Software-in-the-loop calibration method for lane keeping curve feedforward

A lane keeping and calibration method technology, applied in the field of automatic driving, can solve problems such as low test case coverage, insufficient test scenarios, and low matching efficiency, and achieve the effects of rapid iterative optimization, improved coverage, and efficient matching

Pending Publication Date: 2022-03-15
魔视智能科技(上海)有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Solve the problems of insufficient test scenarios, low coverage of test cases, multiple trial and error due to the lack of true value of the curve radius in the matching process, low matching efficiency, waste of resources, etc.

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
  • Software-in-the-loop calibration method for lane keeping curve feedforward
  • Software-in-the-loop calibration method for lane keeping curve feedforward

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention.

[0020] like Figure 1-2 As shown, a software-in-the-loop calibration method for lane keeping curve feedforward, including the following steps:

[0021] Step S1: Build a curve scene environment, design test cases with different radii such as 100m, 150m, 200m... 1000m, 1500m, 2000m, 5000m, etc., and simulate the visual camera characteristics based on the road model to construct the left and right lane line parameter input signals, using CarMaker or Prescan commonly used software to build curve road models;

[0022] Step S2: By using the lane line parameter signal in the curved road model as the input signal of the lane keeping feedforward algorithm in the Matlab environment, construct the feedforward contro...

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

A software-in-the-loop calibration method for lane keeping curve feedforward comprises the following steps: building a curve scene environment, designing test cases with different radiuses, and building a curve road model; constructing a feedforward control algorithm model, and observing the position change of the vehicle in the curve road model in real time; a real vehicle is built in a loop control project, a lane keeping algorithm is compiled and loaded into an AutoBox controller, and a steering torque control request is output; testing scenes with different radiuses are selected, a driver drives a vehicle to run at a set vehicle speed, a matching engineer sets feedforward parameters according to the radius of a curve, an AutoBox controller outputs a torque request, and an EPS controls the vehicle to steer; and the feed-forward parameters are optimized. The method overcomes the defects in the prior art, and gets rid of the dependence of traditional lane keeping parameter matching on the environment. The problems that test scenes are insufficient, the coverage rate of test cases is low, repeated trial and error are needed due to lack of curve radius true values in the matching process, the matching efficiency is low, and resources are wasted are solved.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to a software-in-the-loop calibration method for lane keeping and curve feedforward. Background technique [0002] The lane keeping function generally adopts the feedback + feedforward control algorithm, the lane keeping is realized by feedback in the straight road scene, and the lane keeping is realized by feedback + feedforward in the curve scene. Feedback enables closed-loop tracking of targets, and feed-forward provides open-loop steering assistance based on the radius of the curve. In engineering, a large amount of calibration work on actual vehicle parameter matching is required for feedforward. [0003] At present, the parameter calibration of the lane keeping feed-forward algorithm is mostly carried out by the matching engineer on the external public roads, searching for a large number of real road scenes with different curve radii for trial-and-error matching. T...

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 Applications(China)
IPC IPC(8): G06F11/36G06F30/20
CPCG06F11/3676G06F11/3688G06F30/20
Inventor 桂科
Owner 魔视智能科技(上海)有限公司
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