Development and Design of Object Avoider Robot and Object, Path Follower Robot Based on Artificial Intelligence

Abstract

Robot path planning is a critical challenge in robotics, demanding efficient navigation and effective obstacle avoidance in complex environments. This research investigates the application of the gray wolf optimizer (GWO) algorithm in designing robots capable of obstacle avoidance and path following. The primary objective is to determine the shortest and safest path from a starting point to a target destination while effectively avoiding obstacles. To assess the efficacy of GWO, a comparative analysis was conducted against several established optimization algorithms, including discrete artificial bee colony (DABC), artificial bee colony (ABC), particle swarm optimization (PSO), PSO combined with ant colony optimization (PSOACO), PSO combined with genetic algorithm (PSOGA), and the A* algorithm. The study utilized six distinct experimental scenarios, each featuring different obstacle arrangements, to rigorously evaluate the path optimization capabilities of these algorithms. The results demonstrate that GWO consistently outperforms other algorithms in terms of efficiency and effectiveness across all scenarios. GWO’s effectiveness is attributed to its strategic balance between exploration and exploitation, guided by the top three solutions within the search space, and its rapid convergence toward optimal solutions. These characteristics render GWO highly adaptable and proficient for parallel problem-solving, making it an ideal choice for dynamic and intricate robot path planning tasks.