Dynamic last-mile routing that re-plans during the day
Inspired by publicly reported work at UPS
Plan delivery routes that respect time windows and re-plan them when traffic or new pickups change the day.
The brief
UPS has described the newer ORION recalculating routes through the day as traffic, pickups and delivery orders change, alongside turn-by-turn navigation for drivers. Build a dynamic router on real last-mile route data: plan routes with time windows, then re-plan when new pickups or delays arrive, and learn from how experienced drivers actually sequenced their stops. Good looks like: route quality and on-time rate against the drivers' real sequences, re-planning in seconds, a simulation of a full day, and a driver-facing map view.
Read the case first
What UPS has said in public about this kind of work, on its own pages:
Make it your own
Re-plan something else that changes during the day: ambulance positioning, a garbage collection round, or service engineers' visits. Decide what "late" costs in that service and optimise for it.
AITeky has no link with UPS, which has not reviewed or endorsed this brief. The brief only draws on what the company has published, uses open data rather than its data, and is a learning exercise: don't present your project as UPS's work or system.
What you will build
- Explore the routes, stops, time windows and driver sequences
- Plan routes with time windows (OR-Tools)
- Learn stop-order preferences from real driver sequences
- Simulate a day with new pickups and delays and re-plan
- Compare distance and on-time rate with the real routes
- Build a dispatcher dashboard and a driver map view
Free, open data to build it with
Sign up free to get the data and links
It takes a minute with your email. AiTeky Pass (₹999/month or ₹9,999/year) is free for your first 30 days.