Automatic driving direction prediction method based on lightweight neural network

Abstract

The invention specifically discloses an automatic driving direction prediction method based on a lightweight neural network. The method comprises the following steps: step 1, a neural network model is trained; and step 2, the neural network model is tested; in the neural network model training process, the obtained images are preprocessed, and data are subjected to horizontal overturning, brightness adjustment, angle adjustment and data screening operation, so that a data set is enriched, training samples are increased, and the network model is better trained. And the EffNet network and the BP neural network propagation algorithm are combined to adjust the error between the predicted steering wheel rotation angle and the actual steering wheel rotation angle, so that the network budget demand is reduced, and the method has actual reference value and a great market prospect.

Description

technical field [0001] The invention belongs to the technical field of automatic driving direction prediction, and in particular relates to an automatic driving direction prediction method based on a lightweight neural network. Background technique [0002] Self-driving car technology mainly relies on artificial intelligence, assisted by various other technologies, such as millimeter-wave radar ranging, lidar ranging, GPS, etc. Effective environment perception and object detection are prerequisites for safe driving. The document "Policy-Gradient and Actor-Critic Based State Representation Learning for SafeDriving of Autonomous Vehicles" proposes an environment perception framework for autonomous driving using state representation learning (SRL). Document [ 2] A gravity search algorithm for obstacle avoidance path planning in automatic driving is proposed to improve the speed of response and reduce the occurrence of accidents. The literature "Research on Obstacle Avoidance P...

AI Technical Summary

Problems solved by technology

[0003] With the development and wide application of deep learning, Marius.B and others proposed an end-to-end deep learning automatic driving technology "End to End Learning for Self-Driving Car", which speeds up the calculation speed, but requires high hardware configuration

Using the traditional convolutional neural network to predict the steering wheel rotation angle, due to the low configuration of the hard disk, the calculation speed is slow, which may cause the vehicle to drive out of the lane

Images