Researchers Work On Ambient Free Energy For 'Internet Of Things'
Will "Internet of Things" Demand Perpetual Power?
By Intel Free Press
In the future, computers will sense what we are doing, where we are going and the very context of lives. However, the promise of the so-called Internet of Things won't become reality without a new generation of pervasive computing systems that use "perpetual power" to keep running indefinitely.
Dieter Fox, University of Washington associate professor of computer science and engineering, and other researchers are now working to develop "perpetual power" techniques that harvest energy from ambient sources and could allow computer and sensor systems to run ad infinitum.
A former director of the Intel Research Lab Seattle, Fox is part of the core research team for the Intel Science and Technology Center for Pervasive Computing. The center's research focus is developing the fundamental technologies needed to power the next generation of pervasive computing systems. Also referred to as ubiquitous computing, pervasive computing is a post-desktop model of computer interaction that integrates information processing into everyday objects and activities, making the Internet of Things possible.
The science and technology center launched in 2011 and brings together researchers from top-tier research universities. The University of Washington is the hub, coordinating research among the five other universities involved in the collaboration: the Georgia Institute of Technology, Cornell University, the University of Rochester, UCLA and Stanford University.
Fox recently discussed the research work at the center and the challenges in enabling systems that are trustworthy, always aware and continuously learning and adapting.
How close are we to the Internet of Things becoming an everyday reality?
For the past 20 years, the pervasive computing community has developed technology that allows sensing, computing and wireless communication to be embedded in everyday objects, from cell phones to running shoes, enabling a range of context-aware applications. While these apps are useful, the time has come to develop the next generation of pervasive computing systems. These future systems will support applications that have much deeper awareness of users and their activities, context and goals. They will be able to learn and adapt continuously to user's habits, routines, and preferences. These future apps will be capable of supporting complex tasks, such as cooking a soufflé or building a complicated piece of furniture. In the process, they will deliver far richer user experiences than the technologies of today can offer.
How important is low-power to the Internet of Things?
Pervasive computing systems must be continuously aware of the environment, the people nearby and the activities in which they're engaged. Because of the need for such systems to be "always on," saving power whenever possible is crucial. The researchers are developing "perpetual power" techniques that harvest energy from ambient sources and allow simple sensing and computing systems to run indefinitely. For larger devices, they are exploring how to dynamically use the most energy-efficient 802.11 and cellular modes available in the current locale, based on RF conditions and competing network traffic. Because pervasive computing systems perform continuous sensing and inference about people, within their homes and on the go, developing privacy and trust is paramount. With that in mind, the researchers are investigating how applications, sensors and data coding techniques can be modified to improve privacy. We're also investigating new sensing modalities, both for mobile devices and embedding in the environment that can be used to infer the state of people and their surroundings.
Declining costs have made it possible to deploy sensors on a much broader scale than ever before. What will the data from those sensors make possible?
Next-generation pervasive systems require fine-grained recognition of activities, objects and social context. To achieve this, researchers are deploying dense, heterogeneous sensors in mobile environments and smart spaces, including audio and depth video sensors (via cameras that measure 3-D shapes) as well as classic pervasive computing sensors such as GPS, accelerometers and 802.11, cellular and RFID wireless signals. Research focuses largely on developing new algorithms to extract complex context and activity information from sensor data far more accurately and robustly than the current state of the art. The algorithms might determine not just that someone's in the kitchen but that the person is slicing an onion, and that the slices are too thick for the recipe being used. To be the most useful, pervasive computing systems must be able to assess the user's context in real-time, a challenge for systems that must operate on low power. To address the challenge, researchers are exploring how to divide the computational work involved, like executing algorithms, between mobile devices and the cloud.
With the Internet of Things, smart devices will be constantly gathering data about us. Will we reach a point where computers "know us" and even make some decisions on our behalf?
Successful pervasive computing systems must be able to learn interactively the environments, objects, schedules and preferences of their users. It should be easy for a user to teach a device to recognize activities such as a regular jogging routine, places such as a favorite grocery store or objects such as the user's car. The research in this area focuses on developing probabilistic techniques for handling the complex estimation and learning problems required for lifelong learning, adaptation and personalization of systems for individual users.
Probabilistic graphical models that describe users and their context will continuously adapt, allowing the incorporation of new places, activities, personal objects and social contexts over time. In addition to personalizing what systems know, the researchers are building systems that personalize how they interact with users. Their goal is to enable interactions between users and systems that seamlessly blend multiple modalities -- gestures and natural language, for instance -- enabling users to focus on their goals rather than making the technology work.