Intelligent Waste Pickup Routing for Smart Cities

An Screenshot of the main web interface

Inspiration

What it does

How we built it

Challenges we ran into

Accomplishments that we're proud of

Inspiration

Urban waste collection in most cities still follows fixed routes and schedules. This often results in overflowing garbage bins in busy areas while trucks unnecessarily visit half-empty bins elsewhere. Observing these inefficiencies inspired us to explore how real-time data and AI could make waste collection smarter, cleaner, and more efficient.

What it does

Our project is an AI-based waste pickup route optimization system. Smart bins (simulated using IoT concepts) report their fill levels in real time. Based on this data, the system identifies bins that require immediate pickup and dynamically generates optimized routes for multiple garbage trucks. The routes are re-optimized whenever new bin data indicates a potential overflow.

How we built it

We built a web-based dashboard that visualizes garbage bins on a city map with real-time fill status. A FastAPI backend processes bin data and uses Google OR-Tools to solve a multi-vehicle routing problem (VRP). The frontend displays optimized routes for each truck, and dynamic updates are pushed when bin conditions change. A Tinkercad-based smart bin simulation demonstrates how real-world sensor data would be generated.

Challenges we ran into

Designing efficient routing logic for multiple trucks under time and capacity constraints
Handling dynamic route re-optimization when bin fill levels suddenly change
Balancing realism with simplicity for a hackathon-scale prototype
Clearly demonstrating IoT concepts without physical hardware

What we learned

We gained hands-on experience in route optimization, real-time system design, and integrating AI decision-making with urban infrastructure problems. The project also highlighted how data-driven approaches can significantly improve sustainability and operational efficiency.

What's next

Future improvements include real hardware integration, predictive waste generation models, traffic-aware routing, and large-scale deployment across multiple city zones.