Taxify launches machine learning competition to optimize traffic in future cities

May 09, 2018

Europe’s leading ridesharing platform Taxify and Robotex International 2018 are announcing an open machine learning competition focusing on solving problems for future cities. The contestants will need to build an intelligent fleet management algorithm for a fleet of self-driving cars.

The competition challenges teams to build an optimal dispatching system for a self-driving car fleet in Estonian capital Tallinn and optimizing it for highest total ride value, using synthetic data for Tallinn as input and various constraints to simulate a real environment. The team coming up with the best solution will receive an award of 4000€.

Taxify’s mission is to make transport affordable and accessible to everyone. Therefore, the goal is to have a car available within a couple of minutes for anyone in any location across the cities we operate in. We’re close to that in a lot of cities we’re operating in today, but self-driving fleets that complement human drivers will be the next big leap,” says André Karpištšenko, Taxify’s Head of Data Science.  

“We’re asking the contestants to imagine a city in 2022. Self-driving car fleets will have become a reality even though drivers will still be playing a crucial role in the industry. The cars will be moving independently between passengers and depots where they can recharge. The competition helps to focus the the global tech and machine learning community on challenges around urban mobility and how we can contribute to making traffic in future cities more efficient,” Karpištšenko explains.

Today, more than 500,000 drivers use Taxify’s platform to offer rides to passengers. The competition paints a picture of a combined fleet of self-driving cars as well as human drivers. “On-demand is on a fast rise to enable more people to use ride-sharing as a means for transportation. Today, on-demand rides make up 2% of all the rides in a city. Taxify estimates that by 2025, the share of on-demand trips will have increased to a third of total. Additionally, we’ll be seeing different types of autonomous vehicles – some geared towards families, others playing the role of mobile offices or entertainment centres,” says Karpištšenko.

One of the challenges is to optimise the time spent between driving passengers and waiting for the next ride. It will require the participants to develop various dispatching, routing, rebalancing, depot planning and pooling algorithms.

The competition is open to everyone interested in machine learning, but will be especially exciting for experts and enthusiasts.

The teams selected for the finals will be invited to the Robotex International festival in Tallinn, Estonia from November 30th to of December 2nd 2018. The winners will be selected and announced by Taxify’s Data Science team in December and will be invited to speak at the North Star AI machine learning conference as well as highlighted in the next year’s competition.

Read the official competition rules from here.

For any questions please contact us via e-mail robotex@taxify.eu.