Ocean Big Data (OBD) is an emerging area of research that benefits ocean environmental monitoring, offshore exploration, disaster prevention, and military surveillance. It is now affordable for oil and gas companies, fishing industry, militaries, and marine researchers to deploy physical undersea sensor systems to obtain strategic advantages. However, these sensing activities are scattered, isolated, and often follow the traditional "deploy, wait, retrieve, and post-process" routine. Since transmitting information underwater remains difficult and unreliable, these sensors lack a cyber interconnection, which severely limits ocean cyber-physical systems. This project aims to providing a viable cyber interconnection scheme that enables distributed, efficient, ubiquitous, and secure (DEUS) data delivery from underwater sensors to the surface station. The proposed cyber interconnection scheme features cheap underwater sensor nodes with energy harvesting capability, a fleet of autonomous underwater vehicles (AUVs) for information ferrying, advanced magnetic-induction (MI) antenna design using ferrite material, distributed algorithms for efficient data collection via AUVs, and secure data delivery protocols. The success of this project will help push the frontier of Internet of Things in Oceans (IoTO) and OBD, both of which will find numerous underwater applications in offshore oil spill response, fisheries management, storm preparedness, etc., which impact the economy and well-being of not only coastal regions but also inland states. The project will also provide special interdisciplinary training opportunities for both graduate and undergraduate students, particularly women and minority students, through both research work and related courses on underwater wireless communication, network security, and AUV designs. The DEUS project provides a viable cyber interconnection scheme that enables distributed, efficient, ubiquitous, and secure data delivery in underwater environment via four synergistic thrusts: (1) integration of underwater wireless sensor and communication systems, which will enhance the current MI and light communication means of underwater sensors, integrate acoustic transmission systems for long-range communications between anchor nodes and AUVs, and design energy harvesting and replenishment solutions to prolong the lifetime of underwater sensors (30+ years); (2) distributed and ubiquitous data delivery via multiple AUVs, which aims to collect the distributed data and deliver them ubiquitously throughout the underwater network by employing ferrite material and triaxial induction antennas and mounting them outside of the AUV body for MI enhancement, and developing algorithms of multiple AUVs' path-planning, trajectory optimization, etc. under dynamic network conditions; (3) efficiency and security in data delivery, which designs network algorithms to improve the efficiency and security of data delivery. Instead of collecting data from every sensor via acoustic communications, the AUVs choose some sensors to collect data with the high data rate transmission mode in near field (e.g., light), and allowing the sensor far away from the AUVs to send its data either directly to AUVs via acoustic wave or to its nearby chosen sensors via MI/light communications. A secure data delivery scheme will also be developed to not only secure the data delivery against typical malicious attacks and guarantee the integrity of collected data, but also allow the data aggregation of one business entity without knowing others' private business information; (4) experimental validation and testing, which will verify the proposed data delivery schemes, and quantitatively present the performance gains through simulations, experiments and field test, based on existing facilities.

This project expands how reinforcement learning frameworks can be used for Cyber-Physical Systems (CPS) for autonomy. The research utilizes intermittent reinforcement, where a reward is not given every time the desired response is performed. This differs from traditional reinforcement learning mechanisms, in which a reward is given for each point during online training. What is novel in this framework is that it can demonstrate how reinforcement learning can be used when rare events, or noisy and adversarial data, can affect the training and performance of these algorithms. The work will be validated on collaborative road freight transport and collaborative robotics testbeds, through international partnerships with Sweden and the United Kingdom. The project includes activities that integrate high-school students into challenging problems in machine learning areas, motivated through drone racing competitions. The goal of this research is to expand foundational knowledge through deepened ties between the learning, control, game theory, and CPS communities. The approach is to, (i) unify new perspectives of learning in engineering with respect to resiliency, bandwidth efficiency, robustness, and other aspects that cannot be achieved with the state-of-the-art approaches; (ii) develop intermittent deep learning methods for CPS that can mitigate sensor attacks and can handle cases of limited sensing capabilities; (iii) incorporate nonequilibrium game-theoretic learning in CPS with components whose decision-making, rationality, and information usage are fundamentally different; and (iv) investigate ways to transfer learning to new platforms. The project's education and outreach component includes internships that will lead to technology transfer, summer camps with a special focus on reaching out to underrepresented minorities and women, and collaboration with institutions in Sweden and the United Kingdom through student exchange programs.

