Registration 9:00 - 9:30
9:30 - 10:00
Opening Address
MOU Signing between Kagawa Kosen and STUST
Group Photo
Break 10:00 - 10:15 (15 min)
10:15 - 11:00
Title: Engineering Education at Kagawa Kosen: Journey from Local Collaborations to Student Startups
Speaker: Prof. Yukinori Misaki, Kagawa Kosen
Abstract: As one of the few higher education institutions in the region, Kagawa Kosen has devoted its efforts to providing engineering education to the younger generation. Beyond developing competent engineers, Kagawa Kosen has also been emphasizing collaborations with local industries and governments for many years. More recently, Kagawa Kosen pioneered AI education in all Kosens across the country, which resulted in the establishment of three AI startup companies. In this talk, the transformation of its unique engineering education as well as future prospects at Kagawa Kosen will be reviewed.
Bio: Yukinori Misaki, PhD, is a professor at the Department of Electronic Systems Engineering at Kagawa Kosen, Japan. Additionally, he holds the positions of director in the AI Social Implementation Education and Research Division and the Center for Collaborative Education and Research for Future Technologies at Kagawa Kosen. His research focuses on biosensing and robotics. Furthermore, he has supervised the students' robot competition team for more than 30 years, leading the team to win the national championship five times, making it the most successful team in Japan.
Host: Prof. Naoya Iwamoto, Kagawa Kosen
11:00 - 11:45
Title: Toward the Development of Secure Digital Twins Environments
Speaker: Prof. Wen-Yu Su, NCKU
Abstract: This paper presents a digital twin environment built with ROS2 for robotic control and experimentation. ROS2, a widely adopted open-source project in robotics, serves as the backbone for our system. Leveraging Unity 3D—a popular game engine with a versatile development environment—we create a seamless bridge between virtual robots and their real-world counterparts. Our approach involves implementing an ROS bridge with an OpenAI Gym-like data interface. This bidirectional connection enables robots operating within the virtual environment to communicate with the central ROS system, which controls physical robots. Notably, control commands issued via the equipped dashboard or a separate ROS node are published as ROS topics, allowing twin robots to synchronize their movements to enhance coordination and testing various scenarios. The system integrates Simultaneous Localization and Mapping (SLAM) techniques, You Only Look Once (YOLO) object detection model and so on. These tools enhance perception and navigation capabilities. We also delve into the security aspects of ROS2, highlighting potential vulnerabilities and proposing mitigation strategies.
Bio: Dr. Wen-Yu Su was born in Kaohsiung, Taiwan. He received his M.S. and Ph.D. degrees in Computer Science from the Tandon School of Engineering at New York University in 1993. He conducted postdoctoral research at Stanford University from 1993 to 1994. From 1994 to 1999, he was an Associate Professor of Computer Science at Chung Hua University in Hsinchu. Since 2000, he has been a Professor in the Department of Computer Science and Engineering at National Cheng Kung University in Tainan. In 2024, he also served as an adjunct professor at Southern Taiwan University of Technology, where he mainly conducts research on robots and the integration of cross-domain technologies and applications.
In 2013, Dr. Su founded the Program The World Association. He provides free programming and information technology courses for disadvantaged students from low-income families in rural middle and elementary schools and non-profit after-school tutoring programs in Taiwan. He also advocates for information tool usage courses for special needs students. To date, tens of thousands of students have benefited from his programs. He has also developed many free open-source courses that are available for public download and use. His work has attracted the attention of the government and society. He was awarded the Hing-Yun Education Award in 2019 and the Taiwan Ministry of Education's Master Teacher Award in 2020.
Host: Prof. Chih-Tsun Huang, NTHU
Lunch Break 11:45 - 13:00 (75 min)
13:00 - 15:00
Session Co-Chairs:
Prof. Naoya Iwamoto, Kagawa Kosen
Prof. Chih-Tsun Huang, NTHU
Title: Foundation Models for Robot Learning
Speaker: Prof. Tatsuya Matsushima, Univ Tokyo
Abstract: In recent years, large-scale language models (LLMs) and large-scale visual language models (VLMs) have been utilized as recognition and planning modules that are robust to changes in tasks and environments in the real world. Researchers utilize data from robot actions in the real world to construct a foundation model more closely linked to robot control (a so-called robotic foundation model). In this presentation, I will briefly overview these works and our efforts to scale up models and datasets to build these robot-based models.
Bio: Tatsuya Matsushima is a project (postdoc) researcher at the University of Tokyo. He currently leads the robotics research team in Matsuo-Iwasawa lab at the University of Tokyo. His research interests include robot learning and service robotics.
