Research on Improving Genetic Algorithm in Mobile Robot Path Planning

Abstract

Sound path planning is essential for mobile robots to carry out exploration tasks. To date, the use of various intelligent algorithms in robot path planning has yielded significant advancements, particularly in areas such as path planning, obstacle avoidance, and collaborative control. These advancements enhance the robots' capabilities, collaboration, and efficiency in complex environments. However, traditional algorithms like particle swarm optimization, ant colony algorithms, and dynamic window algorithms face challenges in robot path planning, including slow convergence and a tendency to get stuck in local optima. Addressing the complexities of mobile robot path planning, genetic algorithms have been integrated. Yet, standard genetic algorithms suffer from slow convergence and low efficiency. An enhanced mobile robot path planning scheme using an improved genetic algorithm has been proposed. Simulation tests in a grid environment demonstrate that this approach narrows the local search range for paths, enhancing the algorithm's adaptability, convergence speed, and global search capabilities. Overall, it outperforms the standard genetic algorithm, offering valuable insights for researchers studying and applying algorithms in mobile robot path planning.