Burcin Becerik-Gerber - US grants

The research objective of this award is to test the hypothesis that interactive, sensor monitoring and online control can significantly reduce the energy consumption of buildings (by 20 percent or more) while maintaining occupant comfort. Through simulations and experimentation, inputs from a wide range of modalities and platforms in a heterogeneous sensor system (including wired and wireless sensors; mobile and static sensors; automatic and human-input-based sensors) will be integrated and fused in order to measure and track indoor climate, energy usage, as well as occupant location, activities, and preferences with much higher accuracy and lower cost compared to homogeneous systems. The research will encompass mathematical and empirical analysis and evaluation of efficient online stochastic algorithms based on multi-armed bandit theory that take the integrated sensor measurements as input to learn over time how to automatically operate building controls, so as to minimize energy consumption while maintaining occupant comfort, and quantify the gains in energy consumption obtained in typical environments.

If successful, the research will establish a framework, where humans and building systems interact ubiquitously in real time through an integrated mobile sensor and control system for energy awareness and learning and energy efficiency in buildings. The results will be disseminated through and contribute to the civil and environmental engineering, electrical engineering and computer science curricula, multiple conference talks, and publications. A public outreach and energy education program is planned to raise public awareness on energy efficiency in buildings. Targeting K-12 classrooms, this program aims to attract minority students to the engineering profession in the greater Los Angeles area. An interactive game, focusing on teaching K-12 students how they can conserve energy in their daily life by modifying their behavior and habits will be prototyped and tested.

The NSF Sustainable Energy pathways (SEP) Program, under the umbrella of the NSF Science, Engineering and Education for Sustainability (SEES) initiative, will support the research program of Profs. Burcin Becerik-Gerber of the Department of Civil and Environmental Engineering, Wendy Wood of the Department of Psychology, David Gerber of the Department of Architecture, and Milind Tambe of the Department of Computer Science at the University of Southern California (USC). The multi-disciplinary team of investigators will develop an energy-aware, cyber-physical multi agent framework of buildings, humans, and intelligent software agents for sustainable energy management, taking a collective, energy literacy approach to influencing building occupants, operators, designers, and engineers. The investigators will first assess behavior and preferences of building occupants, evaluate building design/system specifications, and identify building operational policies. They will then build a multi-agent model to integrate these different systems. Building on fundamental research in agents' autonomy and teamwork, the multi-agent framework will facilitate negotiations between occupants and building devices. The agents will provide feedback to the occupants and control building devices to conserve energy. Based on this integrated model, feedback about occupant energy use to building designers will be provided to shape early-stage design decisions that have the longest lasting impact on building's lifecycle footprint. The central focus is designing a multi-component model of energy consumption in office buildings in order to identify and test the optimal points of change in energy systems. Specifically, the research predicts that energy use could be optimized and occupant comfort could be maximized in an integrated way by changing occupant behavior, design/system specifications, and building operators' policies via an agent-based system. The research will be validated in an office building, where occupants lack the individual financial incentives for energy consumption. The system will be tested both in professional and student designer studios to validate the impact of the model in energy aware design decisions. The research differentiates itself by treating occupant preferences and behavior not only as input data but also as controllable variables in a broader energy system; it then harnesses a complex multiagent system to control these variables for energy savings. It also extends energy literacy into the arena of design and engineering by providing human behavior input in early design stages, as well as into the arena of building operations by dynamically controlling buildings based on human behavior and preferences.

With respect to the increasing energy needs of our country and world, this research has far-reaching impact on environmental conservation, pollution, and the economy. The primary impact of this research is identifying the key factors that create significant energy savings for buildings, resulting in monetary savings and environmental protection. The results will be disseminated through and contribute to multiple conference talks and publications. A game, in which students will compete to save the most energy, will be developed with the aim of teaching how to conserve energy in daily life. Energy-focused workshop lessons will be developed and delivered to minority-majority K-12 schools in USC's neighborhood and other children and their families. In addition, the research team will partner in research with the computer science department of California State University, Dominguez Hills, a minority majority institution.

