Pheromone-Based Path Planning for Mobile Robots Using Ant Colony Optimization in Grid Environments

This paper presents an effective Ant Colony Optimization (ACO)-based path planning algorithm for indoor grid navigation of mobile robots. The method utilizes pheromone reinforcement, heuristic assessment, and collision avoidance to navigate robots from their initial to goal locations with reduced path length and travel time. A sequence of simulations is performed for three different situations: single robot in an obstacle free environment along its path towards goal, single robot navigating in an environment filled with obstacle in its path towards goal, and multiple robots moving through an obstacle-laden complex environment. Most of the main algorithmic parameters, including evaporation rate for pheromone, deposition constant, and weights for the heuristics, were set up to investigate how their modification affected performance. The outcomes prove the efficacy of the suggested approach in preventing deadlocks, smooth navigation, and adjusting to environmental complexity. The outcomes identify the algorithm’s potential for practical applications in warehouse automation, indoor surveillance, and collaborative robotics.