The prevalence of developmental disabilities has increased significantly in the United States with one in six children ages three (3) to 17 now diagnosed. A common behavior among children with developmental disabilities is wandering---the act of leaving an area without supervision or permission. The impetus for wandering ranges from a benign desire to explore to an attempt tom escape uncomfortable sensory stimuli. Wandering often continues into adulthood, representing a serious health, economic and resource issue. Wandering behavior places affected individuals at elevated risk for psychological harm, injury or death. Current approaches to address wandering include physical barriers, such as gates or locks, alarm systems, and GPS/electronic surveillance systems. These approaches are limited in their efficacy and often infringe upon an individual's autonomy, privacy, and quality of life. This planning project aims to develop SafeGuard, a suite of non-invasive technologies that is founded on technical and social-science innovation to detect, mitigate, and de-escalate wandering events. SafeGuard will be designed as a system-of-systems that can be integrated with low-cost sensors and hardware into existing residential and commercial infrastructure. SafeGuard will also include predictive intelligence to identify individuals at a greater flight risk and the ways they might demonstrate their intent to wander. Several agencies working with individuals with developmental disabilities and their families, disability agency staff and first-responders comprise the planning effort to lay the foundation for a large-scale system to reduce wandering among children and adults with developmental disabilities.

The objectives of SafeGuard will be realized via the exploration of four distinct research questions: (1) How can the quality of life be improved for individuals with developmental disabilities who are predisposed to wander, as well as for their family members and caregivers? (2) Can sensor-based technologies be developed to detect wandering? (3) Can SafeGuard identify intent to wander through multimodal data streams? And, (4) Can SafeGuard de-escalate a wandering incident before and during its occurrence? The team will actively engage the numerous and varied stakeholders in meaningful dialogue and collaboration via an advisory group, focus groups, surveys and a pilot study. The team bridges the social sciences, engineering, and computer science from academia with individuals with developmental disabilities and the communities that serve them. SafeGuard will leverage new opportunities at the nexus of intelligent sensing, data analytics, and digital intervention to mitigate wandering and improve quality-of-life.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.