Almusawi, HusamEgharevba, Osasere2025-09-042025-09-042024-12-02https://hdl.handle.net/2437/397298This paper focuses on enhancing autonomous navigation through improved path planning techniques. It highlights the limitations of traditional algorithms like A* and Dijkstra's in dynamic and complex environments. The study proposes modifications to the Grey Wolf Optimizer (GWO), a bio-inspired metaheuristic algorithm, to address these challenges. By introducing nonlinear convergence factors and adaptive parameter tuning, the research aims to enhance GWO's exploration and exploitation balance, leading to better obstacle avoidance and path smoothness. The methodology includes testing in both simple and complex static environments, utilizing random maze generation and benchmark comparisons with other optimization algorithms. The results demonstrate GWO's superior performance in terms of convergence rate, computational efficiency, and path quality compared to methods like Particle Swarm Optimization and Ant Colony Optimization. The study concludes that the proposed enhancements make GWO a viable solution for real-world path planning problems in robotics and autonomous systems.69enGrey wolf optimizerPath planningAutonomous navigationEngineering Sciences::EngineeringHozzáférhető a 2022 decemberi felsőoktatási törvénymódosítás értelmében.