Tuning Trains Speed in Railway Scheduling

Abstract

Railway scheduling consists in ensuring that a set of trains evolve in a shared rail network without collisions, while meeting schedule constraints. This problem is notoriously difficult, even more in the case of uncertain or even unknown train speeds. We propose here a modeling and verification approach for railway scheduling in the presence of uncertain speeds, encoded here as uncertain segment durations. We formalize the system and propose a formal translation to parametric timed automata. As a proof of concept, we apply our approach to benchmarks, for which we synthesize using IMITATOR suitable valuations for the segment durations.