Abstract
Congestion road condition is an important factor that must be considered in urban traffic path planning, while most path planning algorithms only consider the distance factor, which is not suitable for the current complex urban traffic congestion road condition. In order to solve the above problems, this article proposes a dynamic path planning method based on improved ant colony algorithm in congested traffic. The method quantifies the main attributes of urban road length, number of lanes, incoming and outgoing traffic flow, and introduces the road factor used for replacing the distance parameters of particle swarm optimization and ant colony algorithm. In the method, the particle swarm algorithm can effectively optimize the parameters of the ant colony algorithm, and significantly improve the efficiency of ant colony algorithm, such that it is more applicable for dynamic path planning application to greatly reduce the congestion rate of path planning. In addition, this article selects some intersections in the Beijing area to carry out the dynamic path planning experiment based on the improved ant colony algorithm under congested road conditions. The experimental results show that, compared with the ant colony algorithm based on distance parameter, the proposed dynamic path planning method can effectively reduce the average congestion rate ranging from 9.73% to 13.63%.
Highlights
With the rapid development of the economy and the rapid growth of urban car ownership, traffic congestion has become a serious problem faced by all large and medium-sized cities
This method combines the advantages of particle swarm optimization (PSO) and ant colony optimization (ACO), and replaces the distance parameter in the two algorithms with the road condition factor, which is more suitable for dynamic path planning in congested roads
Under congested road conditions, compared with the ACO algorithm based on distance parameter, the dynamic path planning method based on the improved ant colony algorithm proposed in this article can reduce the average congestion rate ranging from 9.73% to 13.63%
Summary
With the rapid development of the economy and the rapid growth of urban car ownership, traffic congestion has become a serious problem faced by all large and medium-sized cities. Most existing ACO and PSO algorithms are distance-based path planning algorithms, which are not suitable for the current complicated urban traffic congestion road conditions due to the neglect of practical road condition factor. This article proposes a dynamic path planning method based on improved ant colony algorithm in congested roads This method combines the advantages of particle swarm optimization (PSO) and ant colony optimization (ACO), and replaces the distance parameter in the two algorithms with the road condition factor, which is more suitable for dynamic path planning in congested roads. Under congested road conditions, compared with the ACO algorithm based on distance parameter, the dynamic path planning method based on the improved ant colony algorithm proposed in this article can reduce the average congestion rate ranging from 9.73% to 13.63%.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
