Many emerging cyber-physical systems (CPS) are composed of a network of autonomous agents that make high-impact decisions, for example, a network of robots or drones that are on a search and rescue (SAR) mission. Such systems are referred to as high-impact decision making cyber-physical systems (HI-CPS). This research aims at building a unified theoretical framework for HI-CPS and validating this framework by fully implementing and testing a concrete example of such systems, namely, a network of autonomous agents that search for a lost person in dire conditions. This research brings together concepts from probability theory, decision theory, information theory, wireless networks, machine learning, and transportation engineering. By definition, this research focuses on high-impact systems, and it can directly impact the design of important emerging real-life systems. Educational and outreach activities are well-integrated into the research and include developing an honors thesis seminar course, workshops for underrepresented groups, and creating open educational content. 

The research has two thrusts: In Thrust 1, a new general theory of decision making suitable for such high-impact decision making is developed. This is based on the novel idea that the very notion of probability is insufficient when we are making high-impact decisions. It is shown that the approach is a multi-dimensional generalization of expected utility. A universality result is proved showing that any other decision-making operation can be framed as a special case of the proposed approach, emphasizing the sufficiency of the approach. Thrust 2 focuses on extending the framework to include two vital factors in HI-CPS: (1) timeliness and efficiency of information transmission as well as (2) power management. Thus, HI-CPS is designed and developed by incorporating all of these factors into a decision-making framework. To validate the theory, a concrete example of HI-CPS, i.e., an SAR system using a network of autonomous agents is built and tested. This research directly addresses Science of Cyber-Physical Systems (CPS) by providing new models and theories that unify HI-CPS.

Many emerging cyber physical systems are composed of a large number of mobile intelligent agents. In these systems, each agent travels along a trajectory that is often not pre-determined. At any time interval, new agents might appear in the system, and some existing agents might disappear. Additionally, these agents are normally capable of communicating with each other or outside stations using wireless communications. We refer to these systems as Trajectory-Based Cyber-Physical Networks (TCN). Examples of such systems are abundant and range from future generations of Unmanned Aircraft Systems (UAS) to networks of human or robot agents that are deployed in an area to perform missions such as disaster recovery. The goal of this research is (1) to develop a unifying theory called "Trajectory Process Theory" for TCNs, and (2) to design, implement, and test two specific real-life TCNs based on the proposed theory.

This research has two main thrusts: Thrust 1 builds the foundations of Trajectory Process Theory. Thrust 2 applies the theory to UAS technologies, specifically aerial base stations and unmanned aircraft delivery systems. This research brings together concepts from probability theory, stochastic geometry, wireless networks, and transportation engineering. The proposed research can directly impact the design of important emerging real life systems such as UASs. Educational and outreach activities including workshops for underrepresented groups as well as creating open educational content are undertaken.

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).

Medical Cyber-Physical Systems (MCPS) increasingly rely on complex and connected software and artificial intelligence for control and decision making in various diagnostic and therapeutic applications. But contrary to other CPS, they often depend on advanced medical knowledge and human expertise for real-time operation. Tele-operated surgical robots for minimally invasive surgery are an example of the most complex human-in-the-loop MCPS, envisioned to enable remote operations in inaccessible areas, low-resource populations, and extreme environments. However, an increasing number of recalls and adverse event reports have shown the vulnerability of MCPS to accidental or maliciously-crafted faults and human errors with potential negative impacts on patients. The objective of this research is to investigate the fundamental problem of runtime safety assurance in human-in-the-loop MCPS, and to develop integrated model and data-driven capabilities for timely detection and mitigation of safety hazards and reducing the risk of harm to patients.

