Agent and Multiagent Systems | Department of Intelligent Systems

Agent and Multiagent Systems

In broad sense, an agent is an intelligent, autonomous entity that perceives its environment through sensors and acts upon that environment through actuators. We work on a wide range of topics, for example:

  • Learning agents, including computational architectures for learning agents, evolution, adaptation, and multi-agent learning
  • Agent-based simulation, including emergent behavior, participatory simulation, and simulation techniques, tools and environments
  • Agent decision-making architectures and their evaluation, including reasoning (single and multi-agent), knowledge representation, ontological reasoning, and planning
  • Agent-oriented software engineering, including agent development techniques, tools and environments, agent programming languages
  • Virtual agents, including agents in games and virtual environments, companion and conversational agents

Contact: A. Tavčar (ales.tavcar@ijs.si)

Research Projects

  • ACCUS
    The project is aimed at developing an integration and coordination platform for urban systems to build applications across urban systems, provide adaptive and cooperative control for urban subsystems, and to optimize the combined performance.
  • Opus
  • Agent-based HVAC control system for smart buildings

Past Projects

  • e-Assistant
    The goal of the project is to develop a virtual conversation agent platform as a web service free of charge. The project will focus on providing the service to over 100 Slovenian municipalities.
  • Eusas
    The aim is to develop a new approach to mission analysis and training for low level units facing asymmetric threats in an urban environment.

Doctoral Research Projects

  • Agent behaviour analysis and cloning in security domains
    Aleš Tavčar, supervisor: Matjaž Gams