Applying reinforcement learning for generating controlling schedules for public transit in Lausanne

(Industry collaboration with Transports publics lausannois)

Context: Public transport network constitutes for an indispensable part of a city by providing mobility services to the general masses. To improve ease of access and reduce infrastructural investments, public transport authorities often adopt proof of payment system. Such a system operates by eliminating ticket controls when boarding the vehicle and subjecting the travelers to random ticket checks by affiliated personnel (controllers). Although cost efficient, such a system promotes free-riders, who deliberately decide to evade fares for the transport service.

Objective: Use datasources provided by TL such as ridership numbers, fraud history, ticket sales to generate a datat drive scheduling pattern for their controllers to go to stop in order to maximize controlling people without valid tickets.

Contact: Vaibhav Kulkarni (