The proposed research will advance the state-of-the-art in runtime verification and anomaly detection by introducing three novel principles for design of context-aware safety engines for MCPS: (i) Formal specification and learning of human-cyber-physical system contexts and their relationship with potentially unsafe control actions that lead to hazards and accidents; (ii) Real-time inference of the human-cyber-physical context through multi-level monitoring and model-based state estimation to detect the likelihood, timing, and risk of impending hazards; (iii) Risk-aware hazard mitigation through the context-aware generation of safe and corrective response actions that prevent adverse consequences in the physical layer. The research activities will be integrated with education through multi-disciplinary curriculum development and hands-on training for graduate students, research experience for undergraduates, and engagement activities, including summer internships, Girls? Geek Days, tech camps, and hackathons for K-12 students. These activities aim to broaden the participation of students from underrepresented groups and minorities in CPS and engineering in medicine research and train the next generation of diverse CPS professionals with expertise in areas such as healthcare, robotics, safety, and security that have the potential for significant societal impact.

Smart manufacturing, in which manufacturing processes become increasingly automated using algorithms intended to boost profits and reduce resource use while decreasing human error, is expected to enhance production efficiency in industries where chemical reaction, separation, and transport are important. Heightened communication and automation are also impacting other industries that involve control of molecular-level processes, as in healthcare, water treatment, and irrigation. However, a challenge for enhanced automation of these processes is preventing cyberattacks on the systems (referred to as control systems) that perform communication and computation to enable automation. If a cyberattack on a control system succeeds, it may impact factors such as safety, profitability, or production volume. Though safety-critical industries have many defenses in place to seek to prevent attackers from causing harm, an open question is how to design stronger safeguards against successful attacks into automation systems. This work aims to develop fundamental advances in advanced control algorithms integrated with algorithms for detecting cyberattacks and alerting company personnel to their presence for chemical processes described by complex dynamic models. This project seeks to characterize the conditions under which the process automation algorithms can be made resilient to cyberattacks on various aspects of the automation systems (e.g., sensors and actuators) in the sense that attacks cannot succeed at creating problematic process behavior from a safety standpoint even if they breach certain information technology defenses. The project will also pursue the development of a number of algorithms for enhancing safety and efficiency for next-generation manufacturing, and explore how cyberattacks may impact these. To disseminate information on these topics broadly, a live action and an animated short video to be shared via YouTube will be developed, in which the plot and the world in which the characters live expose viewers to the concepts of control, cybersecurity, and engineering pursued in this research through story.

The planned research program will comprehensively evaluate the characteristics of cyberattacks for processes involving molecular-level phenomena of different types, and will develop fundamental advances in control theory and algorithms for enhancing cybersecurity for these processes through control designs integrated with other frameworks such as detection algorithms. The theoretical conditions under which cybersecurity is enhanced by the proposed developments (in the sense that the attacks cannot create a safety issue for the process) will be characterized. Specifically, the following will be addressed: a) a mathematical formalization of the definition of different types of "undesirable behavior" for various chemical processes and clarification of reasonable types of cyberattacks for different chemical process systems will be developed; b) control and state estimation designs will be combined with detection techniques to allow guarantees to be developed on the conditions under which a cyberattack cannot create undesirable behavior even if it penetrates certain information technology defenses; c) novel sensing and control capabilities for cyber-physical systems will be developed that take advantage of machine learning and mathematics to increase flexibility of chemical processes, with investigations of how these advances may be cyberattacked; d) techniques for understanding and preventing undesirable behavior during a cyberattack through physical means (e.g., materials/equipment design and selection) will be developed; and e) the developments will be demonstrated and evaluated within the context of chemical processes across a variety of industries. These developments will focus on processes described by nonlinear dynamic models under model predictive control, but will also make extensions to processes of other types (e.g., a class of stochastic differential equations or partial differential equations).