Next-generation cyber-physical systems (CPS) will increasingly rely on machine learning algorithms for situational awareness and decision-making, with the promise of enhancing human capabilities. Examples range from autonomous vehicles and robots to computer-controlled factory lines and wearable medical devices. However, learning-enabled systems have shown to be very sensitive to training data and have difficulty in ensuring functional safety and robustness. The undesired outcomes of recent deployments, such as the accidents involving semi-autonomous vehicles, raise questions about the design principles needed to build learning-enabled systems that are safe. This project aims to develop the foundations of a novel methodology for the design and verification of learning-enabled CPS. It will pursue a compositional framework and computational tools that can reason about the uncertainty and approximation introduced by learning components and enable system design via a hierarchical and modular approach. The proposed research can have a highly positive influence on the design and real-world deployment of safe and cost-effective autonomous systems for a variety of applications, including autonomous driving, robotics, and industrial automation. Moreover, it has the potential to offer a unifying framework for reasoning about a number of robust and fault-tolerant design approaches that are currently based mostly on ad hoc solutions. Collaborations with industry partners will be pursued to facilitate transitioning the research findings into practice. An educational plan including new undergraduate and graduate courses and a program for pre-college students will complement the research effort, aiming to educate the next generation of engineers and researchers on the concepts and the multidisciplinary attitude needed to realize "intelligent" systems that are safe, technologically and economically feasible, and seamlessly interacting with people. The project develops a compositional framework for reasoning about the probabilistic behaviors of CPS built out of unreliable components. The framework relies on stochastic models of the interfaces between the components and their environments, termed deep contracts, together with rigorous rules for composing and refining them. Rich, quantitative, logic-based stochastic specification formalisms and data-driven modeling techniques will be leveraged to express and propagate computationally tractable representations of uncertainty at different abstraction levels. The framework will be vertically-integrated and offer mapping mechanisms to bridge heterogeneous models and heterogeneous decomposition architectures in the design hierarchy. It will provide computational tools to efficiently solve verification and synthesis problems with stochastic contracts. Finally, it will offer mechanisms to monitor requirements throughout the entire system life-cycle and provide assurance both at design time and runtime.

This robustifying machine learning (ML) for cyber-physical systems (CPSs) project focuses on detecting and reducing the vulnerabilities of ML models that have become pervasive and are being deployed for decision-making in real-life CPS applications including self-driving cars, and robotic air vehicles. The growing prospect of machine learning approaches such as deep Convolutional Neural Networks (CNN) and deep Reinforcement Learning (DRL) being used in CPSs (e.g., self-driving cars) has raised concerns around safety and robustness of autonomous agents. Recent work on generating adversarial attacks have shown that it is computationally feasible for a bad actor to fool a deep learning (DL) model dramatically. Apart from adversarial attacks, such DL models can also succumb to the so-called 'edge-cases' where the real-life operational situation presents data that are not well-represented in the training data set. Such cases have been the primary reason for quite a few self-driving car accidents recently. Although initial research has begun to address scenarios with specific attack models, there remains a significant knowledge gap regarding detection and adaptation of ML models to 'edge-cases' and adversarial attacks in the context of CPS. With this motivation, this project builds a meta-learning-based supervisory framework and associated algorithms to detect and mitigate ML system vulnerabilities which will substantially reduce the risk in using ML for safety and time-critical systems. The science driver applications are self-driving cars and robotics. The algorithm validation and evaluation use experimental self-driving cars and robotics test beds at Iowa State in collaboration with the Institution of Transportation and NVIDIA. Research is integrated with education to support the goal of training students in the critical interdisciplinary area of system theory and data science, which is in dire need of rapid and quality workforce development for sustained economic and social growth of the United States. Education plans also include curriculum development at graduate and undergraduate level, undergraduate research experience, academic competitions and outreach activities involving both high school students and teachers. Outcomes of this project will support NSF's mission of "Harnessing the Data Revolution" for many critical CPSs that currently involve ML or will involve it in future, such as manufacturing processes, power grid, smart cities and transportation systems, to make them safer, more efficient and cost effective.

