To receive credit, Students must be either logged in with their waterloo account into zoom, or change their username formatted as follows prior to joining the Zoom call: First_Name Family_Name Student_ID Program (MASc/MEng/PhD), otherwise the attendance will not be counted. It is the student's responsibility to make sure that their username is properly formatted prior to joining Zoom, as changing it after joining will not be recorded with the correct format, the seminar organizers and the graduate advisor will not make adjustments after the end of the seminar.
Students must attend the full MME Department Research Seminars listed here and complete the Seminar Attendance Form.
To receive credit for attending the Seminar, please complete and submit this form.
You must login to view this form.
Degree Requirements
- MASC students are required to attend 8 seminars for degree completion
- MEng students are required to attend 4 seminars for degree completion
- Students must attend the entire seminar (at least 45 minutes) to receive credit
Note: To receive credit, students can only attend MME Department Research Seminars.
Department Research Seminars
To receive credit, students must attend the full MME Department Research Seminars listed here and complete the Seminar Attendance Form.
ACES MODEL –
Supporting Atlantic Canada’s Pathway to Net-Zero by 2050
Speaker: Dr. Mohammed Alkatheri
Net Zero Atlantic
Theme: Energy
--------------------------------------------
Time: 2024-December-2nd, 4:00-5:00 pm
Location: E5-2004 (In-person only)
Refreshment will be provided
Abstract: This presentation will provide an overview of the ACES Model and explore a scenario analysis assessing Atlantic Canada’s commitment to achieving net-zero emissions by 2050, highlighting both opportunities and challenges.
Why ACES?
To fulfill our mission, Net Zero Atlantic created the Atlantic Canada Energy System (ACES) Model—a comprehensive, bottom-up, capacity expansion and linear optimization tool. By identifying least-cost pathways for energy development within specific policy and technology constraints, ACES provides insights into areas that need further study and helps shape our research priorities.
At Net Zero Atlantic, we lead research and projects that support Atlantic Canada’s transition to a carbon-neutral future. Our mandate centres on objectively assessing the impacts of various energy technologies on both the natural and social environment, helping to guide decision-making.
Dr. Mohammed Alkatheri is an Energy System Modeler at Net Zero Atlantic, where he leads the technical development and application of the ACES model. He holds a PhD in Chemical Engineering from the University of Waterloo, where he specialized in optimizing energy systems using advanced data tools such as AI and machine learning. He also holds an MSc from Khalifa University and a BSc from United Arab Emirates University in Chemical Engineering.
At Net Zero Atlantic, Mohammed has been closely involved in enhancing the ACES model, making it a credible, user-friendly tool for Atlantic Canadians, providing insights into "what if" scenarios. His work supports the region’s transition to a sustainable, low-carbon future by identifying strategic pathways and essential research areas to meet ambitious climate targets.
Please contact the host, Prof. XiaoYu Wu (xiaoyu.wu@uwaterloo.ca), if any questions
Enhancing Image-Guided Surgery through Robotic Surgeon-Support Systems
Speaker: Prof. Mahdi Tavakoli
University of Alberta, Canada
Theme: Robotics
--------------------------------------------
Time: 2024-Nov-29th , 1:00-2:00 pm EST
Online, Zoom meeting: (link)
Abstract: Surgical, therapeutic, and diagnostic interventions can be significantly enhanced using computerintegrated robotic systems with real-time decision-making capabilities that work under the direct, shared, or supervisory control of surgeons and therapists. Incorporating appropriate levels of autonomy in systems for healthcare delivery can lower the mental and physical loads on clinicians while improving the reliability, precision, and safety of the interventions for patients. In this seminar, Dr. Mahdi Tavakoli, Professor and Senior University of Alberta Engineering Research Chair in Healthcare Robotics, discusses several applications of medical robotics and their related challenges and offers solutions based on combining the capabilities of humans with the precision, accuracy, and fast decision-making capabilities of machines.
Prof. Mahdi Tavakoli is a Professor in the Electrical and Computer Engineering Department and the Biomedical Engineering Department and a Senior University of Alberta Engineering Research Chair in Healthcare Robotics. He is also Scientific Vice-Director for the Institute for Smart Augmentative and Restorative Technologies (iSMART) at the University of Alberta. He received his PhD degree in Electrical and Computer Engineering from the University of Western Ontario, Canada, in 2005. From 2006 to 2008, he was a post-doctoral researcher at Canadian Surgical Technologies and Advanced Robotics (CSTAR), Canada, and an NSERC Post-Doctoral Fellow at Harvard University, USA. Dr. Tavakoli’s research interests involve medical robotics, image-guided surgery, and rehabilitation robotics. Dr. Tavakoli is the lead author of Haptics for Teleoperated Surgical Robotic Systems (World Scientific, 2008) and the Specialty Chief Editor for Frontiers in Robotics and AI (Robot Design Section). He is a Senior Member of IEEE and an Associate Editor for the International Journal of Robotics Research, IEEE Transactions on Medical Robotics and Bionics, IEEE/ASME Transactions on Mechatronics’ Focused Section with Advanced Intelligent Mechatronics, and Journal of Medical Robotics Research.
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions.
The Life of an Educator and Entrepreneur
Speaker: Prof. Clovis Maliska
Federal University of Santa Catarina (UFSC), Brazil
Theme: entrepreneurship in mechanical engineering
--------------------------------------------
Time: 2024-Nov-28th, 3:00 pm-4:00 pm EST
In person only in E5-2004
Clovis R. Maliska is a Full Professor in the Department of Mechanical Engineering at the Federal University of Santa Catarina (UFSC), Brazil. He received his PhD in Mechanical Engineering from the University of Waterloo, Canada, under the supervision of Professor George D. Raithby. He teaches fluid mechanics, heat transfer and computational fluid dynamics at the graduate level in mechanical engineering at UFSC. In 1995, he launched a pioneering book in Brazil on Computational Fluid Dynamics, with the second edition, published in 2004, which is used as a textbook in both under and graduate engineering programs. Professor Maliska is a member of the National Academy of
Engineering (ANE), Chair 71, and has also received the citation (medal) of the National Order of Scientific Merit from the Ministry of Science and Technology.
About this talk: Dr. Maliska completed his PhD in 1981 and launched a successful research and teaching career that resulted in the widespread application of Computational Fluid Dynamics (CFD) across all South America. He was the driving force behind the incorporation of ESSS (Engineering Simulation and Scientific Software Ltd.) that now has offices in Brazil, Argentina, Chile, Peru, Mexico, Columbia, USA (Texas), Portugal, Spain and most recently Italy. His most recent book, Fundamentals of Computational Fluid Dynamics, has had more than 16,000 downloads. Dr. Maliska has received many awards for his work, including honoring him, by the President of Brazil, with the title “Commander of the National Order”. This will be a non-technical lecture in which Dr. Maliska describes the evolution of his life as Professor, Researcher and Businessman. It will be of interest to undergraduate and graduate students who might see entrepreneurship in their future.
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions.
Theoretical Performance Bound and its Experimental Validation
of Battery Capacity Estimates in Rechargeable Batteries
Speaker: Professor Balakumar Balasingam
University of Windsor
Theme: Energy
--------------------------------------------
Time: 2024-November-22nd, 4:00-5:00 pm
Location: E5-2004 (In-person only)
Refreshment will be provided
Abstract: Capacity of a battery is a salient indicator of aging. Accurate estimation of capacity will help in evaluating the state of health (SOH), predicting its remaining useful life (RUL), and in determining a suitable second use application for the retired battery. The existing methods in the literature employ slow discharge, standard C-rate discharge, or curve-based approaches to estimate the battery capacity. A major drawback of these methods is that the quality of the estimate is not known. The Cramer–Rao lower bound (CRLB) defines the theoretical minimum error variance of an unbiased estimator. This talk discusses several real-world uncertainties that influence the capacity estimation in batteries. Such uncertainties are taken into consideration in deriving the CRLB for the estimated capacity. The derived performance limits help one to choose the method that best fits the quality of capacity estimation in a given application. Experimental data obtained from cylindrical Li-ion battery cells are used to validate the theoretical derivations of capacity estimation uncertainties.
Dr. Balakumar Balasingam (Ph.D., P.Eng. Ontario) received his B.Sc.Eng. degree specializing in Electronics and Telecommunication Engineering with first class honors from the University of Moratuwa, Sri Lanka, in 2002. He received his M.A.Sc. and Ph.D. degrees, both in Electrical Engineering, from McMaster University, Canada, in 2004 and 2008, respectively. He held postdoctoral position at the University of Ottawa from 2008 to 2010, and then a University Postdoctoral position at the University of Connecticut from 2010 to 2012. From 2012 to 2017, he was an Assistant Research Professor in the Department of Electrical and Computer Engineering at the University of Connecticut. From 2017, he has been with the University of Windsor where he is now an Associate Professor. Dr. Balasingam’s research interests are in signal processing, machine learning, information fusion, and their applications in autonomous systems; particularly, his close interests are in battery management systems, human-machine systems, and surveillance & tracking systems. In these areas, Dr. Balasingam has contributed to over 100 peer reviewed research papers, a US patent grant on battery
management systems, and a book, titled “Robust Battery Management Systems with MATLAB” published by Artech House in 2023. Dr. Balasingam is a senior member of IEEE.
Please contact the host, Prof. XiaoYu Wu (xiaoyu.wu@uwaterloo.ca), if any questions.
Use of Remote Sensing Techniques in the Finance and Insurance
Sector
Speakers: Dr. Xi Zhu and Sebastian Paolini van Helfteren
Wholesale & Rural Innovation, Rabobank (Netherlands)
Theme: Interdisciplinary
--------------------------------------------
Time: 2024-November-13th, 9:30 - 10:30 am (Eastern Time)
Remote: Zoom Link *
Meeting ID: 989 5052 0533 Passcode: MME
Abstract: In this talk, the speakers will be talking about the use of Remote Sensing techniques in the finance and insurance sector, with a focus on the Acorn project. Acorn stands for Agroforestry CRUs for the Organic Restoration of Nature. Acorn is an agroforestry program that unlocks the international voluntary carbon market for smallholder farmers who are realizing agroforestry projects for carbon sequestration through biomass growth, predominantly through trees. Acorn supports the initiation and development of these agroforestry projects and facilitates the subsequent trade of the so-called carbon removal units (CRUs) that are generated from the sequestered carbon. Acorn is currently operating in 28 worldwide projects.
Sebastian Paolini van Helfteren will present in detail the Acorn project and how remote sensing is used in the finance and insurance sector in general, and Dr. Xi Zhu will present the methodology that Acorn used to estimate CRUs for each onboarded plot.
Dr. Xi Zhu and Sebastian Paolini van Helfteren are from Remote Sensing team of Wholesale &
Rural (W&R) Innovation from Rabobank (Netherlands).
