Research on the Planning Method of Traffic Lags Based on Adaptive Ant Colony Algorithms

During the high-speed urbanization process, driverless technology has gradually become one of the mainstream development directions of new energy vehicles, while traffic road planning is one of the core points of driverless technology. During transportation path planning, traffic signs play an indispensable role in one of the most important traffic guidelines in the traffic system. In order to improve the existing path, unmanned driving algorithm, the identification process of the traffic signs needs to be further optimized, and the self-made transportation logo data and algorithm experiments must be made to make full use of their homemade traffic signs. Based on the background mentioned above, this article is improved by adapting the ant colony algorithms to identify the traffic logo data set and iterates optimization of each improvement point, which fully improves the accuracy and reliability of the detection of traffic signs.

I. Introduction

With the rapid development of social modernization, the process of urbanization has become one of the mainstream development directions of the current infrastructure process. During the high-speed urbanization process, unmanned driving technology has gradually become one of the mainstream development directions of new energy vehicles, and it plays an indispensable role in developing new energy vehicles. Traffic road planning is one of the core points of driverless technology. However, the existing unmanned road algorithm often occurs in various problems in identifying the traffic signal logo, which easily overloads in complex road conditions and causes accidents. During transportation path planning, traffic signs play an indispensable role and are one of the most important traffic guidelines in the traffic system [1]. In order to improve the existing path, unmanned driving algorithm, the identification process of the traffic signs needs to be further optimized, and the self-made transportation logo data and algorithm experiments must be made to make full use of their homemade traffic signs. Based on the above background, this paper is improved by the adaptive ant colony algorithm. During the use process, the traditional path planning algorithm and traffic signal recognition algorithm are combined to optimize, and the architecture is redesigned to enable it to identify the traffic logo data set. Optimize the improvement points of each improvement point, which fully improves the accuracy and reliability of the detection of traffic signs.