Improved Ant Colony Algorithm in Optimizing Evacuation Path Planning

Abstract

The traditional ant colony algorithm has played an important role in the evacuation path planning of ship personnel. By simulating the process of ants searching for food, it effectively solves the optimization problem of evacuation paths, improves evacuation efficiency and safety.However, traditional ant colony algorithm in path planning applicationsalsohas some shortcomings, such as the heuristic function does not introduce the distance of the target point, insufficient utilization of obstacle information, and insufficient difference in the probability of each node. Therefore, this paper proposes an improved ant colony algorithmto solve these problems.In view of  that the traditional ant colony algorithm converges slowly and easily falls into local optimum, the distance correction function is introduced into the heuristic function by combining the basic concept of the evaluation function of A* algorithm; the obstacle avoidance function is introduced to make the heuristic function guide the ants forward more reasonably; the smoothness function is introduced to reduce the number of turns and control the turning angle of the planned path.The effectiveness and applicability of the improved algorithm are verified through two sets of experiments, and the improved ant colony algorithm meets the needs of emergency evacuation of actual ship personnel.Simulation and experimental results show that the method proposed can solve the randomness of turning path selection at the early stage of the algorithm, has better global search ability and convergence, and performs better in the number of iterations and computation time, and can provide efficient and safe evacuation plan in the shortest time, which meets the demand of emergency evacuation of actual cruise ship personnel.