CPS: Medium: Learning-Enabled Assistive Driving: Formal Assurances during Operation and Training
Lead PI:
Panagiotis Tsiotras
Co-Pi:
Abstract

Despite claims in popular media, current ?self-driving? and advanced driver assist systems (ADAS), based on purely data-driven, machine learning algorithms may still suffer from catastrophic failures. This tendency of ?theoretical statistical accuracy? but ?demonstrated fragility in practice? makes current deep learning algorithms unsuitable for use within feedback loops for safety-critical, cyber-physical applications such as assisted or unsupervised self-driving cars in traffic. Regardless of these shortcomings, it is certain that automation and autonomy will play a crucial role in future mobility solutions, either for personally owned or shared-mobility vehicles; and regardless of the level of automation, at least in the foreseeable future, the driver should be in the loop. There is currently a need to quantify the impact of the human driver within the autonomy loop, both from an individual experiential perspective, as well as in terms of safety. In addition, the next generation of ?self-driving? or ?driver-assist? systems should be able to sense, learn and anticipate driver?s habits, skills and adapt accordingly, thus making driving more intuitive and safer at the same time. How to best integrate the driver?s learning goals and preferences in a transparent manner to enhance the ?driving experience? without sacrificing safety requires further work, however.

The main objective of this research is to utilize techniques and models from reinforcement learning and formal methods to develop the next generation of ADAS that can accommodate the driver preferences and habits with safety constraints. The aim is to increase the performance and safety guarantees of deep neural network architectures operating within a feedback loop that includes the driver by: a) using redundant architectures that blend model-free and model-based processing pipelines; and b) adding safety guarantees both during training and during execution by leveraging recent advances of formal methods for safety-critical applications. Specifically, the technique consists of learning a state prediction model to estimate the internal reward function of the driver using a novel neural network architecture, accompanied by a federated, lifelong learning approach to identify heterogeneous driver preferences and goals. The proposed approach will further add a layer of safety and robustness by incorporating the neural network architecture with a differentiable Signal Temporal Logic (STL) framework to meet temporal safety constraints, and will meet with an additional safety layer using a run-time assurance (RTA) mechanism that combines reachability analysis with a monitoring approach to ensure that system cannot be steered to unsafe conditions. The proposed framework will be validated and tested in two stages. The first stage will involve simulations and experiments on several non-trivial problems using high-fidelity driving simulation platforms such as CARLA. The second stage will conduct human-in-the-loop experiments using a driving simulator developed at Georgia Tech. The research will involve both graduate and undergraduate students. The results of this research will be disseminated to the community by journal and conference publications, organization of invited workshops and seminar presentations, and by targeted exposure (press releases, interviews) to popular media.

Panagiotis Tsiotras
Performance Period: 06/15/2022 - 05/31/2025
Institution: Georgia Institute of Technology
Sponsor: National Science Foundation
Award Number: 2219755
CPS: Medium: A meta-learning approach to enable autonomous buildings
Lead PI:
Panagiota Karava
Co-Pi:
Abstract

Buildings are vitally important because they contribute to the well-being and productivity of their occupants - however, these benefits come at a high environmental cost. Collectively, buildings account for 40% of the US primary energy usage and CO2 emissions and 70% of the electricity consumption. Furthermore, buildings put a tremendous strain on the power grid as they are largely responsible for the peaks in energy demand. Making buildings smarter through the deployment of sensors, actuators, and controllers, which collectively serve as the backbone of building cyber-physical systems (CPS), can achieve more than 30% annual energy savings and can also significantly smooth peak demand. Thus, smart buildings are vital to a sustainable energy future. However, the road to large-scale realization of smart buildings is inhibited by their heterogeneity, which requires engineering customized, site-specific, and, thereby, costly solutions.

