CAREER: Toward Embedding Perpetual Intelligence into Ultra-Low-Power Sensing and Inference Systems

Years of technological advancements have made it possible for small, portable, electronic devices of today to last for years on battery power, and last forever - when powered by harvesting energy from their surrounding environment. Unfortunately, the prolonged life of these ultra-low-power systems poses a fundamentally new problem. While the devices last for years, programs that run on them become obsolete when the nature of sensory input or the operating conditions change. The effect of continued execution of such an obsolete program can be catastrophic. For example, if a cardiac pacemaker fails to recognize an impending cardiac arrest because the patient has aged or their physiology has changed, these devices will cause more harm than any good. Hence, being able to react, adapt, and evolve is necessary for these systems to guarantee their accuracy and response time.

This project is aimed at devising algorithms, tools, systems, and applications that will enable ultra-low-power, sensor-enabled, computing devices capable of executing complex machine learning algorithms while being powered solely by harvesting energy. Unlike common practices where a fixed classifier runs on a device, this project takes a fundamentally different approach where a classifier is constructed in a manner that it can adapt and evolve as the sensory input to the system, or the application-specific requirements, such as the time, energy, and memory constraints of the system, change during the extended lifetime of the system. To demonstrate the efficacy of the proposed systems, several application-specific, battery-less systems will be developed and deployed, which includes – (1) a personalized air quality index predictor for asthmatic individuals, (2) an ultra-low-power voice assistant that gives voice to everyday objects, and (3) a real-time tracker for shared resources.

This research will enable smarter and more intelligent microbots and autonomous systems that will help improve healthcare, agriculture, manufacturing, and the environment. Outcomes of this research bear the potential to transform healthcare through the development of batteryless medical implants and wearable devices that will be able to monitor and learn person-specific physiologic parameters and thus be able to detect anomalies at their onset, which could be the cause of developing the disease. A direct impact of this research is the development of a low-cost, portable, real-time air quality monitor that will transform asthma and chronic obstructive pulmonary disease (COPD) management. Hardware and software tools will be open-sourced. Summer research opportunities will be opened up to high school students and undergrads. An Internet of Things-focused curriculum of interdisciplinary courses will be offered to broaden the participation of students from the health informatics program. Participation of women and members of underrepresented groups will be ensured. Outreach activities in collaboration with local makerspaces, a science center, and a high school will be performed to provide research exposure and to increase awareness of energy harvesting.

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.