Optimizing Delivery Routes in LATAM using AI Planning
In this high-impact 8-week challenge, 50 AI engineers have collaborated to build a route optimisation tool using Google´s OR-Tools and Open Street Map. of the division of deliveries between delivery vehicles using AI.
The results showed optimum routes of the city of Bogota and the techniques are reproducible in other locations or cities as well.
Bogota, Lima, Mexico City, and Rio de Janeiro are among the most congested cities in the world. General mobility trends in the area, together with the population growth in urban areas, suggest that the levels of congestion currently present in cities in the area will not be reversed soon. The logistics industry, particularly last-mile logistics, bears a disproportionate amount of this burden, particularly with the growth of e-commerce in the wake of the COVID-19 pandemic.
Optimized deployment of existing resources (vehicles and drivers) can improve the level of service for customers, reduce carbon footprint, enrich the well-being and livelihood of drivers, and lessen the industry’s overall impact on urban congestion. With the opportunity to create such an impact, the Omdena collaborators and partner Carryt came together to address the issue at hand.
The Colombian company and Omdena partner, Carryt wants to optimize routes to improve logistics using artificial intelligence and route planning. Carryt, a technology company with a field-services solution has recently become a last-mile logistics provider with a technology product empowering the gig economy, providing drivers with a livable wage, and offering delivery services to customers. Carryt conducts operations in Mexico and soon in Brazil with more than 200K deliveries per month in 2021 and aiming to increase up to 1 million deliveries per month in 2022.
The project outcomes
The Omdena collaborators thoroughly studied the dataset provided by Carryt (Shapefile and OSM file formats). The collaborators researched for relevant knowledge resources, conducted data preparation including wrangling, preprocessing, and exploratory data analysis, modeling, and algorithms, and explored deployment options.
The team started exploring multiple alternative modeling approaches and later on narrowed it down to the use of an open-source software suite for optimization route, Operations Research tool (OR-tool) from Google AI that allows the flexibility to consider the restrictions, and transportation regulations aiming for reduced time and shorter routes. The challenge was addressed by individual task teams that also cooperated on dependent tasks. The nature of Omdena collaborator teams allowed the team to explore multiple alternative routes and solutions before narrowing it down to the final solution.
The data preparation team explored how to better understand, clean, and analyze the partner-provided datasets. They identified data quality issues and prepared a separate guide for special handling of harder-to-incorporate data. They also worked for hand in hand with the modeling and deployment teams to help create a robust optimization solution.
Google Operations Research tool and deployment
The team customized an OR tool to map the exact routes considering the restrictions from the dataset. Finally, a high-performance deployment web service using a flask web framework was implemented on AWS.
Despite the complexity of the challenge, the contributors showed strong teamwork and remote collaboration of talent globally to achieve the project goals. The quality of data available, and the limitations of domain expertise in the field challenged the team in achieving the project goals. Given the limited time and resources, the results showed optimum routes for the city of Bogota and the techniques are reproducible in other locations or cities as well. Future works should aim at the preparation of quality datasets or limited restrictions to optimize routes for multiple vehicles in shorter times and distances.
This challenge has been hosted with our friends at