Ogawa, Daichi (The University of Tokyo), Hato, Eiji (The University of Tokyo)

Analysis of Mutual Spatial Features in Mixed Pedestrian and Vehicular Spaces Using AIRL

Scheduled for presentation during the Regular Session "Modeling, Simulation, and Control of Pedestrians and Cyclists I" (WeAT8), Wednesday, September 25, 2024, 11:50−12:10, Salon 16

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on December 26, 2024

Abstract

The evaluation of interaction among transportation modes is getting importance in urban planning, especially at the transportation hubs, because the endogenous interaction can cause asymmetric and inefficient traffic conditions. Route choice models are powerful tools to evaluate the utility of the street space, but the direct evaluation of the interaction can be unstable because of the multiple equilibria. In this study, we propose a method to evaluate the interaction among transportation modes with stability. In addition, we propose a model to estimate interaction from satellite image data, which helps the route choice model to capture spatial structure. The proposed method is applied to the case study in Matsuyama, Japan, and the incorporation of the stabilization of interaction and use of satellite image data are shown to improve the performance of the route choice model from the view of log-likelihood and accuracy.