Han-Lim Choi, KAIST, Korea
Multi-Agent Planning for Information Gathering
Abstract: This talk addresses planning of networked agents, in particular when the goal is to collect/extract information from the mission environment. Two representative formulations – maximization of mutual information and traveling salesperson with neighborhoods – are introduced, and the associated solution methodologies are presented. Key challenges in decentralized decision making in the information gathering contexts are also discussed.
Bio: Han-Lim Choi is a Professor of Aerospace Engineering at KAIST (Korea Advanced Institute of Science and Technology), and a Visiting Scholar in the School of Aeronautics and Astronautics at Purdue University. He received his B.S. and M.S. degrees in Aerospace Engineering from KAIST, Daejeon, Korea, in 2000 and 2002, respectively, and his PhD degree in Aeronautics and Astronautics from Massachusetts Institute of Technology (MIT), Cambridge, MA, USA, in 2009. He then worked at MIT as a postdoctoral associate until he joined KAIST in 2010. His current research interests include planning and control of multi-agent systems, planning and control under uncertainty, and Bayesian inference for large-scale systems. He (together with Dr. Jonathan P. How) is the recipient of Automatica Applications Prize in 2011, and he was selected as the main role for 100 key future technologies by The National Academy of Engineering of Korea in 2017.
Fan Zhu, XJTLU, China
Robotic intelligence and automation: from robotic manipulator to mobile robot
Abstract: With the development of robotic intelligence and automation, robots are widely applied not only in manufacturing but also in the service industry. Engineers have yet to solve some fundamental problems involving robotic perception, world modelling, automated reasoning, manipulation of objects and locomotion.
The talk will first address the intelligent robotic manipulation with sensor fusion. It attempts to understand and emulate the restraint and manipulation of objects as humans. The talk will also present algorithms to navigate for an autonomous mobile robot. In a rapidly ageing society, the significance of mobile robotics for the elderly community will be highlighted in the demonstration.
Bio: Dr. Fan Zhu received her Ph.D. degree in Computer Science from The University of Hong Kong in 2021. In 2016, she obtained her B.Eng. degree in Computer Science and Technology at Shandong University. Her research interests include Computer Vision, AI-driven Robotic Manipulation, Autonomous Navigation, and Sensor Fusion in Robotics.
Yeong Che Fai, Universiti Teknologi Malaysia
Autonomous Mobile Robot (AMR) Technology for Industry 4.0 & Sustainability
Abstract: The Fourth Industrial Revolution, Industry 4.0, brings a paradigm shift with interconnected systems and the rise of robots, especially Autonomous Mobile Robots (AMRs). These robots, capable of navigating industrial terrains, play crucial roles in automating indoor logistic material handling. AMRs enhance operational efficiency and provide real-time data insights. Their impact on sustainability is profound: reducing the need for human labor cuts down daily commutes and associated CO2 emissions. Their precision minimizes waste and optimizes resource use, marrying productivity with environmental responsibility. This talk offers a deep dive into AMRs’ case studies and transformative potential in a sustainable, interconnected future.
Bio: Dr. Yeong Che Fai is an Associate Professor at Universiti Teknologi Malaysia. He is also the CEO and Co-founder of DF Automation and Robotics. Dr. Yeong earned his PhD from Imperial College London and specializes in robotics and entrepreneurship. Dr. Yeong has co-founded several companies. One of his most notable ventures is DF, which produces Industry 4.0-enabled robots that have been successfully exported to various countries including to Asia, Mexico and Europe. Dr Yeong is also a frequent keynote speaker and three-time TEDx speaker.
Xiaowei Huang, University of Liverpool, United Kingdom
Challenges on Safety and Trustworthiness of Learning-Enabled Autonomous Systems
Abstract: Systems with machine learning components, or AI-based systems, have become ubiquitous and indispensable in our daily lives. Their adoptions in safety critical sectors, such as nuclear and aerospace, are lagging behind. Even for other safety critical sectors where machine learning has been applied, e.g., the transportation sector where various vehicles with machine learning models integrated to support perception and adaptive control, AI regulations have been imposed to ensure their safety and trustworthiness. This talk will present the challenges that data-driven machine learning systems bring to the field of rigorous engineering for safety critical systems, and discuss why such challenges call for new verification and validation techniques.
Bio: Xiaowei Huang is Professor of Computer Science at the University of Liverpool, leads the Trustworthy Autonomous Cyber-Physics Systems laboratory, and acts as the Research Lead of the school of EEECS. His research interests span over AI Safety and Security, verification and validation of learning-enabled systems, explainable AI, and formal methods. He had seminal works on “safety verification of deep learning” and published a textbook “Machine Learning Safety”. He has published 100+ papers, most of which appeared in top conferences such as AAAI, IJCAI, CAV, ICSE, NeurIPS, CVPR, ICRA, and IROS. He co-chairs AISafety workshops since 2018, and his research is supported by EPSRC, EU, Innovate UK, and Dstl.
