Paratransit Routing Considering Dwell Time Uncertainty and Contexts of Requests

EasyChair Preprint no. 10809

Abstract

Paratransit services are indispensable for vulnerable road users, especially for the elderly and the disabled who lack other available mobility options or face lower accessibility to public transit systems. There are some recurrent disturbances that would be simpler to predict and, it is reasonable suspicion that there exists a significant relationship between the spatiotemporal characteristics of a location and the amount of potential delay. Therefore, this study proposes the incorporation of dwell time uncertainty in paratransit operation systems. It will use temporal multimodal multivariate learning (TMML) and the contextual bandit (CB) to estimate the impact of features on loading time.

Keyphrases: Dwell time uncertainty, Reinforcement Learning, vehicle routing

@Booklet{EasyChair:10809,
  author = {Gyugeun Yoon and Hyoshin Park and Kai Monast},
  title = {Paratransit Routing Considering Dwell Time Uncertainty and Contexts of Requests},
  howpublished = {EasyChair Preprint no. 10809},

  year = {EasyChair, 2023}}