Abstract
We formulate a vacant ride-sourcing or taxi driver’s routing decision as an infinite-horizon semi-Markov decision process (SMDP) in a road network, where a driver decides which link to take at each node and transitions to a new node depending on the stochastic vehicle-passenger matching process. A driver’s decision is based on observable and unobservable states.
The modeler’s job is to jointly estimate an average driver’s parameterized utility function as well as the state transition function based on the sequence of observed states and actions. We establish the existence and uniqueness of a fixed point solution to the Bellman equation for the SMDP, which is needed for the maximum likelihood estimation of model parameters. We use parallel computing to speed up the estimation algorithm to be applicable to a case study in a large network.
The expected fare, expected operating cost and number of intersections in the urban area are found to be significant predictors of drivers’ routing decisions. Comparison with several base models suggest the advantage of considering multiple decision cycles, low discount rate (corresponding to a discount factor close to 1), and joint estimation of routing and matching parameters.
Song Gao is Professor of Civil and Environmental Engineering at the University of Massachusetts Amherst. Her research focuses on travel behavior and transportation system analysis, with applications in smart and shared mobility, transportation planning, and sustainable transportation systems, and has been funded by local, regional and federal government agencies and private foundations, including the Massachusetts Department of Transportation, National Science Foundation, FHWA, and APRA-E. Prior to joining UMass, Prof. Gao worked as a transportation engineer at Caliper Corporation. She is an Editorial Board Editor of Transportation Research Part B, and past Associate Editor of Transportation Science. She received her Ph.D. and M.S. in Transportation from MIT, and B.S. in Civil Engineering from Tsinghua University.