Participatory science has opened opportunities for many to participate in data collection for science experiments about the environment, local transportation, disaster response, and public safety where people live. The nature of the collection by non-scientists on a large scale carries inherent risks of sufficient coverage, accuracy and reliability of measurements. This project is motivated by the challenges in data and predictive analytics and in control for participatory science data collection and curation in cyber-physical systems (CPS) experiments. This project focuses on data-driven frameworks to address these challenges in CPS-enabled participatory science that builds on statistics, optimization, control, natural language processing, CPS fundamentals, and coordination of participants, known as crowd steering. This framework, known as DCCDI for Data-driven Crowdsensing CPS Design and Implementation, tightly combines the underlying methods and techniques, especially focusing on physical sensors, mobility, and model-based approaches, to improve efficiency, effectiveness, and accountability. Validation of the DCCDI framework is conducted through simulations, case studies, and on real-world CPS-enabled experiments. This project closely integrates education and training with foundational research and public outreach that enhances interdisciplinary thinking about CPS systems, engages the public through participatory science, and broadens participation in science, technology, engineering, mathematics, and computer science.

The goal of this project is to achieve coordination and localization among robots, even if some of the robots are behaving in an untrustworthy way. The approach is to use communication signals, and to control the motion of some robots, to learn about the environment and other agents in a way that provably supports coordinated behaviors. Multi-agent Cyber-Physical Systems (CPS) are poised for impact in society as self-driving cars, delivery drones, and disaster response robots. The results from this project will lead to improved mission intelligence for robotic platforms with significance across many areas: from Search and Rescue (SAR) tasks, to CubeSats and space exploration. The project includes tight integration between research tasks and educational activities, including participation in Hack for Humanity where students will explore SAR tasks. This project will derive the algorithmic foundations of robust and secure contextual awareness for coordination of multi-agent CPS by bridging robotics and communication. A core enabling capability for these systems is secure, robust, contextual awareness and coordination. Agents must know their state, others' states, and how best to use this information to coordinate and complete mission-level goals. However, while this need is universal, the CPS themselves are not. Thus, there exist technological barriers to obtaining this critical information across heterogeneous platforms. An algorithmic and mathematical framework will be explored to 1) combine communication and mobility control of CPS agents to enable communication-as-a-sensor that unlocks a new understanding of interactions with the world and 2) capture the impact of this information on reliability, robustness, and security of multi-agent tasks.

In the United States, there is still a great disparity in medical care and most profoundly for emergency care, where limited facilities and remote location play a central role. Based on the Wessels Living History Farm report, the doctor to patient ratio in the United States is 30 to 10,000 in large metropolitan areas, only 5 to 10,000 in most rural areas; and the highest death rates are often found in the most rural counties. For emergency patient care, time to definitive treatment is critical. However, deciding the most effective care for an acute patient requires knowledge and experience. Though medical best practice guidelines exist and are in hospital handbooks, they are often lengthy and difficult to apply clinically. The challenges are exaggerated for doctors in rural areas and emergency medical technicians (EMT) during patient transport. This project's solution to transform emergency care at rural hospitals is to use innovative CPS technologies to help hospitals to improve their adherence to medical best practice. The key to assist medical staff with different levels of experience and skills to adhere to medical best practice is to transform required processes described in medical texts to an executable, adaptive, and distributed medical best practice guidance (EMBG) system. Compared to the computerized sepsis best practice protocol, the EMBG system faces a much bigger challenge as it has to adapt the best practice across rural hospitals, ambulances and center hospitals with different levels of staff expertise and equipment capabilities. Using a Global Positioning System analogy, a GPS leads drivers with different route familiarity to their destination through an optimal route based on the drivers' preferences, the EMBG system leads medical personnel to follow the best medical guideline path to provide emergency care and minimize the time to definitive treatment for acute patients. The project makes the following contributions: 1) The codification of complex medical knowledge is an important advancement in knowledge capture and representation; 2) Pathophysiological model driven communication in high speed ambulance advances life critical communication technology; and 3) Reduced complexity software architectures designed for formal verification bridges the gap between formal method research and system engineering.

