The gradual deployment of self-driving cars will inevitably lead to the emergence of a new important class of cyber-physical-human systems where autonomous vehicles interact with human-driven vehicles via on-board sensors or vehicle-to-vehicle communications. Reinforcement learning along with control theory can help meet the safety requirements for real-time decision making and Level 5 autonomy in self-driving vehicles. However, it is widely known that conventional reinforcement learning policies are vulnerable to adversarial or non-adversarial perturbations to their observations, similar to adversarial examples for classifiers and/or reward (packet) drops of the learning. Such issues are exacerbated by concerns of addressing resiliency as the use of open communication and control platforms for autonomy becomes essential, and as the industry continues to invest in such systems. Decision making mechanisms, designed to incorporate agility with the help of reinforcement learning, allow self-adaptation, self-healing, and self-optimization. This research will contribute and unify the body of knowledge of several diverse fields including reinforcement learning, security, automatic control, and transportation for resilient autonomy with humans-in-the-loop.
In this project, to counter action and observation manipulation as well as reward drops, the principal investigators will leverage proactive switching policies that aim (i) to provide robustness to adversarial inputs and reward drops in the closed-loop reinforcement learning mechanisms, (ii) to increase the cost of manipulation by deception, (iii) to limit the exposure of vulnerable actions and observations, and (iv) to provide stability, optimality, and robustness guarantees. Ultimately, the investigators will develop fundamental contributions to each of the above-mentioned fields and amalgamate these fields to provide a unique synthesis framework. The outcomes of this project will increase levels of confidence in autonomous technologies from ethical perspectives by providing an underpinning for curtailing accidents. The proposed framework can be extended to other key enablers of the global economy, including smart and connected cities, healthcare, and networked actions of smart systems while decreasing environmental pollution and minimizing the adverse environmental impacts on human health. The project will train the next generation of students from various levels, ages, and cultures through well-coordinated, level appropriate involvement in research and educational activities while providing a unique opportunity for the students to appreciate efficient, autonomous, and low-cost designs. This project will also contribute to future engineering curricula, pursue a substantial integration of research and education, and provide opportunities to engage students from the underrepresented group.
Kyriakos G. Vamvoudakis was born in Athens, Greece. He received the Diploma (a 5-year degree, equivalent to a Master of Science) in Electronic and Computer Engineering from the Technical University of Crete, Greece in 2006 with highest honors. After moving to the United States of America, he studied at The University of Texas at Arlington with Frank L. Lewis as his advisor, and he received his M.S. and Ph.D. in Electrical Engineering in 2008 and 2011 respectively. From May 2011 to January 2012, he was working as an Adjunct Professor and Faculty Research Associate at the University of Texas at Arlington and at the Automation and Robotics Research Institute. During the period from 2012 to 2016 he was project research scientist at the Center for Control, Dynamical Systems and Computation at the University of California, Santa Barbara. He was an assistant professor at the Kevin T. Crofton Department of Aerospace and Ocean Engineering at Virginia Tech until 2018.
He currently serves as the Dutton-Ducoffe Endowed Professor at The Daniel Guggenheim School of Aerospace Engineering at Georgia Tech. He holds a secondary appointment in the School of Electrical and Computer Engineering. His expertise is in reinforcement learning, control theory, game theory, cyber-physical security, bounded rationality, and safe/assured autonomy.
Dr. Vamvoudakis is the recipient of a 2019 ARO YIP award, a 2018 NSF CAREER award, a 2018 DoD Minerva Research Initiative Award, a 2021 GT Chapter Sigma Xi Young Faculty Award and his work has been recognized with best paper nominations and several international awards including the 2016 International Neural Network Society Young Investigator (INNS) Award, the Best Paper Award for Autonomous/Unmanned Vehicles at the 27th Army Science Conference in 2010, the Best Presentation Award at the World Congress of Computational Intelligence in 2010, and the Best Researcher Award from the Automation and Robotics Research Institute in 2011. He is a member of Tau Beta Pi, Eta Kappa Nu, and Golden Key honor societies and is listed in Who's Who in the World, Who's Who in Science and Engineering, and Who's Who in America. He has also served on various international program committees and has organized special sessions, workshops, and tutorials for several international conferences. He currently is a member of the Technical Committee on Intelligent Control of the IEEE Control Systems Society, a member of the Technical Committee on Adaptive Dynamic Programming and Reinforcement Learning of the IEEE Computational Intelligence Society, a member of the IEEE Control Systems Society Conference Editorial Board, an Associate Editor of: Automatica; IEEE Transactions on Automatic Control; IEEE Transactions on Neural Networks and Learning Systems; IEEE Computational Intelligence Magazine; IEEE Transactions on Systems, Man, and Cybernetics: Systems; IEEE Transactions on Artificial Intelligence; Neurocomputing; Journal of Optimization Theory and Applications; and of Frontiers in Control Engineering-Adaptive, Robust and Fault Tolerant Control. He had also served as a Guest Editor for, IEEE Transactions on Automation Science and Engineering (Special issue on Learning from Imperfect Data for Industrial Automation); IEEE Transactions on Neural Networks and Learning Systems (Special issue on Reinforcement Learning Based Control: Data-Efficient and Resilient Methods); IEEE Transactions on Industrial Informatics (Special issue on Industrial Artificial Intelligence for Smart Manufacturing); and IEEE Transactions on Intelligent Transportation Systems (Special issue on Unmanned Aircraft System Traffic Management). He is also a registered Electrical/Computer engineer (PE), a member of the Technical Chamber of Greece, an Associate Fellow of AIAA, and a Senior Member of IEEE.
