IROS 2025 Keynotes - Humanoid Robot Systems: Kei Okada

Why It Matters

Okada’s vision positions humanoid robots as adaptable, human‑centric assistants, accelerating their commercial viability and reshaping how businesses deliver personalized, safe automation in everyday environments.

Key Takeaways

• Humanoid robots leverage human-centric tool use for everyday tasks.
• Open-source platforms like HRP and ROS lower development barriers.
• Semantic internet knowledge enables robots to plan without explicit programming.
• Reconfigurable and transformable designs promise multi‑purpose humanoid capabilities.
• Human‑centric memory and interaction foster trust and shared experiences.

Summary

The keynote by Kei Okada traced the evolution of humanoid robotics from the early HRP2 platform to today’s foundation‑model‑driven systems, emphasizing that robots must coexist with humans in environments built for us. He argued that the defining trait of humanity—tool manipulation—should be the core capability of any humanoid, and that open‑source stacks such as HRP’s walking controller and ROS’s perception‑navigation modules have repeatedly lowered the barrier to higher‑level research. Okada highlighted three technical pivots: the release of reusable hardware/software platforms, the integration of semantic knowledge harvested from the internet to let robots reason about tasks like making a sandwich, and the shift toward reconfigurable bodies that can morph or swap modules for different functions. Demonstrations included a robot fetching a cup from a fridge using ROS‑based task decomposition, a scooter‑style robot that folds into a stationary carrier, and a modular humanoid whose legs, wheels, and arms can be magnetically re‑attached without rewiring. Memorable moments included his reference to the SICP abstraction barrier as a metaphor for robotics, the claim that “humans are tool‑using apes,” and the live showcase of a robot remembering personal preferences and sharing memories with a student on campus. These examples underscored the move from isolated, pre‑programmed actions to robots that can learn, recall, and converse with users. The implications are profound: as hardware reliability and AI foundations mature, humanoids can become general‑purpose machines—akin to personal computers—capable of adapting form and function on demand. This promises new business models in home assistance, logistics, and care, while also raising questions about safety, trust, and the integration of personal knowledge into autonomous systems.

Original Description

"Keynote Title: ""Transforming Humanoid Robot Intelligence: From Reconfigurable Hardware to Human-Centric Applications""

Speaker Biography

""Kei Okada is a Professor at the Interfaculty Initiative in Information Studies, The University of Tokyo. He received his B.E. degree in Information Science from Kyoto University in 1997 and his Ph.D. in Engineering from The University of Tokyo in 2002. He has since worked at The University of Tokyo, where he became Associate Professor in 2009 and Professor in 2018. His research focuses on humanoid robotics, reconfigurable robot architectures, tool-use intelligence, bio-inspired and tissue-level humanoid systems, and the integration of perception and action for human-robot collaboration. He has led and contributed to multiple large-scale national and international research projects, and has published extensively in leading conferences and journals in robotics.""

Abstract

""With the spread of foundation models and affordable humanoid platforms, the possibilities of humanoid research are becoming increasingly tangible. As the next stage of development, this talk will address two perspectives: hardware innovation and the deepening of human-centric applications. On the hardware side, I will present a trajectory that extends from our previous work on tool-use intelligence—where robots adaptively employ tools for tasks—towards reconfigurable humanoids that can construct their own bodies according to the task at hand. In a separate line of research, I will introduce bio-inspired humanoids evolving towards tissue-level imitation, aiming to contribute to scientific understanding by mimicking biological organization at the structural level. On the application side, I will highlight the vision of human-centric humanoids that truly serve people, showcasing an example of a humanoid capable of assisting a person to stand up or be lifted. Through these discussions, I would like to explore with the audience how humanoid research can be further developed beyond the current state.""

"