Driver vision fusion method for automatic driving trajectory tracking

A trajectory tracking and automatic driving technology, which is applied in the directions of instruments, calculations, character and pattern recognition, etc.
CN111797809AActive Publication Date: 2020-10-20JILIN UNIV
3 Cites 7 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
JILIN UNIV
Publication Date
2020-10-20

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a driver vision fusion method for automatic driving trajectory tracking. The method comprises the steps of 1, acquiring a front view image and eye movement data of the view angle of a driver; 2, separating driver fixation points from the front view image of the view angle of the driver; 3, after the driver fixation points are positioned under a fixed coordinate system, obtaining the fixed coordinates of the driver effective fixation points; 4, determining normal distribution characteristics of the fixed coordinates of the effective fixation points of the driver, and determining a driver preview point according to fitting parameters of normal distribution of the fixation points; 5, converting the driver preview point into a ground coordinate system to obtain the ground coordinates of the preview point; calculating the forward-looking preview time corresponding to the preview point according to the ground coordinates of the preview point, and obtaining a forward-looking preview time probability density graph according to the vehicle speed, the probability density of the preview point and the forward-looking preview time corresponding to the preview point; and6, correcting a predictive control driver model according to the forward-looking preview time probability density graph.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of automatic driving, and in particular relates to a driver vision fusion method for automatic driving trajectory tracking. Background technique

[0002] As the core decision-making control unit in the human-vehicle-road closed-loop system, the research on the driver is of great significance for understanding the interaction mode between the human-vehicle-road and the overall system optimization. Among them, an effective research method is to establish a driver model, which is the process of abstracting the actual driver's process of manipulating the car into a mathematical expression.

[0003] The research on driver model has been carried out for more than half a century and has been applied in many aspects. In the vehicle design process, the introduction of the driver model can objectively, accurately, comprehensively and deeply evaluate the control performance of the overall human-vehicle-road closed-loo...

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