* Students who need seminar attendance credit must log in with their UWaterloo accounts or write their name + student ID clearly before joining the meeting. Only attendance > 45 min will count. Otherwise, no attendance credit would be issued.
Please contact the host, Prof. XiaoYu Wu (xiaoyu.wu@uwaterloo.ca), if any questions
Structured Representations for Human-Centered
Embodied AI
Speaker: Prof. Jiajun Wu
Standford University, USA
Theme: Robotics, Reinforcement Learning
--------------------------------------------
Time: 2024-Oct-25th, 1:00-2:00 pm EDT
Online, Zoom meeting: (link)
Abstract: For embodied AI systems to assist humans in the real world, we must consider
human factors in all aspects. In this talk, I'll introduce our recent work on developing humancentered
embodied AI, including assets, environments, tasks, and learning algorithms. What
is shared across all these works is our choice of structured representations inspired by human
sensory observations, skills, and behaviors. I will discuss how we design the representations,
and how we use them to collect assets, build environments, design tasks, and finally
develop algorithms to solve embodied AI problems.
Jiajun Wu is an Assistant Professor of Computer Science and, by courtesy, of Psychology at Stanford
University, working on computer vision, machine learning, and computational cognitive science. Before
joining Stanford, he was a Visiting Faculty Researcher at Google Research. He received his PhD in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology. Wu's research has been recognized through the Young Investigator Programs (YIP) by ONR and by AFOSR, the NSF CAREER award, paper awards and finalists at ICCV, CVPR, SIGGRAPH Asia, CoRL, and IROS, dissertation awards from ACM, AAAI, and MIT, the 2020 Samsung AI Researcher of the Year, and faculty research awards from J.P. Morgan, Samsung, Amazon, and Meta.
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions.
Challenges of Economic Research in Energy Systems
Speaker: Dr. Patrick Jochem
German Aerospace Centre (DLR)
Theme: Interdisciplinary
--------------------------------------------
Time: 2024-October-10th, 9:30 - 10:30 am (Eastern Time)
Remote: Zoom Link *
Meeting ID: 919 6700 2966 Passcode: MME
Abstract: The presentation focuses on challenges in decarbonized energy systems and their current transition phase for achieving greenhouse gas emission targets. The consequential conversion of these energy systems correlates with several challenges with regard to technical applicability, economic concerns or social acceptance (among others). The talk will highlight three research areas: (1) Analysis of potential resource scarcities in future energy systems and during their transition including associated threads due to political tensions and dependencies. (2) The technical transition is in most countries well defined, and several suitable scenarios show potential pathways. However, their implementation and the resulting impact on macroeconomic indicators are highly uncertain. Agent based macroeconomic modelling might help to understand these hurdles and develop suitable policy instruments for realizing these transition pathways. Finally, (3) the research on synergetic integration of electric vehicles in national electricity systems is illustrated by presenting current modelling approaches and results, such as resulting greenhouse gas emissions, flexibility provision due to controlled charging etc. For (2) and (3) open-source tools are available, i.e. AMIRIS, sfc tools, REMix, and venco.py.
Bio: Patrick Jochem studied economics at the universities of Bayreuth, Mannheim and Heidelberg, Germany. In 2009, he completed his award-winning doctorate in the field of transport economics at the University of Karlsruhe (TH), funded by the German Federal Environmental Foundation (DBU). In 2009, he founded the "Transport and Energy" research group at the Karlsruhe Institute of Technology (KIT), which he headed until 2019. Between 2014 and 2019, he was a fellow of the Heidelberg Academy of Sciences and Humanities. In summer 2015, he was a visiting professor at the University of Waterloo, Ontario, and completed his habilitation in 2016 with the topic "Electric Mobility and Energy Systems - A techno-economic impact analysis of electric vehicles on the energy system" in the field of business administration at KIT. Since 2016, he has been a member of the editorial board of the journal "Transportation Research Part D: Transport and Environment" and since 2020 he has been Head of Department of Energy System Analysis at the Institute of Networked Energy Systems of the German Aerospace Centre (DLR-VE). Patrick Jochem has published over 100 scientific papers and has an excellent international network in the interdisciplinary field of transport and energy.
* Students who need seminar attendance credit must log in with their UWaterloo accounts or write their name + student ID clearly before joining the meeting. Only attendance > 45 min will count. Otherwise, no attendance credit would be issued.
Please contact the host, Prof. XiaoYu Wu (xiaoyu.wu@uwaterloo.ca), if any questions
Innovating at Interfaces: Enhancing Performance and Longevity of Sustainable Energy Systems
Speaker: Dr. Sami Khan
Simon Fraser University
Theme: Thermal, Fluids
--------------------------------------------
Time: 2024-September-30th, 3:00-4:00 pm
Location: E5-2004 (In-person only)
Refreshment will be provided
Abstract: Interfaces are ubiquitous, and bottlenecks to performance and longevity in sustainable energy systems often occur due to interfacial interactions. Deciphering and controlling mechanisms underlying these interactions is critical to designing improved and long-lasting sustainable energy and chemical generation systems. My group has developed a novel approach to reduce soot accumulation on biomass combustor surfaces using microtextures, reporting that randomly microtextured surfaces obtained by sandblasting shows a 71% reduction in the time taken to oxidize 90% of surface soot coverage when compared to smooth surfaces at 530°C. We also study grooved microtextures fabricated via laser ablation and find that grooves with widths between 15 and 50 µm enhance soot oxidation, while the expedited advantage is lost when the groove width is 85 µm, indicating that there is an optimal length-scale of surface roughness for this self-cleaning effect to take place. Microtextured surfaces that facilitate soot oxidation upon contact could significantly improve performance and longevity in various combustion applications.
Bio: Dr. Sami Khan is an Assistant Professor in the School of Sustainable Energy Engineering at Simon Fraser University. He obtained his Ph.D. in Mechanical Engineering from MIT in 2020. At SFU, Dr. Khan leads the Engineered Interfaces for Sustainable Energy (EISEn) group, which aims to improve the performance and longevity of sustainable energy systems by fundamentally understanding and tuning electro-chemo-physical interactions at interfaces, with a particular focus on enhancing CO2 capture and conversion processes. He has previously worked in the rare-earth mining industry in Canada and was a Science and Technology Advisor to the Chief Scientist of Natural Resources Canada. He is the recipient of many awards including the Action Canada Fellowship (2021) and the Marcel Pourbaix Award for Best Poster in Corrosion Science (received at the NACE International CORROSION conference in 2019).
Please contact the host, Prof. XiaoYu Wu (xiaoyu.wu@uwaterloo.ca), if any questions.
Leveraging Structure and Abstractions for OOD Generalization
Speaker: Prof. Amy Zhang
UT Austin, Texas, USA
Theme: Robotics, Reinforcement Learning
--------------------------------------------
Time: 2024-Sept-13th , 2:00-3:00 pm EDT
Online, Zoom meeting: (link)
Abstract: Out-of-distribution generalization relies on leveraging structure inherent to our problem domain. We explore how different structural assumptions common to robotics can be incorporated into reinforcement learning and planning algorithms for improved sample efficiency and generalization. Specifically, we explore object-oriented representations and using them to decompose object rearrangement tasks and quasimetric structure and richer learning signals in goal-conditioned problems.
Prof. Amy Zhang: I am an assistant professor at UT Austin in the Chandra Family Department of Electrical and Computer Engineering. My work focuses on improving generalization in reinforcement learning through bridging theory and practice in learning and utilizing structure in real world problems. Previously I was a research scientist at Meta AI - FAIR and a postdoctoral fellow at UC Berkeley. I obtained my PhD from McGill University and the Mila Institute, and also previously obtained an M.Eng. in EECS and dual B.Sci. degrees in Mathematics and EECS from MIT
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions.
Harnessing the Power of Green Hydrogen Production and Utilization
Speaker: Dr. Hamed Aslannejad
Copernicus Institute of Sustainable Development, Utrecht University
Theme: Thermal
--------------------------------------------
Time: August 12, 2024, 2:00-3:00 pm
Location: E5-2004 (In-person only)
Refreshment will be provided
Abstract: As the global community strives towards a sustainable energy future, green hydrogen has emerged as a pivotal element in our energy transition strategy. Current projections indicate a necessity to amplify hydrogen production sixfold compared to our present consumption levels, which predominantly rely on grey hydrogen sources. This lecture will delve into the transformative potential of green hydrogen across various sectors, including transportation, industry, and power generation.
We will explore innovative production techniques and applications of hydrogen, with a special emphasis on the role of Solid Oxide Fuel Cells (SOFCs) and Solid Oxide Electrolyzers (SOEs). These technologies offer promising pathways for efficient hydrogen production and utilization, contributing to reduced carbon footprints and enhanced energy security.
The session will also spotlight the strategic importance of international collaborations in advancing hydrogen technology and deployment. We will introduce a pioneering Dutch-based hydrogen initiative that exemplifies the collaborative efforts needed to scale up green hydrogen production and integrate it into global energy systems.
Dr. Hamed Aslannejad is a Chemical Engineer, having obtained his Bachelor's, Master's, and Ph.D. degrees with Cum Laude honors. His research interests lie in the area of renewable energies, which he began exploring in 2008 when he joined the Niroo Research Institute. During his time there, he was involved in various solar, wind, biomass, geothermal, and hydrogen projects, focusing on the latter. He has extensive hands-on experience working with fuel cells and electrolyzers. Additionally, he has utilized computational modeling to simulate the performance of electrochemical systems. During his Ph.D., he delved into the intricate details of fluid flow in porous media, acquiring a broad knowledge of multi-scale, multi-phase fluid flow modeling tools. He also employed machine learning to facilitate fluid flow simulation cases.
Currently, Hamed is an Assistant Professor at the Copernicus Institute of Sustainable Development, where he is a key player in hydrogen production, storage, and use. He leads several projects focused on Green Hydrogen production and use. His research profile demonstrates his commitment to advancing the field of renewable energies and sustainability through cutting-edge research and collaboration.
Please contact the host, Prof. XiaoYu Wu (xiaoyu.wu@uwaterloo.ca), if any questions.
Micro-3D printing empowered microfluidics study for water-energy nexus applications
Speaker: Dr. Hongxia Li
Technology Innovation Institute in Abu Dhabi, UAE
Theme: Thermal, Fluids
-------------------------------------------
Time: 2024-August-6th, 4:00-5:00 pm
Location: E5-3052 (In-person only)
Refreshment will be provided
Abstract: On-chip flow imaging and characterization offer great opportunities in probing microscopic
multiphase flow physics for novel subsurface energy, water, environmental, and space applications. The emerging micro-stereolithography-based (μ-SL) 3D printing enables microfluidic chip fabrication with up to 2 micrometer feature resolution, providing opportunities for “rock-on-chip”, “vessel-on-chip”, and so on.
