LAUSR

Unmanned aerial vehicle (UAV) path following issue is a significant part of the UAV mission arranging framework, which needs to get an ideal way following and handle collision avoidance instantaneously. To resolve this issue, a hybrid algorithm termed NFMGOA is presented by combining the neuro-fuzzy and modified grasshopper optimization algorithm (NFMGOA). In the proposed work, unlike regularly utilized strategies, the consequent parameters of the neuro-fuzzy are updated by utilizing the modified grasshopper optimization algorithm for efficient collision avoidance. Furthermore, possible collisions must be recognized and automatically settled as the vehicle moves toward the way. Emergency avoidance is designed by autonomously changing the heading and speed of every UAV. Initially, the position of the obstacle is attained by Kalman filtering, the input UAV data. Subsequently, cooperative path flow is produced by the Lyapunov function. Finally, effective NFMGOA is utilized for better collision avoidance. The examining outcomes of single and multiple UAVs demonstrated that the presented technique outperforms the existing methodologies regarding convergence and execution time performance assessments.