The Path Planning of Mobile Robots Based on an Improved Genetic Algorithm

Abstract

In the field of mobile robot path planning, traditional genetic algorithms face issues such as slow convergence, lack of dynamic adaptability, and uncertain mutation directionality. To address these issues, a dichotomy-based multi-step method was used during the population initialization phase to enhance both the quality and diversity of the population. The selection strategy was improved for tournament selection, which reduces the monopolistic dominance of exceptional individuals and preserves population diversity through multiple rounds of grouping competitions. The crossover strategy adopted an adaptive crossover point number, with parents chosen based on a dynamic threshold. The mutation strategy combines a two-layer encoding approach: the first layer uses random mutations to enhance diversity, while the second layer performs goal-oriented mutations, with the selection probability of each layer dynamically adjusted during iterations. Bezier curve optimization of the optimal path was conducted. Experimental results show that the improved genetic algorithm demonstrates significant advantages in terms of path length, smoothness, iteration speed, and computational efficiency.