R&D Project

Last updated:

NONAKA Tetsushi PM Photo

Goal 3 R&D Projects (Selected in FY2026)Learning to Learn: Principles of Active On-Site Learning for General-Purpose RobotsJPMJMS263O

Project manager (PM)NONAKA TetsushiProfessor, Graduate School of Human Development and Environment, Kobe University

Summary of the project

Toward the realization of robots that continuously learn from the environment in which they are embedded, this project explores the principle of “learning to learn”: learning to obtain information relevant to the situation by spontaneously acting on the environment. We focus on tasks in which a robot uses tools on the spot to organize purposive encounters with the environment. Drawing on the approaches of reservoir computing and embodied intelligence, we aim to open a path toward robots that actively move their bodies to tune their attention to the information that specifies affordances—the possibilities for action offered by the human environment.

Image
Schematic images of robots learning to control their actions through active engagement with the environment

Milestone by year 2028

By 2028, we will formalize the principles for generating behavior that acts on the environment in order to attune to task-relevant modes of interaction, and we will realize a robot that autonomously acquires such “self-tuning behavior” across a range of tool-use tasks.

R&D Items

  • [1] Principles of generating embodied active self-tuning behavior

Performers

R&D Item [1] NAKAJIMA Kohei The University of Tokyo
R&D Item [1] IIDA Fumiya The University of Tokyo
R&D Item [1] NONAKA Tetsushi Kobe University

PDF Download

News & Events