Login
Register
Reset Password
Publish & Distribute
Publishing Solutions
Distribution Solutions
Subjects
Architecture and Design
Arts
Business and Economics
Chemistry
Classical and Ancient Near Eastern Studies
Computer Sciences
Cultural Studies
Engineering
General Interest
Geosciences
History
Industrial Chemistry
Jewish Studies
Law
Library and Information Science, Book Studies
Life Sciences
Linguistics and Semiotics
Literary Studies
Materials Sciences
Mathematics
Medicine
Music
Pharmacy
Philosophy
Physics
Social Sciences
Sports and Recreation
Theology and Religion
Publications
Journals
Books
Proceedings
Publishers
Blog
Contact
Search
EUR
USD
GBP
English
English
Deutsch
Polski
Español
Français
Italiano
Cart
Home
Journals
International Journal on Smart Sensing and Intelligent Systems
Volume 13 (2020): Issue 1 (January 2020)
Open Access
1/10th scale autonomous vehicle based on convolutional neural network
Avishkar Seth
Avishkar Seth
,
Alice James
Alice James
and
Subhas C. Mukhopadhyay
Subhas C. Mukhopadhyay
| Aug 25, 2020
International Journal on Smart Sensing and Intelligent Systems
Volume 13 (2020): Issue 1 (January 2020)
About this article
Previous Article
Next Article
Abstract
Article
Figures & Tables
References
Authors
Articles in this Issue
Preview
PDF
Cite
Share
Article Category:
Research-Article
Published Online:
Aug 25, 2020
Page range:
1 - 17
Received:
Jul 26, 2020
DOI:
https://doi.org/10.21307/ijssis-2020-021
Keywords
Autonomous vehicle
,
Convolutional neural network
,
Raspberry pi 4
,
Ultrasonic sensor
,
Camera
© 2020 Avishkar Seth published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Figure 1:
Picture of the individual vehicle hardware components used in the system.
Figure 2:
Complete system circuit diagram.
Figure 3:
CAD design for the laser cut base plate implemented on Autodesk Fusion 360 (left) and the base plate placed on the vehicle chassis (right).
Figure 4:
CAD design for the tower type case implemented on Autodesk Fusion 360 (left) and the physical PLA material 3D printed case (right).
Figure 5:
The overview of the software message queue of the system (vehicle state).
Figure 6:
Windows host PC installation steps.
Figure 7:
Software configuration steps for the Raspberry Pi 4 setup.
Figure 8:
Screenshot of the camera code configuration and sample 160 × 120 pixels image from the vehicle on board camera.
Figure 9:
Screen capture of the I2C detected on the Rpi terminal.
Figure 10:
The Localhost web interface (screen capture) to control the vehicle.
Figure 11:
The complete assembly of the vehicle hardware system.
Figure 12:
The code snippet program of the motor calibration.
Figure 13:
The steering servo and PWM working principle.
Figure 14:
Table generated for steering Angle and PWM equivalent values.
Figure 15:
The custom-built indoor track design and its implementation.
Figure 16:
A sample training dataset from the track training.
Figure 17:
Training data model loss graph.
Figure 18:
The car algorithm flowchart.
Figure 19:
Training and autopilot steering angle histogram graph plot analysis.
No.
Convolution filters
Strides
FC layers
Parameters
Loss
1
12 × 3 × 3, 18 × 3 × 3, 24 × 3 × 3, 36 × 3 × 3
3,2,2,1
900, 246, 32
1,100k
0.098543