The goal of this project is to develop a CPS solution for autonomous buildings that will enable non-expert building managers to deploy asset-specific, smart control policies. The advantage of the proposed solution relies on the fact that the approach can be applied on a large-scale even without any human intervention. The resulting software solution is the Artificial-Intelligence-Enabled Building Energy Expert (AI-BEE) and it will be demonstrated using simulations and experiments at the Center for High Performance Buildings at Purdue University. The proposed research will result in foundational contributions in core CPS areas, including machine learning and control, that will be translational to other application areas, such as large-scale energy systems (power grid), transportation, civil infrastructure, and unmanned vehicles.

The technical details of our approach are as follows. First, a taxonomy of building types is being developed. The idea is that the energy behavior of every building should be completely specified by a finite set of variables in a machine-readable format. Second, each complete building description is associated with a set of dynamical systems that describes the energy consumption. In this way, non-experts will be able to specify building characteristics and get a set of plausible dynamical systems that include a description of the building. This set of dynamical systems is what is called the relevant model universe to the building at hand. Third, meta reinforcement learning is being used to discover a self-improving control algorithm that works well for all dynamical models in the relevant model universe. The final step is to deploy the discovered algorithm to the building and let it self-improve further.

Panagiota Karava
Performance Period: 07/01/2021 - 06/30/2024
Institution: Purdue University
Sponsor: National Science Foundation
Award Number: 2038410
CPS: TTP Option: Medium: Collaborative Research: Cyber-Physical System Integrity and Security with Impedance Signatures
Lead PI:
Pablo Tarazaga
Co-Pi:
Abstract

Cyber-physical systems (CPS), such as automobiles, planes, and heavy equipment rely on complex distributed supply chains that source parts from manufacturers across the world. A fundamental problem that these systems face is ensuring the safety, security, and integrity of both the cyber components and physical parts that they receive through their supply chain. Because of the separation between the manufacturer and the consumer of the part, there are immense challenges in ensuring that physical parts arrive from the desired source and are not modified or swapped for inferior copies in transit. For example, the Aerospace Industries Association states that "though we know counterfeit parts enter the aerospace supply chain, the time and place of their entry is unpredictable." If either the cyber-components or the physical parts being incorporated into these systems have been tampered with, significant cyber-physical security risk is introduced. As an example, an attacker who has a part's cyber-information can simply produce a counterfeit part, clone any physical identifiers (serial numbers, etc.), and claim that the cyber-information is for the cloned part.

While cyber-security techniques, such as roots of trust and signing chains, exist to help ensure software integrity, there are no commensurate roots of trust and signing chains that can guarantee the source and integrity of both the cyber components and physical parts. As such, there is a risk that the algorithms and control approaches used in a supply chain will not identify the inferior performance characteristics of a counterfeit part and control its operation in an unsafe manner. The primary goal of this research is to create an integrity mechanism based on physically unclonable functions to ensure that an entire CPS is built from both trusted software and physical parts. To achieve this goal, the research investigates (i) a physical measurement technique (electro-mechanical impedance) to provide parts an unclonable physical identity and (ii) the cyber signing approaches to build chains of trust from these identities.

Pablo Tarazaga
Performance Period: 10/01/2019 - 09/30/2024
Institution: Virginia Polytechnic Institute and State University
Sponsor: National Science Foundation
Award Number: 1932213
Collaborative Research: CPS: TTP Option: Medium: i-HEAR: immersive Human-On-the-Loop Environmental Adaptation for Stress Reduction
Lead PI:
Olga Boric-Lubecke
Co-Pi:
Abstract

There is no question that indoor environments are often uncomfortable or unhealthy for occupants. This is an even more critical issue in healthcare facilities, where patients may experience the stressful effects of poor thermal, luminous, and acoustic environments more acutely. With complementary expertise from engineering and psychology, the proposed research is focused on creating a human-on-the-loop, responsive indoor environmental system with the potential to offer better quality of care in hospitals. The outputs of this project will have profound societal impacts on the wellbeing of both healthy individuals and on recovering sick individuals. Research outcomes will enable real time human-built environment interaction to minimize stress and optimize performance in any built environment, and ultimately lead towards economic benefits achieved through wellness and higher productivity. Improved indoor environmental quality in hospital settings will improve patient healing, which is an important societal benefit. Similar strategies can be used for educational facilities, and office buildings. This research encourages Broadening Participation through inclusion of individuals from underrepresented groups (female and Latinx Co-PIs), female and minority students, and a minority serving lead institution from an EPSCoR state. Results will be disseminated broadly through scientific publications and seminars, and K-12 outreach, including STEM competitions, and summer programs.

