Smartphone-based system to improve transportation access for the cognitively impaired.

This project developed and evaluated a smartphone-based system to improve mobility and transportation access for the cognitively impaired. The proposed system is intended to allow the cognitively impaired to use public transportation systems, community transportation and dedicated transportation services for the disabled with greater ease and safety. Individuals with cognitive disabilities are often unable to operate an automobile, or may require a prolonged recovery period before resuming driving. Public transportation systems represent a significant means to allow these individuals to maintain independence. Yet public transportation systems can pose significant challenges to individuals with cognitive impairment. The goal of this project is to develop a system to reduce these barriers via a technological solution consisting of components developed both for the cognitively impaired user and their caregiver or family member. The first component consists of a cognitive prosthetic device featuring traditional memory cueing and reminders as well as custom location-based transportation specific functions. This cognitive mobility assistant will leverage the computing power and GPS location determination capabilities of inexpensive, powerful smart phones. The second component consists of a management application which offers caregivers the ability to configure and program the reminder and transit functions remotely via the Internet. Following completion of the prototype system a pilot human test was performed with cognitively disabled individuals and family members or caregivers to assess the usability and acceptability of both system components.

Indoor inertial waypoint navigation for the blind.

Indoor navigation technology is needed to support seamless mobility for the visually impaired. This paper describes the construction and evaluation of an inertial dead reckoning navigation system that provides real-time auditory guidance along mapped routes. Inertial dead reckoning is a navigation technique coupling step counting together with heading estimation to compute changes in position at each step. The research described here outlines the development and evaluation of a novel navigation system that utilizes information from the mapped route to limit the problematic error accumulation inherent in traditional dead reckoning approaches. The prototype system consists of a wireless inertial sensor unit, placed at the users' hip, which streams readings to a smartphone processing a navigation algorithm. Pilot human trials were conducted assessing system efficacy by studying route-following performance with blind and sighted subjects using the navigation system with real-time guidance, versus offline verbal directions.

Indoor magnetic navigation for the blind.

Indoor navigation technology is needed to support seamless mobility for the visually impaired. This paper describes the construction of and evaluation of a navigation system that infers the users' location using only magnetic sensing. It is well known that the environments within steel frame structures are subject to significant magnetic distortions. Many of these distortions are persistent and have sufficient strength and spatial characteristics to allow their use as the basis for a location technology. This paper describes the development and evaluation of a prototype magnetic navigation system consisting of a wireless magnetometer placed at the users' hip streaming magnetic readings to a smartphone processing location algorithms. Human trials were conducted to assess the efficacy of the system by studying route-following performance with blind and sighted subjects using the navigation system for real-time guidance.

Public transportation assistant for the cognitively impaired.

This project developed and evaluated the utility of a mobility assistant cognitive prosthetic that leverages the computing power and GPS location determination capabilities of smart phones to provide location-sensitive mobility assistance. New relatively inexpensive smart phones offer powerful computing and location sensing capabilities. A prototype cognitive prosthetic was developed to assist users in their use of transportation systems. User Interface design included remote caregiver programming features, and automated SMS status generation. Location specific memory cues are triggered by comparing current GPS coordinate location with expected route coordinates obtained from stored route databases based on the GTFS feeds from transit systems. Additional development focused on developing algorithms to identify potential user errors, such as wrong-bus. These reminders and instructions will allow cognitively disabled persons to utilize public transportation systems with greater confidence leading to greater mobility and independence.

Indoor waypoint navigation via magnetic anomalies.

A wide assortment of technologies have been proposed to construct indoor navigation services for the blind and vision impaired. Proximity-based systems and multilateration systems have been successfully demonstrated and employed. Despite the technical success of these technologies, broad adoption has been limited due to their significant infrastructure and maintenance costs. An alternative approach utilizing the indoor magnetic signatures inherent to steel-frame buildings solves the infrastructure cost problem; in effect the existing building is the location system infrastructure. Although magnetic indoor navigation does not require the installation of dedicated hardware, the dedication of resources to produce precise survey maps of magnetic anomalies represents a further barrier to adoption. In the present work an alternative leader-follower form of waypoint-navigation system has been developed that works without surveyed magnetic maps of a site. Instead the wayfarer's magnetometer readings are compared to a pre-recorded magnetic "leader" trace containing magnetic data collected along a route and annotated with waypoint information. The goal of the navigation system is to correlate the follower's magnetometer data with the leader's to trigger audio cues at precise points along the route, thus providing location-based guidance to the user. The system should also provide early indications of off-route conditions. As part of the research effort a smartphone based application was created to record and annotate leader traces with audio and numeric data at waypoints of interest, and algorithms were developed to determine (1) when the follower reaches a waypoint and (2) when the follower goes off-route. A navigation system utilizing this technology would enable a low-cost indoor navigation system capable of replaying audio annotations at precise locations along pre-recorded routes.