Connected vehicles are an integral part of the future of intelligent transportation systems. They use wireless and sensing technologies to enable communication and cooperation between vehicles and infrastructure. Nonetheless, sensor reliability and data integrity play a crucial role in these vehicles. As vehicles and infrastructures grow increasingly networked and automated, there is a pressing need to identify sensor-related anomalies and mitigate potential safety hazards they might pose. The overarching goal of this project is to protect the connected vehicular network against anomalous sensor readings from any cause to ensure the safety of vehicles and passengers. The research aims to (1) provide new capabilities to broadly address safety concerns in connected vehicles to meet emerging future needs of intelligent transportation systems, and (2) enable a diverse and inclusive community of scientists and engineers to work in multidisciplinary areas such as cognitive machine learning and cybersecurity.

With the ever increasing complexity of connected vehicles operating in a more complicated cyber-physical social environment, conventional anomaly detection methods will likely not be able to keep pace with the demands of these challenges and function safely in a tomorrow's smart and connected communities. This project will explore (1) novel algorithmic methods that will enable the vehicles to quickly classify different types of sensor failures, learn new emerging anomalous patterns of sensor activity, and assess their risks relative to vehicle safety, and (2) designs for efficient scalable safe multi-agent models to build reputational trust among the connected vehicles in order to facilitate V2V information sharing, learning, and cooperative decision-making, and (3) new consensus-based protocols for connected vehicles that provide for resilience and adaptivity in the presence of disruptions, interruptions, and changes to vehicle participation. Initial test and evaluations are conducted by computer simulations with publicly-available data sets on connected vehicles and autonomous systems.

Advances in artificial intelligence (AI) make it clear that intelligent systems will account for the next leap in scientific progress to enable a myriad of future applications that improve the quality of life, contribute to the economy, and enhance societal resilience to a broad spectrum of disruptions. Yet, advances in AI come at a considerable resource costs. To reduce the cost of AI, this project takes inspiration from biological systems. It is well-known that a key bottleneck in AI is the perception subsystem. It is the part that allows AI to perceive and understand its surroundings. Humans are very good at understanding what?s critical in their environment and the human perceptual system automatically focuses limited cognitive resources on those elements of the scene that matter most, saving a significant amount of ?brain processing power?. Current AI pipelines do not have a similar mechanism, resulting in significantly higher resource costs. The project refactors data analytics and machine intelligence pipelines to allow for better prioritization of external stimuli leveraging and significantly extending advances in scheduling previously developed in the real-time systems research community. The refactored AI pipeline will improve the efficiency and efficacy of AI-enabled systems, allowing them to be safer and more responsive, while at the same time significantly lowering their cost. If successful, the project will help bring machine intelligence solutions to the benefit of all society. This is achieved through interactions between research, education, and outreach, as well as integration of multiple scientific communities, including (i) researchers on embedded computing who offer platforms and schedulers, (ii) researchers on IoT and networking, and (iii) researchers on intelligent applications and application domain experts. The work is an example of cyber-physical computing research, where a new generation of digital algorithms learn to exploit a better understanding of physical systems in order to improve societal outcomes. 

The project removes systemic priority inversion from machine intelligence pipelines in modern neural-network-based cyber-physical applications. In general, priority inversion occurs in real-time systems when computations that are less critical (or with longer deadlines) are performed ahead of those that are more critical (or with shorter deadlines). The current state of machine intelligence software suffers from significant priority inversion on the path from perception to decision-making, resulting in vastly inferior system responsiveness to critical events, thereby jeopardizing safety and increasing the cost of hardware to meet application needs. By resolving this problem, this project shall improve system ability to react to critical inputs, while at the same time significantly reducing platform cost. The intellectual merit of the project lies in investigating the intersection of two core areas in cyber-physical computing: (i) data analytics and machine learning and (ii) real-time systems. Specifically, the project refactors data analytics and machine intelligence pipelines to remove priority inversion. Mitigation of priority inversion problems in different systems has been one of the key contributions of the real-time community. Removal of priority inversion from machine intelligence pipelines makes several other scientific contributions. Namely, (i) the refactored AI pipeline improves the efficiency and efficacy of AI-enabled mission-critical systems, (ii) it enables autonomous systems to be more responsive, while lowering their cost, and (iii) it contributes to safety of intelligent systems by ensuring that critical inputs are processed first. The project expects to demonstrate significant improvements in performance of modern machine-learning-based inference protocols, while offering service differentiation that dramatically improves predictability and timeliness of reactions to critical situations. If successful, the project will significantly reduce the cost of deploying machine intelligence solutions in future cyber-physical systems, while improving predictability and temporal guarantees. In addition to delivering the technical contributions of this project, an explicit purpose of the work is to advance education and workforce development on Intelligent CPS topics. This is achieved through interactions between activities for research, education, and broadening participation, as well as integration of multiple communities, including (i) researchers on embedded computing who offer platforms and schedulers, (ii) researchers on IoT and networking, and (iii) researchers on intelligent applications and application domain experts.

