A vehicle trajectory prediction and driving behavior analysis method

Abstract

The invention discloses a vehicle driving track prediction algorithm based on a graph convolutional neural network with interactive perception, including a semi-global graph data processing algorithm, an M-product-based interactive perception graph convolutional neural network and a An algorithm for driving behavior analysis on predicted trajectories. Vehicle trajectory data is organized into a graph data format consisting of feature matrix and adjacency matrix. The processed trajectory data is sent to the dual parallel network, and the sub-networks output different embeddings respectively, and after splicing, they are input into the subsequent GRU-based encoder-decoder network, which is used for feature mining of time series data and outputs the final predicted trajectory . The invention can more efficiently extract the space-time dependent features between multiple vehicles in the driving scene, has higher vehicle trajectory prediction accuracy, and solves the problem of data construction in the graph convolutional network and the analysis of the scene background features in the driving behavior analysis. Insufficient consideration.

Description

technical field

[0001] The invention relates to a vehicle track prediction and driving behavior analysis method, belonging to the technical fields of intelligent transportation and artificial intelligence. Background technique

[0002] The research and application of autonomous driving technology began as early as the 1970s. The automatic driving system is a complex system integrating control technology, perception algorithm, path planning, space modeling and positioning and other technologies. In the past ten years, with the development of deep learning technology and the improvement of computer computing performance, technologies related to autonomous driving have also developed rapidly. But today, there are still many obstacles to the popularization of autonomous driving technology, such as how to ensure sufficient safety. Among them, the prediction of vehicle trajectory and its behavior analysis are extremely important in the link of providing necessary information for ...

Images