Indoor environmental quality (IEQ) not only impacts the physical health of patients, but also their psychological health. Yet environmental controls for heating, cooling and ventilation, noise attenuation, and lighting in hospitals are based on outdated models of how hospitals function, who occupies these settings, and what emerging technologies are available. As a result, many hospitals are just functionally adequate, often likely to be too cold or hot, too loud, or too bright. In order to capitalize on the healing potential of the hospital?s built environment, we propose a three-year collaborative effort between the University of Hawaii at Manoa, Arizona State University, and Drexel University to develop innovative biosensor technologies, deep-learning health data analytics, and user-centric control algorithms to connect these three domains in which the interdependencies of the physiological, physical, and psychological will be investigated, quantified, and addressed. The team is partnering with the Children?s Hospital of Philadelphia (CHOP) to validate the approach. Specific anticipated engineering/science contributions include: 1) innovative cyber-physical system architecture using heterogeneous biosensing and data analytics for real-time control; 2) new sensor fusion based technology for non-invasive, precise physiological measures that are surrogate stress indicators; 3) progressive development of innovative human centric deep model linking physiological biometrics to psychological measures, and connecting environmental factors to psychological measures facilitated with physiological biometrics; 4) new stress responsive real-time supervisory control strategies including optimal environmental adjustment, and 5) multi-level system evaluation via virtual, laboratory, and field testing at a hospital environment at CHOP.

Olga Boric-Lubecke
Performance Period: 10/01/2021 - 09/30/2024
Institution: University of Hawaii
Sponsor: National Science Foundation
Award Number: 2039089
Collaborative Research:CPS Medium: Population Games for Cyber-Physical Systems: New Theory with Tools for Transportation Management under Extreme Demand
Lead PI:
Nuno Martins
Abstract

A sudden surge in demand in traffic networks disrupts the equilibrium conditions upon which these networks are planned and operated. Lack of understanding of the population's strategic choices under extreme demand may result in paradoxical outcomes, such as evacuations aiming to save lives instead resulting in mass casualties on the road or opening up of new roads increasing rather than decreasing travel time. This project will devise systems and procedures for managing the strategic choices of populations (e.g., whether to evacuate or shelter in place, which escape routes to take) and the actions of the authorities (e.g., which zones to evacuate and in which sequence, where to route the traffic, whether to close some roads or open extra lanes in a given direction). The tools resulting from this project will enable better response systems to assist local authorities in managing extreme demand, such as when entire counties have to be evacuated to protect the residents from a wildfire. The project will develop a modeling and simulation tool chain to predict traffic bottleneck locations and their severity together with expected travel times and delays, thus determining the spectrum of outcomes, identifying worst cases, and enabling the authorities to make informed decisions.

The technical approach is rooted in population games, which model the dynamics of strategic noncooperative interactions among large populations of agents competing for resources. The project, however, will depart from the equilibrium focus of the existing theory and will offer transient analysis tools that account for not only the strategy revisions of the agents, but also a host of cyber and physical dynamics, such as queueing dynamics in traffic flow, responsive signal control at intersections, information dissemination to agents, and evolution of hazards, such as fire propagation. The research tasks to enable the project's vision of a "cyber-physical population game theory" include characterizing transient behavior with system-theoretic methods, accounting for uncertainty in strategy revision models, extending the theory to a continuum of user preferences, rethinking the stochastic processes underlying the dynamical models, modifying the theory for short-term horizons for time-critical operations, learning dynamical models from data, and formulating extensive form games between a population and a single agent, motivated by the population response to evacuation orders. In addition, the project will identify control actions (such as responsive signal policies, road closures, disabling certain turns) to close the data-decision-action loop and steer the dynamics towards desirable outcomes and avoiding unsafe ones.

