Sorry, you need to enable JavaScript to visit this website.

SENSOR

Saving Energy Nationwide in Structures with Occupancy Recognition

The projects of ARPA-E's SENSOR (Saving Energy Nationwide in Structures with Occupancy Recognition) program will develop user-transparent sensor systems that accurately quantify human presence to dramatically reduce energy use in commercial and residential buildings. SENSOR projects will focus on one or more of four areas: 1) human occupancy sensors for residential use, 2) occupant-counting sensors for commercial buildings, 3) CO2 sensors to enable the use of variable building ventilation based on data from occupant-counting sensors, and 4) real-world testing and energy savings validation of these technologies. Projects in the SENSOR program seek to reduce energy used by heating, ventilation, and air conditioning (HVAC) systems by 30% in both residential and commercial buildings, potentially producing savings of 2-4 quadrillion BTU (quads) across the U.S. power system. SENSOR projects will develop sensing technologies that minimize or eliminate the need for human intervention while pursuing aggressive cost, performance, privacy, and usability requirements in order to gain the acceptance and penetration levels needed to achieve this 30% reduction in HVAC energy consumption.

Boston University

Scalable, Dual-Mode Occupancy Sensing for Commercial Venues

Boston University (BU) will develop an occupancy sensing system to estimate the number of people in commercial spaces and monitor how this number changes over time. Their Computational Occupancy Sensing SYstem (COSSY) will be designed to deliver robust performance by combining data from off-the-shelf sensors and cameras. Data streams will be interpreted by advanced detection algorithms to provide an occupancy estimate. All processing will be performed locally to mitigate security concerns. The system will be designed to accommodate various room sizes and geometries. Occupancy data will be sent to the building control system to manage the heating, cooling, and air flow in order to maximize building energy efficiency and provide optimal human comfort. Energy costs of heating and cooling can be reduced by up to 30% by training the building management system to deliver the right temperature air when and where it is needed. The system's use of components readily available in the market today promises low cost and fast commercialization.

Cornell University

Indoor Occupant Counting Based on RF Backscattering

Cornell University will develop an occupant monitoring system to enable more efficient control of HVAC systems in commercial buildings. The system is based on a combination of "active" radio frequency identification (RFID) readers and "passive" tags. Instead of requiring occupants to wear tags, the tags, as coordinated landmarks, will be distributed around a commercial area to enable an accurate occupancy count. When occupants, stationary or moving, are present among the RFID reader and multiple tags, their interference on the backscattering paths can be exploited to gain insights on the room population. The distributed tags will operate without the need for a power source. The system will employ efficient biomechanical models and inverse imaging algorithms to estimate the size, posture, and motion of the collected geometry and distinguish people from furniture and pets. Occupancy data is then sent to the building control system to manage the heating, cooling and air flow in order to maximize building energy efficiency while providing optimal human comfort.

Duke University

Detecting Human Presence Using Dynamic Metasurface Antennas

Duke University will develop a residential sensor system that uses a dynamic meta-surface radar antenna design to determine occupancy in residential buildings. Traditional line-of-sight movement sensors suffer from high error rates. To increase accuracy, the Duke team will develop a sensor that monitors electromagnetic waveforms that are scattered both directly and indirectly off a person, eliminating the need for a direct line-of-sight between the sensor and the person. The sensor hardware continuously generates distinct microwave patterns to probe all corners of the house. Once a person enters a room, their motion changes the scattering statistics of the environment, which is used to establish real-time room occupancy. These characteristics are then analyzed using machine-learning techniques to establish human presence. The radar antenna can quickly sample an area and this information can be used to distinguish humans with the sensitivity to detect even stationary human's micro movements such as breathing. Further, the system operates at microwave frequencies, ensuring minimal concern for human safety. The proposed sensor does not require an internet connection or communication links, ensuring minimal security and privacy concerns. If successful, the system promises detection of occupants and near-zero false negative rate without any complex user interactions.

