Create a program that applies one or more quantum algorithms to address a sustainability challenge.
Welcome to the Qommute - Quantum Routing and Placement Project! This project aims to tackle the challenging task of optimizing bus station placements and routing using a combination of quantum computing and machine learning. By leveraging cutting-edge technologies, we aim to revolutionize public transportation systems for greater efficiency and reduced delays.
To run this project locally, follow these steps:
- Clone this repository to your local machine.
- Install the required dependencies as listed in the Prerequisites section.
- Use the provided guide to run quantum placement, machine learning predictions, and routing calculations.
- Explore the interactive visualization to interpret the results.
- Quantum placement optimization: Find the optimal bus station placements using quantum algorithms.
- Machine learning-based delay prediction: Predict delays using machine learning models trained on historical data.
- Optimum routing calculation: Determine the best routes considering quantum placement and delay predictions.
- Interactive visualization of results: Visualize the optimized placements, predicted delays, and optimum routing on a user-friendly interface.
In the quantum placement component, we utilize quantum computing to search for the best locations for bus stations. We employ quantum algorithms and libraries like Qiskit to optimize the placement for minimal travel times and passenger convenience.
Our machine learning model predicts delays in the transportation system. It is trained on a comprehensive dataset of time of the year, category of transportation, previous delays, history of delays, category and subcategory of delays such as crew availability, infrastructure, police and medical, operating conditions, planned ROW works and so forth. The model architecture, dataset details, and training process can be found in the project's documentation.
The optimum routing component combines the results from quantum placement and the machine learning model. By factoring in both optimized placement and predicted delays, we calculate the most efficient routes for buses to minimize delays and enhance the overall transportation system.
Our project offers an intuitive visualization tool to interactively explore the optimized placements and routing results. Check out the project's presentation for detailed information.
The project has the following prerequisites:
- Python 3.7 or higher
- Qiskit for quantum computing
- PyTorch for machine learning
Code Devs: Samyam Lamichhane, Sarthak Malla, Sasha Malik
Contributors: Aibar Talip, Andy Lee, Erik Lee, Josh Handelman
This project was created at the 2023 Tandon hAQathon to address a sustainability challenge to solve using quantum computation.