Nuno Martins
Performance Period: 01/01/2022 - 12/31/2024
Institution: University of Maryland
Sponsor: National Science Foundation
Award Number: 2135561
Collaborative Research: CPS: Medium: ASTrA: Automated Synthesis for Trustworthy Autonomous Utility Services
Lead PI:
Nuno Martins
Abstract

Large-scale systems with societal relevance, such as power generation systems, are increasingly able to leverage new technologies to mitigate their environmental impact, e.g., by harvesting energy from renewable sources. This NSF CPS project aims to investigate methods and computational tools to design a new user-centric paradigm for energy apportionment and distribution and, more broadly, for trustworthy utility services. In this paradigm, distributed networked systems will assist the end users of electricity in scheduling and apportioning their consumption. Further, they will enable local and national utility managers to optimize the use of green energy sources while mitigating the effects of intermittence, promote fairness, equity, and affordability. This project pursues a tractable approach to address the challenges of modeling and designing these large-scale, mixed-autonomy, multi-agent CPSs. The intellectual merits include new scalable methods, algorithms, and tools for the design of distributed decision-making strategies and system architectures that can assist the end users in meeting their goals while guaranteeing compliance with the fairness, reliability, and physical constraints of the design. The broader impacts include enabling the automated design of distributed CPSs that coordinate their decision-making in many applications, from robotic swarms to smart manufacturing and smart cities. The research outcomes will also be used in K-12 and undergraduate STEM outreach efforts.

The proposed framework, termed Automated Synthesis for Trustworthy Autonomous Utility Services (ASTrA), addresses the design challenges via a three-pronged approach. It uses population games to model the effect of distributed decision-making infrastructures (DMI) on large populations of strategic agents. DMIs will be realized via dedicated networked hybrid hardware architectures and algorithms we seek to design. ASTrA further introduces a systematic, layered methodology to automate the design, verification, and validation of DMIs from expressive representations of the requirements. Finally, it offers a set of cutting-edge computational tools to facilitate our methodology by enabling efficient reasoning about the interaction between discrete models, e.g., used to describe complex missions or embedded software components, and continuous models used to describe physical processes. The evaluation plan involves experimentation on a real testbed designed for zero-net-energy applications.

Nuno Martins
Performance Period: 04/01/2022 - 03/31/2025
Institution: University of Maryland
Sponsor: National Science Foundation
Award Number: 2139713
Collaborative Research: CPS: Medium: Mutualistic Cyber-Physical Interaction for Self-Adaptive Multi-Damage Monitoring of Civil Infrastructure
Lead PI:
Nora El-Gohary
Co-Pi:
Abstract

This project aims to enable mutualistic interaction of cyber damage prognostics and physical reconfigurable sensing for mutualistic and self-adaptive cyber-physical systems (CPS). Drawing inspiration from mutualism in biology where two species interact in a way that benefits both, the cyber and the physical interact in a way that they simultaneously benefit from and contribute to each other to enhance the ability of the CPS to predict, reconfigure, and adapt. Such interaction is generalizable, allowing it to enhance CPS applications in various domains. In the civil infrastructure systems domain, the mutualistic interaction-enabled CPS will allow for reconfiguring a single type of sensor, adaptively based on damage prognostics, to monitor multiple classes of infrastructure damages ? thereby improving the cost-effectiveness of multi-damage infrastructure monitoring by reducing the types and number of sensors needed and maximizing the timeliness and accuracy of damage assessment and prediction at the same time. Enabling cost-effective multi-damage monitoring is promising to leapfrog the development of safer, more resilient, and sustainable infrastructure, which would stimulate economic growth and social welfare for the benefit of the nation and its people. This project will also contribute to NSF?s commitment to broadening participation in engineering (BPE) by developing innovative, interdisciplinary, and inclusive BPE programs to attract, train, and reward the next-generation engineering researchers and practitioners who are capable creators of CPS technology and not only passive consumers, thereby enhancing the U.S. economy, security, and well-being.

