A vehicle trajectory prediction and driving behavior analysis method

A vehicle trajectory and behavior analysis technology, applied in the direction of registration/instruction of vehicle operation, registration/instruction, instrument, etc., can solve problems such as sparse adjacency matrix, avoid underfitting and overfitting, improve the overall prediction effect, The effect of guaranteeing efficiency and precision

Active Publication Date: 2022-05-17
HUNAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the data processing part, a semi-global graph is proposed to solve the problem of sparse adjacency matrix in traditional graph model data

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A vehicle trajectory prediction and driving behavior analysis method
  • A vehicle trajectory prediction and driving behavior analysis method
  • A vehicle trajectory prediction and driving behavior analysis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] Attached below Figures 1 to 4 The preferred embodiment of the present invention is described further:

[0058] Step1: Model input data processing

[0059] Before the model is trained, the data needs to be processed into the required form. The trajectory data input for trajectory prediction is processed by a semi-global graph algorithm to generate an adjacency matrix and a feature matrix as the input of the model. Introduce respectively below.

[0060] (1) Trajectory data:

[0061] The original trajectory data is a two-dimensional table, each row is a data sampling point, including information such as time stamp, vehicle identification number, local coordinates, etc., sliced ​​according to time (the length of each segment is the history step plus the prediction step). Among them, the historical vehicle trajectory of the driving scene consists of vehicle trajectory data of τ historical time steps: The trajectory data at each time step is It consists of the local ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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 ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G07C5/08G06N3/04
CPCG07C5/0808G06N3/045Y02T10/40
Inventor 安吉尧刘韦郭亮付志强李涛
Owner HUNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap