MyPath

Identifying Surface Characteristics for Generating Personalized Accessible Routes for Wheelchair Users through Participatory Sensing

Welcome to the MyPath project. The purpose of this project is to build an accessible routing and navigation system for wheelchair users to get to their destination from any source location. We determine accessible routes by classifying surfaces from vibration data. In existing mapping systems, the developers rarely consider the experience of the persons with disabilities in most cases. For example, wheelchair users may encounter steep slopes or other barriers in the built environment which they cannot overcome, or uneven road surfaces and broken sidewalks that are not suitable for wheeled navigation. In order to solve this problem and improve the user experience, we proposed the MyPath solution. We analyze and classify the data collected by sensors and then using the ML model to predict any new surface data available during the testing phase of the system. The road surface information is then updated in a research-oriented open-source mapping system known as the OpenStreetMap (OSM). Finally, we combine the user’s personalized requirements and the accessibility of each road to generate an accessible route for wheelchair users through the use of Graphhopper which is a dedicated routing engine for the OSM.

Sign up for our study

If you are a wheelchair user and you feel interested in our study and would like to be a part of it, please check the following flyer to complete a short survey.

news

Sep 15, 2021 IEEE International Conference on Digital Health 2021

selected publications

  1. COMPSAC
    A Transfer Learning Approach to Surface Detection for Accessible Routing for Wheelchair Users
    Mokrenko, Valeria, Yu, Haoxiang, Raychoudhury, Vaskar, Edinger, Janick, Smith, Roger O, and Gani, Md Osman
    In 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC) 2021
  2. BuildSys
    Smart Surface Classification for Accessible Routing through Built Environment: A Crowd-Sourced Approach
    Gani, Md Osman, Raychoudhury, Vaskar, Edinger, Janick, Mokrenko, Valeria, Cao, Zheng, and Zhang, Ce
    In Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation 2019