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

Abstract

The invention discloses a multi-time-scale self-learning lane change method considering personalized driving experience, which is carried out according to the following steps: the first step is preparation; the second step is offline learning; the third step is online operation; The multi-time-scale self-learning algorithm controls the host vehicle for L4 automatic driving and learns the driver's driving habits online, and updates the personalized driving experience data set, multi-time-scale neural network, and multi-time-scale self-learning algorithm itself according to the driver's driving habits , lane-changing model and reward function, the transition probability is introduced through the Markov decision-making lane-changing model to capture the variation between individuals and within individuals, so that the automatic control output of the electronic control device for lane-changing gradually approaches the driving of the host vehicle driver himself Get used to it and improve your driving experience. The present invention adopts a learning structure combining offline strategy and online strategy, which not only considers the generality, but also considers the particularity, which is very in line with 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