Zahari Taha, Academy of Sciences Malaysia
AI Machine Vision for Sustainable Digital Manufacturing
Abstract: Sustainable manufacturing focuses on the efficient use of natural resources, minimizing waste and reducing energy consumption. The implementation of sustainable manufacturing can range from very simple process improvements to large investments in new technologies and product redesign. Artificial Intelligence can be implemented at the various stages of the implementation of sustainable manufacturing which includes housekeeping, process optimization, raw material substitution, new technologies and new product design. In this presentation we discuss an area of Artificial Intelligence which is deep learning machine vision and how it can create a sustainable digital manufacturing environment. Machine vision is a key technology for industrial automation, enabling faster, safer, and more accurate production processes. In particular deep learning machine vision can be applied in detecting defects more efficiently which will help to reduce waste. Deep learning-based systems are well-suited for visual inspections that are more complex in nature: patterns that vary in subtle but tolerable ways. It is good at addressing complex surface and cosmetic defects, like scratches and dents on parts that are turned, brushed, or shiny. By using cameras, sensors, and deep learning software to inspect and measure the quality and performance of products and components, deep learning machine vision can save material and energy costs, and avoids the environmental impact of disposing or recycling faulty products. Data on defects can also be collected and analyzed for process improvement. Deep Learning machine vision can enable predictive maintenance, which is the use of data and analytics to anticipate and prevent failures and breakdowns of machines and devices. By using machine vision to collect and process information about the condition, performance, and wear of equipment, industrial automation systems can schedule and perform timely repairs and replacements, avoiding downtime and extending the lifespan of the assets. An example of this is corrosion. According to the NACE International, The Worldwide Corrosion Authority, the global cost of corrosion is estimated to be US$2.5 trillion. Implementing corrosion management practices could save between 15-35% – around US$875 billion annually. The traditional maintenance process involves an engineer spending a month studying around 6,000 images to manually mark up the corrosion. Each oil rig has an average of 20,000 images, meaning that would take over four months of human analysis per rig.
Bio: Professor Zahari Taha received his BSc (Hons) in Aeronautical Engineering from the University of Bath in 1983 and at 27 received his Ph.D. from the University of Wales Institute of Science and Technology in 1987 (now known as University of Wales Cardiff). He then joined the mechanical engineering department at UM as a lecturer in 1987. He was promoted to Professor Grade C in 2000 and Professor Grade B in 2008. Professor Zahari was appointed Dean of Engineering from 2001 to 2004 during which the faculty of engineering and the university obtained MS ISO 9001:2000, the first University to do so in Malaysia. University of Malaya also rose to 89th position among the world’s top 100 universities in THES-QS (Times Higher Education Supplement-Quacquarelli Symonds) ranking in 2004. He was appointed again as Dean from 2006 to 2007. He was also the founding Director of the Center for Product Design and Manufacturing at UM. In 2010, he was invited as Professor Grade A in Mechatronics and Manufacturing for the joint degree program between University Malaysia Pahang and Karlsruhe University of Applied Science Germany. He was appointed Dean of Mechanical Engineering and Assistant Vice Chancellor of Pekan Campus from 2011 to 2013. Prof Zahari taught and conducted research in the areas of industrial automation, robotics, ergonomics, sustainable manufacturing and sports engineering. At UMP he was the founding Director of Innovative Mechatronics, Manufacturing and Sports Laboratory (IMAMS). Research at Professor Zahari’s laboratory focused on sustainable manufacturing particularly developing practical tools for evaluating products at the design stage based on the triple bottom line concept namely economics, environmental and social aspects and also key advances in Fuzzy AHP for decision making and GA for optimization. Prof Zahari also conducted research on industry 4.0 core technologies namely simulation and modeling of manufacturing, virtual reality and augmented reality applications in manufacturing, optimization in 3D printing and data analytics in manufacturing. He also conducted research in sports engineering in particular new knowledge on the impact of soccer balls on the brains has been discovered. His lab has also developed instrumentation and mobile based applications for monitoring performance in sports and at work. Professor Zahari led a project on Solar Car for the fifth edition of the World Solar Challenge in Australia and also led UMP to win second place in the inaugural Proton Electric Car Green Challenge. In ergonomics, his research included determining the factors that affect near accidents in long distance bus drivers.. Prof Zahari’s research in robotics was focused on autonomous mobile robots, autonomous helicopters, and quad copters, unmanned surface vessels and exoskeletons for rehabilitation. He had also developed applications on mobile devices for autonomous navigation using GPS. Professor Zahari, together with his research group and collaborators, has published 16 chapters in books, more than 150 peer reviewed archival journal publications. He is an inventor or co-inventor on three issued Malaysian Patents and has mentored 43 Masters theses. and 25 Ph.D. theses as well as several postdoctoral fellows. Professor Zahari is a fellow of the Academy of Sciences Malaysia and was the Deputy head of the Industry and Innovation cluster of the National Council of Professors. He is a Chartered Engineer registered with the Engineering Council of UK as well as a member and regional coordinator of the Institution of Engineering Designers, United Kingdom. He was also the chief editor of Movement Health and Exercise, a journal of the Ministry of Education. Prof Zahari also chaired the University Professor Council of Universiti Malaysia Pahang. He was awarded a Hitachi fellowship by the Hitachi Scholarship Foundation in 1990 and the Young Scientist Award Malaysia by the Ministry of Science Technology and Innovation in 1992. He was also awarded an honorary professor by Hebei University, China in 2012. He is a Board Member and Fellow of the Asia Pacific Industrial Engineering and Management Society. Since his retirement, Prof Zahari has started his own consultancy and training company (www.dzuki-consult.com) focusing on Deep Learning machine vision. He is a registered trainer with HRDC and his company is registered as an HRDC training company. Prof Zahari has developed deep learning solutions for HP Malaysia, IdealVision, Motorola Solutions, Mafipro, Prima Automation, and PDKM(Perodua Vendor). Dr Zahari has also conducted training on industry 4.0 courses such as IIOT, Machine Learning and Manufacturing Simulation for CREST, FMM, UTM and Universitas Syiah Kuala. He had also conducted a manufacturing simulation study for Panasonic Air Conditioning Malaysia