Rapid growth in additive manufacturing (AM) has improved the accessibility, customizability and affordability of making products using personal printers. Designs can be developed by consumers, if they have enough knowledge of mechanical design and 3D modeling, or they can be obtained from third parties. However, the process of translating a design to a program that can be successfully executed by a 3D printer often requires specialized domain knowledge that many end-users currently lack. In the meantime, lots of objects, which may be very similar or identical to what the non-technical user aims to design and print, have been produced by experts in industry and, hence, millions of proven part designs already exist. This research aims to fill the above-mentioned gap by developing a theoretically sound and practically deployable, domain-specific online search engine, called Srch3D, for 3D models. Srch3D will provide the non-technical end-users with a user-friendly solution to efficiently search for their components in a large repository of existing proven part designs.
The Internet of Things (IoT) is described as networks of small physical devices, embedded with sensors, software, and other technologies, that easily exchange data with other devices and systems over the Internet. The convergence of traditional technologies from wireless networking, control systems, and automation with miniaturization and low-powered devices contributed to the development of IoT, spurred on by strong demand and rapid growth in smart home automation and smart cities. Affordable interoperable IoT systems are increasingly ubiquitous in daily life. These IoT devices, working closely together, orchestrate a range of tasks, increasingly used for such activities as programmable personalized control of heating, cooling, and security in homes and offices. As these IoT devices become more capable, more computationally demanding tasks can be performed by these devices singly or in combination as a local distributed network bringing computing closer to the location where needed to improve responsiveness, i.e., at the edges of the Internet. The challenge is to ensure the highly capable, timely performance, seamless collective operation of IoT devices with edge computing and even cloud services as an efficient purposeful system.
This project studies the relationships between system resource utilization and energy efficiency in various edge and IoT systems in order to better understand how to optimize the key performance parameters of edge computing systems. This project explores mitigating the inefficiency in edge systems through a data-driven approach. Specifically, the primary research directions include: (1) analyzing the power inefficiency in different edge systems and develop a data-driven energy-aware framework for runtime edge and IoT applications, (2) tailoring the edge runtime framework including parts of data and control planes to reveal hidden dependencies, and (3) scaling and evaluating this framework and methodology in high-fidelity realistic test scenarios.
This Cyber-Physical Systems (CPS) grant will study smart tracking systems on scooters for ensuring safe and smooth interaction with other vehicles and pedestrians on the road. The smart system consists of inexpensive sensors, active sensing based estimation algorithms, and deep learning based robust image processing to enable trajectory tracking of all nearby vehicles on the road. If the danger of a scooter-vehicle collision is detected, an audio-visual alert is automatically provided to the car driver to make them aware of the presence of the scooter. The system also monitors the scooter rider's behavior, provides real-time feedback to improve rider compliance with traffic signals and sidewalk rules, and documents the information as a part of the rider's safety record. The key attractive features of the system are that it is inexpensive (< $500), is immediately useful on today's roads without requiring the vehicles on the road to be equipped with additional technology, and is potentially commercializable. The project contributes to the society by improving safety of micro-transportation systems, and broadens participation in computing via undergraduate research activities and promoting significant cross-disciplinary collaboration between faculty in engineering, computer science and human factors.
Piloting an aircraft is popularly described as hours of abject boredom punctuated by periods of abject terror. Similarly, a spacecraft in transit to a distant target remains largely dormant but for periodic heightened activity required for maintenance and staying on course. Aircraft and spacecraft are complex systems of systems that must seamlessly work together, switching control through a carefully orchestrated hierarchy representing different levels of abstraction, e.g., exemplified by different timescales for events. Each on-board system presents its own verification challenge; verifying that the symphony of all of them playing together at the same time, in the face of potentially unexpected environmental inputs, is particularly daunting. We can supplement design-time verification with efficient runtime verification engines, but they need to grow to be able to reason about the hierarchical nature of complex systems-of-systems, where single requirements may need to encapsulate multiple levels of abstraction. The final result must be able to execute in real time, within system resource constraints. Existing tools for runtime verification aren't capable of obeying constraints imposed by running them on real systems (or in real missions), and don't have parameters to focus their computational demands on the tasks most impactful on system safety. Achieving safe CPS depends on growing the tools and algorithms of real-time verification to integrate realistic safety checks into their control architectures and dynamic environments.
