Michael Buettner

Recognizing daily activities with RFID-based sensors

We explore a dense sensing approach that uses RFID sensor network technology to recognize human activities. In our setting, everyday objects are instrumented with UHF RFID tags called WISPs that are equipped with accelerometers. RFID readers detect when the objects are used by examining this sensor data, and daily activities are then inferred from the traces of object use via a Hidden Markov Model. In a study of 10 participants performing 14 activities in a model apartment, our approach yielded recognition rates with precision and recall both in the 90% range. This compares well to recognition with a more intrusive short-range RFID bracelet that detects objects in the proximity of the user; this approach saw roughly 95% precision and 60% recall in the same study. We conclude that RFID sensor networks are a promising approach for indoor activity monitoring.

An empirical study of UHF RFID performance

This paper examines the performance of EPC Class-1 Generation-2 UHF RFID reader systems in a realistic setting. Specifically, we identify factors that degrade overall performance and reliability with a focus on the physical layer, and we explore the degree to which reader configuration options can mitigate these factors. We use a custom software-radio based RFID monitoring system and configurable RFID readers to gather fine-grained data and assess the effects of the different factors. We find that physical layer considerations have a significant impact on reader performance, and that this is exacerbated by a lack of integration between the physical and MAC layers. We show that tuning physical layer operating parameters can increase the read rate for a set of tags by more than a third. Additionally, we show that tighter integration of the physical and MAC layers has the potential for even greater improvements.

A software radio-based UHF RFID reader for PHY/MAC experimentation

We present the design and evaluation of a flexible UHF RFID reader that enables new PHY/MAC designs to be prototyped and evaluated. Our reader is built using the USRP software radio platform in conjunction with software we developed in the open-source GNU Radio framework. We believe it is the first inexpensive tool that readily enables changes to the physical and MAC layer of RFID systems. We evaluate our reader and show that it can inventory commercial tags out to 6 meters, which approximates the range of a commercial reader with comparable transmit power. We then show two applications of our reader. The first evaluates the real-world performance of the EPC frame selection algorithm and finds that it performs better than expected. Second, using the Intel WISP programmable RFID tag, we implement and evaluate an extension to the Gen 2 standard that results in up to a five-fold increase in sample rate for streamed sensor data.

RFID: From Supply Chains to Sensor Nets

The next generation internet will be the internet of things (and not just of computing devices like PCs, PDAs); this is presumed to be enabled by integrating simple computing plus communications capabilities into common objects of everyday use. Radio-frequency identification (RFID) is a compelling technology for creation of such pervasive sensor networks due to its potential for ubiquitous, low-cost/low-maintenance use. However, the current drivers for RFID deployment emphasize supply chain management using passive tags, implying that RFID sensor nets require advances beyond the components and system designs aimed at supply chain applications. This work provides a glimpse of how this may be achieved.

RFID sensor networks with the Intel WISP

We demonstrate a simple RFID sensor network comprised of an Intel WISP and a commodity UHF RFID reader. WISPs are devices that gather their operating energy from RFID reader transmissions, in the manner of passive RFID tags, and further include sensors, e.g., accelerometers, and provide a very small-scale computing platform. We believe that the small form factor and lack of battery makes the WISP an attractive alternative to motes for many of the original smart dust applications that require very small or long-lived sensors. The Intel WISP that we demonstrate has an ultra-low-power microcontroller, 32K of program space, 8K of flash, and accelerometer and temperature sensors. It harvests power from and communicates sensor data to standard (EPC Class 1 Gen 2) UHF RFID readers with a range of roughly 10 feet. This combination of RFID technology and sensor networks raises many research challenges, such as how to function with intermittent power and how to modify RFID protocols to support sensor queries.

A "Gen 2" RFID monitor based on the USRP

We have developed a low cost software radio based platform for monitoring EPC Gen 2 RFID traffic. The Gen 2 standard allows for a range of PHY layer configurations and does not specify exactly how to compose protocol messages to inventory tags. This has made it difficult to know how well the standard works, and how it is implemented in practice. Our platform provides much needed visibility into Gen 2 systems by capturing reader transmissions using the USRP2 and decoding them in real-time using software we have developed and released to the public. In essence, our platform delivers much of the functionality of expensive (<

Implementing the Gen 2 MAC on the Intel-UW WISP

50,000) conformance testing products, with greater extensibility at a small fraction of the cost. In this paper, we present the design and implementation of the platform and evaluate its effectiveness, showing that it has better than 99% accuracy up to 3 meters. We then use the platform to study a commercial RFID reader, showing how the Gen 2 standard is realized, and indicate avenues for research at both the PHY and MAC layers.