Endeveo, Inc

Hotspot Enabled Accurate Determination of Common Area Occupancy Using Network Tools (HEADCOUNT)

Endeveo will develop an occupancy sensor system to accurately determine the presence of occupants in residential buildings and enable temperature setbacks to provide energy savings of 30% per year. Their technique uses standard Wi-Fi-equipped devices, such as routers, to monitor an environment using the wireless channel state information (CSI) collected by these devices and occupancy-centric machine learning algorithms to determine occupancy from changes in CSI. The developed algorithms will distinguish between humans and pets, sense presence even when occupants are stationary for extended periods of time, and possess the flexibility to adapt to activities of daily living such as furniture being moved or opening doors. While their sensor hardware components use so-called "Wi-Fi protocols" to wirelessly probe an environment, they do not require nor utilize any internet access, Wi-Fi or otherwise. If successful, the system could offer cost-effective occupancy sensing to homes with and without internet service or broadband access.

Iowa State University

Simulation, Challenge Testing & Validation of Occupancy Recognition & CO2 Technologies

Iowa State University (ISU) will develop a comprehensive testing protocol and simulation tools to evaluate the energy savings and reliability of occupancy recognition sensor technologies for commercial and residential buildings. A barrier to wide adoption of new occupancy sensors is the lack of rigorous and widely accepted methodologies for evaluating the energy savings and reliability of occupancy recognition of these systems. To address this need, ISU's protocols will allow them to determine occupancy recognition, sensor effectiveness, and reliability in both laboratory and real-world conditions for residential and commercial applications. Using their protocol and simulation tools, sensor technologies will be tested, including occupancy presence technologies for residential buildings, occupant counting solutions for commercial buildings, and CO2 sensing technologies for commercial buildings. For commercial buildings, the office, and academic submarkets will be the focus of these efforts, two of the highest energy-consuming building sectors. For residential buildings, a diversity of building types and interior layouts located in Ames, Iowa will be used to conduct real-world field testing. Results from the proposed work will be used to develop the framework for two nationwide test standards.

Matrix Sensors, Inc

Stable, Low Cost, Low Power, CO2 Sensor for Demand-controlled Ventilation

Matrix Sensors and its partners will develop a low-cost CO2 sensor module that can be used to enable better control of ventilation in commercial buildings. Matrix Sensor's module uses a solid-state architecture that leverages scalable semiconductor manufacturing processes. Key to this architecture is a suitable sensor material that can selectively adsorb CO2, release the molecule when the concentration decreases, and complete this process quickly to enable real-time sensing. The team's design will use a new class of porous materials known as metal-organic frameworks (MOFs). MOFs possess high gas uptake properties, molecule selectivity and high stability. As the MOF adsorbs and desorbs CO2, a connected transducer detects the change in mass. Beyond developing the MOF, key goals for the team include developing capable transducers for the MOF gas sensor, as well as the development of wireless sensor module which will be self-contained including the sensor element, micro-processor, battery, and wireless interface. The sensor will be wall-mounted and easily installed since it will not require wired power. If successful, the project will result in a CO2 sensor system with a total cost of ownership that is 5 to 10x lower than today's systems.

N5 Sensors, Inc

Digital System-on-chip CO2 Sensor

N5 Sensors and its partners will develop and test a novel semiconductor-based CO2 sensor technology that can be placed on a single microchip. CO2 concentration data can help enable the use of variable speed ventilation fans in commercial buildings. CO2 sensing may also improve the comfort and productivity of people in commercial buildings, including academic spaces. N5 Sensor's solution will determine CO2 concentrations through absorption of CO2 when the concentrations are high in the environment, and desorption of CO2 when the concentrations are low. The team's project combines innovations in a number of areas: ultra-low power sensing architecture, semiconductor microfabrication, effective gas separation membranes, novel signal processing, and machine learning. If successful, the project can result in a 10x reduction in the price of CO2 sensors and the innovation will ultimately result in a low-cost, highly autonomous systems with "peel, stick and press button" type of installation and operation.

