Keynote Speaker I

 

Prof. Maria Pia Fanti (IEEE Fellow)

Polytechnic University of Bari, Italy

Biography

Maria Pia Fanti (IEEE Fellow and Fellow of the Asia-Pacific AIA) received the Laurea degree in electronic engineering from the University of Pisa, Pisa, Italy, in 1983. She was a visiting researcher at the Rensselaer Polytechnic Institute of Troy, New York, in 1999. Since 1983, she has been with the Department of Electrical and Information Engineering of the Polytechnic of Bari, Italy, where she is currently a Full Professor of system and control engineering and Chair of the Laboratory of Automation and Control. Her research interests include modeling and control of complex systems, intelligent transportation systems, smart logistics; Petri nets; consensus protocols; fault detection. Prof. Fanti has published more than +310 papers and two textbooks on her research topics. She was senior editor of the IEEE Trans. on Automation Science and Engineering and member at large of the Board of Governors of the IEEE Systems, Man, and Cybernetics Society. Currently, she is Associate Editor of the IEEE Trans. on Systems, Man, and Cybernetics: Systems, member of the AdCom of the IEEE Robotics and Automaton Society, and chair of the Technical Committee on Automation in Logistics of the IEEE Robotics and Automation Society. Prof. Fanti was General Chair of the 2011 IEEE Conference on Automation Science and Engineering, the 2017 IEEE International Conference on Service Operations and Logistics, and Informatics and the 2019 Systems, Man, and Cybernetics Conference.

Abstract

Classical approaches to system identification are based on parametric estimation paradigms from mathematical statistics. In this setting, a key point is the selection of the most adequate model structure which is typically performed via complexity measures such as the Akaike's criterion. Starting from the linear scenario, then moving to the nonlinear one, this talk will describe how the model selection problem can be successfully faced by a different approach based on regularization theory. In particular, I will discuss the use of Bayesian kernel-based methods where the unknown system is seen as a Gaussian process whose covariance (kernel) includes information on system stability and/or fading memory. Here, tuning of model complexity gets a whole new dimension and richness in the choice of (continuous) regularization parameters compared to the choice of (discrete) model orders.

Keynote Speaker II


Prof. Shaoping Bai (ASME Fellow)

Aalborg University, Denmark

Biography

Shaoping Bai is a full professor at the Department of Materials and Production, Aalborg University (AAU), Denmark. His research interests include wearable sensors, medical and assistive robots, and exoskeletons. Prof. Bai leads several national and international research projects in exoskeletons, including EU AXO-SUIT and IFD Grand Solutions project EXO-AIDER, and Danish Independent Research Council project VIEXO, among others. He is a recipient of several best paper awards in conferences including IEEE CIS-RAM 2017, IFToMM MEDER 2018, MESROB 2023, IFToMM ISRM 2026, in addition to   WearRAcon2018 Grand Prize of Innovation Challenges and the Best Paper Award 2024 from Biomimetic Intelligence and Robotics journal.  Prof. Bai is an associate editor of Robotica,  ASME Letters in Translations Robotics, and Wearable Technologies. He is the founder of BioX ApS and an elected member of IFToMM Executive Council.

 

Abstract

To be added...

Keynote Speaker III

 

Prof. Tony Prescott

University of Sheffield, UK

Biography

Tony Prescott (him/his) is a Professor of Cognitive Robotics at the University of Sheffield who develops robots that resemble animals including humans. His goal is both to advance the understanding of natural intelligence and to create useful new technologies such as assistive, educational and entertainment robots. Tony has published over 250 refereed articles and conference papers at the intersection of robotics and psychology and has received over £10M in funding from UK and European research agencies. He is the author of the book The Psychology of Artificial Intelligence (Routledge, 2024) and lead editor of Living Machines: A Handbook of Research in Biomimetic and Biohybrid Systems (OUP, 2018). With collaborators he has developed several bespoke biomimetic robots including the commercial MiRo-e robot animal-like companion robot. His research has been covered by the major news and scientific media including the BBC, CNN, Discovery Channel, The Guardian and New Scientist.