Title: Applications of brain-computer interfaces: Electric wheelchair and household appliance controlled by brain signals
Speaker: Prof. Akinari Onishi, Kagawa Kosen
Abstract: Brain-computer interfaces (BCIs) translate brain signals into control commands for, e.g., an electric wheelchair and household appliances. This talk provides from basic to application of the BCIs as follows: (1) fundamentals of electroencephalography and the BCI, (2) BCI demonstration video clips that controlling an autonomous electric wheelchair with a robot operating system and household appliances with ESP32 microcontrollers.
Bio: Akinari Onishi received his Ph.D. degree from Kyushu Institute of Technology in 2015. He is currently a Seinor Lecturer at the National Institute of Technology, Kagawa College (Kagawa KOSEN). His research interests include brain-computer interfaces, biomedical engineering, assistive technologies, and engineering education.
Title: Wearable sensors without skin-contact
Speaker: Prof. Kohei Ishii, Kagawa KOSEN
Abstract: Nail tip sensor as a wearable sensor without skin-contact is developed to realize long-term continuous monitoring in daily life environment. Natural health condition can be monitored by the pulse wave sensor without uncomfortable wearing feeling, because sensory nerves are not distributed in nails. As the results of prototyping, typical pulse wave and also waveform changes associated with body motion can be observed in experiments under daily life environment.
Bio: Kohei Ishii received his Ph.D. degree in medicine from the University of Tokyo in 2013, and is presently an associate professor at the Department of Electro-Mechanical Systems Engineering, National Institute of Technology, Kagawa College. His research interests are biomedical engineering, in particular wearable sensors and devices working on nail surface. He is a member of Japanese Society for Medical and Biological Engineering (JSMBE) and IEEE Engineering in Medicine and Biology Society (EMBS).
Title: Augmented Vision Projector for Assisting Visual Inspection Tasks
Speaker: Prof. Naoya Iwamoto, Kagawa KOSEN
Abstract: Due to the huge progress in deep learning technologies in the last decade, the accuracy of image recognition AI has been drastically improved. The augmented vision projector uses image recognition AI and projection mapping technologies to not only detect objects but also display the detection results directly on them. This technology has been shown to improve the efficiency of visual inspection tasks through a benchmarking test.
Bio: Naoya Iwamoto is an assistant professor at the Department of Electronic Systems Engineering at Kagawa Kosen, Japan. He earned his PhD in 2012 from the University of Electro-Communications, Japan. Following that, he worked as a postdoctoral researcher at the Japan Atomic Energy Agency and the University of Oslo, Norway, where he focused on developing wide-bandgap semiconductor devices. Since 2016, he has been a part of Kagawa Kosen. His current research interests include the applications of AI and robotics technologies in industries and education.
Title: Exploring Collaborative Teaching in Robotics Education: Insights and Innovations
Speaker: Prof. Yi-Yu Alan Hsu, NCKU
Abstract: "Exploring Collaborative Teaching in Robotics Education: Insights and Innovations" explores the exciting world of robotics education, shedding light on collaborative teaching methods. From NCKU and NITKC's partnership to the groundbreaking projects at the AI Robotics Lab, this talk highlights the latest trends and advancements in the education scene. The audience will discover insights on deep learning, interdisciplinary connections, and global partnerships. Whether you're a student, teacher, or robotics enthusiast, this talk aims to spark inspiration and provide valuable information. Together, we can pave the path for a future where collaborative teaching fuels innovation in robotics education.
Bio: Yi-Yu Alan Hsu, Ph.D. in Computer Science and Information Engineering from National Cheng Kung University, is a seasoned computer scientist specializing in machine learning. With a focus on biomedical imaging and text mining, he has led numerous research projects and developed algorithms to enhance data curation processes using natural language processing and named entity recognition techniques. Previously, he served as a Research Scientist at Howard University's Department of Radiology, where he pioneered the development of a Deep Learning Framework based on U-Net architecture for cell proliferation and brain glucose metabolism quantification. Currently, Hsu is an Assistant Professor at the Miin Wu School of Computing, National Cheng Kung University, where he teaches courses integrating deep learning models with GPU-related hardware.
Title: Development of Predictive Maintenance Strategies for Electrical Motors with the Vibration Sensing IoT Systems
Speaker: Prof. Jeng-Han Li, STUST
Abstract: With the vigorous development of industrial automation, more and more automation equipment is introduced into the manufacturing lines. Most automation equipment can be classified as electromechanical integration systems, which integrate electric motors and peripheral mechanisms to complete automation operations. For allowing automation equipment to operate stably for a long time, the implementation of predictive maintenance has been the main trend in the industry in recent years, and can greatly reduce maintenance costs. In this talk, I will introduce our developed vibration-sensing IoT module with the CC3200 wireless communication module of Texas Instruments. The IoT module integrates the ADXL355 accelerometer of Analog Devices to provide industrial-grade 3-axis vibration sensing. For establishing the predictive maintenance model, we integrated CNN and LSTM neural networks to complete it. Compared with other neural networks, the proposed CNN-LSTM model has faster training speed and great correctness of equipment fault identification.
