Parking system for autonomous vehicles using Q-Learning

This project focuses on developing a system that enables a vehicle to park automatically without human intervention. It uses a reinforcement learning technique called Q-learning to simulate a real-world parking environment. The system considers factors such as the position of the vehicle, its distance from the parking slot, and the presence of obstacles in the surroundings. Based on this information, the agent decides the best possible action, such as moving forward, turning, or adjusting its position.

The system also provides real-time visualization, allowing users to observe how the vehicle learns and performs the parking task step by step. The main objective of this project is to make parking more efficient and safe, while demonstrating how reinforcement learning can be applied to solve practical problems in intelligent transportation systems.