Towards a geographically even level of service in on-demand ridepooling

Conference paper (2021)

Authors

Andres Fielbaum Learning & Autonomous Control - Mechanical, Maritime and Materials Engineering
J. Alonso-Mora Learning & Autonomous Control - Mechanical, Maritime and Materials Engineering
Research Group
Learning & Autonomous Control (Mechanical, Maritime and Materials Engineering) (TU Delft)
Copyright: © 2021 Pieter Schuller, Andres Fielbaum, J. Alonso-Mora
DOI: https://doi.org/10.1109/ITSC48978.2021.9564910
More Info
expand_more

Published Date

2021

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical, Maritime and Materials Engineering

Department

Cognitive Robotics

Research Group

Learning & Autonomous Control

Abstract

On-demand ridepooling systems usually need to decide which requests to serve, when the number of vehicles is not enough to transport them all with waiting times that are acceptable by the users. When doing so, they tend to provide uneven service rates, concentrating rejections in some zones within the operation area. In this paper, we propose two techniques that modify the objective function governing the assignment of users to vehicles, to prioritize requests originated at zones that present a relatively large rejection rate. The goal is to diminish the Gini Index of the rejections' rate, which is a well established way to measure inequality in economics. We test these techniques over an artificial small network and a real-life case in Manhattan, and we show that they are able to reduce the Gini Index of the rejection rates. Moreover, the overall rejection rate can be simultaneously reduced, thanks to utilizing the vehicles more efficiently.

Files

Towards_a_geographically_even_... (pdf)
(pdf | 2.18 Mb)
- Embargo expired in 25-04-2022
Unknown license