The envisioned CPS includes three integrated components: (1) data-driven, knowledge-informed deep learning methods for generalizable damage prognostics to predict the onset and propagation of infrastructure damages, providing information about target damages to inform reconfigurable sensing, (2) signal difference maximization theory-based reconfigurable sensing methods to optimize and physically control the configurations of the sensors to actively seek to monitor each of the predicted target damages, providing damage-seeking feedback to inform damage prognostics, and (3) quality-aware edge cloud computing methods for efficient and effective damage information extraction from raw sensing signals, serving as the bridge between damage prognostics and reconfigurable sensing. The proposed CPS will be tested in multi-damage monitoring of bridges using simulation-based and actual CPS prototypes, and would be generalized to monitoring other civil infrastructure in the future. The proposed CPS methods have the potential to transform the way we design, create, and operate CPS to enable the next-generation CPS that have greater predictive ability, reconfigurability, and adaptability.

Nora El-Gohary
Performance Period: 08/01/2023 - 07/31/2026
Institution: University of Illinois at Urbana-Champaign
Sponsor: National Science Foundation
Award Number: 2305883
Collaborative Research: CPS: Medium: Timeliness vs. Trustworthiness: Balancing Predictability and Security in Time-Sensitive CPS Design
Lead PI:
Ning Zhang
Abstract

Many cyber-physical systems (CPS) have real-time (RT) requirements. For these RT-CPS, such as a network of unmanned aerial vehicles that deliver packages to customers? homes or a robot that performs/aides in cardiac surgery, deadline misses may result in economic losses or even fatal consequences. At the same time, as these RT-CPS interact with, and are depended on by, humans, they must also be trustworthy. The goal of this research is to design secure RT-CPS that are less complex, easier to analyze, and reliable for critical application domains such as defense, medicine, transportation, manufacturing, and agriculture, to name just a few. Since RT-CPS now permeate most aspects of our daily lives, especially in the smart city and internet-of-things (IoT) context, this research will improve confidence in automated systems by users. Research results will be disseminated to both academia and industry, and permit timely adoption since the hardware required in this research is already publicly available. This project will result in a pipeline of engineers and computer scientists who are well-versed in the interdisciplinary nature of securing RT-CPS, as well as course modules and red-teaming exercises for undergraduate students in all engineering disciplines and interactive learning modules and internship experience for K-12 students in D.C., Detroit, Dallas, and St. Louis.

The goal of this research is to design secure RT-CPS from the ground up while explicitly accounting for physical dynamics of said RT-CPS at runtime to achieve resilience via prevention and detection of, and recovery from, attacks. This will be accomplished by (i) securing the scheduling infrastructure from the ground up, (ii) using a formal framework for trading off security against timeliness while accounting for system dynamics, and for the cost of security to be explicitly quantified, and (iii) performing state- and function-dependent on-demand recovery. Said RT-CPS will be able to proactively prevent attacks using moving target defenses, as well as detect and recover from attacks that cannot be avoided. This research will pave the way for RT-CPS and internet-of-things (IoT) to be implemented with confidence: their timely and correct operation guaranteed. Specific contributions of this research are: (i) a trusted scheduling infrastructure that can protect the integrity of the real-time tasks, the scheduler, its task queues, and I/O, and which can recover from (intentional) errors, (ii) a probabilistic real-time/security co-design framework that exploits trusted execution to protect the security of the real-time tasks, (iii) novel schedulability analysis techniques, (iv) an incremental recovery mechanism for continuous operation, and (v) validation on automated ground vehicles, drones, and robot arms. Contributions expanding the knowledge base will be made to the fields of CPS, IoT, real-time systems, security, and control systems.

