R.A.D.A.R

"Real-time Analytic Detection of Available Restrooms" maps the shortest path to vacant stalls and prioritizes maintenance based on real-time usage data.

Comment

Inspiration

Having worked in a large-scale corporate environment with over 10,000 employees, we frequently encountered a relatable frustration: the inability to find an available restroom when needed. In a massive office complex, finding a vacant stall shouldn't feel like a guessing game. This inspired us to develop the Real-time Analytic Detection of Available Restrooms, or R.A.D.A.R.

What it does

R.A.D.A.R. is an intelligent navigation and maintenance application designed for large facilities. After a user provides their current location, the app identifies the nearest available restroom and generates an optimized, easy-to-follow map. Additionally, we implemented a Clean Monitor feature that tracks toilet usage frequency since the last cleaning cycle, helping facility staff prioritize maintenance based on actual demand.

How we built it

The core of R.A.D.A.R. is built on a Graph Data Structure. We designed a comprehensive database to store office layouts as a collection of nodes (restrooms and intersections) and weighted edges. Using Python, we retrieve this spatial data to reconstruct the map as a graph and apply Dijkstra’s Algorithm with a priority queue to calculate the shortest path to an available facility.

Challenges we ran into

One of our biggest hurdles was data generation and spatial alignment. To make the navigation accurate, we had to model a 3D office environment and manually define the relationships between nodes and edges. Writing the complex SQL insert statements to define these edges in a 3D coordinate system was a meticulous and time-consuming process.

Accomplishments that we're proud of

We are particularly proud of successfully deploying our database on Azure Cloud and establishing a seamless connection between our cloud infrastructure and the Python backend. Achieving reliable, real-time data retrieval from a remote database was a significant technical milestone for our team.

What we learned

During this project, we deepened our understanding of graph theory and its practical applications in indoor navigation. We also gained valuable experience in cloud database management and the importance of data normalization when handling complex spatial relationships.

What's next for R.A.D.A.R.

  1. Real-time GPS Integration: Automating user location tracking so users don't have to input their coordinates manually.
  2. IoT Connectivity: Integrating live sensors to detect stall occupancy automatically.
  3. Predictive Analytics: Using usage data to predict peak times and optimize cleaning schedules.
  4. Community Ratings: Implementing a user-driven review system to rank locations based on cleanliness and accessibility.
  5. Global Crowdsourcing: Scaling into a worldwide app where users contribute to a live map of accessible facilities.
  6. Commercial Partnerships: Enabling businesses to "merchandise" their locations by listing facilities to drive foot traffic and offer premium user experiences.
Share this project:

Updates