Besides, μ-SL system also exhibits great flexibility in cooperating multi-materials during its printing process.
Herein we have developed a novel “micro-3D printing-on-membrane” technique and managed to integrate fish gill-mimicked microstructures, metallic micromesh, and polymeric membrane within a single 3D-printed on-chip device for water filtration study. Another demonstration is “rock-on-chip” technology for subsurface energy recovery applications. By incorporating micro-3D printing and surface modification techniques, we have created a rock replica with the same porous structures and surface mineralogy of nature rock. With this real yet transparent ‘rock’, the microscale rock-fluid interactions in complex pore/throat networks is investigated to bring innovative solutions for effective energy and water production.
Dr. Hongxia Li is a senior researcher at the Technology Innovation Institute in Abu Dhabi, UAE. She also serves as the acting chair of the International Associate for Green Energy (IAGE)-UAE chapter. She received her Ph.D. degree from Khalifa University in 2018, and was a visiting scholar of the Massachusetts Institute of Technology (MIT) and University of Texas at San Antonio (UTSA). USA. Dr. Li has been actively working on innovative subsurface water and energy solutions for many years. Her research topics include multiphase flow, micro- 3D printing, microfluidics, and novel material and surface engineering for the water-energy nexus. To date, she has filed four patent applications, two of which have been granted by the United States Patent and Trademark Office. She has over 30 journal and conference publications, including articles in top journals such as Nature Energy, Nature Communications, and Joule, with more than 2000 citations.
Please contact the host, Prof. XiaoYu Wu (xiaoyu.wu@uwaterloo.ca), if any questions
Speaker: Prof. Wael Suleiman (University of Sherbrooke)
Theme: robotics
July 18th, 2024
2-3PM, Online
(More information to follow)
Interaction of boundary layer instabilities and geometrical wall features: some recent work and ideas for next steps
Speaker: Marios Kotsonis, Prof. TU Delft
Theme: Fluids
Time: 2024-July-3rd, 9:00 am-10:00 am EDT
Hybrid in E7-2343, Zoom meeting: (link)
Abstract: Boundary layer instabilities are of paramount importance for the dynamics of transitional flows, themselves dominating drag production and efficiency of many relevant systems such as aircraft wings.
However, in most real-life cases, aerodynamic surfaces are not smooth or geometrically perfect. Surface nonuniformities are inevitable due to debris, damages, and manufacturing features such as joints, panels, rivets etc. These geometrical features have a profound effect on boundary layer instabilities and transition. These effects are reviewed in this talk, based on recent experimental and numerical studies of our team. Expectedly, in most cases the effect of these features is detrimental, thus leading to anticipation of transition. However, we have discovered limited cases where roughness can actually lead to a delay of transition. These cases have revealed a wealth of fundamental interaction mechanisms, which can pave the way to passive flow control methods. Some next steps and ideas in moving forward will be shared.
Marios Kotsonis is Professor of Flow Control at Delft University of Technology, Faculty of Aerospace Engineering. His interests cover laminar-turbulent transition, flow instabilities, flow control and flow actuators, using theoretical, numerical and experimental techniques. He is recipient of the Veni and Vici grants of the Dutch Research Council and Starting, Proof-of-Concept and Consolidator grants of the
European Research Council.
Students must be either logged in with their waterloo account into zoom, or change their username formatted as follows prior to joining the Zoom call: First_Name Family_Name Student_ID Program(MASc/MEng/PhD), otherwise the attendance will not be counted. It is the student's responsibility to make sure that their username is properly formatted prior to joining Zoom, as changing it after joining will not be recorded with the correct format, the seminar organizers and the graduate advisor will not make adjustments after the end of the seminar.
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions
Versatile Imitation Learning and Reinforcement Learning with Motion Primitives in Robotics Speaker: Prof. Gerhard Neumann
Karlsruhe Institute of Technology, Germany
Theme: Robotics, Machine Learning
--------------------------------------------
Time: 2024-June-20th, 10:00-11:00 am EDT
Online, Zoom meeting: (link)
Abstract: In this talk, I will present our recent work on imitation learning and reinforcement learning in robotics. I will provide an overview of motion primitives (MPs) in robotics, which have been highly successful for smooth motion generation, and discuss their advantages and disadvantages compared to standard action-based policies. Additionally, I will introduce a novel MP representation called Probabilistic Dynamic Movement Primitives (ProDMPs). This representation can be easily integrated into a neural network architecture while ensuring smooth motion generation.
In the area of imitation learning, I will showcase new augmented reality-based user interfaces that facilitate low-effort data generation. Using these interfaces, we have collected diverse benchmark datasets for evaluating the latest imitation learning algorithms. Diffusion-based policies demonstrate impressive performance in this context. To enhance versatility, we extend the ProDMP framework with diffusion-based policies, ensuring smooth behavior representation.
For reinforcement learning (RL), I will highlight the beneficial exploration properties of MPs by exploring the parameter space of MPs rather than the robot's action space. I will introduce MP-based RL algorithms that treat the RL problem as a black-box optimization problem, requiring the algorithm to select MP parameters instead of low-level control actions. We have developed a novel RL algorithm incorporating differentiable trust region projection layers, which is well-suited for high-dimensional action spaces. This algorithm is extended for replanning and learning versatile behaviors.
Finally, I will discuss how approaches that incorporate human feedback can make reinforcement learning more practical for practitioners by eliminating the need for complex reward functions.
Prof. Gerhard Neumann is a full professor at the KIT and heading the chair "Autonomous Learning Robots" since Jan. 2020. Before that, he was group leader at the Bosch Center for AI and industry on campus professor at the University of Tübingen (from March to Dec. 2019) and full professor at the University of Lincoln in the UK (2016-2019). Gerhard completed my PhD in 2012 at the TU Graz and
was afterwards PostDoc and Assistant Professor at the TU Darmstadt. His research is focused on the intersection of machine learning, robotics and human-robot interaction. His goal is to create data-efficient machine learning algorithms that are suitable for complex robot domains, which includes learning from human feedback, versatile skill learning, learning learning to manipulate deformables, multiagent reinforcement learning as well as fundamental research in machine learning such as variational inference or meta-learning.
Students must be either logged in with their Waterloo account into zoom, or change their username formatted as follows prior to joining the Zoom call: First_Name Family_Name Student_ID Program(MASc/MEng/PhD), otherwise the attendance will not be counted. It is the student's responsibility to make sure that their username is properly formatted prior to joining Zoom, as changing it after joining will not be recorded with the correct format, the seminar organizers and the graduate advisor will not make adjustments after the end of the seminar.
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions
CONSTRAINED RADIAL BASIS FUNCTION (RBF) REGRESSION FOR THE MESHLESS AND BINLESS DATA ASSIMILATION IN IMAGE VELOCIMETRY
Speaker(s): Prof. M.A. Mendez and M. Ratz von Karman Institute, Belgium
Theme: Fluids and Solids
--------------------------------------------
Time: 2024-Apr-30th , 10:00 am-11:00 am EST
Zoom meeting: (link) Meeting ID: 789 699 0683
Passcode: MME2024
Abstract: Tracking-based image velocimetry is currently gaining prominence over traditional cross-correlation-based image velocimetry. Modern tracking methods can process images with high tracer density, generally enabling much higher resolution than cross-correlation-based velocimetry while circumventing its inevitable window or voxel averaging. On the other hand, tracking methods produce randomly scattered data, challenging the measurement post-processing to compute derivatives (e.g., velocity gradients or vorticity) or statistics (e.g., mean flow, turbulence intensity fields). A significant research effort in the community resulted in the development of many algorithms to map scattered velocity fields onto grids or bins, the first used to compute derivatives using traditional numerical methods (e.g. finite differences), the second to compute local statistics. Since these often combine data with physical priors (e.g. solenoidal field in incompressible flows), these algorithms fall in the data assimilation framework for image velocimetry. We recently proposed an approach for data assimilation in image velocimetry that requires no interpolation into grids or mapping into bins and achieves super-resolution. The approach uses constrained Radial Basis Functions (RBF) regression to derive an analytic expression of both the flow fields and their statistics. This talk presents the fundamentals of constrained RBF and showcases the method used in synthetic and experimental data to compute derivatives, flow statistics, and pressure fields. We also present our recently released open-source software package SPICY (Super-resolution and Pressure from Image veloCimetrY), developed at the von Karman Institute and close with a perspective on the current and future developments. The talk is based on these publications [1-3].
The talk will be given by Prof. M.A. Mendez and his student M. Ratz. M. A. Mendez is an associate professor at the von Karman Institute, leading the group on machine learning for applied fluid dynamics. His research group focuses on experimental and numerical methods, reduced-order modelling, flow control, digital twinning, and machine learning for industrial and environmental flows. M. Ratz is a PhD candidate at the von Karman Institute and at the Université Libre de Bruxelles, currently leading the developments of SPICY. His PhD focuses on data assimilation and numerical modelling of drone propeller’s aerodynamics.
References: [1] Sperotto, P., Pieraccini S., Mendez, M.A. (2022) A Meshless method to measure pressure fields from Image Velocimetry, Measurement Science and Technology, 33, 094005, Arxiv at https://arxiv.org/abs/2112.12752 [2] Sperotto, P., Ratz, M., Mendez, M.A (2023), SPICY: a Python toolbox for meshless assimilation from image velocimetry using radial basis functions, Journal of Open-Source Software 9(93), 5749, https://doi.org/10.21105/joss.05749 (open access) [3] Ratz, M., Mendez, M. A. (2024), A Meshless and binless approach to compute statistics in 3D Ensemble PTV, submitted to Experiments in Fluids. arvix at https://arxiv.org/abs/2403.11828.
Please contact the host, Prof. Zhao Pan (zhao.pan@uwaterloo.ca), if any questions.
Towards motor intelligence for soft robots
Speaker: Dr. Cosimo Della Santina
TU Delft, Netherlands
Theme: Robotics, Soft Robots
--------------------------------------------
Time: 2024-Apr-11th, 10:00-11:00 am EDT
Online, Zoom meeting: (link)
Abstract: Continuum soft robots are actuated mechanical systems whose body is composed of continuously deformable materials. In the past decade, substantial progress has been made in developing a low-level artificial brain for soft robotic systems that can make them execute precise motions and eventually exploit the intelligence embedded in their complex mechanical structures. In this talk, I will briefly introduce this grand challenge within the soft robotic field and then present
the model-based view of its solution. I will show how simplified models can be combined with nonlinear control theory and machine learning, leading to precise and dynamic task execution. I will conclude by presenting recent activities within my group concerning combining models with data and
transferring this body of knowledge toward the manipulation of soft objects.
