Keynote Speakers

Jinoh Lee

German Aerospace Center

It will be updated.

Biography

Jinoh Lee is the Lead of the Humanoid and Legged Robots team and a Principal Investigator (PI) with the Institute of Robotics and Mechatronics at the German Aerospace Center (DLR). Since 2022, he has served as an Adjunct Professor in the Department of Mechanical Engineering at KAIST, South Korea, and in 2026, he was appointed Adjunct Professor in the Department of Electrical & Computer Engineering at the University of Guelph, Canada.

He received his B.S. degree (Summa Cum Laude) in Mechanical Engineering from Hanyang University, Seoul, in 2003, and earned both his M.Sc. and Ph.D. degrees in Mechanical Engineering from KAIST, Daejeon, in 2012. Prior to joining DLR in 2020, he was a Postdoctoral Fellow (2012–2017) and subsequently a Research Scientist (2017–2020) within the Department of Advanced Robotics at the Istituto Italiano di Tecnologia (IIT) in Genoa, Italy. Additionally, he served as a Research Consultant for Disney Research (DR) in Los Angeles and Pittsburgh from 2017 to 2018.

His expertise lies in robotics and control engineering, specifically focusing on loco-manipulation of humanoids, robust control of nonlinear systems, and compliant robotic control. He has authored or co-authored over 50 papers in top-tier robotics journals and 46 papers at major international conferences, including IEEE ICRA, IROS, and Humanoids. Dr. Lee serves as a Senior Editor on the Conference Paper Review Board (CPRB) for IEEE/RSJ IROS, Co-Chair of the IEEE Technical Committee (TC) on Humanoid Robotics, and Spokesperson for the Legged Locomotion Technical Cluster in the Robotics Institute Germany (RIG). He is also the Vice President of the Korea Robotics Society (KROS) Europe branch and has been a long-standing organizer of the “Can we build Baymax?” workshop series at the IEEE Humanoids conference for over a decade.

Daniel Seita

University of Southern California

Doing More With Less: Expanding Experience and Preserving Capabilities in Robot Learning

Robot learning has made impressive progress, but physical interaction remains expensive, and robots have finite physical resources. This talk asks how robots can do more with less along two complementary dimensions. First, how can we expand a robot’s experience from limited real-world data? I will present methods that augment bimanual demonstrations across camera views, use video diffusion models to generate consistent visual variations and transfer data across robot embodiments, and extend augmentation to language, failure-driven environment generation, and tactile signals. Second, how can robots preserve capabilities during long-horizon tasks? I will discuss dexterous manipulation methods that reuse object-centric skills, coordinate sequential and concurrent actions, and allocate fingers so early actions do not consume resources needed later. Together, these projects support generalist robots that can learn and compose diverse manipulation skills by expanding experience while preserving physical capabilities.

Biography

Daniel Seita is an Assistant Professor in the Computer Science department at the University of Southern California and the director of the Sensing, Learning, and Understanding for Robotic Manipulation (SLURM) Lab. His research interests are in computer vision, machine learning, and foundation models for robot manipulation, focusing on improving performance in visually and geometrically challenging settings. Daniel was a postdoc at Carnegie Mellon University’s Robotics Institute and holds a PhD in computer science from the University of California, Berkeley. Daniel has been honored with the AAAI 2026 New Faculty Highlights program. He presents his work at premier robotics conferences such as ICRA, IROS, RSS, and CoRL.

Sarthak Pathak

Shibaura Institute of Technology

From 3D Reconstruction Towards Queryable Environments: Geometry-Driven 360° Intelligent Sensing

Understanding and interacting with real-world environments is a fundamental challenge in robotics and intelligent systems, with important applications in factory digitalization, infrastructure inspection, and construction site management. This talk presents research on geometry-driven intelligent sensing using 360° and other cameras and sensors, covering topics including motion estimation, 3D reconstruction, localization, and semantic mapping. A key theme throughout is the careful consideration of sensor and environment geometry to achieve robust and practical sensing in real-world conditions, without relying solely on learning-based approaches. Recent work on integrating visual SLAM with open-world object detection to build semantic maps of real indoor environments is also presented, along with a vision towards queryable environments where reconstructed spaces can be explored and inspected intuitively using natural language.

Biography

Sarthak Pathak is an Associate Professor at Shibaura Institute of Technology, where he leads the Intelligent Sensing Systems Laboratory. His research focuses on geometry-driven 360° intelligent sensing for real-world environments, including 3D reconstruction, visual SLAM, semantic mapping, and vision-language integration for remote inspection of industrial and infrastructure sites. His work has been recognized with the ICCAS 2016 Student Best Paper Award, the JRM 2018 Best Paper Award, and the FA Foundation Paper Award. He has active industry collaborations on intelligent sensing of environments with several companies. Sarthak received his PhD from the University of Tokyo and his B.Tech. and M.Tech. from the Indian Institute of Technology Madras.

Jiyeon Kang

GIST

It will be updated.

Biography

Heejin Ahn

KAIST

Future Mobility: Collaborative Autonomous Driving

Autonomous driving has primarily focused on improving the intelligence of individual vehicles. As systems are deployed in increasingly complex urban environments, considering interactions among multiple vehicles opens up new opportunities for improving both safety and efficiency. In this talk, I revisit autonomous driving from a multi-vehicle perspective, emphasizing how information sharing and coordination can enhance both perception and decision-making. I will present recent work on collaborative perception and planning, along with validation results from a miniature testbed that captures key aspects of multi-vehicle interaction. Finally, I will discuss current research directions and remaining challenges toward more reliable and scalable autonomous driving systems.

Biography

Heejin Ahn is currently an EWon-endowed Assistant Professor at the School of Electrical Engineering, Korea Advanced Institute of Science & Technology (KAIST), South Korea. She received her S.M. and Ph.D. degrees in Mechanical Engineering from the Massachusetts Institute of Technology (MIT), USA in 2014 and 2018, respectively. She received her B.S. degree in Mechanical and Aerospace Engineering from Seoul National University (SNU), South Korea in 2012. Before joining KAIST, she worked as an Assistant Professor at the Department of Electrical and Computer Engineering at SNU, as a postdoctoral research fellow at the University of British Columbia, Canada, and as a visiting research scientist at Mitsubishi Electric Research Laboratories, USA. Her research interests include the design and analysis of multi-agent control and AI safety with applications to intelligent transportation systems.

Joohyung Kim

University of Illinois Urbana-Champaign

It will be updated.

Biography

.