Prediction of Steering Angle for Autonomous Vehicles Using Pre-Trained Neural Network

Sokipriala Solomon Jonah

doi:10.24018/ejeng.2021.6.5.2537

Prediction of Steering Angle for Autonomous Vehicles Using Pre-Trained Neural Network

Sokipriala Solomon Jonah

Rivers State University

Research output: Contribution to journal › Article › peer-review

Abstract

Autonomous driving is one promising research area that would not only revolutionize the transportation industry but would as well save thousands of lives. accurate correct Steering angle prediction plays a crucial role in the development of the autonomous vehicle .This research attempts to design a model that would be able to clone a drivers behavior using transfer learning from pretrained VGG16, the results showed that the model was able to use less training parameters and achieved a low mean squared error(MSE) of less than 2% without overfitting to the training set hence was able to drive on new road it was not trained on.

Original language	English
Pages (from-to)	171-176
Number of pages	6
Journal	European Journal of Engineering and Technology Research
Volume	6
Issue number	5
DOIs	https://doi.org/10.24018/ejeng.2021.6.5.2537
Publication status	Published - 30 Aug 2021
Externally published	Yes

Bibliographical note

This journal provides immediate open access to its content on the principle that making research freely available after publication on the EJ-ENG website to the public supports a greater global exchange of knowledge.

Keywords

Autonomous vehicles
Convolution neural network
VGG16
Transfer Learning

Access to Document

10.24018/ejeng.2021.6.5.2537

Cite this

@article{974eb9b3ce8c43a2a18c6c4f1ba5624a,

title = "Prediction of Steering Angle for Autonomous Vehicles Using Pre-Trained Neural Network",

abstract = "Autonomous driving is one promising research area that would not only revolutionize the transportation industry but would as well save thousands of lives. accurate correct Steering angle prediction plays a crucial role in the development of the autonomous vehicle .This research attempts to design a model that would be able to clone a drivers behavior using transfer learning from pretrained VGG16, the results showed that the model was able to use less training parameters and achieved a low mean squared error(MSE) of less than 2% without overfitting to the training set hence was able to drive on new road it was not trained on.",

keywords = "Autonomous vehicles, Convolution neural network, VGG16, Transfer Learning",

author = "Jonah, {Sokipriala Solomon}",

note = "This journal provides immediate open access to its content on the principle that making research freely available after publication on the EJ-ENG website to the public supports a greater global exchange of knowledge.",

year = "2021",

month = aug,

day = "30",

doi = "10.24018/ejeng.2021.6.5.2537",

language = "English",

volume = "6",

pages = "171--176",

journal = "European Journal of Engineering and Technology Research",

issn = "2736-576X",

number = "5",

}

TY - JOUR

T1 - Prediction of Steering Angle for Autonomous Vehicles Using Pre-Trained Neural Network

AU - Jonah, Sokipriala Solomon

N1 - This journal provides immediate open access to its content on the principle that making research freely available after publication on the EJ-ENG website to the public supports a greater global exchange of knowledge.

PY - 2021/8/30

Y1 - 2021/8/30

N2 - Autonomous driving is one promising research area that would not only revolutionize the transportation industry but would as well save thousands of lives. accurate correct Steering angle prediction plays a crucial role in the development of the autonomous vehicle .This research attempts to design a model that would be able to clone a drivers behavior using transfer learning from pretrained VGG16, the results showed that the model was able to use less training parameters and achieved a low mean squared error(MSE) of less than 2% without overfitting to the training set hence was able to drive on new road it was not trained on.

AB - Autonomous driving is one promising research area that would not only revolutionize the transportation industry but would as well save thousands of lives. accurate correct Steering angle prediction plays a crucial role in the development of the autonomous vehicle .This research attempts to design a model that would be able to clone a drivers behavior using transfer learning from pretrained VGG16, the results showed that the model was able to use less training parameters and achieved a low mean squared error(MSE) of less than 2% without overfitting to the training set hence was able to drive on new road it was not trained on.

KW - Autonomous vehicles

KW - Convolution neural network

KW - VGG16

KW - Transfer Learning

U2 - 10.24018/ejeng.2021.6.5.2537

DO - 10.24018/ejeng.2021.6.5.2537

M3 - Article

SN - 2736-576X

VL - 6

SP - 171

EP - 176

JO - European Journal of Engineering and Technology Research

JF - European Journal of Engineering and Technology Research

IS - 5

ER -

Prediction of Steering Angle for Autonomous Vehicles Using Pre-Trained Neural Network

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this