Frontiers Session
October 31(Thu), 13:00-14:30, Landing Ballroom
 |
Dr. Daegyu Lim ROBROS Inc., Korea |
Learning-based Approaches for Safety and Dexterity of HumanoidsAbstract: In recent years, AI technology has rapidly advanced, leading to significant progress in AI-based humanoid robots and a booming humanoid industry. While we often imagine humanoid robots soon integrating into our daily lives, companies like Tesla, Figure AI, Apptronix in the US, and UBITECH in China currently limit their application to specific manufacturing lines, such as automobile factories. The two main obstacles preventing humanoid robots from entering our everyday lives are safety and dexterity. In this presentation, I will discuss my past research on improving the safety of humanoid robots with uncertainty torque learning, share the latest research progress on the imitation learning of dual manipulation at ROBROS, and outline our vision for the future of AI humanoid in the service Industry. Biography: |
|
 |
Prof. Jungwon Park SeoulTech, Korea |
Collision Avoidance and Deadlock Resolution for Decentralized Multi-robot SystemsAbstract: Multi-agent trajectory planning (MATP) plays a crucial role in enhancing the productivity and efficiency of multi-robot systems, including mobile robots and unmanned aerial vehicles (UAVs). Biography: Jungwon Park received the B.S. degree in Electrical and Computer engineering in 2018, and the M.S. and Ph. D. degrees in Mechanical and Aerospace engineering at Seoul National University, Seoul, Korea in 2020 and 2023, respectively. |
|
 |
Prof. Seong-Min Lee Jeju National University, Korea |
Prediction-Based Control for Mechatronics and Virtual Reality With Time DelayAbstract: Time delay issues have been critical across various industries and remain significant challenges to overcome. Most practical mechatronics systems experience delays related to actuators, measurements, motion, and communication, which directly affect control stability and can often lead to operational failures. Moreover, the control stability is extremely degraded in the presence of disturbances. Time delays in virtual reality systems are also critical, as humans in these environments can perceive even small delays, leading to motion sickness and a sense of unreality. In this talk, I will introduce a prediction-based strategy to address time delays and present practical implementation results to validate the effectiveness of the proposed controller. Biography: Seong-Min Lee received the B.S. degree in Mechanical and Advanced Materials Engineering from Ulsan National Institute of Science and Technology (UNIST), Ulsan, South Korea, in 2015, and the Ph.D. degree in Mechanical Engineering from UNIST in 2021. He is currently an assistant professor in the Department of Mechanical Systems Engineering, Jeju National University. His research interests include mechatronics and robotics, motion platform, human-machine interaction, and control theory. |
|
 |
Prof. Kyoung-Soub Lee University of Ulsan, Korea |
Towards Lightweight Rehabilitation Robots: Integrating Soft Materials and AIAbstract: Robotic systems have shown great potential in rehabilitation, but factors like size, weight, and cost have limited their widespread use. Our research initially focused on developing a shoulder rehabilitation robot capable of various training exercises using a single motor. While we achieved positive outcomes and obtained medical device certification through industry collaboration, commercialization was constrained due to the robot’s weight and high production costs. Biography: |
|
