ABSTRACT: Sidewalks form the fabric of urban life, connecting nearly every kind of travel and mode of transportation. As individual travelers, we present varied information requirements about the pedestrian environment consisting of static and transient attributes of the sidewalks ranging from elevation changes to curb ramps to transient surface conditions. Surprisingly, such data, and even the location of sidewalks, are generally unavailable in a user-consumable format.
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 along pedestrian paths. However, existing routing solutions are rarely aware of sidewalks as data entities and 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 represents sidewalk segments and the way they connect and that can be visualized and populated with data to parameterize a personal 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 for Accessible Technology at the Paul G. Allen School engages with and co-designs solutions with accessibility advocacy groups, data scientists, and academics. Anat Caspi will present a set of tools and applications we have developed under the OpenSidewalks and AccessMap projects that enable custom pedestrian routing and improved infrastructure investment in urban planning.
About the speaker:
Dr. Anat Caspi is Director of the Taskar Center for Accessible Technology (TCAT) whose mission is to develop, translate, and deploy technology that improves quality of life for individuals with diverse mobility and speech abilities. The TCAT projects presented here focus on improving mobility options and access to commuting options for individuals of all abilities. Caspi directs 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 Data Science for Social Good. 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 inclusively designed technology. Caspi is currently helping to evolve and scale the inclusive design curriculum at the Paul G. Allen School of Computer Science & Engineering. Caspi received a B.S. with Honors and M.S. in Computer Science from Stanford University; she received a Ph.D. in Bioengineering from the joint graduate group in BioE at the University of California at Berkeley and San Francisco. Caspi is the 2017 recipient of Northwest Access Fund Innovation Award, recognizing her contribution and development of products that have improved the quality of life for individuals with a disability in the Pacific Northwest region.
