Research On Ant Colony Algorithm And Its Application In Path Optimization

Today,the number of cars in the world has been keeping a high growth rate,more and more people rely on private car travel,which not only brings a huge burden to road transportation,but also causes serious environmental pollution.Through the rational path planning,path optimization can not only reduce the time cost and economic cost to a certain extent,effectively alleviate the pollution caused by motor vehicles to the air,provide a safe and green travel environment for travelers,but also improve the utilization of traffic,reduce the occurrence of traffic congestion.Ant colony algorithm(ACO),as a classic intelligent optimization algorithm,has been widely used in path optimization and even intelligent transportation system.However,there are still obvious shortcomings such as low operational efficiency,poor optimization effect and unstable performance.In this paper,the ant colony algorithm and its application in path optimization are studied.First,the basic principles and characteristics of the basic ant colony algorithm are described,and the advantages and disadvantages of the basic ant colony algorithm and the reasons for their emergence are analyzed in detail.Secondly,the influence of four important parameters,ant number,pheromone Volatilization Coefficient,information heuristic factor and expected heuristic factor in ant colony algorithm,on the performance of the algorithm is analyzed,and the reasonable range of their value is obtained by the experiment.An improved ant colony algorithm for adaptive adjustment of expected function,improved ant colony algorithm with ant death strategy and improved ant colony algorithm with punishing reward mechanism are proposed for different environments,improves the optimization ability in special search environment.An improved ant colony algorithm based on bird colony algorithm is proposed to optimize initial pheromone to improve the defect of ant colony algorithm,such as slow convergence speed and the path quality is not high enough.Then a comprehensive improved ant colony algorithm based on the above four improved strategies is studied.Moreover,the road condition reference coefficient is introduced and the real-time traffic and road conditions are included into the evaluation factors of the road to realize the application of comprehensive improved ant colony algorithm in vehicle navigation.Finally,aiming at the weak performance of ant colony algorithm local path planning,an improved ant colony algorithm with sector search strategy is proposed.By reasonably dividing the search area,the local path planning ability of ant colony algorithm is improved.The simulation experiment shows that the improved ant colony algorithm with the adaptive adjustment of expected function has a stronger local search ability,faster convergence speed and higher quality of path optimization than the basic ant colony algorithm.In the search environment,when there are obstacles with sunken space,the improved ant colony algorithm with death strategy is much better than the basic ant colony algorithm for searching the path.And in large roundabout roads,the ant colony algorithm with penalty reward strategy can get shorter path.By comparing with ant colony algorithm,bird swarm algorithm and particle swarm optimization algorithm,the ant colony algorithm with initial pheromone optimization strategy has higher operational efficiency and path optimization ability,and has more obvious advantages in large search environment with complex obstacle distribution.And the comprehensive improved ant colony algorithm has higher search ability in the complex environment with many kinds of obstacles.In the case of unknown environment,the sector search strategy improves the performance of the path optimization of the ant colony algorithm.It can get a shorter path under the condition of the unknown obstacle,and is more suitable for the vehicle's independent obstacle avoidance.