Modeling adaptive preview time of driver model for intelligent vehicles based on deep learning

Abstract

In order to improve the adaptability and tracking performance of intelligent vehicles under complex driving conditions, and simulate the manipulation characteristics of the real driver in the driver–vehicle–road closed-loop system, a kind of adaptive preview time model for intelligent vehicle driver model is proposed. This article builds the intelligent vehicle driver model based on optimal preview control theory and the basic preview time is identified to minimize path error under various conditions based on particle swarm optimization. Then, the ideal compensation preview time is constructed in various conditions and the appropriate factors affecting compensation preview time are filtered out according to correlation analysis. Moreover, the architecture and training procedure of deep network is specified for compensation preview time prediction. Finally, the adaptive preview time is modeled by combining the basic preview time with the compensation preview time and the validity of adaptive preview time model is verified by the driver–vehicle–road closed-loop system under normal and aggressive driving conditions. The results show that the proposed adaptive preview time model can help intelligent vehicles better adapt complex driving conditions and effectively improve the path-following performance.

Variable transmission ratio design of a steer-by-wire system for intelligent vehicles

“…The particle swam optimization algorithm [23][24][25] is referred to as PSO algorithm, which has a faster search speed and is better than the genetic algorithm (GA) in search performance: 1) Its computational complexity is lower than GA and 2) it can find optimal solution in a short time. Therefore, the PSO algorithm is selected for optimization in this paper.…”

Study of Methods for Constructing Intelligent Learning Models Supported by Artificial Intelligence

“…From the learner's perspective, intelligent learning is a result, mainly used to cultivate various types of talents; literature [10] defines the intelligent learning model through intelligent devices, using machine learning technology to predict and analyze the learner's learning data; literature [11] uses data mining technology, reasoning and analysis algorithms to train the subject's learning style, and uses a variety of augmentation techniques to improve the learner's ability; literature [12] takes the learner-centred, intelligent learning to support learners in any place, any time, recognize the content to build a new model of intelligent learning based on the network and intelligence; literature [13] believes that intelligent learning is the intelligent learning style, building a variety of intelligent algorithms for learning, to improve the efficiency of learning and enhance the quality of teaching. From the technology-learner perspective, intelligent learning combines technology and learners, using intelligent technology, carrying out intelligent learning activities, allowing the learning subject to participate in the learning process actively, and cultivating intelligent talents; literature [14] constructs an intelligent learning model from the multi-dimensional aspects of teaching methods, learning psychology, learning attitudes, etc., to promote learners' learning motivation and enthusiasm, and improve learners' learning ability; literature [15] puts forward the intelligent learning environment based on network mobile terminals, which can not only develop learners' learning space, but also improve learners' ability to cultivate learning; literature [16] believes that intelligent learning activities can be carried out to make learners actively participate in the learning process, and cultivate intelligent talents. Cluster analysis [19] is an unsupervised learning machine learning method that divides the objects in a dataset into different groups or "clusters" so that objects within the same group have a higher degree of similarity.…”