R&D Project
Last updated:
Goal 3 R&D Projects (Selected in FY2026)Integrated Research and Development of Humanoids Capable of Operating in Challenging EnvironmentsJPMJMS263E
Project manager (PM)HARADA KensukeProfessor, Graduate School of Engineering Science, The University of Osaka
Summary of the project
This research aims to realize a humanoid robot capable of performing real physical work in unstructured and challenging environments such as construction sites. Its novelty lies in the integrated development of: (i) lightweight, high-power, and highly durable hardware; (ii) locomotion and whole-body motion planning that fuses model-based control with learning; (iii) manipulation skill acquisition that structures and extends the tacit knowledge of skilled workers; and (iv) human–humanoid and multi-robot collaborative intelligence enabled by multimodal AI. Using actual construction and manufacturing sites as demonstration fields, we will verify the system in a stepwise manner. We will establish the core technological foundation required for practical deployment at limited work sites by 2030 and for the realization of general-purpose autonomous humanoid AI robots by 2050. This project will make a significant contribution to resolving the increasingly severe labor shortage and to achieving safe and sustainable on-site operations.

*Certain illustrations in this document were created with the assistance of generative AI.
Milestone by year 2030
- Enable the developed humanoid to perform load-slinging, test-piece retrieval, and maintenance and inspection tasks.
- Enable the developed humanoid to move autonomously over narrow scaffolds and stairs, using handrails.
- Achieve load-slinging work with an efficiency comparable to that of a human by observing the operations of skilled workers, directly estimating their end-effector impedance characteristics, and reproducing these characteristics on the robot.
- Establish an intelligence platform that, in industrial environments and on the basis of multimodal observations covering the actions of both humans and multiple robots, autonomously selects, switches, and adapts learned collaboration policies according to the situation across multiple levels of collaboration.
- Compile recommendations toward safety standards for humanoid robots performing on-site work.
R&D Items
- [1] Development of Humanoid Hardware
- [2] Development of Locomotion Control Technologies Applicable to On-Site Work
- [3] Application of On-Site Workers' Manipulation Skills to Robots
- [4] Development of Human Multi-Robot Collaboration Strategies Using Multimodal AI
- [5] Research on Ethical, Legal, and Social Issues Surrounding Humanoids in the Physical AI Era
Performers
| R&D Item [1] | KAWASUMI Yuichiro | Kawada Technologies, Inc. |
|---|---|---|
| R&D Item [1] | WATANABE Tetsuyou | Kanazawa University |
| R&D Item [1] | HARADA Kensuke | The University of Osaka |
| R&D Item [2] | KAJITA Shuuji | Chubu University |
| R&D Item [2] | KOMIZUNAI Shunsuke | Kagawa University |
| R&D Item [3] | HASEGAWA Yasuhisa | Nagoya University |
| R&D Item [3] | KIYOKAWA Takuya | The University of Osaka |
| R&D Item [3] | KAKIUCHI Yohei | Toyohashi University of Technology |
| R&D Item [3] | TSUICHIHARA Satoki | University of Fukui |
| R&D Item [3] | SENOO Taku | Hokkaido University |
| R&D Item [4] | XIAO Ling | Hokkaido University |
| R&D Item [4] | MATSUBARA Takamitsu | Nara Institute of Science and Technology (NAIST) |
| R&D Item [5] | AKASAKA Ryota | The University of Osaka |
PDF Download
- Summary of the project (408 KB)