Smart Control Engineering (SCE), Digital Twins, and Industrial AI (IAI) – A New Research Frontier
Half-Day: 8:30am-1:00pm Pacific
Experienced control engineers and researchers agree that before designing a controller, we need to ask two questions 1) “What do we have/know?” and 2) “What do we want?” and after we have designed a controller, we also need to ask two questions 1) “How optimal?” and 2) “How robust?”. With the emerging wave of “Digital Transformation” such as Industry 4.0, I promote asking the third question: “How smart?”. This talk introduces a new frontier for control engineering: Smart Control Engineering (SCE), using Digital Twins (DT) as the enabler technology combined with IAI (industrial artificial intelligence) and breaking technologies like Deep Learning, AI, Data Analytics, Big Data, and edge computing.
For SCE, the concept of “smartness” follows the notion of the US NSF program on S&AS (smart and autonomous systems) based on the following attributes 1) Taskable; 2) Cognitive; 3) Reflective; 4) Ethical; 5) Knowledge-rich. It means that a smart control system can learn from past actions and induced errors (resilience), discover hidden patterns and anomalous behaviors at multiple time scales and reach the desired closed-loop and operation specifications. This workshop will present a case study to illustrate the SCE fundamentals enabled by DT using IAI for process control engineering.
This tutorial workshop prepares CCTA2021 our audience with:
- What is SCE – smart control engineering and how to make control systems smarter?
- Digital Twins (DT) concept, example DT platforms, and DT behavior matching algorithms, and practical implementation
- SCE control design based on DT (SOC, ITL, R2R)
- Edge computing, embedded and industrial AI applications towards SCE
- Rich future research opportunities in SCE and DT.
Organizer: Prof. Yang Quan Chen, UC Merced, firstname.lastname@example.org
Motion Planning, Control, and Learning for Autonomous Driving Systems
Half-Day, 8:30am-1:00pm Pacific
This workshop is designed to stimulate a discussion on the state of the art and roadmap for the research and application of advanced techniques on the Motion Planning, Control, and Learning for Autonomous Driving Systems. As we move to increasingly complex transportation systems and more complex urban environments, new approaches are needed to accommodate the challenges associated with agent interactions, planning and control under uncertainty, and long-tail scenarios. The intersection of motion planning, control, and learning provides opportunities to explore the solutions for these challenges and apply those solutions to real-world applications (including driver-assistance systems, connected and automated vehicles, and fully autonomous driving systems).
We will discuss the strengths and limitations of the different approaches and assist with system level design choices. We will also discuss how to leverage real world driving data to address the challenges of the motion planning and control of autonomous driving systems through different learning methods.
Organizers: Yan Chang (Lyft), Andreas Malikopoulos (University of Delaware)
Practical Methods for Real-World Control Systems
Half-Day, 8:30am-1:00pm Pacific
Rationale: The proverbial “gap” between control theory and practice has been discussed since the 1960s, but it shows no signs of being any smaller today than it was back then. Despite this, the growing ubiquity of powerful and inexpensive computation platforms, of sensors, actuators and small devices, the “Internet of Things”, of automated vehicles and quadcopter drones, means that there is an exploding application of control in the world. Any material that allows controls researchers to more readily apply their work and/or allows practitioners to improve their devices through best practices consistent with well understood theory, should be a good contribution to both the controls community and the users of control. This workshop is intended as a small but useful step in that direction.
Prerequisite skills (of participants): Undergraduate level knowledge of feedback systems, sampled data systems, and programming. An honest interest in being able to translate control theory into physical control systems.
Intended Audience: We believe that this workshop will be of great interest to three types of audience members:
- Academic researchers who are well versed in control theory but would like to learn more about issues practicing control engineers often encounter as well as techniques and methods often used outside of standard textbook solutions to enhance their students’ experience in the classroom and laboratory.
- Practicing engineers who work on physical control systems and products that use control with an interest in connecting their work to “best practices” motivated by theory.
- Students who may be interested in adding laboratory experiments to their research or want to know how to make what they have learned applicable in industry.
For each of these groups – and those that are somewhere in the intersection of them – this workshop will address the gap from both sides, so as to give the participant a more complete understanding of how it applies to their particular situation.
Topic overview: The general style for each topic will be to present the issue, discuss rational ways of thinking about a solution, and where possible, show a demo to illustrate the idea.
- Overview, a.k.a. “Mind the Gap.”
- System Models and Characterizing Them with Measurements, or why it’s both important and annoying to be discrete
- Simple Controllers for Simple Models, or why so many controllers are PIDs, and why some are not Practical Loop Design, Or Why Most Open Loops Should Be an Integrator, and How to Get There Resonances, Anti-Resonances, Filtering, and Equalization Signal Detection, Sensors, Sample Rates, and Noise (Oh My!)
- Integrating in Feedforward Control
- Ask Your Doctor: Is State Space Right for You?
- Pick a Chip, Any Chip: Or why real-time programming is too important to leave to folks who only know programming
- Closing Thoughts/Discussion
Organizer: Daniel Abramovitch
Multi-Vehicle and Assured Autonomous Control for Aerospace Applications
Full-Day, 8:30am-5:00pm, Pacific
This one day workshop will focus on current control system topics that are having an impact in the aerospace industry. The workshop will be presented by leading control systems experts from industry and academia that are involved in some of the most exciting researchand development efforts in the field of Aerospace. This workshop is intended for students and professors in search of current applications in need of solutions as well as industry and government professionals interested in potential solutions from academia and adjacent branches of the aerospace industry. This workshop is sponsored and presented by members of the IEEE CSS Technical Committee on Aerospace Controls and their collaborators. The purpose of the technical committee is to help build an international scientific community and promote awareness of outstanding achievements in the field of Aerospace Controls.
In this offering the workshop will present a sample of current topics related to the intelligent control of cooperating groups of unmanned air vehicles (UAV’s), spacecraft, drones and miniature projectiles. Our experts will present the theoretical background, rigorous methods and experimental results that are creating an exciting new chapter in field of Aerospace Control. Recent advances in adaptive and nonlinear robust control theory are used to form the basis for safe, resilient and certifiable systems of co-operative platforms. Future directions for research are included in discussion of the roles of artificial intelligence (AI) and augmented and virtual reality (AR/VR), as well as emerging applications in Aerospace Control for adversarially robust cyber resistant systems. The workshop will offer opportunities for questions and answers, and provide an open forum for discussion of applications for current theoretical advances and potential enabling technologies. The proceeds from this workshop will be donated by the organizers and presenters to help fund student awards and participation in CSS technical committee and conference activities.
Organizers: Richard Hull (Collins Aerospace), Venanzio Cichella (University of Iowa)
The Confluence of Vision and Control
Full-Day, 8:30am-5:00pm, Pacific
The use of visual sensors in feedback control has been an active topic of research for decades. As the cost of hardware lowers and computational capabilities increase, vision-based control is reaching new levels of capability and application. Recent innovations in computer vision can provide greater capabilities to control applications such as autonomous vehicles and robots. At the same time, open problems in computer vision can be solved through control theory, such as nonlinear and adaptive control. We present twelve discussions on recent work in vision-based control, the application of control to computer vision, and topics in which vision and control are uniquely intertwined. We seek to highlight recent developments and open problems that exist at the intersection of vision and control and spur further research and development in the community.
Organizers: Kaveh Fathian (MIT), Nicholas Gans (University of Texas at Arlington)