Ning Zhang
Performance Period: 02/01/2021 - 01/31/2025
Institution: Washington University
Sponsor: National Science Foundation
Award Number: 2038995
Collaborative Research: CPS: Medium: RUI: Cooperative AI Inference in Vehicular Edge Networks for Advanced Driver-Assistance Systems
Lead PI:
Shen Shyang Ho
Abstract

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.
 

Shen Shyang Ho
Performance Period: 10/01/2021 - 11/07/2022
Institution: Rowan University
Sponsor: National Science Foundation
Award Number: 2128341
CPS: Medium: Coupled cAscade Modeling, Prevention, and Recovery (CAMPR): When Graph Theory meets Trajectory Sensitivity
Lead PI:
Nilanjan Ray Chaudhuri
Co-Pi:
Abstract

The proposed research focuses on cascading failures in electrical energy cyber-physical systems (CPS), which is a critical infrastructure of our nation. Cascading failures, where the failure of one or few components causes a wide-spread failure of the interconnected system, is a major cause of blackouts in power grids. The mechanism of such failures is highly complex as it involves the physical layer of the grid (e.g. generators, transmission lines, etc.) and the cyber layer (e.g. communication and control elements) in a coupled manner. This is a very important problem to investigate as cascading failures can cost our economy billions of dollars. This project takes a holistic view at taming cascading failures in electrical energy CPS. The proposed research has two tightly coupled thrust areas. Thrust 1 aims at an accurate understanding of the cascading failure mechanism and its prevention, while Thrust 2 focuses on recovery following blackouts under uncertainty of failure locations. Theory of trajectory sensitivity and graph theory are leveraged to develop a fundamental understanding of cascading failures in energy CPS, which can be applied to other CPSs where the physical system is dynamic in nature and the failure propagation in the physical system and the cyber system are coupled. The proposed preventive control strategy can protect critical infrastructures from large-scale failures and facilitate higher resiliency, whereas the proposed recovery strategy is applicable in the aftermath of a blackout caused by cascades, natural disasters, or other events, which will reduce downtime of the critical infrastructure. In support of the Broadening Participation in Computing initiative among women, the proposed research will be integrated into the one-week summer camps offered by the School of EECS at Penn State. Presentations about this research will be given to high school girls over the course of one week in the 2019 camps, and then camps focused on curriculum on the topic of this research will be offered in 2020 and 2021.

The proposed research has two key objectives (a) develop an accurate understanding of the cascading failure mechanism and its prevention, and (b) develop a recovery plan following blackouts under uncertainty of failure locations and budget constraints. The quasi-steady-state (QSS) model of power grid used in literature for studying cascade propagation produces inaccurate results towards the later stages of blackouts, whereas a fully dynamic model is impractical for large-scale statistical analyses. To solve this, a 'temporally hybrid' and a 'spatio-temporally hybrid' model are proposed, which quantify the stress of the grid at the systems level and the component level, respectively, using trajectory sensitivity theory, and appropriately switch from the QSS to the dynamic model. Next, a unified graph-based model for interdependent power grid and communication systems is developed, which takes into account several special features of the legacy Supervisory Control and Data Acquisition (SCADA) system along with the modern Wide-Area Monitoring, Protection, and Controls (WAMPAC) system, and the observability and controllability they provide for the CPS. Furthermore, a stability-constrained remedial action scheme for cascade prevention is proposed. Finally, a new approach for progressive assessment and recovery, which leverages the hybrid power grid models and the unified communication network model, is proposed in the presence of budget constraints and failure uncertainties.

Nilanjan Ray Chaudhuri
Performance Period: 09/01/2018 - 08/31/2024
Institution: Pennsylvania State University
Sponsor: National Science Foundation
Award Number: 1836827
Subscribe to