APPLICATION BASED SELF-DRIVING CAR SIMULATOR USING MODIFIED CNN NVIDIA MODEL

APPLICATION BASED SELF-DRIVING CAR SIMULATOR USING MODIFIED CNN NVIDIA MODEL
Author(s):
Dr. Poovarasan Selvaraj, Ajithkumar. R
Keywords:
DAVE-2 System, CNN, CNN Model, Autonomous Land Vehicle in a Neural Network (ALVINN) system.
Abstract
Self-driving car system using NVIDIA’s Convolutional Neural Network (CNN) model, which maps raw pixel data from a single front-facing camera directly to steering commands. Leveraging deep learning, we trained the model on a diverse dataset encompassing city streets, highways, and off-road terrains. The simulation showcases the model's ability to autonomously navigate complex driving conditions without traditional components like lane detection, path planning, or control algorithms. Instead, the model learns to interpret and respond to road features and driving scenarios solely from human steering inputs during training. Our findings highlight the benefits of an end-to-end learning approach, where the CNN optimizes the entire driving task integrally, achieving robust performance across various driving contexts. This method potentially enhances efficiency and effectiveness over traditional autonomous driving systems, demonstrating the feasibility of streamlined, deep learning-based solutions for self-driving technology.
Article Details
Unique Paper ID: 167187 Publication Volume & Issue: Volume 11, Issue 3 Page(s): 526 - 531
Article Preview & Download

Share This Article

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on [email protected]