Carpooling : the 2 Synchronization Points Shortest Paths Problem

Arthur Bit-Monnot (1) , Marie-José Huguet (1) , Marc-Olivier Killijian (2) , Christian Artigues (1)

1 LAAS-MOGISA
2 LAAS-TSF - Équipe Tolérance aux fautes et Sûreté de Fonctionnement informatique

Carpooling is an appropriate solution to address traffic congestion and to reduce the ecological footprint of the car use. In this paper, we address an essential problem for providing dynamic carpooling: how to compute the shortest driver's and passenger's paths. Indeed, those two paths are synchronized in the sens that they have a common subpath between two points: the location where the passenger is picked up and the one where he is dropped off the car. The passenger path may include time-dependent public transportation parts before or after the common subpath. This defines the 2 Synchronization Points Shortest Path Problem (2SPSPP) and focus explicitely on the computation of optimal itineraries for the 2SPSPP, i.e. determining the (optimal) pickup and drop-off points and the two synchronized paths that minimize the total traveling time. We also define restrictions areas for reasonable pick-up and drop-off points and use them to guide the algorithms using heuristics based on landmarks. Experiments are conducted on real transportation network showing the efficiency of the proposed algorithms and accelerations.

Mots clés: Dynamic Carpooling; Shortest Path Problem; Synchronized Paths

Domaines: Recherche opérationnelle [math.OC]; Algorithme et structure de données [cs.DS]

Arthur Bit-Monnot, Marie-José Huguet, Marc-Olivier Killijian, Christian Artigues. Carpooling : the 2 Synchronization Points Shortest Paths Problem. 2013. ⟨hal-00843628v1⟩