The goal of Project ACCESS (Assisted Cognition in Community, Employment and Support Settings) was to create novel technologies that would enhance the quality of life of people with cognitive disabilities and their caregivers. In our 5 years of funding (2004-2009), we focused on the development of devices for providing assistance in route finding and community mobility. Technology for wayfinding has the potential to significantly improve the quality of life of many individuals with cognitive impairments who must currently rely on caregivers or cumbersome systems of accessible transit.
Because the user interface of such technologies is as crucial as the underlying implementation and localization technology, our work has focused on both. We built a system using the Wizard-of-Oz technique that let us experiment with many guidance strategies and interface modalities. Through user studies, we evaluated various configurations of the user interface for accuracy of route completion, time to completion, and user preferences.
Based on our findings from our studies, we have developed a framework for automatically generating directions. By using a Markov decision process (MDP) as the model for choosing appropriate directions, we can customize directions to accommodate individual health conditions, direction preferences, place familiarity, and wayfinding error behavior. In addition, MDPs provide a way to continuously adapt to the user, so that customizations can be adjusted over time.
Although project funding has ended, we continue to work on the development of these technologies and to seek funding to move devices forward to commercialization.