Excellent driver lane changing imitation model establishment method based on GRU network

Abstract

The invention discloses an excellent driver lane changing imitation model establishment method based on a GRU network, belonging to the field of smart car automatic driving. The method comprises the following steps: performing real vehicle experiment under a lane changing condition, acquiring an excellent driver steering characteristic parameter, a vehicle dynamics parameter and a track parameter,and forming a lane changing behavior data set; performing training learning for the lane changing data set through the GRU network, and obtaining the excellent driver lane changing imitation model based on the GRU network. In the method provided by the invention, based on strong nonlinear fitting ability of the GRU network on a long-time sequence, one simple and efficient excellent driver lane changing imitation model is realized, further improvement of accuracy of learning can be guaranteed based on fast learning, imitating a lane changing behavior of an excellent driver can be realized better, and in the future, the method has certain referential significance in such field and other prediction problems related to driver models.

Description

technical field [0001] The invention belongs to the field of automatic driving of smart cars, and in particular relates to a method for establishing a lane-changing model for imitating excellent drivers based on a GRU network. Background technique [0002] In recent years, with the rapid integration of computer, Internet, communication and navigation, automatic control, artificial intelligence, machine vision, precision sensors, high-precision maps and other high-tech and advanced automotive technologies, smart cars (or driverless cars, self-driving cars ) has become a research hotspot in the field of automotive engineering in the world and a new driving force for the growth of the automotive industry. According to authoritative media at home and abroad, technological innovation in the field of intelligentization of the automobile industry will account for 90% of the entire automobile industry. The intelligence of the car is mainly reflected in the replacement of manual ope...

AI Technical Summary

Problems solved by technology

[0003] On the other hand, driver model research is a key issue in the design process of smart cars. At present, the more commonly used model is the driver model based on the "preview follow" theory proposed by Academician Guo Konghui, but the theory does not consider the steering of real drivers. Habits and steering characteristics, which have certain deficiencies in simulating the handling level of a real driver

The driver model based on neural network control theory is closer to the driving behavior of real drivers to a certain extent, but its algorithm learning speed is often slow, and at the same time lacks good global optimization capabilities, resulting in low final output accuracy

At present, there are few literatures on intelligent vehicle steering control from the field of human-like intelligent control.

Images