 

Abstract

Classical approaches to system identification are based on parametric estimation paradigms from mathematical statistics. In this setting, a key point is the selection of the most adequate model structure which is typically performed via complexity measures such as the Akaike's criterion. Starting from the linear scenario, then moving to the nonlinear one, this talk will describe how the model selection problem can be successfully faced by a different approach based on regularization theory. In particular, I will discuss the use of Bayesian kernel-based methods where the unknown system is seen as a Gaussian process whose covariance (kernel) includes information on system stability and/or fading memory. Here, tuning of model complexity gets a whole new dimension and richness in the choice of (continuous) regularization parameters compared to the choice of (discrete) model orders.

Invited Speaker I

 

Prof. Jouni Mattila

Tampere University, Finland

Biography

Jouni Mattila is a Full Professor of Machine Automation at Tampere University, Finland, a position he has held since 2011. He received the M.Sc. and Doctor of Technology degrees from Tampere University of Technology in 1995 and 2000, respectively. From 1998 to 2000, he was a visiting scientist at the Robotics and Control Laboratory, University of British Columbia, Canada.
His research focuses on modeling, estimation, and control of heavy-duty robotic systems, with particular emphasis on autonomous mobile manipulators, flexible manipulators, teleoperation, and electrification of heavy-duty machinery. His work spans nonlinear and model-based control, learning-based methods, distributed sensing and state estimation, and human–robot interaction, with applications in mining, construction, forestry, material handling, and fusion remote handling. A central theme is bringing advanced robotics, learning, and safety-aware control methods from theory to full-scale machines operating autonomously in demanding real-world environments.
Prof. Mattila has initiated and led numerous national and European research projects in close collaboration with industry. He has supervised 24 completed doctoral degrees since 2011 and coordinated major European doctoral training programmes in robotics and remote handling. He served on the Technical Editorial Board of the IEEE/ASME Transactions on Mechatronics from 2015 to 2020 and as Publicity Chair of the 2025 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM).

Abstract

Classical approaches to system identification are based on parametric estimation paradigms from mathematical statistics. In this setting, a key point is the selection of the most adequate model structure which is typically performed via complexity measures such as the Akaike's criterion. Starting from the linear scenario, then moving to the nonlinear one, this talk will describe how the model selection problem can be successfully faced by a different approach based on regularization theory. In particular, I will discuss the use of Bayesian kernel-based methods where the unknown system is seen as a Gaussian process whose covariance (kernel) includes information on system stability and/or fading memory. Here, tuning of model complexity gets a whole new dimension and richness in the choice of (continuous) regularization parameters compared to the choice of (discrete) model orders.

Invited Speaker II

 

Assoc. Prof. Masoumeh Iran Mansouri

University of Birmingham, UK

Biography

Masoumeh Iran Mansouri is an Associate Professor in the School of Computer Science at the University of Birmingham, UK. Her research spans several complementary areas, including robot planning, cultural robotics, and the social study of AI/robotics. She was previously a researcher at the Centre for Applied Autonomous Sensor Systems at Örebro University, Sweden, and has held visiting positions at the Oxford Robotics Institute and in Sven Koenig's lab at the University of Southern California. Her core technical work addresses automated planning for (semi-)autonomous robotic systems, both single- and multi-robot, that share space with humans. This includes hybrid methods combining task and motion planning, scheduling, and spatio-temporal reasoning for real-world settings from mining to museum service robotics as well as planning under uncertainty and failure recovery in assembly tasks. She has also worked extensively on settings that require coordination and collaboration among robots, developing methods for multi-robot trajectory optimization and formation planning, with applications such as object transport and fleet management in warehouses. Her research also extends to cultural robotics, a field dedicated to studying the effects of integrating cultural models into robots. She approaches cultural robotics from a critical perspective, calling for a deeper understanding of the new forms of culture that emerge in human–robot interactions, the impacts of these cultures on participants, the contexts in which such interactions occur, and their influence on broader societies.

Abstract

Classical approaches to system identification are based on parametric estimation paradigms from mathematical statistics. In this setting, a key point is the selection of the most adequate model structure which is typically performed via complexity measures such as the Akaike's criterion. Starting from the linear scenario, then moving to the nonlinear one, this talk will describe how the model selection problem can be successfully faced by a different approach based on regularization theory. In particular, I will discuss the use of Bayesian kernel-based methods where the unknown system is seen as a Gaussian process whose covariance (kernel) includes information on system stability and/or fading memory. Here, tuning of model complexity gets a whole new dimension and richness in the choice of (continuous) regularization parameters compared to the choice of (discrete) model orders.