Sethu Vijayakumar

Chair in Robotics within the School of Informatics at the University of Edinburgh
Director of the Edinburgh Centre for Robotics and Programme Director for Robotics and AI at The Alan Turing Institute
University of Edinburgh, UK

Speech Title: From Automation to Autonomy: Embodied Generative AI Driving the Future of Work

Speech Abstract:
The use of AI and Robotics in our society is becoming ubiquitous and inevitable across various walks of life. The new generation of robots work much more closely with humans, other robots and interact significantly with the environment around it. As a result, the key paradigms are shifting from isolated decision making systems to one that involves shared control — with significant autonomy devolved to the robot platform; and end-users in the loop making only high level decisions.
This session will introduce powerful machine learning technologies ranging from robust multi-modal sensing, shared representations, scalable real-time learning and adaptation, and compliant actuation that are enabling us to reap the benefits of increased autonomy while still feeling securely in control – with focus on latest algorithmic and hardware developments. This also raises some fundamental questions: while the robots are ready to share control, what is the optimal trade-off between autonomy and control that we are comfortable with? Domains where this debate is relevant include deployment of robots in surgical interventions, extreme environments, self-driving cars, asset inspection, repair & maintenance, factories of the future and assisted living technologies including exoskeletons and prosthetics to list a few.

Sethu Vijayakumar FRSE holds a Personal Chair in Robotics within the School of Informatics at the University of Edinburgh and is the Director of the Edinburgh Centre for Robotics and Programme Director for Robotics and AI at The Alan Turing Institute. He is a Fellow of the Royal Society of Edinburgh and the winner of the 2015 Tam Dalyell Prize for Excellence in Engaging the Public with Science. He was a judge on the latest edition of BBC Robot Wars, a hugely popular technology show as well as involved with the launch of the BBC micro:bit coding initiative.

Yizhou Yu

Chair Professor
Fellow of ACM/IEEE
The University of Hong Kong, China

Speech Title: Towards Region Understanding Vision Language Model

Speech Abstract:
Vision language models (VLMs) have experienced rapid advancements through the integration of large language models (LLMs) with image-text pairs, yet they struggle with detailed regional visual understanding due to limited spatial awareness of the vision encoder, and the use of coarse-grained training data that lacks detailed, region-specific captions. To address this, we introduce RegionGPT (short as RGPT), a novel framework designed for complex region-level captioning and understanding. RGPT enhances the spatial awareness of regional representation with simple yet effective modifications to existing visual encoders in VLMs. We further improve performance on tasks requiring a specific output scope by integrating task-guided instruction prompts during both training and inference phases, while maintaining the model’s versatility for general-purpose tasks. Additionally, we develop an automated region caption data generation pipeline, enriching the training set with detailed region-level captions. We demonstrate that a universal RGPT model can be effectively applied and significantly enhance performance across a range of region-level tasks, including but not limited to complex region descriptions, reasoning, object classification, and referring expressions comprehension.

Yizhou Yu is a chair professor and the director of AI Lab in the Department of Computer Science at the University of Hong Kong. He was first a tenure-track and then a tenured professor at University of Illinois, Urbana-Champaign (UIUC) for twelve years. He has also collaborated with Google Brain and Microsoft Research in the past. He received his PhD degree in computer science from the computer vision group at University of California, Berkeley. He also holds an MS degree in applied mathematics and a BE degree in computer science and engineering from Zhejiang University. He is an ACM Fellow and IEEE Fellow.

Dipti Srinivasan

Professor, IEEE Fellow
National University of Singapore, Singapore

Speech Title: Harnessing Data Analytics and Deep Learning for Uncertainty Management in Smart Grids

Speech Abstract:
The evolution from traditional power systems to smart grids presents both unprecedented opportunities and complex challenges, particularly with the extensive integration of renewable energy sources. The inherent variability and uncertainty associated with renewable generation significantly threaten grid stability, reliability, and efficiency. In response to these challenges, data analytics has emerged as a crucial tool, enabling the effective capture, modeling, and management of uncertainties within smart grid operations. This lecture will explore the critical role of data analytics in capturing and managing uncertainties within smart energy systems. The discussion will focus on three key areas: (1) the challenge of modeling uncertainties in renewable energy generation, particularly from rooftop photovoltaic (PV) systems; (2) addressing the variability in energy demands at both the community and building levels; and (3) strategies for managing uncertainties to ensure the efficient and reliable distribution of energy. Real-world examples will be presented to illustrate how these techniques are applied in practice. Additionally, the lecture will highlight emerging challenges and innovative solutions for uncertainty management as smart energy systems evolve in complexity.

Dipti Srinivasan is a Professor in the Dept. of Electrical & Computer Engineering, where she also heads the Centre for Green Energy Management & Smart Grid (GEMS). She is a Fellow of IEEE, and was awarded the IEEE PES Outstanding Engineer award in 2010. She is currently serving as an Associate Editor of IEEE Transactions on Sustainable Energy, IEEE Transactions on Smart Grid, IEEE Transactions on Evolutionary Computation, IEEE Transactions on Neural Networks and Learning Systems, and IEEE Computational Intelligence magazine.

Claudio Cañizares

University Professor
Fellow of CAE/IEEE
University of Waterloo, Canada

Speech Title: Microgrids Overview

Speech Abstract:
Microgrids are not new to power systems, since these local and small grids have been widely deployed and utilized for decades to supply electricity in remote and isolated communities such as islands and remote villages throughout the world. However, more recently, there has been a rapid development and deployment of microgrids in the context of smart and resilient power networks and cities, in good part motivated by the need to integrate distributed generation, especially if powered by renewable resources such as wind and solar, to reduce operational costs and environmental impact, as well as increase energy resiliency, particularly in diesel-depended isolated microgrids.

The presentation will provide a general overview of microgrids and the research work being carried out by Prof. Canizares’ group at the University of Waterloo on the area, including a summary of a survey carried out by the group on remote microgrids in Canada, and a detailed description of the microgrid in one of these communities, namely, the Kasabonika Lake First Nation (KLFN) community microgrid in Northern Ontario, where a one-year measuring campaign was carried out to identify main technical issues associated with these kinds of microgrids. A general description of the group’s main research contributions and findings in the area of microgrids, with several practical examples, will be provided, focusing on dispatch, control, stability, and optimal planning. In particular, the following subjects will be discussed in some detail: Energy Management Systems (EMS) considering renewable power uncertainty; thermal energy system integration in microgrids with high penetration of variable renewable power; voltage and frequency control and stability and its definitions, modeling, simulation, and analysis; optimal placement and sizing of renewable power equipment for minimization of costs and diesel use, considering secure system operation; and dc microgrid EMS.

Claudio Cañizares is a University Professor and Hydro One Endowed Chair in the electrical and computer engineering (ECE) department at the University of Waterloo, where he has held various academic and administrative positions since 1993. In 2021, he was appointed the Executive Director of the Waterloo Institute for Sustainable Energy (WISE). He is the current Editor-In-Chief of the IEEE Transactions on Smart Grid, a Fellow of the Institute of Electrical & Electronic Engineering (IEEE), a Fellow of the Royal Society of Canada, a Fellow of the Canadian Academy of Engineering, and a Fellow of the Chinese Society for Electrical Engineering (CSEE).