CCTA 2020 is pleased to offer workshops on topics in control technology and applications. These tutorials are proposed, organized and delivered by international experts. Information on the workshops is given below. For additional information, contact the Workshop Chair: Sergey Nersesov (firstname.lastname@example.org).
Information about registration is available here.
- Workshop attendance requires a separate registration payment.
- Workshop fees are
$120$40 (before June 30) or $150$50 (after July 1).
- Participants from W1 can join either W2/ W3 in the afternoon session.
- The workshop will be canceled if the registration number of participants of that workshop is insufficient. Participants will be invited to join other workshop or to have a refund.
W1: Machine Learning for Scalable, Reliable and Online Design and Decision Making (August 23, 9:00-13:30)
Organizer: Mahdi Imani, George Washington University
Organizer: Seyede Fatemeh Ghoreishi, University of Maryland
Abstract: Demand for learning and decision making is higher than ever before. Autonomous vehicles need to learn how to ride safely by recognizing pedestrians, traffic signs, and other cars, or in cyber-physical systems, one needs to process a large amount of data for proper learning and decision making, while continuously adapting the learning process or strategies according to possible gradual (e.g., natural or aging process) or sudden (e.g., faults or malicious attacks) changes in systems. Despite several advances made in learning and decision making in recent years, unrealistic assumptions, inefficiency and lack of interpretability combined with unavoidable ethical, economic, and physical constraints avoid the applicability of the existing techniques in many practical problems. This workshop will focus on three main topics:
1) The first topic will be around Bayesian optimization techniques for enhancing the reliability, speed, and efficiency of design and decision-making processes. These include developing online/non-stationary, dimensionality reduction and multi-fidelity Bayesian optimization techniques to go beyond the existing techniques;
2) The second topic will be around reinforcement learning and how Bayesian statistical frameworks can allow going beyond the existing learning techniques and enabling online/real-time self-learning frameworks that are highly scalable, capable of considering various sources of uncertainty, acting safe and making informative decisions in non-stationary environments;
3) The last topic will be around our developed non-stationary risk-based time-dependent classification techniques to overcome the deterministic decision making and unrealistic assumption regarding stationarity of the process, a critical factor in dealing with most practical domains.
W2: Practical Methods for Real-World Control Systems (August 23, 13:00-17:30)
Organizer: Daniel Abramovitch, Agilent Technologies
Abstract: 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. The workshop is designed to be useful to industry practitioners wishing to apply more advanced control methods as well as academics wishing to make their algorithms more applicable to real world problems.
W3: State-of-the-art Applications of Model Predictive Control (August 23, 9:00-17:00)
Organizer: Martina Mammarella, National Research Council of Italy
Organizer: Mohammadreza Chamanbaz, Singapore University of Technology and Design
Organizer: Fabrizio Dabbene, CNR-IEIIT
Abstract: Aim of this workshop is to present state-of-the-art applications of model predictive control (MPC), because of its long tradition of success as a very powerful and versatile advanced control technique and the growing interest shown by industry in a large variety of application domains. Emphasis will be given to highlighting the benefits of exploiting these advanced control techniques and the main challenges tackled when innovative and promising theoretical approaches have to be combined and have to comply with application requests and limitations. The range of applications that will be presented in the workshop includes virtual vehicles and driving simulators, personalized medical treatment, attack detection in cyber-physical systems, unmanned spacecraft maneuvers, Unmanned Aerial Vehicles (UAVs) for agriculture 4.0, autonomous driving. During the workshop, the attendee will be driven through several thrilling and promising applications, each one exploiting a different MPC techniques, ad-hoc tailored for complying with applied domain needs and available computation capabilities.
- More information is available here.