Dr. Cosimo Della Santina is an Assistant Professor at TU Delft and a Guest Scientist at the German Aerospace Institute (DLR). He earned his Ph.D. in robotics (cum laude, 2019) from the University of Pisa. He was a visiting Ph.D. student and a postdoc (2017 to 2019) at MIT's Computer Science and Artificial Intelligence Laboratory. Subsequently, he held a senior postdoc position (2020) and served as a guest lecturer (2021) at the Department of Informatics at the Technical University of Munich (TUM). Cosimo has been awarded the uRobotics Georges Giralt Ph.D. Award (2020), the "Fabrizio Flacco" Young Author Award from I-RAS (2019), and was a finalist for the European Embedded Control Institute Ph.D. award (2020). In 2023, he received the IEEE AS Early Academic Career Award in Robotics and Automation. He is Principal Investigator for European and Dutch projects, such as H2020 Natural Intelligence, HE EMERGE, and Agrifood Nxtgen Hightech. He is an NWO ENI laureate and co-directs the Delft AI lab SELF. Cosimo leads the PhI-Lab at TU Delft, focusing on the study of embodied and disembodied intelligence in physical systems, with an emphasis on elastic and soft robots.
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions
Control of separated flow and suppression of flow-induced vibration with peripheral spinning rods
Speaker: Prof. Gustavo R. S. Assi
University of São Paulo, Brazil
Theme: Fluids and Thermal
--------------------------------------------
Time: Tue, April 9, 2024, 10 - 11 am EST
Location: In person in E7 2343 or Zoom (link) Meeting ID: 789 699 0683
Passcode: MME2024
Abstract: Rotating surfaces are an interesting tool for controlling flow separation around bluff bodies. When spinning rods are strategically placed around a circular cylinder, they disrupt the flow in the boundary layer and near wake, effectively delaying separation and vortex formation. This technique not only influences flow patterns but also reduces separation and mitigates vibration effects induced by the flow, thus helping to minimize vortex-induced vibration. With sufficient rotation, a system of rotating actuators can even neutralize drag or generate beneficial lateral forces. In this presentation, we will discuss experimental and numerical findings from our investigation involving eight rotating rods positioned around a central circular cylinder. Our focus will be on unravelling the fundamental physical mechanisms at play. This innovative approach holds great potential for diverse engineering applications, especially in the oceanic, aerospace, automotive, and civil engineering sectors, where managing flow separation, vibration, and noise is important for optimal performance and safety. Of particular interest, this active flow-control method can be applied to large ocean systems, such as floating offshore platforms with cylindrical hulls, offering new ideas for enhancing their efficiency and stability.
Dr. Gustavo R. S. Assi is the Professor of Renewable Energy and Energy Transition Technologies in the Department of Naval Architecture and Ocean Engineering at the University of São Paulo, Brazil. Deputy Director of the OTIC Offshore Technology Innovation Centre. Member of the Specialist Committee on Ocean Renewable Energy of the ITTC International Towing Tank Conference. A Naval Engineer from USP and PhD in Aeronautics from Imperial College London, he has worked as a Visiting Scholar at the University of Oxford (2013-14), Caltech (2016-17), and is currently at Texas A&M University (2023-24). His research interests include fluid-structure interaction, flow-induced vibration, experimental and computational fluid dynamics, ocean renewable energy, engineering education, science communication, and philosophy of technology.
Please contact the host, Profs. Serhiy Yarusevych (syarus@uwaterloo.ca, in person) and Zhao Pan
(zhao.pan@uwaterloo.ca, online), if any questions.
Let droplets drop the temperature: Enhancing heat transfer using droplets
Speaker: Patricia Weisensee, PhD
Washington University at St. Louis, USA
Theme: Fluids and Thermal
--------------------------------------------
Time: 2024-Feb-26th, 2:00 pm-3:00 pm EST
Online, Zoom meeting: (link) Meeting ID: 789 699 0683
Passcode: MME2024
Abstract: We experience and rely on droplets almost every single day of our lives: some more familiar (the shower in the morning, the rain on our way to work, printing documents once at work, etc.), some less obvious (atmospheric water harvesting, thermal management & power generation, materials manufacturing and processing). Yet we hardly ever think about them – we take them for granted. In this talk I will show that droplets aren’t only ubiquitous in both nature and industrial processes, but also a complex and fascinating research subject that still holds many mysteries to be solved. In my research group, we are especially interested in the coupling of fluid dynamics, heat transfer, and phase change (condensation or evaporation) during the interaction of droplets with solid or other liquid surfaces.
In this presentation, I will introduce two examples of such interactions: 1) droplet impact and evaporation/boiling dynamics on heated surfaces, and 2) dropwise condensation on so-called lubricant-infused surfaces. These oil-coated surfaces can significantly increase water collection rates compared to bare metal surfaces due to extremely high droplet mobility. Lubricant wetting ridges surrounding droplets introduce an attractive capillary force, leading to self-propelled and gravity-independent droplet motion, which efficiently clears the surface for frequent re-nucleation. On the other hand, restricting the mobility of droplets can be advantageous during droplet evaporation. Interestingly, when droplets impact a heated surface, the creation of additional contact lines, either through wettability-patterning the surface or the formation of an entrapped air bubble, does not significantly alter the heat transfer performance. Instead, convection (at early times) and conduction (at later times) dominate heat transfer, meaning that the addition of – for example – metallic posts with high thermal conductivity on the surface can effectively increase heat transfer rates in these scenarios.
Dr. Weisensee is an Assistant Professor in the Department of Mechanical Engineering & Materials Science at Washington University in St. Louis (WashU). She earned her PhD in Mechanical Engineering from the University of Illinois at Urbana-Champaign (UIUC) in 2016. She received a Diplom-Ingenieur in Mechanical Engineering from TU Munich in 2013 and also holds a M.S. in Materials Sciences from UIUC (2011). At WashU, Dr. Weisensee leads the Thermal Fluids Research Group, which focuses on understanding the interplay of fluid dynamics and heat transfer of droplets and other multi-phase systems, with applications in thermal management, water harvesting, additive manufacturing, and droplet interactions with natural and engineered systems. To fundamentally study these thermal-fluidic interactions, her group combines multiple experimental techniques, such as high-speed optical and infrared (IR) imaging, interferometry, confocal fluorescence microscopy, and conventional heat transfer measurements. Dr. Weisensee is a recipient of the NSF CAREER Award, the NASA Early Career Faculty Award, the AFOSR YIP Award, the 2014 Siemens Energy Award, the 2020 ASME ICNMM Outstanding Early Investigator Award, as well as the St. Louis-wide 2020 Emerson Excellence in Teaching Award.
Please contact the host, Prof. Zhao Pan (zhao.pan@uwaterloo.ca), if any questions
Machine Learning and Control for Robot Interaction Autonomy
Speaker: Dr. Arash Ajoudani
Human-Robot Interfaces and Interaction (HRI2), Italian
Institute of Technology, Italy
Theme: Robotics, Machine Learning
--------------------------------------------
Time: 2024-Mar-6th, 10:00-11:00 am EST
Online, Zoom meeting: (link)
Abstract: Future robots are expected to help us in various tasks, of which many require collaborative effort to be successfully completed. To achieve such behaviours, the robot must be able to physically interact with the human counterpart and predict the intentions of the human counterparts, despite the additional interaction with unpredictable environments. Appropriate robot control methods therefore are essential for the robot to deal with various uncertainties, dynamic aspects, and complex task requirements. A promising direction towards this goal is to adaptively regulate
mechanical parameters of the robot via software, based on the task requirements and robot proprioceptive and exteroceptive sensory information. This talk will explore how the Human-Robot Interfaces and Interaction (HRI²) laboratory is using machine learning and control to create more autonomous yet truly collaborative robots, ultimately leading to more adaptable, more efficient interactions in various settings. The talk will cover topics related to real-time human kinodynamic state monitoring in HRI/C and autonomous robot loco-manipulation controllers using hybrid ML and control.
Dr. Arash Ajoudani is the director of the Human-Robot Interfaces and Interaction (HRI²) laboratory at IIT. He is a recipient of the European Research Council (ERC) proof-of-concept grant 2023 Real-Move and the ERC starting grant 2019 (Ergo-Lean), the coordinator of the Horizon-2020 project SOPHIA, the co-coordinator of the Horizon-2020 project CONCERT, and a principal investigator of the HORIZON-MSCA project RAICAM, and the national projects LABORIUS and COROMAN. He is a recipient of the IEEE Robotics and Automation Society (RAS) Early Career Award 2021, and winner of the SmartCup Liguria award 2023, Amazon Research Awards 2019, of the Solution Award 2019 (MECSPE2019), of the KUKA Innovation Award 2018, of the WeRob best poster award 2018, and of the best student paper award at ROBIO 2013. His PhD thesis was a finalist for the Georges Giralt PhD award 2015 - best European PhD thesis in robotics. He was also a finalist for the best paper award on mobile manipulation at IROS 2022, the best paper award at Humanoids 2022 (oral category), the Solution Award 2020 (MECSPE2020), the best conference
paper award at Humanoids 2018, the best interactive paper award at Humanoids 2016, the best oral presentation award at Automatica (SIDRA) 2014, and for the best manipulation paper award at ICRA 2012.
He is the author of the book "Transferring Human Impedance Regulation Skills to Robots" in the Springer Tracts in Advanced Robotics (STAR), and several publications in journals, international conferences, and book chapters. He is currently serving as an elected IEEE RAS AdCom member (2022-2024), and as chair and representative of the IEEERAS Young Professionals Committee, and as a Senior Editor of the International Journal of Robotics Research (IJRR).
He has been serving as a member of scientific advisory committee and as an associate editor for several international journals and conferences such as IEEE RAL, ICRA, IROS, ICORR, etc. He is a scholar of the European Lab for Learning and Intelligent Systems (ELLIS). His main research interests are in physical human-robot interaction, mobile manipulation, robust and adaptive control, assistive robotics, and tele-robotics.
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions.
CONSTRAINED RADIAL BASIS FUNCTION (RBF) REGRESSION FOR THE MESHLESS AND BINLESS DATA ASSIMILATION IN IMAGE VELOCIMETRY
Speaker(s): Prof. M.A. Mendez and M. Ratz von Karman Institute, Belgium
Theme: Fluids and Solids
--------------------------------------------
Time: 2024-Apr-30th , 10:00 am-11:00 am EST
Zoom meeting: (link) Meeting ID: 789 699 0683
Passcode: MME2024
Abstract: Tracking-based image velocimetry is currently gaining prominence over traditional cross-correlation-based image velocimetry. Modern tracking methods can process images with high tracer density, generally enabling much higher resolution than cross-correlation-based velocimetry while circumventing its inevitable window or voxel averaging. On the other hand, tracking methods produce randomly scattered data, challenging the measurement post-processing to compute derivatives (e.g., velocity gradients or vorticity) or statistics (e.g., mean flow, turbulence intensity fields). A significant research effort in the community resulted in the development of many algorithms to map scattered velocity fields onto grids or bins, the first used to compute derivatives using traditional numerical methods (e.g. finite differences), the second to compute local statistics. Since these often combine data with physical priors (e.g. solenoidal field in incompressible flows), these algorithms fall in the data assimilation framework for image velocimetry. We recently proposed an approach for data assimilation in image velocimetry that requires no interpolation into grids or mapping into bins and achieves super-resolution. The approach uses constrained Radial Basis Functions (RBF) regression to derive an analytic expression of both the flow fields and their statistics. This talk presents the fundamentals of constrained RBF and showcases the method used in synthetic and experimental data to compute derivatives, flow statistics, and pressure fields. We also present our recently released open-source software package SPICY (Super-resolution and Pressure from Image veloCimetrY), developed at the von Karman Institute and close with a perspective on the current and future developments. The talk is based on these publications [1-3].
