Guo, X., He, T., Zhang, Z., Luo, A., Wang, F., Ng, E. J., Zhu, Y., Liu, H., & Lee, C. (2021). Artificial Intelligence-Enabled Caregiving Walking Stick Powered by Ultra-Low-Frequency Human Motion. ACS Nano, 15(12), 19054–19069. https://doi.org/10.1021/acsnano.1c04464
Abstract:
The increasing population of the elderly and motion-impaired people brings a huge challenge to our social system. However, the walking stick as their essential tool has rarely been investigated into its potential capabilities beyond basic physical support, such as activity monitoring, tracing, and accident alert. Here, we report a walking stick powered by ultra-low-frequency human motion and equipped with deep-learning-enabled advanced sensing features to provide a healthcare-monitoring platform for motion-impaired users. A linear-to-rotary structure is designed to achieve highly efficient energy harvesting from the linear motion of a walking stick with ultralow frequency. Besides, two kinds of self-powered triboelectric sensors are proposed and integrated to extract the motion features of the walking stick. Augmented sensing functionalities with high accuracies have been enabled by deep-learning-based data analysis, including identity recognition, disability evaluation, and motion status distinguishing. Furthermore, a self-sustainable Internet of Things (IoT) system with global positioning system tracing and environmental temperature and humidity amenity sensing functions is obtained. Combined with the aforementioned functionalities, this walking stick is demonstrated in various usage scenarios as a caregiver for real-time well-being status and activity monitoring. The caregiving walking stick shows the potential of being an intelligent aid for motion-impaired users to help them live life with adequate autonomy and safety.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - RIE Advanced Manufacturing and Engineering (AME) programmatic grant - Nanosystems at the Edge
Grant Reference no. : A18A4b0055
This work was supported by the research grant of National Key Research and Development Program of China, China (Grant No. 2019YFB2004800, Project No. R-2020-S-002) at NUSRI, Suzhou, China;
Singapore; Guangdong Natural Science Funds (2018A050506001); and Shenzhen Science and Technology Innovation Committee (JCYJ20200109105838951)