TY - JOUR
T1 - Dynamic journeying in scheduled networks
AU - Hame, Lauri
AU - Hakula, Harri
PY - 2013
Y1 - 2013
N2 - We study a dynamic-journey planning problem for multimodal transportation networks. The goal is to find a journey, possibly involving transfers between different transport modes, from a given origin to a given destination within a specified time horizon. Transport services are represented as sequences of scheduled legs between nodes in the transportation network. Due to uncertainty in transport services, we assume for each pair of adjacent legs $i$ and $j$ a probability of a successful transfer from $i$ to $j$. If a transfer between two legs is unsuccessful, the customer needs to reconsider the remaining path to the destination. The problem is modeled as a Markov decision process, and the main contribution is a backward induction algorithm that generates an optimal policy for traversing the public transport network in terms of a given objective, e.g., reliability, ride time, waiting time, walking time, or the number of transfers. A straightforward method for maximizing reliability is also suggested, and the algorithms are tested on real-life Helsinki area public transport data. Computational examples show that, with a given input, the proposed algorithms rapidly solve the journeying problem.
AB - We study a dynamic-journey planning problem for multimodal transportation networks. The goal is to find a journey, possibly involving transfers between different transport modes, from a given origin to a given destination within a specified time horizon. Transport services are represented as sequences of scheduled legs between nodes in the transportation network. Due to uncertainty in transport services, we assume for each pair of adjacent legs $i$ and $j$ a probability of a successful transfer from $i$ to $j$. If a transfer between two legs is unsuccessful, the customer needs to reconsider the remaining path to the destination. The problem is modeled as a Markov decision process, and the main contribution is a backward induction algorithm that generates an optimal policy for traversing the public transport network in terms of a given objective, e.g., reliability, ride time, waiting time, walking time, or the number of transfers. A straightforward method for maximizing reliability is also suggested, and the algorithms are tested on real-life Helsinki area public transport data. Computational examples show that, with a given input, the proposed algorithms rapidly solve the journeying problem.
KW - Itinerary planning
KW - Markov decision process
KW - multimodal transportation network
UR - http://www.scopus.com/inward/record.url?scp=84879323278&partnerID=8YFLogxK
U2 - 10.1109/TITS.2012.2213817
DO - 10.1109/TITS.2012.2213817
M3 - Article
VL - 14
SP - 360
EP - 369
JO - IEEE Transactions on Intelligent Transportation Systems
JF - IEEE Transactions on Intelligent Transportation Systems
SN - 1524-9050
IS - 1
M1 - 6293897
ER -