This project aims to advance knowledge of machine learning for human-in-the-loop cyber-physical systems. Mobile and wearable devices have emerged as a promising technology for health monitoring and behavioral interventions. Designing such systems involves collecting and labeling sensor data in free-living environments through an active learning process. In active learning, the system iteratively queries a human expert (e.g., patient, clinician) for correct labels. Designing active learning strategies in uncontrolled settings is challenging because (1) active learning places a significant burden on the user and compromises adoption of the technology; and (2) labels expressed by humans carry significant amounts of temporal and spatial disparities that lead to poor performance of the system. The research will address technical challenges in designing high performance systems, and enable accurate monitoring and interventions in many applications beyond behavioral medicine.

This project develops mixed-initiative solutions that will enable learning of human behaviors in uncontrolled environments through the following research objectives: (1) investigating combinatorial approaches to maximize the active learning performance taking into account informativeness of sensor data, burden of data labeling, and reliability of prospective labels; (2) constructing a rich vocabulary of complex behaviors based on knowledge graph embedding and semi-supervised learning techniques; (3) developing network-graph-based learning algorithms that infer complex human behaviors; and (4) validating algorithms for off-line active learning, real-time active learning, behavior vocabulary construction, and behavior inference through both in-lab experiments and user studies.

A critical application of smart technologies is a smart, connected, and secured environmental monitoring network that can help administrators and researchers find better ways to incorporate evidence and data into public decision-making related to the environment. In this project, the investigators will establish a secure, trustworthy and reliable air quality monitoring network system using densely deployed low-cost sensors in and around the city of Orlando, Florida, to better inform development of pollution mitigation strategies in the region. Access to the urban-scale air quality sensor data and forecasts can have a positive social impact on environmental justice, public health, and sustainability initiatives. The investigators will incorporate the outcome of the project into courses on computer and network security and privacy, mobile computing, environmental sciences and engineering, and social science. The proposed work will provide hands-on exercises, research, and educational opportunities for undergraduate, graduate students and K-12 students.

The objectives of this project include performing remote low-cost sensor calibration, drift and malfunction detection. An innovative modeling method will be developed to perform remote calibration for low-cost PM2.5 sensors. A triple-sensor system will be developed, employing an operational statistical method that cross-evaluates sensor measurement data every hour to identify potential sensor drifts and malfunctions. The project team will build a trustworthy air quality monitoring network. A trusted boot strategy will be developed to ensure the sensor firmware is genuine at bootstrapping, performing dynamic analysis of states of the system, sending the measurement to a verifier for remote attestation, and accepting commands from the verifier to act on violations. The team will also create an accurate deep learning-based air quality prediction system based on a novel two-stage semi-supervised learning framework from noisy and mixed-labeled sensor big data. Social scientists on the team will conduct a social behavioral study of air quality monitoring and prediction. This project emphasizes sustainable empowerment of residents through processes of education on air quality and training on data utilization and advocacy. The project goes beyond passive citizen science to enable citizens to become advocates for their interests to increase not only outside air quality but also the overall quality of life of citizens in the community.

