The concept of "aging in place", using advanced technology to improve the health and well-being of older adults at home, has become popular as away to reduce costs and allow older adults the dignity of living their final years in the community. This project will use an integrated autonomous system that consists of a mobile robot and smart insole sensors to assist older adults to independently live in their own homes and interact with their communities. The system will have two initial goals: supporting exercise and enhancing social connections. The target exercise is walking, the most preferred and accessible exercise modality among older adults. Regular walking exercises may result in enhanced balance, increased muscle strength, and reduced risk of falling. The system guides individuals in regular walking exercises, autonomously assesses gait states, and provides real-time personalized feedback to engage older adults into the exercise. The robot will also be used to connect older adults with family and friends through a virtual connection. The project team will evaluate the system at a senior center in New York City using objective and subjective performance criteria measuring older adults' experiences with the system. This project serves the national interest because the integrated social assistive robot and wearable sensor system enhances mobility and social connectedness of older adults thus should improve their health and well-being. The project will involve an educational component that provides engineering and research method training to graduate and undergraduate students, as well as STEM outreach to middle and high-school students. Additional efforts will be made to attract and retain women and underrepresented minorities into careers in science and engineering.
This research investigates human-robot-sensor interaction, and aims to enhance mobility and social connectedness of older adults through the use of an assistive service robot. Methods to be developed include autonomous gait analysis combining sensing capability of robot onboard image sensors and the smart insoles through parametric and learning-based calibration models. The use of inverse reinforcement learning to explore cost function representation for robot motion planning. The use of dynamic recurrent neural networks and vibrotactile rhythmic stimuli for collaborative human-robot walking tasks. The project also examines the use of autonomous task scheduling to increase social contacts through telepresence robotic techniques. Finally, the implementation and experimental testing of the integrated system will be conducted in a senior center using objective and subjective performance criteria. The project fills a gap in aging-in-place research by providing an integrated robot and wearable sensor solution for enhancement of mobility and social connectedness. The developed methods will be implemented on open-source platforms, and the experimental and evaluation data will be made available for public use.
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.
