Applying genetic algorithm and ant colony optimization algorithm into marine investigation path planning model

Abstract

Marine resources are vital to the development of a country. Marine investigation can obtain more marine resources and acquire more marine environmental information. A common method used in the marine investigation consumes a large amount of both time and money. Thus, the scientific path planning is important for improving the efficiency and reducing the costs of the marine investigation. Currently, the most commonly used algorithms for path planning are the genetic algorithm (GA) and the ant colony optimization algorithm (ACOA). Through continuous iterations, the initial solutions obtained by GA and ACOA gradually approach the optimal solutions. However, the final solutions of both algorithms are often suboptimal solutions or local optimal solutions. In particular, in terms of the marine investigation path planning that involves enormous stations, both GA and ACOA are prone to premature and local optimal solutions, leading to the stagnation of the searching. Therefore, in order to solve these problems and save the costs of marine investigation, the ACOA and GA are combined to propose a hybrid algorithm for the further improvement in the quality of the solutions. Through the experiments and software implementation, the proposed hybrid algorithm is proved of high effectiveness and robustness, which could obtain the optimal path for single or multiple research vessels, thereby saving the time and costs of marine investigation path planning.