A growing number of natural or man-made detrimental incidents occur every day, which mandate precise monitoring, control/management, and prevention. Otherwise, they can rapidly evolve to turn into unpredictable events with significant losses such as delays of automotive traffics jams, catastrophic devastation assuming lives of innocent citizens as in man-made incidents or explosions, financial and industrial losses as in the case of malfunction or defects in manufacturing plants, and loss of natural resources as in the case of droughts, wildfires, and floods. First responders are at the frontline of counteractions against these incidents with their safety being at a major risk, while the effectiveness and efficiency of their actions may also need improvement for complete closure of the event or prevention of its growth. To further assist the first responders and disallowing the damage due to an incident, this research proposes a cooperative network of unmanned aerial vehicles (UAVs) that are equipped with novel sensing and imaging technologies and can obtain critical information for the safe and more successful operation of first responders by sharing information with them in a short span of time. The UAVs can also assist the first responders by obtaining information from environments that are hard to access such as non-urban areas and environments with extreme conditions e.g., high temperature/elevation. 

The proposed research aims to investigate and realize a re-configurable, aerial, power-efficient, interconnected imaging, and detection (RAPID) CPS that can adaptively tune its configuration and performance (e.g., three-dimensional position of agents, spatial sensing resolution) with respect to the span of impacted area, feature size, and necessary resolution to monitor various incidents. To achieve these goals, three interrelated research thrusts with the following intellectual merits are pursued: (1) design and optimization of coordinated mobility strategies and control for the proposed CPS so as to maintain high-resolution sensing and connectivity of the drones; (2) design of an aerial communication network to realize cooperative sensing/communication and develop power-optimized rate-controllable wireless system per each UAV to exchange acquired image data between cyber and physical agents and track the position of UAVs in the network; and (3) design of a dual-mode sensing fusion embedded within a flying sensor agent comprising a novel low-power, high-resolution mm-wave imaging module to detect mobile/hidden objects and structural defects, and an infra-red (IR) thermal camera to detect high-temperature radiations.

Artificial Intelligence (AI) has shown superior performance in enhancing driving safety in advanced driver-assistance systems (ADAS). State-of-the-art deep neural networks (DNNs) achieve high accuracy at the expense of increased model complexity, which raises the computation burden of onboard processing units of vehicles for ADAS inference tasks. The primary goal of this project is to develop innovative collaborative AI inference strategies with the emerging edge computing paradigm. The strategies can adaptively adjust cooperative inference techniques for best utilizing available computation and communication resources and ultimately enable high-accuracy and real-time inference. The project will inspire greater collaborations between experts in wireless communication, edge computing, computer vision, autonomous driving testbed development, and automotive manufacturing, and facilitate AI applications in a variety of IoT systems. The educational testbed developed from this project can be integrated into courses to provide hands-on experiences. This project will benefit undergraduate, master, and Ph.D. programs and increase under-represented groups? engagement by leveraging the existing diversity-related outreach efforts.

A multi-disciplinary team with complementary expertise from Rowan University, Temple University, Stony Brook University, and Kettering University is assembled to pursue a coordinated study of collaborative AI inference. The PIs explore integrative research to enable deep learning technologies in resource-constrained ADAS for high-accuracy and real-time inference. Theory-wise, the PIs plan to take advantage of the observation that DNNs can be decomposed into a set of fine-grained components to allow distributed AI inference on both the vehicle and edge server sides for inference acceleration. Application-wise, the PIs plan to design novel DNN models which are optimized for the cooperative AI inference paradigm. Testbed-wise, a vehicle edge computing platform with V2X communication and edge computing capability will be developed at Kettering University GM Mobility Research Center. The cooperative AI inference system will be implemented, and the research findings will be validated on realistic vehicular edge computing environments thoroughly. The data, software, and educational testbeds developed from this project will be widely disseminated. Domain experts in autonomous driving testbed development, intelligent transportation systems, and automotive manufacturing will be engaged in project-related issues to ensure relevant challenges in this project are impactful for real-world applications.