The talk will be given by Prof. M.A. Mendez and his student M. Ratz. M. A. Mendez is an associate professor at the von Karman Institute, leading the group on machine learning for applied fluid dynamics. His research group focuses on experimental and numerical methods, reduced-order modelling, flow control, digital twinning, and machine learning for industrial and environmental flows. M. Ratz is a PhD candidate at the von Karman Institute and at the Université Libre de Bruxelles, currently leading the developments of SPICY. His PhD focuses on data assimilation and numerical modelling of drone propeller’s aerodynamics.
References: [1] Sperotto, P., Pieraccini S., Mendez, M.A. (2022) A Meshless method to measure pressure fields from Image Velocimetry, Measurement Science and Technology, 33, 094005, Arxiv at https://arxiv.org/abs/2112.12752 [2] Sperotto, P., Ratz, M., Mendez, M.A (2023), SPICY: a Python toolbox for meshless assimilation from image velocimetry using radial basis functions, Journal of Open-Source Software 9(93), 5749, https://doi.org/10.21105/joss.05749 (open access) [3] Ratz, M., Mendez, M. A. (2024), A Meshless and binless approach to compute statistics in 3D Ensemble PTV, submitted to Experiments in Fluids. arvix at https://arxiv.org/abs/2403.11828.
Please contact the host, Prof. Zhao Pan (zhao.pan@uwaterloo.ca), if any questions.
Towards motor intelligence for soft robots
Speaker: Dr. Cosimo Della Santina
TU Delft, Netherlands
Theme: Robotics, Soft Robots
--------------------------------------------
Time: 2024-Apr-11th, 10:00-11:00 am EDT
Online, Zoom meeting: (link)
Abstract: Continuum soft robots are actuated mechanical systems whose body is composed of continuously deformable materials. In the past decade, substantial progress has been made in developing a low-level artificial brain for soft robotic systems that can make them execute precise motions and eventually exploit the intelligence embedded in their complex mechanical structures. In this talk, I will briefly introduce this grand challenge within the soft robotic field and then present
the model-based view of its solution. I will show how simplified models can be combined with nonlinear control theory and machine learning, leading to precise and dynamic task execution. I will conclude by presenting recent activities within my group concerning combining models with data and
transferring this body of knowledge toward the manipulation of soft objects.
Dr. Cosimo Della Santina is an Assistant Professor at TU Delft and a Guest Scientist at the German Aerospace Institute (DLR). He earned his Ph.D. in robotics (cum laude, 2019) from the University of Pisa. He was a visiting Ph.D. student and a postdoc (2017 to 2019) at MIT's Computer Science and Artificial Intelligence Laboratory. Subsequently, he held a senior postdoc position (2020) and served as a guest lecturer (2021) at the Department of Informatics at the Technical University of Munich (TUM). Cosimo has been awarded the uRobotics Georges Giralt Ph.D. Award (2020), the "Fabrizio Flacco" Young Author Award from I-RAS (2019), and was a finalist for the European Embedded Control Institute Ph.D. award (2020). In 2023, he received the IEEE AS Early Academic Career Award in Robotics and Automation. He is Principal Investigator for European and Dutch projects, such as H2020 Natural Intelligence, HE EMERGE, and Agrifood Nxtgen Hightech. He is an NWO ENI laureate and co-directs the Delft AI lab SELF. Cosimo leads the PhI-Lab at TU Delft, focusing on the study of embodied and disembodied intelligence in physical systems, with an emphasis on elastic and soft robots.
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions
Control of separated flow and suppression of flow-induced vibration with peripheral spinning rods
Speaker: Prof. Gustavo R. S. Assi
University of São Paulo, Brazil
Theme: Fluids and Thermal
--------------------------------------------
Time: Tue, April 9, 2024, 10 - 11 am EST
Location: In person in E7 2343 or Zoom (link) Meeting ID: 789 699 0683
Passcode: MME2024
Abstract: Rotating surfaces are an interesting tool for controlling flow separation around bluff bodies. When spinning rods are strategically placed around a circular cylinder, they disrupt the flow in the boundary layer and near wake, effectively delaying separation and vortex formation. This technique not only influences flow patterns but also reduces separation and mitigates vibration effects induced by the flow, thus helping to minimize vortex-induced vibration. With sufficient rotation, a system of rotating actuators can even neutralize drag or generate beneficial lateral forces. In this presentation, we will discuss experimental and numerical findings from our investigation involving eight rotating rods positioned around a central circular cylinder. Our focus will be on unravelling the fundamental physical mechanisms at play. This innovative approach holds great potential for diverse engineering applications, especially in the oceanic, aerospace, automotive, and civil engineering sectors, where managing flow separation, vibration, and noise is important for optimal performance and safety. Of particular interest, this active flow-control method can be applied to large ocean systems, such as floating offshore platforms with cylindrical hulls, offering new ideas for enhancing their efficiency and stability.
Dr. Gustavo R. S. Assi is the Professor of Renewable Energy and Energy Transition Technologies in the Department of Naval Architecture and Ocean Engineering at the University of São Paulo, Brazil. Deputy Director of the OTIC Offshore Technology Innovation Centre. Member of the Specialist Committee on Ocean Renewable Energy of the ITTC International Towing Tank Conference. A Naval Engineer from USP and PhD in Aeronautics from Imperial College London, he has worked as a Visiting Scholar at the University of Oxford (2013-14), Caltech (2016-17), and is currently at Texas A&M University (2023-24). His research interests include fluid-structure interaction, flow-induced vibration, experimental and computational fluid dynamics, ocean renewable energy, engineering education, science communication, and philosophy of technology.
Please contact the host, Profs. Serhiy Yarusevych (syarus@uwaterloo.ca, in person) and Zhao Pan
(zhao.pan@uwaterloo.ca, online), if any questions.
Let droplets drop the temperature: Enhancing heat transfer using droplets
Speaker: Patricia Weisensee, PhD
Washington University at St. Louis, USA
Theme: Fluids and Thermal
--------------------------------------------
Time: 2024-Feb-26th, 2:00 pm-3:00 pm EST
Online, Zoom meeting: (link) Meeting ID: 789 699 0683
Passcode: MME2024
Abstract: We experience and rely on droplets almost every single day of our lives: some more familiar (the shower in the morning, the rain on our way to work, printing documents once at work, etc.), some less obvious (atmospheric water harvesting, thermal management & power generation, materials manufacturing and processing). Yet we hardly ever think about them – we take them for granted. In this talk I will show that droplets aren’t only ubiquitous in both nature and industrial processes, but also a complex and fascinating research subject that still holds many mysteries to be solved. In my research group, we are especially interested in the coupling of fluid dynamics, heat transfer, and phase change (condensation or evaporation) during the interaction of droplets with solid or other liquid surfaces.
In this presentation, I will introduce two examples of such interactions: 1) droplet impact and evaporation/boiling dynamics on heated surfaces, and 2) dropwise condensation on so-called lubricant-infused surfaces. These oil-coated surfaces can significantly increase water collection rates compared to bare metal surfaces due to extremely high droplet mobility. Lubricant wetting ridges surrounding droplets introduce an attractive capillary force, leading to self-propelled and gravity-independent droplet motion, which efficiently clears the surface for frequent re-nucleation. On the other hand, restricting the mobility of droplets can be advantageous during droplet evaporation. Interestingly, when droplets impact a heated surface, the creation of additional contact lines, either through wettability-patterning the surface or the formation of an entrapped air bubble, does not significantly alter the heat transfer performance. Instead, convection (at early times) and conduction (at later times) dominate heat transfer, meaning that the addition of – for example – metallic posts with high thermal conductivity on the surface can effectively increase heat transfer rates in these scenarios.
Dr. Weisensee is an Assistant Professor in the Department of Mechanical Engineering & Materials Science at Washington University in St. Louis (WashU). She earned her PhD in Mechanical Engineering from the University of Illinois at Urbana-Champaign (UIUC) in 2016. She received a Diplom-Ingenieur in Mechanical Engineering from TU Munich in 2013 and also holds a M.S. in Materials Sciences from UIUC (2011). At WashU, Dr. Weisensee leads the Thermal Fluids Research Group, which focuses on understanding the interplay of fluid dynamics and heat transfer of droplets and other multi-phase systems, with applications in thermal management, water harvesting, additive manufacturing, and droplet interactions with natural and engineered systems. To fundamentally study these thermal-fluidic interactions, her group combines multiple experimental techniques, such as high-speed optical and infrared (IR) imaging, interferometry, confocal fluorescence microscopy, and conventional heat transfer measurements. Dr. Weisensee is a recipient of the NSF CAREER Award, the NASA Early Career Faculty Award, the AFOSR YIP Award, the 2014 Siemens Energy Award, the 2020 ASME ICNMM Outstanding Early Investigator Award, as well as the St. Louis-wide 2020 Emerson Excellence in Teaching Award.
Please contact the host, Prof. Zhao Pan (zhao.pan@uwaterloo.ca), if any questions
Machine Learning and Control for Robot Interaction Autonomy
Speaker: Dr. Arash Ajoudani
Human-Robot Interfaces and Interaction (HRI2), Italian
Institute of Technology, Italy
Theme: Robotics, Machine Learning
--------------------------------------------
Time: 2024-Mar-6th, 10:00-11:00 am EST
Online, Zoom meeting: (link)
Abstract: Future robots are expected to help us in various tasks, of which many require collaborative effort to be successfully completed. To achieve such behaviours, the robot must be able to physically interact with the human counterpart and predict the intentions of the human counterparts, despite the additional interaction with unpredictable environments. Appropriate robot control methods therefore are essential for the robot to deal with various uncertainties, dynamic aspects, and complex task requirements. A promising direction towards this goal is to adaptively regulate
mechanical parameters of the robot via software, based on the task requirements and robot proprioceptive and exteroceptive sensory information. This talk will explore how the Human-Robot Interfaces and Interaction (HRI²) laboratory is using machine learning and control to create more autonomous yet truly collaborative robots, ultimately leading to more adaptable, more efficient interactions in various settings. The talk will cover topics related to real-time human kinodynamic state monitoring in HRI/C and autonomous robot loco-manipulation controllers using hybrid ML and control.
