A Comprehensive Exploration of Self-Driving Car Simulation Using Neural Networks

Authors(2) :-K. Satyam, Julakanti Sai Sree Harshitha

A self-driving car is an autonomous vehicle that uses sensors and AI to navigate without human control, promising enhanced safety and potentially more efficient transportation systems. Self-driving cars have gained prominence in recent times due to technological advancements. This project aims to train a neural network for autonomous driving car using JavaScript with NO libraries. The project's inception involves the construction of a virtual world encompassing roads, buildings, and trees. Graph-based algorithms are employed to generate the infrastructure, offering participants a hands-on experience in world creation. To control the car's movement, the project first applies fundamental physics concepts. The lack of libraries makes it possible to comprehend the simulation's operation on a deeper level. Keyboard inputs are used to manually control the car's movement, and a virtual road is made for visualization. A major part of the project is to simulate sensors on the car. These sensors use segment intersection algorithm to accomplish collision detection and ray casting to detect closeness to other vehicles and road borders. Neural networks are the second component of the project. By using actual brain neurons as inspiration, participants can design and visualize neural networks. Genetic algorithms are among the optimization strategies introduced to enhance the network's performance. Creating a self-driving car simulation from the ground up provides a useful viewpoint on the intricacies of neural networks and autonomous vehicle simulation. It gives learners the knowledge and resources they need to comprehend the fundamental ideas and difficulties of self-driving technology.

Authors and Affiliations

K. Satyam
Assistant Professor, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, Andhra Pradesh, India
Julakanti Sai Sree Harshitha
Post Graduate, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, Andhra Pradesh, India

Self-driving cars, autonomous vehicles, sensors, AI, neural network, JavaScript, graph-based algorithms, collision detection, ray casting, genetic algorithms

  1. Luca Bergamini &Yawei YeOliver Scheel Sim Net: Learning Reactive Self-driving Simulations from Real-world Observations," 2021 IEEE International Conference on Robotics and Automation (ICRA), Xi'an, China, 2021, pp. 5119-5125, doi: 10.1109/ICRA48506.2021.9561666.
  2. S. Lade, P. Shrivastav, S. Waghmare, S. Hon, S. Waghmode and S. Teli, "Simulation of Self Driving Car Using Deep Learning," 2021 International Conference on Emerging Smart Computing and Informatics (ESCI), Pune, India, 2021, pp. 175-180, doi: 10.1109/ESCI50559.2021.9396941.
  3. A. Bhalla, M. S. Nikhila and P. Singh, "Simulation of Self-driving Car using Deep Learning," 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS), Thoothukudi, India, 2020, pp. 519-525, doi: 10.1109/ICISS49785.2020.9315968.
  4. K. O’Shea and R. Nash, "An Introduction to Convolutional Neural Networks", pp. 1-11, 2015.
  5. R. Kulkarni, S. Dhavalikar and S. Bangar, "Traffic Light Detection and Recognition for Self-Driving Cars Using Deep Learning", Proc. - 2018 4th Int. Conf. Comput. Commun. Control Autom.
  6. M. Bojarski et al., "End to End Learning for Self-Driving Cars", Apr. 2016.
  7. A. K. Jain, "Working model of Self-driving car using Convolutional Neural Network Raspberry Pi and Arduino", Proceedings of the 2nd International Conference on Electronics Communication and Aerospace Technology ICECA 2018, pp. 1630-1635, Sep. 2018.
  8. A. K. Jain, "Working model of Self-driving car using Convolutional Neural Network Raspberry Pi and Arduino", Proceedings of the 2nd International Conference on Electronics Communication and Aerospace Technology ICECA 2018, pp. 1630-1635, Sep. 2018.

Publication Details

Published in : Volume 7 | Issue 2 | March-April 2024
Date of Publication : 2024-03-30
License:  This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 28-34
Manuscript Number : SHISRRJ24725
Publisher : Shauryam Research Institute

ISSN : 2581-6306

Cite This Article :

K. Satyam, Julakanti Sai Sree Harshitha, "A Comprehensive Exploration of Self-Driving Car Simulation Using Neural Networks", Shodhshauryam, International Scientific Refereed Research Journal (SHISRRJ), ISSN : 2581-6306, Volume 7, Issue 2, pp.28-34, March-April.2024
URL : https://shisrrj.com/SHISRRJ24725

Article Preview