Comparison of Various Autonomous Vehicle Self-Navigation Paradigms

Location

Presentation- Allen E. Paulson College of Engineering and Computing

Document Type and Release Option

Thesis Presentation (Archived)

Faculty Mentor

Rami Haddad

Faculty Mentor Email

rhaddad@georgiasouthern.edu

Presentation Year

2021

Start Date

26-4-2021 12:00 AM

End Date

30-4-2021 12:00 AM

Keywords

Artificial intelligence, vehicle, Residual Neural Network (RNN)

Description

This project aimed to compare the performance of multiple different artificial intelligence training methods using their performance controlling a vehicle on a testing track. Some of the methods used in this project were a Dense Convolutional Network (DCN), Residual Neural Network (RNN). Using each of these methods, the vehicle was trained to be able to go around the track successfully, though each model had different levels of error and time to go around the track. Based on the results of speed vs errors made, the best model can be determined based on both accuracy, speed, and training time.

Academic Unit

Allen E. Paulson College of Engineering and Computing

Comments

This work is archived and distributed under the repository's standard copyright and reuse license, available here. Under this license, end-users may copy, store, and distribute this work without restriction. For questions related to additional reuse of this work, please contact the copyright owner.

This document is currently not available here.

Share

COinS
 
Apr 26th, 12:00 AM Apr 30th, 12:00 AM

Comparison of Various Autonomous Vehicle Self-Navigation Paradigms

Presentation- Allen E. Paulson College of Engineering and Computing

This project aimed to compare the performance of multiple different artificial intelligence training methods using their performance controlling a vehicle on a testing track. Some of the methods used in this project were a Dense Convolutional Network (DCN), Residual Neural Network (RNN). Using each of these methods, the vehicle was trained to be able to go around the track successfully, though each model had different levels of error and time to go around the track. Based on the results of speed vs errors made, the best model can be determined based on both accuracy, speed, and training time.