Optimal path planning based on ACO in intelligent transportation

Abstract

In the current intelligent transportation system, traffic congestion has become increasingly prominent. There is an urgent need for efficient path planning algorithms to solve this problem. The research aims to explore the optimal path planning scheme for intelligent transportation systems, improve traffic efficiency, shorten vehicle travel time, and allocate traffic resources reasonably. The study adopts an innovative approach that combines the global search capability of genetic algorithms with the local search advantage of ant colony algorithms. Simultaneously, the reward and punishment strategy is introduced, forming a new algorithm. The results show that the algorithm performs well in iteration time, path length, and convergence stability. Compared with traditional ant colony algorithm and genetic algorithm, the new algorithm reduces the iteration time from 45 s and 116 s to 34 s and the path length from 15,940 and 15,758 to 14,578 in the optimal path planning of 16 city coordinates. In actual distribution path planning, the optimal path length is reduced from 109.6 km to 99.2 km, and the number of iterations is reduced from 49 to 36. The research has confirmed that this algorithm effectively overcomes the slow convergence speed and susceptibility to local optima in traditional ant colony algorithms, significantly improving the accuracy and computational efficiency of path planning. It is of great significance for optimizing traffic flow management and reducing resource consumption, providing an efficient and accurate solution for path planning in intelligent transportation systems.