Dr. Arash Ajoudani is the director of the Human-Robot Interfaces and Interaction (HRI²) laboratory at IIT. He is a recipient of the European Research Council (ERC) proof-of-concept grant 2023 Real-Move and the ERC starting grant 2019 (Ergo-Lean), the coordinator of the Horizon-2020 project SOPHIA, the co-coordinator of the Horizon-2020 project CONCERT, and a principal investigator of the HORIZON-MSCA project RAICAM, and the national projects LABORIUS and COROMAN. He is a recipient of the IEEE Robotics and Automation Society (RAS) Early Career Award 2021, and winner of the SmartCup Liguria award 2023, Amazon Research Awards 2019, of the Solution Award 2019 (MECSPE2019), of the KUKA Innovation Award 2018, of the WeRob best poster award 2018, and of the best student paper award at ROBIO 2013. His PhD thesis was a finalist for the Georges Giralt PhD award 2015 - best European PhD thesis in robotics. He was also a finalist for the best paper award on mobile manipulation at IROS 2022, the best paper award at Humanoids 2022 (oral category), the Solution Award 2020 (MECSPE2020), the best conference
paper award at Humanoids 2018, the best interactive paper award at Humanoids 2016, the best oral presentation award at Automatica (SIDRA) 2014, and for the best manipulation paper award at ICRA 2012.
He is the author of the book "Transferring Human Impedance Regulation Skills to Robots" in the Springer Tracts in Advanced Robotics (STAR), and several publications in journals, international conferences, and book chapters. He is currently serving as an elected IEEE RAS AdCom member (2022-2024), and as chair and representative of the IEEERAS Young Professionals Committee, and as a Senior Editor of the International Journal of Robotics Research (IJRR).
He has been serving as a member of scientific advisory committee and as an associate editor for several international journals and conferences such as IEEE RAL, ICRA, IROS, ICORR, etc. He is a scholar of the European Lab for Learning and Intelligent Systems (ELLIS). His main research interests are in physical human-robot interaction, mobile manipulation, robust and adaptive control, assistive robotics, and tele-robotics.
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions.
CASE STUDIES OF MACHINE LEARNING IN HYDROGEN ENERGY: PRACTICAL SOLUTIONS TO IMPROVE THE OPERATION OF HYDROGEN REFUELING STATIONS IN CANADA
Speaker: Yunli Wang, Ph.D.
National Research Council, Canada
Time: 2024-Feb-16th, 11:00 am-12:00 pm EST
In-person at E7-2317 or Zoom meeting: (link)
Meeting ID: 789 699 0683 Passcode: MME2024
Abstract: Hydrogen energy has become an increasingly important renewable energy worldwide. Most existing work developed thermodynamic models or computational fluid dynamics models to investigate the refueling process and optimal hydrogen refueling configurations. In our work, based on real operational data collected from hydrogen refueling stations (HRS) in Canada, we present several case studies using machine learning to improve the operation of HRS. First, classical and robust machine learning models for predicting the refueling process are introduced. Next, several statistical models: Bayesian inference, hierarchical Bayesian inference, and Dirichlet Process Mixture Model are adopted to evaluate the metering accuracy of HRS. Finally, statistical and machine learning models used for predicting the remaining useful life and detecting faults of the compressor in HRS are discussed.
Dr. Yunli Wang is a senior research officer at the Digital Technologies Research Center of National Research Council (NRC). She received her B.S. and M.S. from Northwestern Polytechnical University in 1994 and 1997, and Ph.D. in mechanical engineering from Tsinghua University in 2000. After joining NRC in 2004, she explored the application of machine learning and natural language processing in bioinformatics, public health, and privacy protection of social networks. In recent years, she applied graph neural networks, reinforcement learning, and deep learning models on combinatorial optimization problems and continuous control in robotics. She is leading several NRC projects in AI for design and AI for logistics programs. Since 2019, she has been working on improving the operational efficiency of hydrogen refueling stations. Dr. Yunli Wang has published over 50 journal and peer-reviewed conference papers. She is a PC member and reviewer for AI and NLP conferences such as IJCAI, ACL, LERC, COLING, and journals in health informatics and hydrogen energy.
Please contact the host, Prof. Zhao Pan (zhao.pan@uwaterloo.ca), if any questions
How rain captures air pollution
Speaker: Nathan B Speirs, PhD
BYU Mechanical Engineering Department, USA
Theme: Fluids and Thermal
--------------------------------------------
Time: 2024-Jan-30th, 4:00 pm-5:00 pm EST
Online, Zoom meeting: (link) Meeting ID: 789 699 0683
Passcode: MME2024
Abstract: Human activities and natural sources pollute the air we breathe, harming our health and the environment, and marring the beauty of our skies. One of nature’s processes for cleaning the air is rain. A falling rain droplet sweeps through the air colliding with suspended pollution particles. These particle-droplet collisions have been presumed to be capture events, but the details of what occurs during collision has been unclear. We investigate these collision events and show that rain droplets capture pollution particles internally and on their outer surfaces with multiple collision behaviors, that include cavity-forming droplet entries, ricochets, and more. Rain-drop diameter and free fall velocity, in addition to pollution particle characteristics determine which capture or escape behavior occurs. Our findings reveal that rain does not capture all particulate matter upon collision nor does it capture all airborne pollutants equally. Hence, some pollutants may be more difficult to clean out of the air than others and environmental models on rain scavenging efficiencies should account for both rain and pollution characteristics to more accurately describe pollution fluxes in the environment.
Dr. Nathan B. Speirs joined the faculty of the BYU Mechanical Engineering Department in 2023. His research incorporates high-speed photography with various visualization techniques and theoretical modeling to study interfacial fluid dynamics. Areas of particular interest include how objects enter a body of water, the dynamics of vaporous cavitation bubbles, and the microphysical interactions of rain droplets, cloud droplets, and airborne particulate matter. Before coming to BYU, Dr. Speirs worked at the US Naval Undersea Warfare Center in Newport, RI and as a post-doctoral fellow at King Abdullah University of Science and Technology in Saudi Arabia. He received a PhD in Mechanical Engineering from Utah State University in 2018 and a B.S. in Mechanical Engineering from BYU in 2015.
Please contact the host, Prof. Zhao Pan (zhao.pan@uwaterloo.ca), if any questions
LATEST ADVANCES IN THERMAL INFRARED IMAGING
Speaker: Antoine Dumont, PhD
Telops, Inc., Quebec, Canada
Theme: Thermal and Materials
--------------------------------------------
Time: 2024-Jan-19th, 12:00 pm-1:00 pm ETD
Online, Teams Meeting: (link)
In-person, EC4-1104
Abstract: Telops is pleased to invite you to a Tech Brief Seminar. Discover the most innovative infrared
measurement instruments on the market, offering advanced capabilities for diverse applications including realtime
gas detection, combustion analysis, additive manufacturing, experimental mechanics, IR signature and
more. Antoine Dumont, Field Application Scientist for Telops, will discuss High Speed IR imaging, FTIR
hyperspectral technology, and give a series of examples of measurements acquired with collaborators in the field with Telops’ instruments.
Dr. Antoine Dumont is a Field Application Scientist for Telops in
Quebec City, Canada. He obtained his PhD in Materials Science at the
University of Toronto in 2022. Dr. Dumont has developed an expertise
in a variety of field-based technologies including semiconductor materials
characterization, FTIR and photoelectron spectroscopy, and thin-film
device fabrication. For the past 10 years, he has worked in the area of
optoelectronics and materials physics. In his current role, Dr. Dumont
provides high-level scientific and technical support for Telops’
hyperspectral and broadband infrared imaging cameras for a range of
applications including gas detection, experimental mechanics, mineral
mapping, fluid dynamics, and pyrometry.
If you wish to see live the new hyperspectral cameras with Dr. Dumont, feel free to drop by the seminar inperson in EC4-1104!
Please contact the host, Prof. Kyle Daun (kjdaun@uwaterloo.ca), if any questions
Mechanisms and Consequences of Attributing Socialises to Artificial Agents
Speaker: Prof. Emily Corss
ETH Zurich, Switzerland
Theme: Robotics, Social Interaction
--------------------------------------------
Time: 2023-Nov-17, 10:00 am – 11:00 am
Zoom Meeting ID: 966 7094 8019 (link)
Passcode: MME2022
Summary: Understanding how we perceive and interact with others is a core challenge of social cognition research. This challenge is poised to intensify in importance as the ubiquity of artificial intelligence and the presence of robots in society grows. This talk examines how established theories and methods from psychology and neuroscience reveal fundamental aspects of how people perceive, interact with, and form social relationships with robots. Robots provide a resolutely new approach to studying brain and behavioural flexibility manifest by humans during social interaction. As machines, they deliver behaviours that can be perceived as “social”, even though they are artificial agents and, as such, can be programmed to deliver perfectly determined and reproducible sets of actions. This talk highlights work bridging social cognition, neuroscience and robotics, with important implications not only for social robot design, but equally critically, for our understanding of the neurocognitive mechanisms supporting human social behaviour more generally.
Prof. Emily Cross recently joined ETHZ to establish the Professorship for Social Brain Sciences in Zurich, Switzerland. Prior to this, she was based jointly in Sydney, Australia (at the MARCS Institute at Western Sydney University and the Department of Cognitive Science at Macquarie University) and Glasgow, Scotland (at the School for Psychology and Neuroscience and the University of Glasgow). Emily leads a vibrant and diverse research team that uses brain imaging techniques, robots, and complex action training paradigms to explore how experience-dependent plasticity and expertise is manifest across brain and behaviour, and the affective value of performing arts.