The proposed interdisciplinary research challenges the ways that building engineers and designers, computer scientists, and behavioral scientists look at the pressing challenges of energy-efficient buildings. The research will integrate design with outside data sources and bring behavioral science to design, which in turn will trigger a design-method evolution for sustainable buildings. Through dynamic data collection, spatiotemporal information about energy use, and data on human comfort, the research will improve system optimization and adaptation through the use of intelligent software agents. The project will educate building occupants about their energy consumption and the ways that they can make concrete behavioral changes to achieve greater energy efficiency. The research brings to the problem of energy literacy an interdisciplinary approach in which cyber tools are manifested in physical space.

The purpose of this Faculty Early Career Development (CAREER) Program grant is to advance knowledge about the impact of human-building interactions on energy use, and to explore intelligent, collaborative, and personalized approaches that connect built environments with their users to increase energy efficiency and awareness. Taxonomies of types, features, and patterns of human-building interactions will be developed, based on high-resolution building and human related data. The impact of human-building interactions on energy use and comfort will be quantitatively described using a simulation environment that incorporates multiple simulations and modeling technologies. The research will build on the concept of heterogeneous teamwork between building members and their users, through the use of computer agents that represent and interact with these building systems and their users. A model, capable of learning user preferences for automation, will be employed. A diverse set of communication strategies and styles will be evaluated through human subject experiments that address actions influencing energy and comfort, and increase the trust between humans and the built environment.

If successful, the research will advance the understanding about the impact of human-building interactions on energy, and transform built environments into attentive and self-learning entities that adapt to user preferences of energy conservation. User-related information will be incorporated into building operations thus allowing for proactive accommodation of user needs. Knowledge of human-building interactions will support engineering design and management activities, and foster the evolution of built environments as eco-systems. To increase public engagement, energy related workshops will be organized bringing together parents, teachers and K-12 students to build hands on engineering projects. High school female students will develop computer applications related to energy conservation, attracting them to engineering and technology fields. The work will engage underrepresented students and develop new materials, modules, courses, test beds for research and education.

Buildings consume a staggering 38 percent of our nation's total energy use. Existing automation approaches to address this problem focus either on buildings, allowing them to better sense and respond to the behavior of their occupants, or focus on occupants, seeking to educate them on making more efficient energy choices. In contrast, this EArly-concept Grant for Exploratory Research (EAGER) project considers ways to enhance the interaction between buildings and occupants. The research team hypothesizes that user-building interactions will be most effective when building users establish a relationship of trust with building automation. By developing mathematical models and theory that amplify user capabilities through relational features, users are empowered to improve individual performance as well as building performance, while also improving societal well-being. To do so, the work draws on theories from the behavioral sciences to mathematically model when and how a building should interact with a user and how these interactions should be framed. The results will change the way we perceive and experience today's built environments, leading what could become the creation of unprecedented built environments that are attentive and have an identity. The project will enhance infrastructure for research and education by making the models and data available via a free research license, incorporating research findings into the engineering curriculum, disseminating research findings via publications, and national and international presentations.

The modeling framework for user-virtual human agent interactions is the key contribution to smart engineered systems modeling and design and occurs at the intersection of engineering, the behavioral sciences and computational modeling. If successful, the mathematical framework will be used to design smart buildings that have two-way interactions with people. The research objectives contribute to the ultimate goal of enabling cyber-physical systems to interact and collaborate with humans. This project integrates experimental data into the mathematical models, testing the inclusion of relational elements embedded in the personification of a building. The models will predict which response is the most suitable for a building-user interaction. This model will also be informed and constrained by existing theoretical work on persuasion. The model will account for various contextual, temporal and personal factors as well as the changes in user response due to continuous interactions with the building. The multiple-step modeling methodology incorporates a combination of machine learning techniques, mathematical projections for the classification problem, and statistical models such as Markov model, and autoregressive moving average models. In particular, the contributions are twofold: (1) modeling user-building interactions using virtual human agents personifying buildings; and (2) performing fundamental research on how theories of human interpersonal trust and influence can inform the design of automation. The research will contribute to the fundamental understanding of human-machine teamwork, including elucidating theories of why and how people build connections with automated systems and advance our general understanding of how automation exhibiting relational features can facilitate behavior change in the population served by those systems.