Bio: Prof. Jeng-Han Li is an Assistant Professor in the Department of Electrical Engineering at Southern Taiwan University of Science and Technology. He received his Ph.D. degree in Electrical Engineering from National Cheng Kung University in 2003. His expertise spans both academia and industry. Between 2014 and 2016, Prof. Li contributed significantly as a project manager at the Productibility Promotion Office of MOEA in Taiwan. Since joining STUST in 2016, he has excelled in teaching and actively participated in the robotics community, serving on the competition rules review and referee committees for the prestigious Top International Robotic Tournament since 2018. Prof. Li's work has earned him numerous awards in the National College Creative Design and Production Competition, the DSP Creative Design Contest, and TIRT Robot Competition.
Break 15:00 - 15:30 (30 min)
15:30 - 16:30
Moderator: Prof. Ming-Der Shieh, NCKU
Panelists:
Prof. Yeou-Jiunn Chen, STUST
Bio: Prof. Chen is the chairman of Department of Electrical Engineering, Southern Taiwan University of Science and Technology from 2023. He received his Ph.D. degree from the Institute of Information Engineering, National Cheng Kung University, Tainan, Taiwan, in 1995 and 2000, respectively. He was with the Advanced Technology Center, Computer and Communications Laboratories, Industrial Technology Research Institute, from 2001 to 2005 as a researcher. From 2005 to 2023, he was an assistive professor, associate professor, and professor in the Department of Electrical Engineering, Southern Taiwan University of Science and Technology, Tainan, Taiwan. Since 2023, he has been a Distinguished Professor.
His research interests include intelligent system, artificial intelligence, human machine interfaces, biomedical signal processing, and spoken language processing. Dr. Chen is a member of the Biomedical Engineering Society, Taiwan Rehabilitation Engineering and Assistive Technology Society, and the Association for Computational Linguistics and Chinese Language Processing.
Prof. Wen-Yu Su, NCKU
Bio: Dr. Wen-Yu Su was born in Kaohsiung, Taiwan. He received his M.S. and Ph.D. degrees in Computer Science from the Tandon School of Engineering at New York University in 1993. He conducted postdoctoral research at Stanford University from 1993 to 1994. From 1994 to 1999, he was an Associate Professor of Computer Science at Chung Hua University in Hsinchu. Since 2000, he has been a Professor in the Department of Computer Science and Engineering at National Cheng Kung University in Tainan. In 2024, he also served as an adjunct professor at Southern Taiwan University of Technology, where he mainly conducts research on robots and the integration of cross-domain technologies and applications.
In 2013, Dr. Su founded the Program The World Association. He provides free programming and information technology courses for disadvantaged students from low-income families in rural middle and elementary schools and non-profit after-school tutoring programs in Taiwan. He also advocates for information tool usage courses for special needs students. To date, tens of thousands of students have benefited from his programs. He has also developed many free open-source courses that are available for public download and use. His work has attracted the attention of the government and society. He was awarded the Hing-Yun Education Award in 2019 and the Taiwan Ministry of Education's Master Teacher Award in 2020.
Prof. Yukikazu Murakami, Kagawa Kosen
Bio: Yukikazu Murakami is an Associate professor at the Department of Electrical & Computer Engineering Kagawa Kosen, Japan. Since 2003, he has been a part of Kagawa Kosen. He earned his PhD in 2009 from the Okayama University, Japan. Following that, he worked as a Visiting Associate Professor at the Queens College of the City University of New York in 2017. His current research interests include the "applications of AI" and "Satellite development using IoT technology". His currently work is developing microsatellites named 「KOSEN-3」 and conducting stratospheric balloon experiments.
Prof. Naoya Iwamoto, Kagawa Kosen
Bio: Naoya Iwamoto is an assistant professor in the Department of Electronic Systems Engineering at Kagawa Kosen, Japan. He earned his PhD in 2012 from the University of Electro-Communications, Japan. Following that, he worked as a postdoctoral researcher at the Japan Atomic Energy Agency and the University of Oslo, Norway, where he focused on developing wide-bandgap semiconductor devices. Since 2016, he has been a part of Kagawa Kosen. His current research interests include the applications of AI and robotics technologies in industries and education.
16:30 - 16:40
Closing Remarks
16:40 - 17:10