Purdue University

Building- Integrated Microscale Sensors for CO2 Level Monitoring

Purdue University will develop a new class of small-scale sensing systems that use mass and electrochemical sensors to detect the presence of CO2. CO2 concentration is a data point that can help enable the use of variable speed ventilation fans in commercial buildings, thus saving a significant amount of energy. There is also a pressing need for enhanced CO2 sensing to improve the comfort and productivity of people in commercial buildings, including academic spaces. The research team will develop a sensing system that leverages on-chip integrated organic field effect transistors (FET) and resonant mass sensors. Field effect transistors are chemical sensors that can transform chemical energy into electrical energy. The unique design allows the system to measure two distinct quantities as it absorbs CO2 from the environment - electrical impedance using the FET and added mass using the resonant mass sensors. The design will use low-cost circuit boards and off-the-shelf devices like commercial solar panels and batteries to reduce the cost of the system and enable easy deployment. By combining two unique sensing technologies into a single package, the team hopes to implement a solution for monitoring CO2 levels that could yield a nearly 30% reduction in building energy use.

Rensselaer Polytechnic Institute

Reflected Light Field Sensing for Precision Occupancy and Location Detection

Rensselaer Polytechnic Institute (RPI) will develop a method for counting occupants in a commercial space using time-of-flight (TOF) sensors, which measure the distance from objects using the speed of light to create a 3D map of human positions. This TOF system could be installed in the ceiling or built into lighting fixtures for easy deployment. Several sensors distributed across a space will enable precise mapping, while preserving privacy by using low-resolution images. The technology is being designed around low power infrared LEDs and a patented plenoptic detector technology together with TOF information, which can enable unique combinations of spatial resolution, field of view and privacy. The sensor network will maintain an accurate count of the number of people in the space, and uses a simple program to track people who may be temporarily lost between sensor "blind spots", thus reducing the number of sensors needed. Occupancy data is then sent to the building control system to manage the heating, cooling and air flow in order to maximize building energy efficiency and provide optimal human comfort. Energy costs of heating and cooling can be reduced by up to 30% by training the building management system to deliver the right temperature air when and where it is needed.

Scanalytics

Floor Sensors for Occupancy Counting in Commercial Buildings

Scanalytics will develop pressure-sensitive flooring underlayers capable of sensing large areas of commercial buildings with a high-resolution and fast response time. This technology will enable the precise counting of people in commercial environments like stores, offices, and convention centers. The floor sensors will consist of a material which changes electrical resistance when compressed. Conductive elements above and below the material will measure the resistance at a grid of points within the floor mat, and electronics will control the switching between sensors, cache the results for transmission, and transmit the readings to a local gateway for analysis. The team's system and data processing algorithms will be developed to resolve multiple people in close proximity, as well as account for non-typical travel methods such as wheelchairs and crutches. This occupancy information may be passed directly to HVAC control, or combined with occupancy information from other sensors to manage the heating, cooling and air flow in order to maximize building energy efficiency and provide optimal human comfort. Energy costs of heating and cooling can be reduced by up to 30% by training the building management system to deliver the right temperature air when and where it is needed.

Syracuse University

Microcam: A Low Power Privacy Preserving Multi-modal Platform for Occupancy Detection and Counting

Syracuse University will develop a sensor unit to detect occupancy in residential homes called MicroCam. The MicroCam system will be equipped with a very low-resolution camera sensor, a low-resolution infrared array sensor, a microphone, and a low-power embedded processor. These tools allow the system to measure shape/texture from static images, motion from video, and audio changes from the microphone input. The combination of these modalities can reduce error, since any one modality in isolation may be prone to missed detections or high false alarm rates. Advanced algorithms will translate these multiple data streams into actionable adjustments to home heating and cooling. The algorithms will be implemented locally on the sensor unit for a stand-alone solution not reliant on external computation units or cloud computing. The MicroCam system itself will be wireless and battery-powered (operating for at least 4.5 years on 3 AA or 2 C batteries), and will be designed to be easily installed and self-commissioned.