The construction industry is one of the largest industries in the United States, employing millions of workers, however it is challenged by low productivity rates, worker shortages, and safety concerns. The industry has a tremendous opportunity to improve its productivity and safety with the recent advancements in technology. With the increased level of automation on construction sites, workers need to learn how to work with these new technologies and gain new knowledge and engineering skills. The goal of this project is to create and test a training program delivered through virtual reality (cyberlearning) to educate and re-educate workers for new work experiences that require collaboration with robots on construction sites. The project seeks to improve the teamwork among workers and robots on construction sites, focusing on more than one specific skill set and providing a comprehensive learning experience. The project is significant because it is a pioneering effort in providing learning opportunities to workers with varying levels of language proficiency and education, preparing them for work at the human-technology frontier. Fundamental questions addressed by the project include: 1) How does cyberlearning increase workers' knowledge, safety behavior and trust in automation compared to the traditional training methods? 2) How do individual differences impact workers' cyberlearning? 3) How does trust in automation change based on the construction task? 4) How does cyberlearning affect productivity and safety on construction sites? 5) Does the knowledge and level of trust gained through cyberlearning carry over to actual construction sites? 6) How does cyberlearning influence the development of next generation of construction automation? Through the exploration of these research questions, this project provides evidence for the utility of cost-effective training programs for vocational workforce of the construction industry.

Numerous learning scenarios and types of construction robots are included in the cyberlearning platform, which is developed in Task 1. A construction site is simulated via the use of discrete event simulations and immersive virtual environments where construction workers interact with robots on a given task. To move away from today's lab-based hands-on training, the cyberlearning environment incorporates dynamic construction work environments, such as multiple tasks and crews sharing the same space and conditions, for example, uneven terrain, dust, rain through simulations and by using accurate models of construction sites. The work advances knowledge on the impact of cyberlearning for worker-robot teamwork at two levels: user-level and site-level. For the user-level investigations in Task 2, the work explores: 1) the extent to which cyberlearning increases workers' knowledge, safety behavior, and trust in automation, 2) how individual differences moderate workers' learning and 3) how trust-in-automation changes based on task type. For the site-level investigations in Task 3, the work explores: 1) the extent to which cyberlearning impacts productivity, safety, and trust-in-automation compared to in-person training across all workers on construction sites, and 2) how to both improve the cyberlearning environment and the construction robots for deployment on construction sites. Finally, through simulation-based studies in Task 4, the work explores how human-robot interactions impact construction tasks and workflows, safety procedures and productivity. The cyberlearning program is designed to maximize the extent to which the workers accept and trust construction robots, while at the same time freeing up human resources, improving productivity and safety, both of which are important to both individual workers and society at large.

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.

This project studies how various factors such as building design, size and demographics of the crowd, and individual differences like one's familiarity with the building impact responses to active shooter incidents. Fundamental questions addressed by the project include: 1) How do building attributes designed to enhance security affect human behavior during active shooter incidents? 2) How do individual factors moderate occupant responses? and 3) How does the setting of the incident or familiarity with building affect occupants' situational awareness and occupant behavior? The project explores these objectives by conducting human subject experiments using Immersive Virtual Environments (IVEs). This scientific research contribution thus supports NSF's mission to promote the progress of science and to advance our national welfare. In this case, the benefits will be insights to improve preparedness and response to active shooter events, which will save lives and reduce panic, anger and confusion during these events. The project supports education and promotes diversity through outreach activities aimed at recruiting and retaining under-represented students in research.

The project models the built environment in virtual reality, simulating the behavior of both the adversaries and the crowd. By exposing participants to an active shooter incident using IVE, the researchers can measure their responses in realistic ways that are not possible outside the laboratory environment. Task 1 uses IVEs and agent-based simulations to create representative virtual built environments and realistic active shooter scenarios. There are three critical elements in the development of the IVEs: building attributes that enhance security, setting (school vs. office building), and virtual actors (crowd/adversary). Task 2 examines how various factors (building design attributes, individual factors, participant role, crowd setting, and familiarity with building layout) affect responses to active shooter incidents. Simulation scenarios will include security enhanced buildings versus standard buildings, and school versus office versions. The project outcomes can inform safer building designs and operations and train occupants and security personnel on how to respond to human-enabled catastrophic events, thus saving lives.