The Future of Work at the Human-Technology Frontier (FW-HTF) is one of 10 new Big Ideas for Future Investment announced by the National Science Foundation. The FW-HTF cross-directorate program aims to respond to the challenges and opportunities of the changing landscape of jobs and work by supporting convergent research. This award fulfills part of that aim. Effective decision making by power grid operators in extreme events (e.g., Hurricane Maria in Puerto Rico, the Ukraine cyber attack) depends on two factors: operator knowledge acquired through training and experience, and appropriate decision support tools. Decision making in electric grid operation during extreme adverse events directly impacts the life of citizens. This project will augment the cognitive performance of human operators with new, human-focused decision support tools and better, data-driven training for managing the grid especially under highly disruptive conditions. The development of new generation of tools for online knowledge fusion, event detection, cyber-physical-human analysis in operational environment can be applied during extreme events and provide energy to critical facilities like hospitals, city halls and essential infrastructure to keep citizens safe and avoid economic loss for the Nation. Higher performance of operators will improve worker quality of life and will enhance the economic and social well-being of the country. The project's training objectives will leverage existing educational efforts and outreach activities and we will publicize the multidisciplinary outcomes through multiple venues. The proposed project will integrate principles from cognitive neuroscience, artificial intelligence, machine learning, data science, cybersecurity, and power engineering to augment power grid operators for better performance. Two key parameters influencing human performance from the dynamic attentional control (DAC) framework are working memory (WM) capacity, the ability to maintain information in the focus of attention, and cognitive flexibility (CF), the ability to use feedback to redirect decision making given fast changing system scenarios. The project will achieve its goals through analyzing WM and CF and performance of power grid operators during extreme events; augmenting cognitive performance through advanced machine learning based decision support tools and adaptive human-machine system; and developing theory-driven training simulators for advancing cognitive performance of human operators for enhanced grid resilience. A new set of algorithms have been proposed for data-driven event detection, anomaly flag processing, root cause analysis and decision support using Tree Augmented naive Bayesian Net (TAN) structure, Minimum Weighted Spanning Tree (MWST) using the Mutual Information (MI) metric, and unsupervised learning improved for online learning and decision making. Additionally, visualization tools have been proposed using cognitive factor analysis and human error analysis. We propose a training process driven by cognitive and physiometric analysis and inspired by our experience in operators training in multiple domain: the power grid, aircraft and spacecraft flight simulators. A systematic approach for human operator decision making is proposed using quantifiable human and engineering analysis indices for power grid resiliency.

This project addresses timing attacks in cyber-physical systems, where attackers attempt to compromise the system functionality by changing the timing of computation and communication operations. Timing attacks could be particularly destructive for cyber-physical systems because the correctness of system functionality is affected not only by the data values of operations but also significantly by at what time operations are conducted. The discoveries and methodologies developed in this project will provide fundamental advances in addressing timing attacks, and lead to the design and implementation of more secure cyber-physical systems in a number of key sectors, including automotive and transportation systems, industrial automation, and robotics. In addition to disseminate the research results through publications and workshops, the PIs will collaborate with industry partners on transitioning the research findings into practice. The PIs will also integrate the research into the curriculum at UCR and leverage it for K-12 education through the use of Lego Mindstorm platforms. The project will build a framework for identifying, analyzing and protecting cyber-physical systems against timing attacks. Building the framework consists of three closely-related research thrusts: 1) Investigate potential timing-based attack surface, and further analyze what types and patterns of timing variations the attacks may cause and how attackers may try to hide the traces of such attacks. 2) Based on the identified attack surface and strategies, analyze how timing changes caused by these attacks may affect the overall system properties, in particular safety, stability and performance. 3) Develop control-based and cyber-security defense strategies against timing attacks. This includes run-time security detectors and mitigation/adaptation strategies across control layer and embedded system layer, as well as design-time mechanisms to provide systems that are resilient to timing attacks. This project will focus on vehicle networks and multi-agent robotic systems as main application domains.

Good algorithmic foundations for flight planning on the scale required for managing dense urban drone traffic we can expect to see in the future are currently still missing. This project provides prototype algorithms for managing this dense drone traffic. The project develops a concept for a coordination system that is able to find collision-free paths for a large number of flying unmanned air vehicles of different size and capability. It uses a hierarchical approach, combining centralized and local coordination, to manage complexity for a large-scale problem. The approach developed here can scale up to handle thousands of drones and lead to conflict free flight. It demonstrates the concept using mixed-reality simulations and using existing helicopter-like robots on a smaller scale. Current multi-robot trajectory-planning algorithms typically operate on a single level (which limits their scalability) and assume holonomic robots that can hover motionlessly (which limits their applicability). The core of the project is the development of a novel hierarchical system that addresses these limitations, combining centralized methods with a divide-and-conquer approach. The hierarchical approach allows the system to negotiate collision-free trajectories on a local level, while ensuring that robots complete their tasks on the global level. Additional research integrates several speed-up techniques into the hierarchical system and generalizes its functionality, for example, to accommodate robots of different priorities (such as drones that deliver blood to hospitals). The research involves not only graduate but also undergraduate students and trains them in cross-disciplinary research.