MENU

Alisa Rupenyan

Dr.
Alisa Rupenyan
PI
ZHAW
rupn@zhaw.ch
Curriculum Vitae
I’m excited about interdisciplinary research connecting machine learning and control theory, and opportunities for impact in major application domains.

Alisa Rupenyan is the Rieter endowed professor at  the Zurich University for Applied Sciences (ZHAW) and Head of the Industrial AI group at the ZHAW Center for AI. She leads research projects in the intersection between process optimisation, industrial control, and machine learning for applications strongly connected to manufacturing.

Previously, she led application development in the Zurich-​based startup Qualysense AG for fast grain-​sorting robots using machine learning techniques for high-​dimensional data. Her Ph.D. is in the field of time-​resolved laser spectroscopy from the Vrije Universteit Amsterdam (2009) and her MSc degree is in Laser Physics from the University of Sofia. 

Scientific Publications

Published
Autonomous and data-efficient optimization of turning processes using expert knowledge and transfer learning
Journal of Materials Processing Technology
Vol 303 Pages 117540
Markus Maier, Hannes Kunstmann, Ruben Zwickler, Alisa Rupenyan, Konrad Wegener
Collection
Published
Sequential Quadratic Programming-based Iterative Learning Control for Nonlinear Systems
ArXiv
Samuel Balula, Efe C. Balta, Dominic Liao-McPherson, Alisa Rupenyan, John Lygeros
Collection
Published
Stress flow guided non-planar print trajectory optimization for additive manufacturing of anisotropic polymers
Additive Manufacturing
Xavier Guidetti, Efe C. Balta, Yannick Nagel, Hang Yin, Alisa Rupenyan, John Lygeros
Collection
Published
Meta-Learning Priors for Safe Bayesian Optimization
Proceedings of The 6th Conference on Robot Learning
Pages 205-237
Jonas Rothfuss, Christopher Koenig, Alisa Rupenyan, Andreas Krause
Collection Arxiv.org
Published
Efficient sample selection for safe learning
ArXiv
Marta Zagorowska, Efe C. Balta, Varsha N. Behrunani, Alisa Rupenyan, John Lygeros
Collection
Published
Drone-based Volume Estimation in Indoor Environments
IFAC World Congress 2023
Samuel Balula, Dominic Liao-McPherson, Stefan Stevsic, Alisa Rupenyan, John Lygeros
Collection
Published
Information-Operation Technology Integration in Industrial Cyberphysical Systems
Computer
Vol 55 No 11 Pages 115-118
Mohammad H. Mamduhi, Efe C. Balta, Alisa Rupenyan, John Lygeros
Collection
Published
Data-Driven Process Optimization of Fused Filament Fabrication based on In Situ Measurements
ArXiv
Xavier Guidetti, Marino Kühne, Yannick Nagel, Efe C. Balta, Alisa Rupenyan, John Lygeros
Collection
Published
Controller-Aware Dynamic Network Management for Industry 4.0
IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society
Efe C. Balta, Mohammad H. Mamduhi, John Lygeros, Alisa Rupenyan
Collection
Published
In-layer Thermal Control of a Multi-layer Selective Laser Melting Process
2022 European Control Conference (ECC)
Pages 1678 - 1683
Dominic Liao-McPherson, Efe C. Balta, Ryan Wüest, Alisa Rupenyan, John Lygeros
Doi.org Collection
Published
On Robustness in Optimization-Based Constrained Iterative Learning Control
IEEE Control Systems Letters
Vol 6 Pages 2846-2851
Dominic Liao-McPherson, Efe C. Balta, Alisa Rupenyan, John Lygeros
Doi.org Collection
Published
Safety-Aware Cascade Controller Tuning Using Constrained Bayesian Optimization
EEE Transactions on Industrial Electronics
Mohammad Khosravi, Christopher Koenig, Markus Maier, Roy Smith, John Lygeros, Alisa Rupenyan
Doi.org Collection
Published
Learning-Based Repetitive Precision Motion Control with Mismatch Compensation
60th IEEE Conference on Decision and Control (CDC 2021)
Pages 3605-3610
Efe C. Balta, Kira Barton, Dawn Tilbury, Alisa Rupenyan, John Lygeros
Doi.org Collection
Published
Performance-based Trajectory Optimization for Path Following Control Using Bayesian Optimization
2021 60th IEEE Conference on Decision and Control (CDC)
Pages 2116-2121
Alisa Rupenyan, Mohammad Khosravi, John Lygeros
Doi.org Collection
to Appear
Batch Model Predictive Control for Selective Laser Melting
2022 European Control Conference (ECC)
Efe C. Balta, Alisa Rupenyan, John Lygeros
Doi.org Collection
Plasma Spray Process Parameters Configuration using Sample-efficient Batch Bayesian Optimization
IEEE International Conference on Automation Science and Engineering (CASE)
Xavier Guidetti, Alisa Rupenyan, Lutz Fassl, Majid Nabavi, John Lygeros
Collection
Safe and Efficient Model-free Adaptive Control via Bayesian Optimization
IEEE International Conference on Robotics and Automation (ICRA 2021)
Christopher Koenig, Matteo Turchetta, John Lygeros, Alisa Rupenyan, Andreas Krause
Collection

Research projects

Title
Principal Investigators

Data-assisted model predictive control with applications to industrial processes

Alisa Rupenyan, John Lygeros

Summary

Manufacturing tasks are often repetitive, involving the same processing steps being repeated over and over to produce identical parts. This makes them well suited for data driven methods that exploit repetition, like the ones developed for autonomous racing. This project addresses deploying the data-assisted predictive control methods in manufacturing applications. The resulting optimisation problems are often of formidable complexity, making them challenging to solve in real time. This calls for efficient solution methods that inherit the stability and performance guarantees of the predictive control design even when the search for the optimal solution has to be terminated prematurely.

