0026] By setting reasonable termination criteria, such as the degree of swarm convergence and the stability of the best solution, it is ensured that the algorithm can find a high-quality solution within a reasonable time, and improve the stability and reliability of flight path planning.

[0027] By optimizing the flight path planning, the total flight time and energy consumption of the unmanned aerial vehicle formation can be effectively reduced, thereby optimizing resource utilization and extending the combat endurance of the unmanned aerial vehicle.

[0028] In a dynamically changing battlefield environment, the flight path planning method of the present invention can quickly respond to environmental changes, timely adjust the flight path, and enhance the combat flexibility and reaction speed of the unmanned aerial vehicle formation. The present invention has broad application prospects and important strategic significance in the field of unmanned aerial vehicle formation cooperative combat. Description of the Drawings

[0029] Figure 1This is the flowchart of the method of the present invention;

[0030] Figure 2 This is the flowchart of the UAV path planning of the present invention;

[0031] Figure 3 This is the effect diagram of the particle swarm optimization algorithm of the present invention;

[0032] Figure 4 This is the flowchart of the particle swarm optimization algorithm of the present invention;

[0033] Figure 5 This is the flowchart of the UAV path specification of the present invention;

[0034] Figure 6 This is the evolution diagram of the particle swarm optimization algorithm to the UAV path planning algorithm of the present invention;

[0035] Figure 7 This is the simulation diagram of the evolution generation of the optimal individual of the particle swarm algorithm of the present invention;

[0036] Figure 8 This is the effect diagram of the visualization of the UAV path planning platform software of the present invention. Detailed implementation manners

[0037] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used in this specification includes any and all combinations of one or more of the related listed items.

[0038] Embodiment

[0039] As Figures 1-8 shown, a particle swarm optimization trajectory planning method for UAV formation cooperative operation includes the following steps:

[0040] S1. Initialization stage: First, it is necessary to randomly generate an initial particle swarm, and each particle represents a possible UAV flight path. The initial positions and velocities of these particles are randomly generated according to the starting point, target point of the UAV and various constraint conditions in the flight environment. At the same time, it is also necessary to initialize the individual optimal position and global optimal position in the particle swarm, and these two positions are crucial for the subsequent update of the particle positions.

[0041] S2. Evaluation stage: Calculate the fitness value of each particle according to a predefined objective function. The objective function can be a single objective, such as the total flight distance, energy consumption, task completion efficiency, etc., or a combination of these objectives, i.e., multi-objective optimization. For example, we can design an objective function aiming to minimize the weighted sum of the total flight distance and energy consumption to balance the weights between different objectives.

[0042] S3. Update stage: Update the velocity and position of each particle according to the best position of the current particle, the global best position of the swarm, and an adjustment strategy. The adjustment strategy includes dynamically adjusting the inertia weight, cognitive coefficient, and social coefficient, so as to enable the algorithm to adapt to different search stages or environmental changes. For example, the inertia weight can gradually decrease with the increase of the number of iterations, thus promoting the algorithm to shift from global search to local search in order to find a better solution.

[0043] S4. Check the stopping condition: It is necessary to judge whether the preset maximum number of iterations has been reached, or whether other termination criteria are met, such as the degree of swarm convergence, the stability of the best solution, etc. If the stopping condition is met, the algorithm iteration will stop; if not, the algorithm will return to the evaluation and update stages to continue the evaluation and update of the particle positions.

[0044] S5. Result extraction stage: Select the best solution from the final particle swarm as the multi-UAV cooperative trajectory planning scheme. The selection of the best solution is based on multiple metrics, such as the shortest total flight time, the lowest energy consumption, or the highest task completion efficiency, to ensure the effectiveness and reliability of the selected trajectory scheme in the actual combat environment.

[0045] During the implementation process, multi-objective optimization algorithms such as NSGA-II and MOEA / D can be used to find the Pareto optimal solution set to meet the multi-objective optimization requirements in multi-UAV cooperative combat.

[0046] In addition, in order to handle constraint conditions such as the dynamic limitations of the aircraft, obstacle avoidance rules, and flight airspace limitations, a penalty function can be introduced or a constraint handling strategy can be directly embedded in the particle update mechanism to ensure that the generated trajectory is both optimized and feasible.

[0047] The particle swarm optimization trajectory planning method for UAV formation cooperative combat of the present invention can effectively plan the optimal or approximate optimal trajectory that meets the actual combat requirements, and improve the efficiency and success rate of UAV formation cooperative combat.

