Jiankang Zhang ^*

• CCCC First Highway Consultants Co., Ltd, Xi'an, China

In recent years, the total mileage and line density of China's highways have increased year by year. It is estimated that the total mileage of national highways will exceed 5.74 million kilometers in 2026. Efficient highway network is the only way for a country to move towards traffic modernization, and it is the key guarantee for economic development and improvement of people's livelihood. Among them, the highway route is the basic structure of the highway network, which is related to whether the highway itself can maximize its economic and traffic effects. Therefore, the research on highway route design has important engineering value. Highway planning is a complex problem involving a wide range and many influencing factors. Especially with the strengthening of people's awareness of environmental protection, it is necessary to consider natural problems other than technical and economic costs. Firstly, this paper points out the important position of highway route research in highway rules, summarizes the research status at home and abroad, and lists the conventional highway planning measures. Then, the optimization design based on vehicle running speed and driver comfort is discussed, and the related theories of deep learning and their applicability to multi-objective optimization problems are introduced. Finally, aiming at the problem that highway route planning is influenced by many factors, a deep learning strategy based on multi-objective genetic algorithm is adopted, and its multi-objective optimization model and optimization objective function are given. In this paper, the deep learning strategy of multi-objective genetic algorithm is a new attempt to combine genetic algorithm with deep learning in highway route planning to solve its multi-objective comprehensive optimization problem. It is the early theoretical research of the application of deep learning in highway route optimization design, which can provide a thinking reference for deep learning and other nonlinear multi-objective optimization research, and help the research of highway route optimization design.