People involved

Alisa Rupenyan, John Lygeros, Dominic Liao-McPherson
Data-assisted model predictive control with applications to industrial processes
Alisa Rupenyan, John Lygeros

Manufacturing tasks are often repetitive, involving the same processing steps being repeated over and over to produce identical parts. This makes them well suited for data driven methods that exploit repetition, like the ones developed for autonomous racing. This project addresses deploying the data-assisted predictive control methods in manufacturing applications. The resulting optimisation problems are often of formidable complexity, making them challenging to solve in real time. This calls for efficient solution methods that inherit the stability and performance guarantees of the predictive control design even when the search for the optimal solution has to be terminated prematurely.

Alisa Rupenyan, John Lygeros, Dominic Liao-McPherson
147
66485d7b-630c-43ea-82da-87c0dd002cf0

Predictive Control for Additive Manufacturing

Alisa Rupenyan, Colin Jones, John Lygeros

Summary

Selective laser melting is an additive manufacturing technology that uses a laser to melt powdered metal into a solid structure based on a sliced 3D CAD model. Currently, such processes are only controlled by setting the process parameters and set points in advance, following multiple process optimisation trials. In this project, process parameters will be optimized with a data-driven closed loop control approach, based on combination of predictive and iterative learning control.

People involved

Colin Jones
Alisa Rupenyan, Colin Jones, John Lygeros
Predictive Control for Additive Manufacturing
Alisa Rupenyan, Colin Jones, John Lygeros

Selective laser melting is an additive manufacturing technology that uses a laser to melt powdered metal into a solid structure based on a sliced 3D CAD model. Currently, such processes are only controlled by setting the process parameters and set points in advance, following multiple process optimisation trials. In this project, process parameters will be optimized with a data-driven closed loop control approach, based on combination of predictive and iterative learning control.

Colin Jones
Alisa Rupenyan, Colin Jones, John Lygeros
108
4cf5b44b-ef93-4b8a-bf72-5400eacf6831

Framework for industrial control of CPS

Alisa Rupenyan, John Lygeros

Summary

This project is focused on the development of a data-driven framework for self-maintenance and self-optimization for autonomous (robot-assisted) manufacturing. The framework will be characterized by three main components:

  1. Sensing and data processing
  2. Detection of faults and warnings using the extracted features 
  3. Process control and optimization (maintaining safety, optimizing performance

The acquired process data will be used to optimise the manufacturing process by optimising trajectories of the assisting robots, and process parameters, to improve manufacturing productivity.

People involved

Jürg P. Keller
Alisa Rupenyan, John Lygeros, Jürg P. Keller
Framework for industrial control of CPS
Alisa Rupenyan, John Lygeros

This project is focused on the development of a data-driven framework for self-maintenance and self-optimization for autonomous (robot-assisted) manufacturing. The framework will be characterized by three main components:

  1. Sensing and data processing
  2. Detection of faults and warnings using the extracted features 
  3. Process control and optimization (maintaining safety, optimizing performance

The acquired process data will be used to optimise the manufacturing process by optimising trajectories of the assisting robots, and process parameters, to improve manufacturing productivity.

Jürg P. Keller
Alisa Rupenyan, John Lygeros, Jürg P. Keller
107
74f86789-d97c-4673-a478-7907c8fc7c98

Risk aware Bayesian optimization with applications to adaptive control

Alisa Rupenyan, Andreas Krause

Summary

Our goal is to develop novel algorithms for risk-aware Bayesian optimization and demonstrate them in a case study for high-precision linear drives requiring position accuracy and stability with less than 5 nm deviation. For this system, as for many other applications, it is crucial to optimize expected performance and ensure reliable outcomes.  We will develop computationally efficient algorithms trading expected performance with the variance in the outcome, considering risk measures on the optimization constraints, and compiling thi acquisition functions into neural network policies.

People involved

Andreas Krause
Alisa Rupenyan, Andreas Krause
Risk aware Bayesian optimization with applications to adaptive control
Alisa Rupenyan, Andreas Krause

Our goal is to develop novel algorithms for risk-aware Bayesian optimization and demonstrate them in a case study for high-precision linear drives requiring position accuracy and stability with less than 5 nm deviation. For this system, as for many other applications, it is crucial to optimize expected performance and ensure reliable outcomes.  We will develop computationally efficient algorithms trading expected performance with the variance in the outcome, considering risk measures on the optimization constraints, and compiling thi acquisition functions into neural network policies.

Andreas Krause
Alisa Rupenyan, Andreas Krause
98
09023dea-22c0-46b6-aa47-70bfde44c173

News & Insights