AI Case Study
UPS saves 10 million gallons of fuel and $100 million per year by optimising driver delivery routes that consider real-time traffic and weather information obtained from social media and machine learning
UPS has developed an AI platform ORION (On-road Integrated Optimization and Navigation) to do delivery route optimization. The solutions takes into account the day's deliveries, timings, historical data and combines it with real-time data like those supplied by customers, drivers and the vehicles and can alter the routes on the fly based on changing weather conditions or accidents.
Freight And Logistics
"ORION, which stands for On-Road Integrated Optimization and Navigation, finds the fastest, most fuel-efficient way to get every package to a customer's door through a combination of connected car-like telematics and a lot of data crunching of package information, user preferences and routes. ORION also scans map data and historical GPS tracking of similar routes to come up with a solution.
The software has 250 million address data points to access. Each individual route has an average of 200,000 possible ways to go."
"Orion using “traveling salesman” algorithm, calculates the most efficient path between a variety of points, and geographic mapping."
UPS claim that they:
* Save around 100 million miles and 10 million gallons of fuel per year. It also reduces carbon dioxide emissions by about 100,000 metric tons.
* Expect to reduce operating costs by US$300 million to US$400 million a year
Not everyone agrees though, with some drivers raising concerns that the suggestions are not always optimal as it suggests more left turns and backing up and skipping some deliveries on the way.
Traveling salesman algorithm
For UPS, eliminating one mile, per driver, per day over one year can save up to $50 million.
Telematics – onboard data-gathering technology, GPS tracking equipment, vehicle sensors, combined with drivers' handheld mobile devices, allows UPS to capture data related to vehicle routes, idling times and safety protocols.
Daily delivery and user preference of delivery time
History data about routes
Real-time traffic and weather details
Accesses 250 million address data points.
More than 55,000 routes