Intelligent System Control

Research Staff

  • Prof. Kenji Sugimoto

    Prof.
    Kenji SUGIMOTO

  • Assist.Prof. Taisuke Kobayashi

    Assist.Prof.
    Taisuke KOBAYSAHI

  • Assist.Prof. Kenta Hanada

    Assist.Prof.
    Kenta HANADA

E-mail { kenji, kobayashi, hanada}[at] is.naist.jp

Research Areas

Control systems design

Advanced robust/adaptive control
We study advanced theories in post-modern robust/adaptive control and their applications including current investigations into various schemes of feedforward learning control (feedback error learning). System identification and state estimation are also topics of interest.

Networked dynamical systems
The goal of this research is to provide a better understanding of dynamical processes taking place over complex networks, as well as developing effective strategies to control their behavior. Applications of this research direction can be found in a wide variety of contexts, from social networks to networked infrastructure and cyber-physical systems (Fig. 1).

Multi-agent systems
In multi-agent systems (MAS), each agent tries to achieve a goal of the entire system, for example, averaging values of the initial states or maximizing/minimizing values of the objective function, cooperatively. We are developing novel protocols based on MAS to deal with continuous/discrete (combinatorial) optimization problems in distributed environment. Smart grids and micro grids are crucial applications of MAS in order to control next generations' power systems.

Machine learning for robotics

Biologically-inspired learning
We are studying new (reinforcement) learning structures inspired by animals, which would convert mathematically convenient ones into ones suitable for real robotic problems. For example, we are developing new neural network dynamics, reinforcement learning scheme, reward reshaping to be optimized, and so on (Fig. 2).

Physical human-robot interaction
We are developing for next-generation robots that can physically interact with human and aim to support various human motions: e.g., shared autonomy for autonomous driving car; adaptive robot control based on recognized human behaviors; multi-agent systems including human (Fig. 3).

Key Features

We welcome motivated students from various fields including mechanical/electrical engineering, mathematical/physical science, as well as computer science. The faculty guides students individually, taking into account their backgrounds, and assists them in mastering mathematical system approaches by the end of their course. Thereby they acquire a wide range of technical skills from fundamental theories to applications. The students in our lab are highly motivated, diligent, cooperative and eager to learn from others. We anxiously await such students from all over the world.






Fig.1 Networked control system

Fig.1 Networked control system

Fig.2 Robot control by reinforcement learning

Fig.2 Robot control by reinforcement learning

Fig.3 Multi-agent system for physical human-robot interaction

Fig.3 Multi-agent system for physical human-robot interaction