Path Planning Optimization for Four-Wheeled Mobile Robots Using the Black-Winged Kite Algorithm

Abstract

This paper focuses on the Black-Winged Kite Algorithm (BWKA), which is a nature-inspired metaheuristic algorithm to provide efficient and adaptive path planning of mobile robots. The BWKA uses flight behavior of black-winged kites to find an optimal solution between two processes such as exploration and exploitation. This algorithm is best for his robust performance in both static and dynamic environments. The methodology is helpful in designing multi-objective optimization criteria i.e. path length, smoothness, energy consumption, and obstacle avoidance which are integrated to support better decision-making and scalability processes. As per results, BWKA can provide superior performance in terms of dynamic response of a mobile robot than Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), and Genetic Algorithms (GA). This algorithm reduced path length by an average of 20% keeping in mind the smoothness of path finding up to 23% using curvature metrics. The energy consumption is 15% less than other algorithms while providing the smoother trajectories in the arenas. The convergence rate is also improved by 27% by taking less execution time than PSO and 22% less than ACO, making it highly suitable for real-time applications. The algorithm achieved the success rate of 96.82% in avoiding collisions in dynamic environments, compared to 85% for PSO and 78% for GA. The BWKA’s adaptability to environmental changes and its ability to scale in complex, multi-agent scenarios underscore its potential for diverse applications, including autonomous navigation, industrial robotics, and intelligent transportation systems.