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions
Strategies for Mitigating Fire Performance Problems in New Generation of Concretes and Structures
Speaker: Prof. V.K.R. Kodur
Michigan State University, MI, USA
Theme: Fire
--------------------------------------------
Time: 2023-Nov-16, 3:00 - 4:00pm
In person seminar, Location: E5-2004
Light snacks will be served
Summary: In recent years, the construction industry has shown significant interest in the use of high performance concretes (HPC) in building applications due to the improvements in structural performance, such as high strength and durability, and sustainable solutions that H P C provide as compared to conventional normal-strength concrete (NSC). These high performance concretes, which include concrete types such high strength concrete (HSC), fiber reinforced concrete (FRC), self-consolidated concrete (SCC), and ultra HPC (UHPC), are typically characterized by higher strength, higher sustainability, lower permeability and thus enhanced durability properties. The use of HPC, together with innovative cross-sectional configurations (such as hollow-core slabs, double T beams and deck slabs), and advanced analysis techniques, often lead to slender members in modern structures, especially concrete buildings. Conventional concretes possess good fire resistance properties and hence concrete structures made of NSC exhibit good fire resistance and resiliency properties. However, number of studies have clearly shown that HPC exhibit poor fire resistance properties, as compared to NSC. Specifically, certain HPC types undergo rapid degradation of strength at elevated temperatures and are also susceptible to explosive spalling under severe fire conditions. These poor fire resistance properties of HPC, together with reduced cross sectional sizes of HSC structural members, can lead to lower fire resistance and lower resiliency in HPC structural systems. In the presentation, severe conditions such as high fire intensity, weaker structural configuration, and poorer material characteristics that can be present in modern buildings, with respect to fire performance will be highlighted. The performance problems associated with high performance concretes under fire conditions will be discussed. Examples of innovative strategies for enhancing fire performance and resiliency of HPC structural systems will be presented. Specific guidelines to enhance fire resistance of HPC members, such as the use of bent ties in columns and addition of fibres to HPC to mitigate fire induced spalling, will be discussed. Through case studies it will be demonstrated that by adopting proper strategies, both at material and structural levels, fire resistance and and resiliency of HPC structures can be enhanced.
Dr. Venkatesh Kodur is a University Distinguished Professor and Director of the Centre on Structural Fire Engineering and Diagnostics at Michigan State University. He is an internationally recognized scholar for his contributions in civil and fire engineering fields and his research accomplishments have had major impacts. He has developed fundamental understanding on the behavior of materials and structural systems under extreme fire conditions. The techniques and methodologies resulting from his research is instrumental for minimizing the destructive impact of fire in the built infrastructure, which continues to cause thousands of deaths and billions of dollars of damage each year in the U.S. and around the world. Many of these design approaches and fire resistance solutions have been incorporated in to various construction codes and design standards in the U.S. and around the world. Dr. Kodur has an outstanding record for international research initiatives and collaborations and has collaborated with top researchers and prestigious organizations from about two dozen countries to produce high quality deliverables. He has published results from his research in 500+ peer-reviewed papers in journals and conferences and has given numerous key-note presentations in major international conferences. He is one of the highly cited authors in Civil Engineering and Fire Protection Engineering disciplines, and as per Google Scholar, he has more than 19,800 citations with an "h” index of 79. Dr. Kodur has served in various leadership positions, including as Chairperson (Head) and Associate Chairperson of the Department of Civil and Environment Engineering at MSU, and as Chair of various technical committees of leading professional societies and on editorial boards of leading journals. In recognition of his contributions, he has been elected as Fellow of seven Institutes and Academies; including He has been elected as Fellow of seven Institutes/Academies.
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions
MOTION OF LARGE PARTICLES IN TURBULENT BOUNDARY LAYERS
Speaker: Prof. Ellen Longmire
University of Minnesota, USA
Theme: Solids, materials, and Fluids
---------------------------------------------------
Time: 2023-Oct-26th, 11:30 am-12:30 am ETD
Zoom Meeting ID: 789 699 0683 (link) Pass Code: MME2023
Abstract: Our work is motivated by the need to understand and predict turbulent particle-laden flows across a range of environmental and industrial applications. We consider a relatively canonical yet challenging experimental flow designed to be accessible to direct numerical simulation. A spherical particle in a turbulent boundary layer undergoes complicated particle-wall and particle-turbulence interactions. Particles with significant diameter are subject to variations in shear and normal forces around their circumference. Wall friction will affect the particle rolling and sliding motions while coherent flow structures can lift the particle away from the wall. To resolve the sphere dynamics in such a flow, 3D tracking experiments were conducted in a water channel facility. The translation and rotation of individual spheres released from rest were tracked over distances of 6d for multiple flow Reynolds numbers and particle-to-fluid density ratios. Simultaneous stereoscopic PIV measurements were acquired in the logarithmic region surrounding the moving spheres. While neutrally buoyant particles typically lift off from the wall upon release, denser particles travel mostly along the wall. The relative contributions of turbulence, wall friction, and mean shear to the resulting particle motions will be discussed for the different cases considered.
Professor Ellen Longmire received an A.B. in physics (1982) from Princeton University and M.S. (1985) and Ph.D. (1991) degrees in mechanical engineering from Stanford University. Since 1990, she has taught and directed research in the Department of Aerospace Engineering and Mechanics at the University of Minnesota. She also served as Associate Dean of the College of Science and Engineering for five years. Professor Longmire uses experimentation and analysis to answer fundamental questions in fluid dynamics that affect industrial, biomedical, and environmental applications. She is a Fellow of the American Physical Society and received the UM Distinguished Women Scholars Award, the McKnight Land-Grant Professorship, and the NSF National Young Investigator Award. She is currently an Editor-in-Chief for Experiments in Fluids. She previously served as Chair of the APS Division of Fluid Dynamics and a member of the US National Committee on Theoretical and Applied Mechanics. In her spare time, she enjoys many outdoor activities as well as cooking and travelling.
Please contact the host, Prof. Zhao Pan (zhao.pan@uwaterloo.ca), if any questions.
Introducing crack-arrest features in adhesive bonding by manipulating intrinsic and extrinsic dissipations
Speaker: Prof. Gilles Lubineau
KAUST, Saudi Arabia
Theme: Materials
--------------------------------------------
Time: 2023-Oct-11, 9:00 am – 10:00 am
Zoom Meeting ID: 966 7094 8019 (link) Passcode: MME2022
Summary: Reducing emissions of pollutants is a key priority to fight again the climatic changes that we are going to face over the 21st century. More and more pressing environmental constraints are shaping the new technological solutions in the transportation sector, from personal cars up to mass air transport. Automotive and aerospace industries are then seeking new solutions to create lighter structures to reduce fuel consumption or make easier the transition to electrical vehicles. Extreme lightweight structures can today be obtained by using high-performance composites based on continuous fibers and polymeric matrices. These materials that were reserved before to high tech industries, will become even more common tomorrow with the expected cut in the production cost of carbon fibers. Assembling composite parts is, however, still a challenge that often jeopardizes the energy efficiency of structures. Classical joining techniques, such as bolting and riveting, add to the total structural weight and require hole drilling. These result in extra cost due to manufacturing and to extra weight (due to rivets/bolt and locally increased composite thickness to ensure integrity of the substrate). Designers have thought for a long time about replacing the “bolted” solution with integral adhesive bonding. In such joints, the mechanical cohesion between parts is only ensured by an intermediary adhesive layer. This would minimize the additional work and weight needed to realize the assembly. However, integral adhesive bonding is not used for primary structure today, because of its extreme sensitivity to the quality of the substrate preparation that can largely modify the intrinsic performance of the joint. More important for us, the failure of adhesive joints is often unstable: the joint behaves well until the development of a catastrophic crack that would propagate throughout the whole joint, resulting in the loss of the application. In a sense, adhesive-based-design is missing today the “crack arrest” function that is fulfilled by bolts. There are arresting the cracks even in case of premature failure, providing enough time to repair the structure before catastrophic failure.
Our objective is here to introduce new strategies to equip by design adhesive interfaces with crack arrest features. From a practical point of view, we are manipulating the R-curve of the interface by introducing non-local dissipative mechanisms, such as bridging, that will add to the classical cohesive energy of the adhesive.
Pr. Gilles Lubineau is professor of Mechanical Engineering in the Physical Science and Engineering Division and Director of ENERCOMP, a Technology Consortium for Composites in Energy Applications. He is principal investigator of the Laboratory of Mechanics for Energy and Mobility, an integrated environment for composite engineering that he created in 2009 when joining KAUST). Following his “aggregation” in theoretical mechanics, Pr. Lubineau earned a PhD degree in Mechanical Engineering from École Normale Supérieure de Cachan (ENS-Cachan), France. Before joining KAUST, Pr. Lubineau was a faculty member at the École Normale Supérieure of Cachan, and a non-resident Instructor at the École Polytechnique, France. He also served as a visiting researcher at UC-Berkeley and as Interim Dean of the Physical Science and Engineering Division at KAUST. His fields of research include: integrity at short and/or long-term of composite materials and structures, inverse problems for the identification of constitutive parameters, multi-scale coupling technique, nano and/or multifunctional materials. He covers a wide expertise related to most fields of composite materials, with over 200 published papers in journal spanning from material science (Advanced Materials, Macromolecules, etc..), Composites Engineering, all the way to theoretical mechanics (JMPS, CST, Scientific Reports) and applied maths (IJNME, CMAME, etc..). He is also board member for various journals, including the International Journal of Damage Mechanics. Prof. Lubineau is an elected Member of the European Academy of Sciences and Arts.
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions
Safe and Efficient Robot Learning from Structured Data
Speaker: Dr. Raffaello Camoriano
Politecnico di Torino, Italy
Theme: Robotics, Learning
--------------------------------------------
Time: 2023-Oct-06, 11:30 am – 12:30 pm
In person seminar
Location: E5-2004
Light snacks will be served
Summary: Recently successful machine-learning solutions to longstanding perceptual and decision-making problems focus on accuracy and success-rate metrics to demonstrate superhuman performance. Such endeavors propel the field forward by showing what is achievable, yet with virtually unlimited data, energy, computations, memory, and labeling resources. Meanwhile, real-world domains such as robotics impose a variety of resource budgets on learning systems. This cal ls for the development of more flexible and efficient learning methods in terms of training and prediction time and memory, requiring limited expert supervision. Moreover, robots are required to operate safely in dynamic environments, which requires the ability to operate on structured data (e.g., sequences, manifolds, etc.). In this talk, we will explore a range of solutions for efficient and structured learning. I will introduce recent techniques for trading off time, memory, and accuracy when training large-scale kernel machines. Then, we will see how kernel methods can be extended to enable incremental learning with fixed update complexity, allowing for adaptive learning in real time, e.g., for robot vision, robotic prosthesis control, and dynamics estimation. We will also see how structured prediction enables imitation learning and model learning even in presence of misspecified priors. To conclude, I will present recent work and open challenges on learning for whole-body humanoid robot locomotion control via end-to-end reinforcement learning and efficient trajectory generation via imitation of human motion capture data.
