Study On An Improved Orca Predation Algorithm For Unmanned Aerial Vehicle(uav)path Planning

Unmanned aerial vehicles(UAVs)have advanced quickly in recent years as a result of their benefits,such as their affordability and tiny size.They are extensively utilized in a number of different industries,including power inspection,disaster assistance,and agricultural plant protection.The safety and operational efficiency criteria for UAVs are more demanding as a result of their widespread deployment.For the future development of UAVs,choosing proper ways to create a path that may satisfy the needs of safe and effective operations is of utmost importance.Meta heuristic algorithms are a frequently employed technique for resolving UAV path planning issues due to its great computational accuracy and quick solving speed.In this project,the novel meta heuristic algorithm known as the orca predation algorithm(OPA)is applied to the problem of path planning for unmanned aerial vehicles(UAVs)based on practical application requirements,which includes obstacle avoidance path planning under complex conditions and full coverage path planning for multiple farmland plots.Firstly,an adaptive multi branch chaotic mapping orca predation algorithm(AMCOPA)was suggested as a way to enhance the optimization-seeking strategy of OPA.Second,AMCOPA is used to shorten flight path and lower collision risks in the obstacle avoidance path planning problem of UAVs.Finally,the minimum span method,step rotation method,and AMCOPA are combined to solve the problem of full coverage and optimization of operation sequence for multiple farmland plots.The main research content is as follows.(1)Based on the optimization-seeking strategy of OPA,AMCOPA is proposed in order to improve the shortcomings of OPA.In the proposed algorithm,first,latin hypercube sampling is used to make the initial population evenly distributed in the search space and increase population diversity.Then,weight adaptation and dynamic switching probability strategies are added to OPA to balance the performance of algorithm exploration and exploitation.Finally,in the population update stage,a multi branch chaotic mapping factor is introduced to reduce the probability of the algorithm falling into local optima and improve optimization efficiency.In order to test the optimization ability of AMCOPA,this algorithm was used to solve basic benchmarks,multiple CEC benchmarks,and 3engineering design optimization problems.Simultaneously compare the results with other meta heuristic algorithms.The results show that compared to various algorithms including OPA,AMCOPA has higher optimization accuracy,faster convergence speed,and stronger optimization ability.(2)Using AMCOPA to solve the obstacle avoidance path planning problem for UAVs.Firstly,establish a mathematical model for the types of obstacles that may be encountered during UAV operations,and construct objective and threat functions.Secondly,the solution process of obstacle avoidance path planning is complex.In order to simplify the calculation process,a segmented fitness function strategy is established.The complexity of the fitness function is increased piecewise in the algorithm iteration process to improve the calculation speed.Finally,AMCOPA with segmented fitness function strategy is used to study the obstacle avoidance path planning of UAV.To verify the performance of AMCOPA in obstacle avoidance problems,three environments containing static obstacles and three environments containing dynamic obstacles were established.And other meta heuristic algorithms were added to solve the problem.Through the analysis and comparison of the results,AMCOPA calculates a safest and shortest path,proving its applicability and advantages for obstacle avoidance path planning for UAVs.(3)AMCOPA is used to solve the path planning problem of full coverage of plant protection and operation sequence optimization for multiple farm plots.First,according to the actual operating environment,establish a complex irregular polygon single plot,including convex polygon and concave polygon.For convex polygon,use the minimum span method to optimize,and for concave polygon,use the step rotation method to optimize.Establish three different cases to calculate,and find the best full coverage path scheme.Then,a farmland plot model containing multiple irregular polygons is established to simulate the optimization problem of operation sequence,and AMCOPA is used to solve the problem.To demonstrate the effectiveness of AMCOPA in solving this problem,a complex simulation model and three actual models were established for testing.And the results were compared with other meta heuristic algorithms.The results have shown that AMCOPA also has advantages in solving this problem.