QUANTUM COMPUTING CIRCUITS FOR AUTOMOTIVE INDUSTRY

This project explores the integration of quantum computing circuits with autonomous vehicle technology, focusing on collision-free navigation, route optimization, trajectory planning, and ride pooling systems. We leverage CARLA, an open-source vehicle simulator, to test and evaluate our models under various real-world conditions, including different terrains and weather scenarios. Quantum computing algorithms will be employed to enhance decision-making, improving efficiency, safety, and adaptability in dynamic environments.

Table of Contents

• About the Project
• Problem Statement
• Methodology
• Excepted Outcomes

About the project

The automotive industry is rapidly evolving, with autonomous vehicles becoming a reality. However, real-time decision-making for navigation, collision avoidance, and traffic optimization remains a challenge due to the complexity of processing large datasets. This project integrates quantum computing circuits to enhance the efficiency of autonomous vehicle systems.

We will simulate vehicles using CARLA, an open-source autonomous driving simulator, to test performance across various terrains, weather conditions, and traffic scenarios. Quantum computing will be applied to optimize key driving functions, leveraging its parallel processing power to outperform classical computing approaches.

1. Collision-Free Navigation : Develop algorithms to ensure safe navigation by predicting and avoiding potential obstacles in real-time.
2. Route optimisation: To implement routing algorithms that minimise travel time and distance while factoring in traffic conditions and user preferences.
3. Trajectory planning: To develop smooth and efficient lane change by optimising trajectory paths while ensuring safety.
4. Ride pooling system: To create an efficient ride pooling system that matches passengers with autonomous taxis, optimizing routes for multiple users.

Problem Statement

• Obstacles, construction zones, and unpredictable human behavior complicate the design of fully automated vehicles.
• Lot of autonomous cars are geofenced to particular locations and environmental conditions.
• Increased computational complexity arises from orchestrating data movement, storage, processing, analysis, and knowledge extraction.
• Complex systems require large data sets, as even a small software error can lead to accidents, necessitating rapid decision-making.

Methodology

• CARLA Environmrnt Setup: Configure weather, traffic, road conditions, and predestrain interference using the CARLA API.
• Data Collection and Preprocessing: Extract the data and preprocess it for vechicle perception.
• Quantum-Assisted Collision Avoidance: Feed the data into a quantum circuit to adjust spped, steering, and throttle for pedestrian safety.
• Qunatun Route Optimisation: Use quantum algorithms to determine the most efficient path for autonomous navigation.
• Lane Change and Trajectory Prediction: Develop a rotation matric-based function to make effective decision during lane changes.
• Quantum-Optimized Ride Pooling: Develop a ride-sharing system that assigns optimal routes using quantum computation.

Expected Outcomes

1. Enhanced Collision Avoidance
2. Optimized Route Planning
3. Efficient Trajectory Planning
4. Quantum-Optimized Ride Pooling System
5. Versatile Autonomous Vehicle Simulation