PhD Position: Learning Based Digital Twinning

Department: Systems & Control Laboratory,
Institute: Institute for Computer Science & Control, Hungary
FTE: 1.0
Start date: January 2021

Description:

This PhD position at the Systems & Control Laboratory of the Institute for Computer Science & Control (SZTAKI) in Hungary is part of a research project aiming at the development of artificial intelligence-based modelling and control methods, supported by Ministry of Innovation and Technology NRDI Office within the framework of the Autonomous Systems National Laboratory Program.

Increasing environmental and economical expectations towards many industrial sectors like (i) automotive, (ii) aerospace and (iii) precision mechatronic engineering, have led to a surge of complexity increase of engineering systems (e.g., electric and hybrid cars, aircrafts and drones, wafer scanners, etc.) as they are increasingly relying on a fusion of advanced mechanical, electrical and computer technologies. The current cutting-edge system designs exhibit complicated non-stationary, nonlinear and spatial dynamic behavior. Traditional modeling and control engineering solutions are incapable to cope with this surge of complexity, performance demands and the flood of data available for performance enhancement. On the other hand, recent advances in Artificial Intelligence (AI) methods have shown high potential in solving data-intensive high-complexity modeling and regulatory problems. A major drawback of these methods is that it is difficult to incorporate prior engineering knowledge in them, to give safety and performance guarantees, to provide interpretability and transparency of the solutions, which are essential expectations for applications in sectors (i)-(iii). This PhD research aims to establish the next generation of modeling solutions by developing a novel synergy of AI methods, which can handle the complex nature of these systems with an automated modeling framework. This PhD research aims to establish the next generation of modeling solutions by developing a novel synergy of AI methods, which can handle the complex nature of these systems with an automated modeling framework.

Main research directions:

• Efficient data-driven learning of digital twins: develop a framework that provides statistical guarantees in learning of dynamical models using both user-specified input, measured information, and existing engineering knowledge. For this purpose, deep auto-encoders and recently introduced subspace-encoders, efficient recurrent ANN model structures used in implicit learning, GPs and Bayesian learning, and neuroevolution will be investigated with the objective of automatic complexity optimization of network structures & noise models, statistical and computational efficiency and incorporation of utilization-oriented objectives (e.g., control specifications).
• Incorporation of prior knowledge and physical aspects in learning: Investigation how existing prior knowledge and physical properties, e.g., stability and dissipativity can be exploited to guide the learning process for the estimation of models that provide physical interpretability, compatible with the existing nominal first-principle models and have robust generalization capabilities.

In co-operation with industrial partners, the results of the research will be demonstrated in safe & adaptive performance enhancement of autonomous vehicles (cars and quadcopters developed at SZTAKI) and spacecrafts (in cooperation with ESA). 

The work is also part of a joint research program between SZTAKI and the Technical University of Eindhoven.    

Requirements:

We are looking for a candidate who meets the following requirements:

• You are a talented and enthusiastic young researcher.
• You have experience with or a strong background in systems and control, mathematics, signal processing. Preferably you finished a master in Systems & Control, Computer Science/AI, Mechanical Engineering or Electrical Engineering.
• You have good programming skills and experience (Python, Matlab, C/C++).
• You have good communicative skills, and the attitude to partake successfully in the work of a research team.
• You are creative and ambitious, hard-working and persistent.
• You have good command of the English language (knowledge of Hungarian is not required).

Conditions of employment

• Challenging job in a dynamic and ambitious institute and a stimulating internationally renowned research environment.
• Full-time temporary appointment for 4 years.
• Competitive salary.
• An extensive package of fringe benefits (e.g., excellent technical infrastructure, private health care support, etc.).

Information and application

More information can be obtained from: Dr. Roland Toth (toth.roland@sztaki.hu)

PhD Position: Controller Learning with Guarantees

Department: Systems & Control Laboratory,
Institute: Institute for Computer Science & Control, Hungary
FTE: 1.0
Start date: January 2021

Description:

This PhD position at the Systems & Control Laboratory of the Institute for Computer Science & Control (SZTAKI) in Hungary is part of a research project aiming at the development of artificial intelligence-based modelling and control methods, supported by Ministry of Innovation and Technology NRDI Office within the framework of the Autonomous Systems National Laboratory Program.

Increasing environmental and economical expectations towards many industrial sectors like (i) automotive, (ii) aerospace and (iii) precision mechatronic engineering, have led to a surge of complexity increase of engineering systems (e.g., electric and hybrid cars, aircrafts and drones, wafer scanners, etc.) as they are increasingly relying on a fusion of advanced mechanical, electrical and computer technologies. The current cutting-edge system designs exhibit complicated non-stationary, nonlinear, and spatial dynamic behavior. Traditional modeling and control engineering solutions are incapable to cope with this surge of complexity, performance demands and the flood of data available for performance enhancement. On the other hand, recent advances in Artificial Intelligence (AI) methods have shown high potential in solving data-intensive high-complexity modeling and regulatory problems. A major drawback of these methods is that it is difficult to incorporate prior engineering knowledge in them, to give safety and performance guarantees, to provide interpretability and transparency of the solutions, which are essential expectations for applications in sectors (i)-(iii). This PhD research aims to establish the next generation of modeling solutions by developing a novel synergy of AI methods, which can handle the complex nature of these systems with an automated modeling framework. This PhD research aims to establish the next generation of control engineering solutions by developing a novel synergy of AI methods, which can handle the complex nature of these systems with an automated controller synthesis framework.

Main research directions:

• Safe learning with performance guarantees: development of reliable and efficient learning-based adaptive controllers, i.e., algorithms that automatically learn to realize the desired behavior of an engineering system and during operation tune themselves to refine the overall performance and adapt to changes without endangering safety. Using novel data-based performance concepts, contraction theory and a stochastic learning framework, direct identification of controllers with closed-loop performance and stability guarantees is aimed to be worked out both in online and offline settings, leading to an efficient fusion of adaptive control with reinforcement learning.
• • Incorporation of prior knowledge and physical aspects: Investigation how existing prior knowledge and nominal controllers can be exploited to guide the learning process for the estimation/augmentation of controllers with closed-loop stability and performance guarantees.

In co-operation with industrial partners, the results of the research will be demonstrated in safe & adaptive performance enhancement of autonomous vehicles (cars and quadcopters developed at SZTAKI) and spacecrafts (in cooperation with ESA). 

The work is also part of a joint research program between SZTAKI and the Technical University of Eindhoven.    

Requirements:

We are looking for a candidate who meets the following requirements:

• You are a talented and enthusiastic young researcher.
• You have experience with or a strong background in systems and control, mathematics, signal processing. Preferably you finished a master in Systems & Control, Computer Science/AI, Mechanical Engineering or Electrical Engineering.
• You have good programming skills and experience (Python, Matlab, C/C++).
• You have good communicative skills, and the attitude to partake successfully in the work of a research team.
• You are creative and ambitious, hard-working and persistent.
• You have good command of the English language (knowledge of Hungarian is not required).

Conditions of employment

• Challenging job in a dynamic and ambitious institute and a stimulating internationally renowned research environment.
• Full-time temporary appointment for 4 years.
• Competitive salary.
• An extensive package of fringe benefits (e.g., excellent technical infrastructure, private health care support, etc.).

Information and application

More information can be obtained from: Dr. Roland Toth (toth.roland@sztaki.hu)