WISP Monitoring and Debugging

We present the implementation and evaluation of the Gen 2 anti-collision protocol on the Intel-UW WISP. Because WISPs are wirelessly powered and highly energy constrained, appropriate MAC protocols are an open challenge. The previous approach to medium access on the WISP was to transmit data at every opportunity. This strategy consumes very little energy per data transmission, and works well when only one WISP is active at a time. However, when many tags are present and attempting to transmit simultaneously, their transmissions collide and no WISP can communicate with the reader. The Gen 2 RFID standard speci?es an anti-collision mechanism where tags randomize their transmissions across a number of slots, though this approach has been considered too energy intensive for use on the WISP. Through experimentation with a deployment of WISPs, we show that our Gen 2 MAC implementation allows all tags to communicate at a high rate, generally achieving better than 10 responses per second when close to a reader. This is in contrast to WISPs using the prior MAC approach where no tag can respond to the reader more than once per second in the same scenario. We additionally show that even for a single tag, the use of slotting does not degrade performance. This means that the full Gen 2 MAC is appropriate for use on the WISP, as it enables tags to communicate effectively in deployments consisting of one or many tags.

Development of Sensing and Computing Enhanced Passive RFID Tags Using the Wireless Identification and Sensing Platform

This chapter presents a tool for monitoring WISPs that provides detailed information about the state of program execution, the messages being received and transmitted, and the availability of energy. Traces collected with our tool can be used for debugging, understanding WISP behavior, and tracking how energy is gathered and consumed. Our tool consists of a monitor board and ?rmware we developed and relies on minor instrumentation of the WISP software. The monitor board attaches directly to the WISP, but does not interfere with the powering of the WISP. Even with a monitor board attached, the WISP operates solely on harvested energy from the RF environment. The board can monitor the WISP’s demodulator, modulator, unregulated voltage, supervisor and demodulator enable lines, as well as parse any state information sent explicitly by having the WISP toggle debug pins. Information collected by the board can be sent over a serial connection to a PC for analysis. The monitor board can measure energy at a resolution of 0.14 nJ and the overhead on tracking WISP behavior is only 18 CPU cycles per sample.

Revisiting Smart Dust with RFID Sensor Networks.

Passive RFID tags are becoming increasingly common in home and work environments. As RFID tags find new applications beyond shipment tracking, they are being embedded in objects throughout our environment. RFID tags are already being incorporated in credit cards for touch-free payments, in clothing for merchandise tracking, and in ID cards for building access control. All these “non-shipping” RFID tags are powered wirelessly and are capable of wireless communication and rudimentary computation. Thus they can be viewed as micro-computing platforms with wireless power and communication capabilities. While the functionality of today’s passive RFID tags is extremely limited, today’s tags can already be thought of as a layer of invisible computing that is seamlessly embedded in objects throughout the environment. This primitive layer of embedded intelligence could grow in sophistication if additional sensing and computation capabilities could be added to RFID tags. The authors’ goal is to evolve this layer of passively powered embedded intelligence by creating RFID tags that support sensors and can execute general purpose computer programs. This chapter reviews several years’ work on the development of our open, programmable passive RFID tag, the Wireless Identification and Sensing Platform (WISP). It also shows how to use the EPC Class 1 Generation 2 RFID protocol to implement advanced RFID sensing applications that go far beyond simple tag ID inventorying applications. Our first venture into sensor-enhanced RFID was the α-WISP shown in Figure 1 (Philipose et al., 2005). With this device, one bit of sensor data was encoded by using anti-parallel tilt switches to multiplex one of two RFID tag ICs to a single antenna. Thus, a reader could infer three states about a tagged item (tag right side up, upside down, or not present). This simple example of overloading the EPC ID to encode sensor data allowed inference of very coarse orientation information. However, the use of commercial RFID tag ICs restricted our ability to control the RFID communication channel and in turn our ability to configure WISPs for new applications.