🤖Ph.D. in Engineering
2013-04-01
2017-09-30
Osaka University
M.Eng.
2011-04-01
2013-03-31
Osaka University
B.Eng.
2009-04-01
2011-03-31
Advanced Course in Electronic-Mechanical Engineering, Toyota National College of Technology
Can robots have emotions? How does the human mind develop?
Our research group explores these questions from the perspectives of cognitive developmental robotics and symbol emergence robotics. We work on the computational modeling of emotional development, human-robot interaction based on active inference, the correspondence between qualia structures and information structures, and the modeling of creativity. We also investigate behavior acquisition through imitation and reinforcement learning, robot action planning and task execution leveraging foundation models such as Large Language Models (LLMs) and Vision-Language Models (VLMs), and the construction of embodied intelligence grounded in the integration of multimodal information. Centered on robot learning, our research approaches the essence of intelligence from multiple angles.
Kentaro Nomura of our lab has received the JSAI Annual Conference Award for his presentation at the 40th Annual Conference of the Japanese Society for Artificial Intelligence (JSAI …
I presented the following poster at the workshop “Wanting What is Needed” at the 18th International Conference on the Simulation of Adaptive Behavior (SAB 2026, October 19–22, …
A paper by Kango Yanagida of our lab has been accepted at the 2026 IEEE-RAS 25th International Conference on Humanoid Robots (Humanoids 2026), to be held in December 2026 in Santa …
A research cluster that uses imitation learning, reinforcement learning, and foundation models to build autonomous robots. Concept learning, motor skills, action planning, and …
A research cluster that uses computational models and robots to understand emotion, consciousness, and creativity — the workings of the human mind. Embodiment, interoception, and …
A JST CREST project building an AI foundation that supports behavior change and active social co-creation through symbiosis with "Self Mirroring Twins."
Developing robot learning and skill acquisition algorithms to realize AI cobots that work side by side with humans on shipyard floors.
Elucidating, through cognitive science, the mechanisms and individual differences of social touch that creates a sense of comfort between humans, and between humans and robots.
We propose a task-aware, robot-affordance-centric diffusion policy. By integrating the notion of affordances into a diffusion model, the proposed method enables more adaptive …
This work simulates the systems model of creativity using generative agents. By computationally reproducing human creative processes, we explore how creativity emerges.
We propose a multi-robot task planning method that integrates Large Language Models (LLMs) with linear programming and dependency graphs. By combining the natural-language …
Based on the framework of active inference, we propose an energy-minimization approach to multimodal affective human-robot interaction. The proposed mechanism enables a robot to …
