Multi-time-scale self-learning lane changing method considering personalized driving experience

Abstract

The invention discloses a multi-time-scale self-learning lane changing method considering personalized driving experience. The multi-time-scale self-learning lane changing method comprises the following steps that 1, preparation is conducted; 2, offline learning is carried out; 3, online operation is carried out; an electric control device controls a host vehicle to perform L4-level automatic driving through a multi-time-scale self-learning algorithm, learns the driving habit of the driver on line, and updates the personalized driving experience data set, the multi-time-scale neural network, the multi-time-scale self-learning algorithm, the lane changing model and the reward function according to the driving habit of the driver; transfer probabilities are introduced through a Markov decision lane changing model to capture variations between changing individuals and inside the individuals, so that the automatic control output of the electric control device on lane changing is graduallyclose to the driving habit of a host vehicle driver, and the driving experience is improved. According to the method, a learning structure combining an offline strategy and an online strategy is adopted, the generality and the particularity are considered, and the method quite conforms to the characteristics of L4-level intelligent driving.

Description

technical field [0001] The invention belongs to the field of intelligent driving, and in particular relates to a multi-time-scale self-learning lane changing method considering personalized driving experience. Background technique [0002] In the field of intelligent driving, with the development of vehicle intelligence, the intelligent control unit and the driver are increasingly sharing the underlying control rights of the vehicle, and the intelligent car will inevitably "seize power" from the driver, or at important moments It interferes with the driver's control strategy that is beneficial to the driver's own interests, thereby causing potential safety hazards. Therefore, a smart car cannot ignore the understanding and perception of the vehicle's highest decision maker, the driver. [0003] The advanced driving assistance system at the present stage has initially possessed the monitoring function of driving behavior through the detection of the driver's state, vehicle a...

AI Technical Summary

Problems solved by technology

[0013] The purpose of the present invention is to solve the problem of poor driving experience caused by the lack of consideration of individual differences in current active lane changes, and propose a multi-time-scale self-learning lane change method that considers individualized driving experience

Images