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.

This AccelNet Catalytic level project will facilitate collaborative research, education, and outreach through an International Network of Networks for Well-being In the Built Environment (IN2WIBE). At the core of IN2WIBE is a shared understanding that well-being is strongly dependent on the links between the built environment and the personal, cultural, economic, and social forces that drive health, productivity, satisfaction, and comfort. Research networks on well-being in the built environment exist, however, they are shaped by their institutional, regional, or social contexts and are mostly locally convergent. Well-being in the built environment is a broad research area, and there exist myriad approaches and solutions that emerge from different disciplinary perspectives. These efforts need to be integrated to foster effective, robust, and widely-applicable solutions. IN2WIBE will connect and educate future building scholars on well-being in buildings while informing better building design, construction, operation, and use. This will be achieved through leveraging resources from 34 existing networks and partners in 5 continents (N. America, Africa, Europe, Australia, and Asia), comprising a total of 17 countries. Through strategically designed activities, IN2WIBE will cultivate and foster connections through the development of community consensus.

IN2WIBE provides an opportunity to unite disciplinarily, culturally, and geographically diverse networks around the world. Four objectives of IN2WIBE are to: 1) facilitate new forms of collaborations by integrating disciplines and networks in building and health fields; 2) engage networks at multiple stages and scales, including networks in South Asia, North Africa, and the Middle East; 3) promote innovative human-centric building design and operation strategies that will benefit the larger community of scholars and practitioners; and 4) prepare next generation building professionals with a diverse background. Led by multidisciplinary teams, IN2WIBE will foster collaborative research opportunities by coordinating the networks through a series of focused, cross-disciplinary global activities, including roundtable discussions, scholarly retreats, industry showcases, hackathons, TEDx talks, design charrettes, and research workshops and conferences with focused themes. IN2WIBE is targeted to benefit users by improving productivity, cognition, convenience, comfort, health, and energy conservation. Ultimately, this network of networks will promote awareness of healthy, resilient, and sustainable environments. IN2WIBE outcomes will be disseminated via peer-reviewed publications and international talks. The IN2WIBE team, led by female PIs, will empower future researchers with knowledge in building engineering and science, information science, social science, and public health through an interdisciplinary educational program that includes a student exchange program and a career development roundtable. IN2WIBE will also leverage various outreach activities to facilitate minority student recruitment and retention and to engage existing K-12 education and community outreaching programs.

The Accelerating Research through International Network-to-Network Collaborations (AccelNet) program is designed to accelerate the process of scientific discovery and prepare the next generation of U.S. researchers for multiteam international collaborations. The AccelNet program supports strategic linkages among U.S. research networks and complementary networks abroad that will leverage research and educational resources to tackle grand scientific challenges that require significant coordinated international efforts. This project is co-funded by the Environmental Sustainability (ENG/CBET) program.

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.

Everyday interactions with our physical environment are increasingly becoming "smarter", as we live and work in smart homes, smart offices, or other smart infrastructure. We are also increasingly surrounded by smart furniture, smart appliances and smart building materials. This award will support an interdisciplinary workshop and related activities that will begin to shape the new field of Human-Building Interaction (HBI), which studies the dynamic physical interplay between embodied human and building intelligences. Related activities include an innovative, educational "hack-a-thon" event that will engage a diverse cohort of students in the development of prototype HBI systems. The project serves the national interest by promoting scientific progress related to dynamic human/machine interactions within the context of intelligent buildings and the smart objects that will populate them. The proposed HBI field promises to change the way people interact with and adopt smart building technology by informing the development of the next generation of cognitive buildings that will realize a myriad of benefits for human users, including improved productivity, cognition, convenience, comfort, health and energy use - all of which are essential to societal well-being.