[0048] A particle swarm optimization trajectory planning method for UAV formation cooperative combat provided by the present invention can quickly find the optimal or approximate optimal path that meets complex constraint conditions through the improvement of the particle swarm optimization algorithm, thereby improving the efficiency and success rate of UAV formation in performing tasks.

[0049] By dynamically adjusting parameters such as the inertia weight, cognitive coefficient, and social coefficient, the algorithm can adapt to different search stages or environmental changes, and improve its adaptability to complex environments.

[0050] By using multi-objective optimization algorithms such as NSGA-II and MOEA / D, multiple objectives (such as total flight distance, energy consumption, task completion efficiency, etc.) can be considered simultaneously to find the Pareto optimal solution set, meeting the multi-faceted requirements in actual combat.

[0051] By introducing constraint handling strategies, such as penalty functions or directly embedding constraint handling in the particle update mechanism, it is ensured that the generated flight paths are both optimized and feasible, avoiding the violation of dynamic limitations, obstacle avoidance rules, and flight airspace limitations by the aircraft.

[0052] By setting reasonable termination criteria, such as the degree of swarm convergence and the stability of the best solution, it is ensured that the algorithm can find high-quality solutions within a reasonable time, improving the stability and reliability of flight path planning.

[0053] By optimizing the flight path planning, the total flight time and energy consumption of the UAV formation can be effectively reduced, thereby optimizing resource utilization and extending the combat endurance of the UAVs.

[0054] In a dynamically changing battlefield environment, the flight path planning method of the present invention can quickly respond to environmental changes, timely adjust the flight path, improve the combat flexibility and reaction speed of the UAV formation. The present invention has broad application prospects and important strategic significance in the field of UAV formation cooperative combat.

[0055] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; under the idea of the present invention, the technical features between the above embodiments or different embodiments can also be combined, and the steps can be implemented in any order, and there are many other changes in different aspects of the present invention as above. For the sake of brevity, they are not provided in detail; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A particle swarm optimization trajectory planning method for collaborative combat of unmanned aerial vehicle formations, characterized in that, It includes the following steps: S1. Initialization: Randomly generate an initial particle swarm, where each particle represents a possible UAV flight path; S2. Evaluation: Calculate the fitness value of each particle according to a predefined objective function; S3. Update: Update the velocity and position of each particle based on the best position of the current particle, the global best position of the swarm, and an adjustment strategy; S4. Check the stopping condition: If the preset maximum number of iterations is reached or other termination criteria are met, stop; otherwise, return to S2; S5. Result extraction: Select the best solution from the final particle swarm as the cooperative flight path planning scheme for multiple UAVs.

2. The particle swarm optimization trajectory planning method for collaborative operation of UAV formations according to claim 1, characterized in that, In S1, it includes adaptive adjustment parameters, constraint handling, and multi-objective optimization. The adaptive adjustment parameters include dynamically adjusting the inertia weight, cognitive coefficient, social coefficient, etc., to adapt to different search stages or environmental changes; The constraint handling for the aircraft includes dynamic limitations, obstacle avoidance rules, and flight airspace limitations. Improve the algorithm and introduce a penalty function or directly embed a constraint handling strategy in the particle update mechanism to ensure that the generated flight path is both optimized and feasible; The multi-objective optimization uses NSGA-II, MOEA / D to find the Pareto optimal solution set.

3. A particle swarm optimization trajectory planning method for collaborative combat of UAV formations according to claim 1, characterized in that, In S2, the objective function is one or more of the total flight distance, energy consumption, and task completion efficiency.

4. A particle swarm optimization trajectory planning method for UAV formation cooperative operations according to claim 1, characterized in that, In S3, the adjustment strategy includes dynamically adjusting the inertia weight, cognitive coefficient, and social coefficient to adapt to different search stages or environmental changes.

5. The particle swarm optimization trajectory planning method for collaborative combat of UAV formations according to claim 1, wherein In S4, the other termination criteria include the degree of swarm convergence, the stability of the best solution, etc., to ensure that the algorithm finds a high-quality solution within a reasonable time. During the iteration process, each particle continuously adjusts its flight direction and speed based on its own historical experience and the experience of the entire swarm to find a better flight path.

6. A particle swarm optimization trajectory planning method for collaborative operation of unmanned aerial vehicle formations according to claim 1, characterized in that, In S5, the selection of the best solution is based on multiple metrics, such as the shortest total flight time, the lowest energy consumption, or the highest task completion efficiency, to ensure the effectiveness and reliability of the selected flight path scheme in the actual combat environment.

Images