Oda, Koki (Institute of Science Tokyo), Seo, Toru (Tokyo Institute of Technology)

Passenger Flow Estimation Method for Ridesharing Systems Using Inverse Problem

Scheduled for presentation during the Regular Session "S34a-Data-Driven Optimization and Governance in Intelligent Urban Mobility" (FR-LM-T34), Friday, November 21, 2025, 10:50−11:10, Surfers Paradise 1

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

Ridesharing is attracting attention as a new means of transportation. However, in general, passenger flows in ridesharing systems are difficult to be recognized by third parties due to several reasons. First, unlike conventional private cars, flows of people and cars are disentangled. Second, although companies operating ridesharing systems know their passenger flow in detail, such information might not be fully shared to third parties due to privacy protection and corporate confidentiality. This will pose substantial difficulty for the management or regulation of ridesharing services by public authorities and the integration with other transportation modes provided by other parties. To account for this challenge, this study proposes a novel estimation method for passenger flow in ridesharing systems by using the inverse problem framework. The proposed method estimates passenger flow as well as operational strategy of ridesharing systems from observable vehicle flow data. Results of numerical validations show that the method accurately estimates these information even under erroneous observation.