Intelligent Software Laboratory

(Multi-agent system Laboratory)

Computer Science and Communications Engineering
Waseda University, Japan

Top page

News

  • Feb. 24, 2022: To International course students (Project Research):
    This is Information on open labs only for 2nd and 3rd year students at Waseda University. If you are intersted in Project Research in our lab., please email to Professor (sugawara 'at' waseda.jp) to make an appointment for interview (Zoom, e-mail or face-to-face interview).
    We will hold our open laboratory using Zoom as follows (Passcode is `AI' in capital letters). Students from the lab will explain about the contents of our research and the atmosphere of the lab.

  • March 22nd
     10:30 ― 12:00 (https://zoom.us/j/xxxxxxxxxxxx)
     14:
    00 ― 16:00 (https://zoom.us/j/xxxxxxxxxxx -> Change to in-person briefing session, please come directly to 55N-0502B.)

  • March 23rd
     10:30 ― 12:00 (https://zoom.us/j/xxxxxxxxxxxx)
     14:
    00 ― 16:00 (https://zoom.us/j/xxxxxxxxxxxx)

  • March 24th
     10:30 ― 12:00 for International Course Students (https://zoom.us/j/xxxxxxxxxxxx)
     1
    3:00 ― (https://zoom.us/j/xxxxxxxxxxxx)
    You are free to attend any session. Lab explanations and questions will be in Japanese, but English will be available in the morning of the 24th. Note that the session will be cancelled if there are no participants 15 minutes after the start of the session. When entering a Zoom meeting, change the display of your name to "student number + name" and also enter it to chat window.

  • May 28, 2021: Paper list has been updated.

  • March. 31, 2021: Member list has been updated.


Introduction

The Intelligent Software Laboratory (ISL) explores the theory, development, and analysis of autonomous agents and multi-agent systems (or Distributed Artificial Intelligence) and their applications in various domains, including Internet and/or Web applications and multi-agent simulations. Please note that our laboratory is not engineering oriented and rather focuses on academic and scientific purposes.

Research on multi-agent systems (or Distributed Artificial Intelligence)is one of the active research fields in artificial intelligence (AI). Autonomous agents are intelligent programs that are capable of perceiving local environments and taking appropriate action to move toward their goals based on independent decision-making. An multi-agent system consists of loosely-coupled autonomous, rational agents capable of coordinated/collaborative actions to achieve individual or joint goals in cooperation with other agents. Research activities include a broad range of efforts to develop and apply this type of coordinated actions.

Our research topics include:

  • Multi-Agent Systems

  • Distributed Artificial Intelligence

  • Coordination and Cooperation in Multi-Agent Systems

  • Multi-Agent Planning (such as multi-agent path planning)

  • Machine Learning for Cooperative and Coordinated Activities

  • Negotiation in Massively Multi-agent Systems

  • Effects of organizational and inter-agent network structures

  • Swarm Intelligence

  • Multi-Agent Simulations

  • Coexistence of and mutual effects between agents (including people)

In particular, we have addressed the issues related with large-scale multi-agent systems: Although recent advances in Internet services, sensor networks, pervasive computing, and grid computing exhibit the need for multi-agent systems, they further require more sophisticated multi-agent system technologies for large-scale and busy environments. For example, e-commerce transactions, which frequently appear in the current Internet era, consist of coordinated tasks including interactions among a variety of agents in charge of customer authentication and management, stock management, shipping control, and payment processing. These kinds of tasks simultaneously and frequently occur throughout in the world. In sensor-network applications, agents reside in many sensor and computational devices and, in grid computing, many computational entities should concurrently process the assigned sub-problems into which a large computation problem is decomposed. In these applications, many of the tasks should be allocated appropriately to maximize the entire abilities of multi-agent systems, in order to realize efficiency and high-quality services.

We also think about the coexistence with computer programs that are deployed everywhere in the Internet, smartphone, and often home appliances. They affect each other at many levels of social activities. Taking optimal actions are usually good for individuals (people and programs), but may not be good from social viewpoints due to excessive/wasteful competition. We believe that socially harmonious coexistence between people and programs will be strongly required in near future.

If you are interested in studying our lab as a master or doctor course student, please visit this page.

The Intelligent Software Laboratory is part of the Department of Computer Science and Engineering, Graduate School of Fundamental Science and Engineeing at Waseda University, Tokyo, Japan.