Class
Article
College
College of Science
Department
Computer Science Department
Faculty Mentor
Vicki Allan
Presentation Type
Poster Presentation
Abstract
We propose a unified approach for scheduling taxis across a city. Balancing the supplies and demands on a city scale is a challenging problem in the field of online taxi services. To tackle the problem, we design a unified approach considering two important processes: Taxi-Rider Matching and Taxi Guidance. In the Taxi-Rider Matching, with the help of Lottery Selection (LS) and smoothed popularity score, the approach can balance supplies and demands well, both in the local neighborhood areas and hot places across the city. Regarding Taxi Guidance, we propose Q-learning Idle Movement (QIM) to direct vacant taxis to the most needed places in the city, adapting to dynamic change environments. The experimental results verify that the unified approach is effective and flexible.
Location
Logan, UT
Start Date
4-12-2023 2:30 PM
End Date
4-12-2023 3:30 PM
Included in
A Unified Approach that Makes Online Taxi Service More Effective
Logan, UT
We propose a unified approach for scheduling taxis across a city. Balancing the supplies and demands on a city scale is a challenging problem in the field of online taxi services. To tackle the problem, we design a unified approach considering two important processes: Taxi-Rider Matching and Taxi Guidance. In the Taxi-Rider Matching, with the help of Lottery Selection (LS) and smoothed popularity score, the approach can balance supplies and demands well, both in the local neighborhood areas and hot places across the city. Regarding Taxi Guidance, we propose Q-learning Idle Movement (QIM) to direct vacant taxis to the most needed places in the city, adapting to dynamic change environments. The experimental results verify that the unified approach is effective and flexible.