SOTAVerified

On the Real-time Vehicle Placement Problem

2017-12-04Code Available0· sign in to hype

Abhinav Jauhri, Carlee Joe-Wong, John Paul Shen

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Motivated by ride-sharing platforms' efforts to reduce their riders' wait times for a vehicle, this paper introduces a novel problem of placing vehicles to fulfill real-time pickup requests in a spatially and temporally changing environment. The real-time nature of this problem makes it fundamentally different from other placement and scheduling problems, as it requires not only real-time placement decisions but also handling real-time request dynamics, which are influenced by human mobility patterns. We use a dataset of ten million ride requests from four major U.S. cities to show that the requests exhibit significant self-similarity. We then propose distributed online learning algorithms for the real-time vehicle placement problem and bound their expected performance under this observed self-similarity.

Tasks

Reproductions