Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{180550,
        author = {Bharat Maheshwari and Deepak Kumar and Dr. P Sudhakar},
        title = {Web-Based Self-Driving Car Simulation using  JavaScript and Neural Network},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {2492-2499},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180550},
        abstract = {This paper describes a web-based 
autonomous vehicle simulator constructed through 
JavaScript, HTML5, and the Canvas API, with a built
in feedforward neural network. The simulator 
simulates some of the key aspects of autonomous 
driving, including lane detection, obstacle avoidance, 
and dynamic path planning, all rendered in real time in 
the web domain. Ray-casting sensors simulate LiDAR
like sensing, and decisions are made by a neural 
network whose weights are updated through a 
mutation-based learning method based on genetic 
algorithms. Compared to resource-intensive high
fidelity simulators such as CARLA or LGSVL, or low
fidelity pedagogic simulators such as SIM.JS without 
adaptive intelligence, this project strikes a balance 
between computational expense and behavioral 
richness. The simulation showed progressively more 
effective learning in a 1,000-agent simulated 
population, from 0% success in early runs up to over 
75% successful navigation in the 15th generation. The 
entire platform is browser-native and makes no use of 
external libraries or installations, and is thus well
suited in particular to educational institutions, 
prototyping, and outreach events. This project offers 
an open and scalable alternative to existing simulation 
platforms, which allow autonomous vehicle learning 
and testing for a greater population with minimal 
technical demand.},
        keywords = {Autonomous Vehicles, Sensor Fusion,  LiDAR Data Processing, Vehicle Dynamics, Neural  Networks, Trajectory Prediction, Real Time  Control Systems},
        month = {June},
        }