Texas A&M University

SLEEPIR - Synchronized Low-energy Electronically-chopped PIR Sensor for Occupancy Detection

Texas A&M University will develop an advanced, low-cost occupancy detection solution for residential homes. Their system, called SLEEPIR, is based on pyroelectric infrared sensors (PIR) a popular choice for occupancy detection and activity tracking due to their low cost, low energy consumption, large detection range, and wide field of view. However, traditional PIR sensors can only detect individuals in motion. The team proposes a next-generation PIR sensor that is able to detect non-moving heat sources and provide quantitative information on movement. Their innovation relies on the use of an "optical chopper" which temporarily interrupts the flow of heat to the sensor and allows the device to detect both stationary and moving individuals. The team will evaluate several approaches for the chopper, such as new low-power liquid crystal technology with no moving parts. They will apply new signal processing techniques and machine learning to the infrared data, enabling differentiation between pets and people and potentially sleep vs. active states. A central hub accepts wireless data from the sensors and overrides the home thermostat as needed to adjust temperatures and provide up to 30% energy savings to the home.

United Technologies Research Center

PEOPLE: Platform to Estimate Occupancy and Presence for Low Energy Buildings

United Technologies Research Center (UTRC) will develop a low-cost occupancy solution that combines radar sensing technology with an infrared focal plane array (IR-FPA) to determine occupancy in buildings. The solution will also be deployed as a radar-only residential sensor for true human presence sensing. The radar will detect respiration or heartbeat of non-moving occupants by measuring the radar signal reflections caused by chest movement. The system's machine learning algorithms will allow it to distinguish humans from pets in residential settings and to reduce under-counting errors in commercial deployments. The radar will enable through-wall presence sensing in multiple rooms by a single sensor, reducing the sensor hardware and installation cost on a per square foot basis. The solution aims to address the high cost and failure rate of current presence sensors that are preventing large-scale adoption of occupancy based control of HVAC, lighting, and plug loads.

University of Alabama

Quantification of HVAC Energy Savings for Occupancy Sensing in Buildings Through an Innovative Testing Methodology

The University of Alabama and their partners will develop a new testing and validation protocol for advanced occupancy sensor technologies. A barrier to wide adoption of new occupancy sensors is the lack of rigorous and widely accepted methodologies for evaluating the energy savings and reliability of these systems. To address this need, the Alabama team will develop a testing protocol and simulation suite for these advanced sensors. The protocol and simulation suite will take into account eight levels of diversity: 1) occupant profile, 2) building type and floor plan, 3) sensor type, 4) HVAC controls and modes (e.g., temperature and/or ventilation setback), 5) functional testing diversity, 6) deployment diversity (e.g., sensor location), 7) software diversity (e.g., computation at local vs. hub), and 8) diagnostic diversity (e.g., interpret missing data). The regime's simulation tools will take advantage of data analytics with built-in machine learning algorithms to accurately determine energy savings. Technical results from the testing and validation work will support technology to market efforts, including codes and standards updates.

University of Colorado, Boulder

Battery-Free RFID Sensor Network with spatiotemporal Pattern Network Based Data Fusion System for Human Presence Sensing

The University of Colorado, Boulder (CU-Boulder) will develop an integrated occupancy detection system based on a radio-frequency identification (RFID) sensor network combined with privacy-preserving microphones and low-resolution cameras to detect human presence. The system may also analyze electrical noise on power lines throughout a residential home to infer occupancy in different areas. The system will draw its accuracy from the combination of data sources, uncovering human presence not only from physical image and audio sensor data, but also considering what electrical activity reveals about human activity. All of these data streams (image, audio, and electrical activity) will be combined in computationally efficient ways to enable high accuracy human presence detection. The low powered devices in this system will be wirelessly powered, allowing the system to be deployed in a home without costly and invasive rewiring.
Subscribe to SENSOR