An intelligent vehicle driving decision method based on generative countermeasure network

Abstract

The invention discloses an intelligent vehicle driving decision method based on a generating countermeasure network, which comprises establishing a driving decision model and driving decision control.The invention processes the driving image based on the generated antagonistic network, can process the vehicle driving path planning under the non-ideal road condition, and improves the executabilityof the end-to-end neural network. The invention extracts the most essential characteristics of driving images through the generated antagonistic network processing, maps the driving data of differentsources into a unified virtual domain, realizes the application of reinforcement learning to a real vehicle, improves the generalization of the network and adapts to the ability of different samples.For the input of the driving image, the input image used each time is the first several frames of the current time stamp video image. The predicted images obtained by this method can be used to judgethe driving decision-making planning to a greater extent. As the basis for predicting the optimal decision of the vehicle, the invention builds a bridge from the reinforcement learning to the real vehicle application.

Description

technical field [0001] The invention relates to a decision-making method for driving an intelligent vehicle, in particular to a decision-making method based on driving image input and a generative confrontation network. Background technique [0002] With the development of society and the advancement of science and technology, automobiles have entered thousands of households and caused traffic accidents to gradually increase. Therefore, the research on intelligent vehicles is becoming more and more important. The introduction of intelligent driving vehicle technology has reduced the occurrence of traffic accidents and reduced the driver's driving fatigue to a certain extent, and improved the driver's operation convenience, representing the strategic commanding heights of future automotive technology. Traditionally, smart cars use a single input driving image to perform lane line detection or vehicle tracking detection in the driving environment. Plan the driving path accord...

AI Technical Summary

Problems solved by technology

However, compared with the two, offline training in the real domain requires too large a sample size, and the provided samples often contain concerns that are not related to driving decisions; reinforcement learning in the virtual domain cannot be used in the actual environment for testing, lack of practicality

Therefore, although end-to-end technology is one of the development trends of intelligent driving vehicles, its interpretability, execution and generalization need to be improved.

Images