This workshop will bring together engineers, architects, interaction designers, computer scientists, cognitive and social scientists from academic institutions and from industry to catalyze growth in the field of Human-Building Interaction (HBI). A goal of the workshop is to set the groundwork for developing working models of human behavior in built environments, models that can be incorporated into building intelligence systems to optimize human-building interactions. Another goal is to set a framework for how intelligent buildings might beneficially shape the future of work, by bridging gaps that currently divide current communities of researchers working on separate parts of the problem. Potential discussion themes include: Human-Building Collaboration; HBI and Trust; Design, Engineering and Operation of Cognitive Buildings; Virtual and Deliberate Sensing; and Security and Privacy Challenges. An educational goal is to host a two-day hack-a-thon where teams of students will design prototype HBI systems. A final objective is to publish output from the workshop and hack-a-thon in a HBI white paper.

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.

Stress has been identified as the health epidemic of the 21st century, and office-related work is a significant driver of stress among Americans due to long hours, rapid deadlines, heavy workload, and job insecurity. Yet, office workers are often entirely unaware of the impact of stress until they notice symptoms of declining physical or mental health or well-being, such as musculoskeletal discomfort, headaches, poor sleep, or lack of motivation. Even more problematic, most individuals do not know how their work activities and the physical and social work environments are related to stress and other health outcomes. While stress is almost always treated as unfavorable, stress can be positive. Opportunities exist to better understand how to promote eustress that is energizing and essential for productivity, and minimize distress that leads to negative emotions, disturbed bodily states, strain, and burnout. Thus, this project aims to generate new analytic models to uncover and map the patterns and pathways that influence work-related stress to understand the primary contributing factors to stress across space and time. The project will develop methods for integrating different types of data from the environment, the person, and other existing technologies to identify patterns that inform personalized solutions for improving self-awareness and management of work-related health and well-being. By developing a deeper individualized understanding and detection of eustress and distress, this project will impact and advance workplace health and wellness. The project will serve as a foundation for the development of sensing systems embedded within smart workplaces to automate environmental supports or provide behavioral feedback. These impacts will not only lead to improved worker health and well-being but can support decreased worker absenteeism and improved productivity. Thus, the project has the potential to change the way health and well-being are promoted and achieved in the office by engaging the worker in their health and wellness and ultimately reducing social and financial losses due to stress. The work will also have broader impacts regarding several criteria of NSF interest. It will promote awareness of the effects of the built, social, and work environments on health and well-being to encourage K-12 students to pursue careers in science and engineering. It will enhance the infrastructure for research and education by incorporating findings into the curriculum across multiple disciplines and disseminating findings via publications, presentations, and other media. <br/><br/>The project will use a stakeholder-engaged, transactional approach to describe individualized experiences of stress and develop multimodal models using a wide range of bio-behavioral, environmental, and activity engagement sensing technologies to identify the most valuable combinations of data that inform personalized, automated, or technology-supported intervention approaches to stress management as workers engage in their daily work. To build an individually contextualized understanding of stress among office workers, machine learning methods that can operate with heterogeneous and noisy multimodal data streams at multiple temporal resolutions, including enabling unsupervised discovery of behavioral routines will be developed. Individual interviews and ecological momentary assessment (EMA) surveys will be used to characterize each participant, their work, and how they understand the concepts of stress (i.e., distress and eustress), particularly related to their work. Mobile and wearable technologies will be evaluated to understand stress experiences as workers engage in different workspaces (e.g., home, formal, public) across time. Sensing methods that could be embedded within the formal workspace to obtain alternative, complementary, or additional data useful in determining experiences of worker stress will be evaluated for differentiating worker distress from eustress. Specifically, the contribution of the physical environment, task engagement, posture, and worker emotive states to the understanding of stress will be examined. Additionally, through focus groups that will elicit user insights, feedback, and preferences, the work will advance our knowledge about acceptance of technology for health in work settings, and how that interacts with stress/health self-management including privacy, trustworthiness, acceptance, preferred/appropriate methods for feedback or automation. Novel machine learning methods will be developed and employed to predict positive and negative stress from multimodal data that include reference assessments of behavioral traits and baseline states–including those related to stress, affect, and the job–that serve as constructs for modeling.<br/><br/>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.