Self-Driving Car Simulation with JavaScript

This project is a self-driving car simulation implemented in JavaScript without relying on external libraries. It serves as a comprehensive demonstration of programming fundamentals, artificial intelligence concepts, and problem-solving skills.

Overview

In this project, we aim to create a self-driving car simulation from scratch, covering various components such as driving mechanics, environment definition, sensor simulation, collision detection, and neural network-based car control. The goal is to provide a hands-on learning experience in building complex systems and implementing artificial intelligence techniques.

Key Features

• Custom Implementation: No external libraries are used, demonstrating proficiency in JavaScript and core programming concepts.
• Driving Mechanics: Implementing the fundamental mechanics of car movement and control.
• Environment Definition: Defining the environment in which the car operates, including roads, obstacles, and other elements.
• Sensor Simulation: Simulating sensors for the car to perceive its surroundings.
• Collision Detection: Implementing algorithms to detect collisions between the car and other objects.
• Neural Network Control: Using neural networks to enable the car to control itself based on sensor inputs.
• Visualization: Visualizing the neural network's functionality to aid understanding.

Getting Started

To run the simulation locally, follow these steps:

1. Clone this repository to your local machine.
2. Open the project directory in your code editor.
3. Open the index.html file in a web browser to view the simulation.
4. Use save button:🏆📥, to manually save the best-car-brain in localStorage , Use delete button: 🔪🪦, if you want to clear it from localStorage.
5. Saving a best-car-brain and reloading the page will restart the simulation using this car-brain as a parent.
6. This process subsequently trains the model to become self sufficient in driving between the traffic.
7. After the model is successfully trained, you will find a variable N in main.js change it's value to =1; and reload to see the trained model.