Search for: All records

This paper describes a newly launched project that will produce a new approach to public microtransit for underserved communities. Public microtransit cannot rely on pricing signals to manage demand, and current approaches face the challenges of simultaneously being underutilized and overextended. This project conceives of the setting as a sociotechnical system. Its main idea is to engage users through AI agents in conjunction with platform constraints to find solutions that purely technical conceptions cannot find. The project was specified over an intense series of discussions with key stakeholders (riders, city government, and nongovernmental agencies) and brings together expertise in the disciplines of AI, Operations Research, Urban Planning, Psychology, and Community Development. The project will culminate in a pilot study, results from which will facilitate the transfer of its technology to additional communities. 

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.