An Autonomous Vehicle Prototype for Off-Road Applications based on Deep Convolutional Neural Network

Rahmat Ullah, Ikram Asghar, Mark Griffiths, Gareth Evans, Rory Dennis

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Making autonomous driving a safe, feasible, and better alternative is one of the core problems for researchers from academia and industry. The development of autonomous cars in a real-world setting poses many challenges. This paper presents a low-cost, small-scale self-driving automobile model called ‘Zumee’, powered by a deep convolutional neural network. Zumee offers synchronised image data collection using a camera for deep learning models. The proposed model is experimentally validated using an Nvidia Jetson TX2 board as the onboard computer. Data augmentation, transfer learning, and neural networks are used to train the prototype model. Specifically, a convolutional neural network (CNN) model is trained using data from various scenarios. A robust dataset is generated by augmenting the images obtained using a camera to accommodate multiple environments. The prototype model is trained to imitate the policies used by a human supervisor to drive a robot car autonomously in a closed environment. The proposed prototype could be used as a base for more advanced driverless autonomous vehicles or for educational purposes as an economical prototype model.
Original languageEnglish
Title of host publication8th International Conference on Engineering and Emerging Technologies
PublisherIEEE Computer Society
Pages1-6
Number of pages6
DOIs
Publication statusPublished - 2022
Event8th International Conference on Engineering & Emerging Technologies ICEET 2022 - Kuala Lumpur, Malaysia
Duration: 27 Oct 202228 Oct 2022
Conference number: 8

Conference

Conference8th International Conference on Engineering & Emerging Technologies ICEET 2022
Abbreviated titleICEET 2022
Country/TerritoryMalaysia
CityKuala Lumpur
Period27/10/2228/10/22

Keywords

  • Autonomous car
  • Convolutional Neural Network (CNN)
  • Robots
  • Prototypes
  • Self-driving car

Fingerprint

Dive into the research topics of 'An Autonomous Vehicle Prototype for Off-Road Applications based on Deep Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this