Skip to main content
Have a personal or library account? Click to login
1/10th scale autonomous vehicle based on convolutional neural network Cover

1/10th scale autonomous vehicle based on convolutional neural network

International Journal on Smart Sensing and Intelligent Systems
Volume 13 (2020): Issue 1 (January 2020)
By: Avishkar Seth,  Alice James and  Subhas C. Mukhopadhyay  
Open Access
|Aug 2020
Figures & tables

Figures & Tables

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 filtersStridesFC layersParametersLoss
112 × 3 × 3, 18 × 3 × 3, 24 × 3 × 3, 36 × 3 × 33,2,2,1900, 246, 321,100k 0.098543
DOI: https://doi.org/10.21307/ijssis-2020-021 | Journal eISSN: 1178-5608
Journal RSS Feed
Language: English
Page range: 1 - 17
Submitted on: Jul 26, 2020
Published on: Aug 25, 2020
Published by: Macquarie University, Australia
In partnership with: Paradigm Publishing Services
Publication frequency: 1 issue per year
Keywords:
Autonomous vehicle,
Convolutional neural network,
Raspberry pi 4,
Ultrasonic sensor,
Camera
Related subjects:
Engineering,
Introductions and overviews,
Engineering, other

© 2020 Avishkar Seth, Alice James, Subhas C. Mukhopadhyay, published by Macquarie University, Australia
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Volume 13 (2020): Issue 1 (January 2020)
Previous article
Next article