Equitable pedestrian wayfinding is crucial for a barrier-free city, where people with different abilities can independently access customized, relevant, and up-to-date routing information. Pedestrians present heterogeneous information requirements consisting of static and transient information ranging from elevation changes to curb ramps to transient sidewalk surface conditions. However, such data, including the location of sidewalks, are generally unavailable in a user-consumable format. Moreover, existing routing solutions primarily optimize for distance, offering inappropriate routes, for instance with steep inclines that are unusable by many manual wheelchair users. A data model for equitable pedestrian wayfinding must flexibly support an annotated pedestrian network: a connected graph model that can be visualized and populated with data to parametrize a personalizable cost function. With adequate data, we are able to model navigation behavior and wayfinding among people with disabilities, and build generalized models for non-motorized behavior in pedestrian travel networks. To address these challenges, the Taskar Center engages with and co-designs solutions with accessibility advocacy groups, data scientists, and academics. I present a set of capabilities we have developed under the OpenSidewalks and AccessMap projects that enable ability-based pedestrian routing and improved infrastructure investment planning.
Anat Caspi is Director of the Taskar Center for Accessible Technology whose mission is to translate, develop and deploy technology that improves quality of life for individuals with diverse mobility and speech abilities. The research presented here focuses on improving mobility options and access to commuting options for individuals of all abilities. Caspi coordinates several accessible technology projects at the Paul G. Allen School along with collaborations with other departments at the University of Washington. Caspi’s research interests are in the areas of ubiquitous sensing and computing, and applications of machine learning in modeling everyday decision-making processes. Caspi is particularly interested in ways in which collaborative commons and community cooperation can challenge and transform the current economics of assistive technology and incentivize rapid development and deployment of equitably- and universally designed technology.