Path Optimization Research Based On Improved Ant Colony Algorithm

The living standards of people in today's society are constantly improving,and the number of private cars is growing rapidly,which has led to urban traffic congestion is getting worse,and affected people's travel seriously.In order to alleviate this problem,it is necessary to make reasonable planning of the travel route.Therefore,path optimization has become a hot issue for many scholars.Path optimization is designed to rationally plan travel routes through intelligent algorithms to alleviate traffic congestion and create a convenient travel environment for people.The ant colony algorithm in the intelligent optimization algorithm is widely used in the optimal path finding in intelligent transportation systems because of its high parallelism,strong robustness and easy implementation.However,the ant colony algorithm also has certain limitations,including large computational complexity,poor feasible solution performance,and low efficiency.In view of this,this paper proposes a comprehensive improved algorithm which based on the ant colony algorithm,applies the algorithm in scenarios of congestion and obstacle distribution is unknown,and finally obtain better path optimization results.According to the existing shortcomings of traditional ant colony algorithm,a comprehensive improved algorithm is proposed.The algorithm firstly uses the better solution generated by GA to initialize the pheromone distribution of the ant colony algorithm,then uses the adaptive expectation function to improve the heuristic function mechanism,and finally improves the global pheromone update mechanism by adaptive parameter p,and through contrast experiments,it proves that the algorithm can still maintain high search ability in the environment such as roundabout road and "dead road".According to the problem of low search efficiency for ant colony algorithm in real-time changing environment of congestion,comprehensively consider the four factors affecting road congestion,such as road length,road current limit,traffic signal and semi-congested road,to model the environment and introduce a congestion factor in the comprehensive improvement algorithm,makes the comprehensive improvement algorithm change the pheromone update mechanism based on the congestion factor,which further improves the search efficiency of the algorithm,and verifies the feasibility of searching for the optimal path in the congestion environment through simulation experiments.According to the problem that the ant colony algorithm has a large search complexity under the environment of unclear obstacle distribution,this paper conducts polar coordinate modeling according to the local search environment,and based on the comprehensive improvement algorithm,the search area is reasonably divided(divided into sectors and searched in order),which further reduce the search complexity of the algorithm.The comparison experiments show that the algorithm can improve the local search ability of the algorithm.