This project adapts techniques from formal methods, control theory, hardware-software integration, and software engineering to design runtime monitors that inspect cyber-physical systems of systems without interfering with their normal operation. The project designs, analyzes, and implements fundamental runtime verification techniques by dealing with three general and orthogonal problems: mixed-abstraction-level granularity in specifications, resource-awareness to ensure non-intrusiveness of runtime monitors, and augmenting monitors with model-prediction to enable on-deadline mitigation triggering. Key innovations stem from this rigorous foundation in establishing a new formal semantics for hierarchical, mixed-abstraction-level specification, and evaluating formal specifications without interfering with the system's normal operation, while maximizing utilization of resources within realistic constraints of embedded CPS. The project generalizes the new theory into specification patterns for hierarchical functional requirements and synthesize predictive models to enable better, more automated creation of runtime verification configurations to meet scalability demands of modern CPS. Flight tests of small aircraft swarms are used to validate this approach.
Origami-inspired structures that fold flat sheets along creases with designed patterns to create transformable structures have been widely applied in science and engineering, especially in space operations, e.g., for deployment of folded solar panels equipped on launched satellites. Although the deformation process plays an essential role in transitions between the origami states, few studies focus on the control and actuation of the origami folding mechanism toward high autonomy of the deformation process. This project aims to develop an autonomous origami-inspired transformable system to enable high-performance deformation maneuvering in space operations requiring frequent and/or time-responsive shape changes. The integrative research incorporating theory, analysis, algorithm development, and experimental verification will contribute to a theoretical and experimental platform to advance the autonomy of origami system operations in challenging environments. The research products will have significant impacts on the proliferated satellite marketplace where low mass, small volume, and adaptable structures/subsystems of space vehicles are in demand. Going beyond the applications in space missions, origami-inspired transformable systems have much broader applications in science and engineering. Moreover, the collaboration of experts in both cyber and physical areas promotes the creation of interdisciplinary products that bridge different disciplines.
Origami-inspired structures that fold flat sheets along creases with designed patterns to create transformable structures have been widely applied in science and engineering, especially in space operations, e.g., for deployment of folded solar panels equipped on launched satellites. Although the deformation process plays an essential role in transitions between the origami states, few studies focus on the control and actuation of the origami folding mechanism toward high autonomy of the deformation process. This project aims to develop an autonomous origami-inspired transformable system to enable high-performance deformation maneuvering in space operations requiring frequent and/or time-responsive shape changes. The integrative research incorporating theory, analysis, algorithm development, and experimental verification will contribute to a theoretical and experimental platform to advance the autonomy of origami system operations in challenging environments. The research products will have significant impacts on the proliferated satellite marketplace where low mass, small volume, and adaptable structures/subsystems of space vehicles are in demand. Going beyond the applications in space missions, origami-inspired transformable systems have much broader applications in science and engineering. Moreover, the collaboration of experts in both cyber and physical areas promotes the creation of interdisciplinary products that bridge different disciplines.
This project proposes a novel cyber-physical paradigm for enhancing the security in networks of advanced robots from external malicious cyber attacks (and internal non-malicious malfunctions as well). Such systems have tremendous potential for improved productivity, but also carry new risks: malicious actors could exploit the connectivity of the devices to carry out attacks with consequences in the physical world.
The core idea of this project is to provide a novel layer of security against such threats by designing distributed security specifications based on introspection: agents use physical-sensing capabilities to surveil the behaviors of other agents in the team in addition to the task-specific mission objective. Such specifications will offer an additional layer of protection in emerging applications with networked robots.
This project aims to create a cyber physical system for remotely controlling cellular processes in real time and leverage the biomedical potential of synthetic biology and microrobotics to create pancreatic tissue. With 114,000 people currently on the waitlist for a lifesaving organ transplant in the United States alone, the ability to directly produce patient-compatible organs, obviating the need for animal and clinical studies can revolutionize personalized medicine. Tissues in the human body such as liver, kidney, and pancreatic islets comprise cells arranged in complex patterns spanning both 2D and 3D structures. However, scaffold- and microgel-based tissue engineering approaches along with 3D bioprinting are often unable to create these complex 3D structures. In this project, the team focuses on the pancreas, which has a unique anatomical structure composed of the regular arrangement of circular cell clusters called islets. The proposed research aims at overcoming the hurdle of recreating these spatial patterns in vitro by developing a cyber physical process by which swarms of microrobots will be steered in 3D to regulate the differentiation of genetically engineered stem cells and drive these cells into forming desired pancreatic tissue. The broader impacts of this line of work are significant because it is a key first step in the synthesis of new, or the repair of ailing, human organs, providing for interactive behavior between computer controlled microrobots and genetically programmed stem cells. Manufacturing living tissue is revolutionary as it could act as a bridge between preclinical and clinical trials, to ensure better drug testing models and develop more personalized precision medicine. For pancreatic components, in particular, generating human organoids compliant with pharmaceutical standards is an exceptional challenge, and current methods are laborious, time-consuming, expensive, and irreproducible, which has caused industry to shy away from this organ. The education and outreach activities that complement the research component of this project address the need to increase underrepresented minorities (that is, women and under-served populations) in problem-solving research careers, like Engineering in K-12.