A Fuzzy Gain-Based Dynamic Ant Colony Optimization for Path Planning in Dynamic Environments

Path planning can be perceived as a combination of searching and executing the optimal path between start destination locations. Deliberative capabilities are essential for motion autonomous unmanned vehicles in real-world scenarios. There is challenge handling uncertainty concerning obstacles dynamic scenario, thus requiring an intelligent, robust algorithm, with minimum computational overhead. In this work, fuzzy gain-based ant colony optimization (FGDACO) proposed to effectively plan collision-free smooth paths, feasible length time. The system’s pheromone update mechanism was enhanced sigmoid gain function effective exploitation during planning. Collision avoidance achieved through logic control. results were validated using occupancy grids variable size, compared against existing methods performance metrics, namely, time length. consistency algorithm also analyzed, statistically verified.