•
Duan A, Batzianoulis I, Camoriano R, Rosasco L, Pucci D, Billard A, A Structured Prediction Approach for Robot Imitation Learning, IJRR (to appear), 2023
•
Viceconte PM, et al. "Adherent: Learning human-like trajectory generators for whole-body control of humanoid robots." IEEE RAL, 2022
•
Ferigo D*, Camoriano R*, et al. "On the emergence of whole-body strategies from humanoid robot push-recovery learning." IEEE RAL, 2021
Dr. Raffaello Camoriano received his B. Sc. in Computer Engineering cum laude in 2011 and his M. Sc. in Robotics Engineering with top grades in 2013 from the University of Genoa (UniGe), Italy. He was awarded a 5-year ISICT/ISSUGE scholarship for the highest-ranking EECS students in Genoa, and a regional government prize for excellent students. He completed his Ph. D. in Bioengineering and Robotics (curriculum in humanoid robotics) at UniGe in 2017, also working at the Italian Institute of Technology (IIT) under the supervision of Prof. Giorgio Metta and Prof. Lorenzo Rosasco. He was awarded the IEEE Computational Intelligence Society Italy Section Chapter s 2017 Best Ph. D. Thesis Award for his Thesis "Large-scale Kernel Methods and Applications to Lifelong Robot Learning". After his Ph. D., Raffaello worked as a PostDoc at IIT on machine learning (efficient and scalable kernel methods, lifelong/incremental learning, and reinforcement learning) and applications to robotics (model learning, locomotion control, and robot vision) in collaboration with Lorenzo Rosasco, Lorenzo Natale, and Daniele Pucci. Raffaello is currently an Assistant Professor at Politecnico di Torino, Italy, and a membr of the ELLIS Unit Turin and the VANDAL Laboratory. His research interests lie at the intersection between the Science and the Engineering of artificial learning systems. In particular, his work is chiefly focused on devising theoretically-grounded Machine Learning methods capable of scaling up to large and structured datasets, adapting to changing conditions in time, and efficiently interacting with their environments to learn faster and generalize better. He also finds Robotics to be a rich source of -and a particularly well-suited testing platform for- challenging open research problems in Machne Learning. His work in this direction mainly spans locomotion control, model learning, and imitation learning, reinforcement learning, and visual object recognition.
Please contact the host, Prof. Yue Hu (yue.hu@uwaterloo.ca), if any questions
PhD Seminars | MASc Seminars | Past Seminars
PhD Seminars
PhD Comprehensive Examination
( Attendance is at the discretion of the supervisor and student who hold the exam)
Akash Chowdhury - Thursday, October 3, 2024 from 1:00 PM - 4:00 PM E5 - 3006 in person
Title: Dynamics of droplet impact at different interfaces
Supervisor: Sushanta Mitra
JiUng Kim - Tuesday, October 29, 2024 from 1:00 PM to 4:00 PM in person
Title: LME Crack In-situ Monitoring by Photography and Thermography: Role of Temperature Gradient at Shoulder Area on LME Crack during Resistance Spot Welding
Supervisor: Elliot Biro
Will Thibault - Monday, November 11, 2024 from 10:00 AM to 1:00 PM Remote
Title: Humanoid Loco-manipulation for Object Handling in Logistics and Warehouse Settings
Supervisors: William Melek / Katja Mombaur
Wang June - Monday, November 11, 2024 from 3:00 PM to 6:00 PM Remote
Title: Scalable diagnostic of two-dimensional materials and device applications
Supervisors: Kyle Daun / Na Young Kim
Maksym Veremchuk - Tuedsay, November 12, 2024 from 12:15 PM to 3:15 PM E5-2004 Hybrid
Title: Integrating Nudging and Neural Operators in a Data-Driven Assimilation Framework
Supervisors: Zhao Pan / Andrea Scott
Jose Roberto Rosas Bustos - Monday, November 25, 2024 from 10:00 AM to 1:00 PM E5 - 3006 in person
Title: Enhancing Quantum Internet Security and Efficiency through Dynamic Modulation, Data Co-Transmission and Quantum State Authentication
Supervisors: Roydon Fraser / Jesse Van Griensven Thé
Navid Assi - Wednesday, December 4, 2024 from 9:00 AM to 12:00 PM Remote
Title: Metal Extraction from Lunar Regolith and Their Applications in Emerging Energy and Material Technologies
Supervisor: John Wen
PhD Defense
Ahmad Reza Alghooneh - Friday, November 8, 2024 from 2:30 PM to 5:30 PM Remote
Title: A Unified Multi-Frame Approach for Autonomous Vehicle Perception and Localization Using Radar, Camera, LiDAR, and HD Map Fusion
Supervisors: Amir Khajepour / George Shaker
Farima Liravi - Friday, November 8, 2024 from 1:00 PM to 4:00 PM Online
Title: Machine Learning-Driven Optimization of Laser Powder Bed Fusion: From Powder Characterization to Process Parameter
Supervisor: Ehsan Toyserkani
Devon Hartlen - Thursday, November 14, 2024 from 9:00 AM to 12:00 PM EC 4 - 1104 In Person
Title: Development of Novel Techniques to Characterize the Traction-Separation Responses of Delamination in Fibre-reinforced Plastic Laminates
Supervisors: John Montseno / Duane Cronin
Lei Wang - Friday, November 22, 2024 from 8:00 AM to 11:00 AM Remote
Title: Modulation Strategies of Cu-based electrocatalysts for Enhancing Electrocatalytic CO2 Conversion
Supervisors:Yimin Wu / Chao Tan
Ahmed Abdalhamid - Wednesday, November 27, 2024 from 10:00 AM to 1:00 PM PM E5 - 3052
Title: Development of Conditional Source-term Estimation (CSE) Framework for Turbulent Buoyant Diffusion Flames
Supervisor: Cecile Devuad
Salman Lari - Thursday, December 5, 2024 from 9:00 AM to 12:00 PM online
Title: AI-Assisted Ultrasound-Guided High-Intensity Focused Ultrasound (USgHIFU) in Non-Invasive Surgery
Supervisors: HJ Kwon / Jong Uk Kim
Alison Zilstra - Monday, December 9, 2024 from 9:00 AM to 12:00 PM E5 - 3052
Title: The Role of the Laminar Separation Bubble in Wind Turbine Aeroacoustics and Dynamic Stall
Supervisor: David Johnson
Martine McGregor - Tuesday, December 10, 2024 from 12:00 PM to 3:00 PM E5 - 3052 in person
Title: A Biomechanical Investigation of Traditional and Additively Manufactured Lumbar Spinal Implants under Physiologic Loading
Supervisor: Stewart McLachlin
Wenrui Ye - Thursday, January 9, 2025 from 1:00 PM to 4:00 PM Remote
Supervisors: John Wen / Jatin Nathwani
Title: AI-Driven Simulation and Optimization of Renewable Energy Systems
Adithya Legala - Friday, January 17, 2025 from 10: 00 AM to 1:00 PM Remote
Title: Data-Based Modeling of Electrochemical Energy and Thermal Systems: Fuel Cell and Lithium-Ion Battery
Supervisor: Xianguo Li
Master's Seminars
Mohsen Mondegari - Dec 13th 2024 in E5-3006, 3:00pm
Title: Modeling Ablation in Al/CuO Nanothermite Pellet Combustion
Supervisor: Dr. Jean-Pierre Hickey
Jonathan Chu - December 11, 2024, 1:00pm, E5 3052
Title: Detection of Cervical Spine Vertebrae on MRI towards Improving Multi-modal Image Registration
Supervisor: Stewart McLachlin and Alexander Wong
Sophia Ngan - Friday, December, 6, 2024, 1:30 pm, EC 1104
Title: Multi-Physics Smoothed Particle Hydrodynamics Implementation to Enhance Vertebral Fracture in a Finite Element Model of a Lower Cervical Spine Segment Under Compression
Supervisor: Duane Cronin
Matheus Seif Reis - November 29, 2024, at 1:30 pm, EC4-1104 (in person)
Title: Neck Injury Risk in Non-Neutral Position Rear Impact Scenarios Using a Reference Geometry-Based Head Repositioning
Supervisor: Duane Cronin
Andrew Ko - 29 November 2024 - 1:00 to 2:00 PM, Online
Title: Durability of Aluminum-Copper Laser Welds for EV Battery Applications
Supervisor: Hamed Jahed and Adrian Gerlich
Steven Tuer - August 8, 2024 at 1:00pm in room E3 4117
Title: MPC for Off-Road Vehicle Trajectory Tracking
Supervisor: Amir Khajepour
Maltiti Braimah - August 1, 2024, 9:00amin room E3 4117
Title: Design, Fabrication, and Testing of Assistive Mobility Solutions for Health Care Facilities
Supervisor: Amir Khajepour
Geoffrey Hanks - July 25, 2024, 11:00am, E512103
Title: Skill Transfer from Multiple Human Demonstrators to a Robot Manipulator Using Neural Dynamic Motion Primitives
Supervisor: Yue Hue
Tanvi Seeburrun - Wednesday, June 26th at 9:30 AM in EC4 1104
Title: Investigation of Brain Response in Canadian Armed Forces Volunteers Subjected to Recoil Force from Firing Long-Range Rifles Using Instrumented Mouthguards and Finite Element Head Model
Supervisor: Duane Cronin
Brijesh Parsana - : April 16, 2024, 9:00 AM to 10:00 AM, E5 3052
Title: Finite Element Analysis of Multi-Material Die-Cast Tooling by Additive Manufacturing
Supervisors: Mihaela Vlasea and Saeed Maleksaeedi
Kai Zhang - April 15th, 2:30 pm
Title: A Study on Laser Tissue Welding Using Porcine Skeletal Muscle Tissue as a Model
Supervisors: Michael Mayer and Norman Zhou
Dominic Tung - Tuesday, April 9th from 10:30am - 11:30am in E5 3006.
Title: Design & Development of Microneedle Pads for AEDs
Supervisor: Naveen Chandrashekar
Rami Hakim - April 4 from 2 pm to 3:30 pm. E5 3052
Title: Characterization in Wire Arc Additive Manufacturing: Anisotrophy Analysis and Layer Height Investigation
Supervisor: Adrian Gerlich
Nourhan Abdulazeem - April 3, at 10:30 am in room E5-3006.
Title: Quantifying Human Mental States in Physical Human-Robot Interaction
Supervisor: Yue Hu
Javier Maldonado-Echeverria - January 24th, from 3:30 to 5:30 pm, EC4 1104
Title: Brain Response to Overpressure and Recoil Loads from Discharge of Long-Range
Precision Rifle
Supervisor: Duane Cronin
Chenshuo Wang - January 15, 2024, from 12:30 pm to 2:30 pm at ERC-3012
Title: Utilization of industrial waste alloy as an alternative to micron-Al in energetic applications
Supervisor: John Wen
John Francis Marrone - December 4th at 3pm, E5-2103
Title: Adapting Regenerative Braking to Driver Preference
Supervisor: Dr. Roydon Fraser
Alex DiPaola - Friday Dec 1st, 2023, 9:30 am to 11:00 am, E5 3006
Title: Furniture Fire Dynamics and Smoke Flow in a Two-Story House With Mechanical Ventilation
Supervisor: Beth Weckman
Michael Lenover - November 22, 2023. This seminar will be held online.
Title: Development of a Scalable Machining Feature Recognition System
Supervisor: Sanjeev Bedi & Stephen Mann