Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Evaluation method and device of longitudinal control model of end-to-end automatic driving system

A longitudinal control and automatic driving technology, applied in the computer field, can solve the problems that limit the development of deep learning and cannot meet the evaluation requirements of the longitudinal control model of the automatic driving system, and achieve the effect of improving learning efficiency

Inactive Publication Date: 2018-03-09
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this solution is more biased towards the evaluation of the steering angle, which cannot meet the evaluation requirements for the longitudinal control model of the automatic driving system, thus limiting the development of deep learning in the field of automatic driving.

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
  • Evaluation method and device of longitudinal control model of end-to-end automatic driving system
  • Evaluation method and device of longitudinal control model of end-to-end automatic driving system
  • Evaluation method and device of longitudinal control model of end-to-end automatic driving system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] In the prior art in this field, the longitudinal control of the automobile mainly refers to the speed control. However, the traditional evaluation method can only evaluate the self-learning driving system by simulating the driver's intervention and calculating the time proportion of the autonomous vehicle. In fact, the longitudinal control model of the automatic driving system is much more complicated, so the traditional methods cannot meet the requirements of evaluating the longitudinal control model of the automatic driving system.

[0051] Therefore, this embodiment proposes yet another evaluation method for a longitudinal control model of an end-to-end automatic driving system, combining figure 2 , including the following steps:

[0052] S210. Calculate a reference standard speed sequence.

[0053] Based on the UTC, read the due east velocity component v at the current moment east and the velocity component v in the north direction north , and by computing the ...

Embodiment 2

[0065] In the existing technology in this field, since traditional evaluation methods can only evaluate some single parameters, for example, by calculating the number of simulated human interventions initiated when the simulated vehicle deviates from the center line by more than one meter, that is, the time of the automatic driving system ratio to evaluate the steering angle. Since the longitudinal control of the car mainly refers to the speed control, these methods cannot evaluate the longitudinal control model of the autonomous driving system.

[0066] Therefore, this embodiment proposes an evaluation method for a longitudinal control model of an end-to-end autonomous driving system, combining image 3 , including the following steps:

[0067] S310. Read the UTC, the due east velocity component, and the due north velocity component in the reference standard file.

[0068] The time in the predetermined navigation system is usually a GPS week. For the convenience of calculat...

Embodiment 3

[0097]In the prior art in this field, the longitudinal control of the automobile mainly refers to the speed control. However, the traditional evaluation method can only evaluate the self-learning driving system by simulating the driver's intervention and calculating the time proportion of the autonomous vehicle. In fact, the longitudinal control model of the automatic driving system is much more complicated, so the traditional methods cannot meet the requirements of evaluating the longitudinal control model of the automatic driving system.

[0098] Therefore, this embodiment proposes another evaluation device for a longitudinal control model of an end-to-end automatic driving system, combining Figure 5 As shown in , including the following devices:

[0099] A device for calculating a reference standard speed sequence (hereinafter referred to as "the first calculation device") 510;

[0100] A device for reading the estimated velocity sequence of the longitudinal control mode...

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 provides an evaluation method and device of a longitudinal control model of an end-to-end automatic driving system. The method comprises the steps of determining a reference standard speed sequence according to a speed sequence extracted from a predetermined navigation system; reading an estimation speed sequence of the longitudinal control model; evaluating the longitudinal controlmodel of the end-to-end automatic driving system according to a mean square error of the reference standard speed sequence and the estimation speed sequence. According to the reference standard speedsequence obtained through calculation in the predetermined navigation system and the estimation speed sequence read from the longitudinal control model, the means square error is determined, accordingto the mean square error, the longitudinal speed model is estimated, therefore the effect of the longitudinal model can be objectively and authentically evaluated, and the study efficiency of deep learning in the field of automatic driving is improved.

Description

technical field [0001] The invention relates to the field of computers, in particular to an evaluation method and device for a longitudinal control model of an end-to-end automatic driving system. Background technique [0002] With the rapid development of deep learning and the in-depth research of artificial intelligence, the automotive industry has undergone revolutionary changes. Realizing automatic driving through end-to-end deep learning is a major research direction in the field of automatic driving. In the prior art, many driving models can be generated by different neural networks. For example, an automated driving system model can be evaluated by counting the number of simulated driver interventions that occur when a simulated vehicle deviates from the centerline by more than one meter, and by calculating the fraction of time that an autonomous vehicle is driven. However, this solution is more biased towards the evaluation of the steering angle, which cannot meet 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): G06F17/18G06F17/50
CPCG06F17/18G06F30/20
Inventor 闫泳杉郁浩郑超唐坤张云飞姜雨
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com