Grants‎ > ‎

Planning and Learning in BDI Agents - ARC LP0560702

Project Description

This project aims to increase the power and flexibility of one of the most popular and successful kinds of agents paradigms, known as BDI (Belief, Desire, Intention). By incorporating abilities to plan and to learn into BDI agent development platforms, agent systems built using this technology can be far more robust and flexible. If the system can adapt and learn new information or develop new plans after deployment, then not everything needs to be programmed at the start. Also these techniques can relieve the developer of some effort as the system can improve itself after deployment. 

Participants

  • Prof. Lin Padgham (RMIT University)
  • Dr. Andrew Lucas (AOS)
  • Dr. Andy Song (RMIT University)
  • Dr. Sebastian Sardina  (RMIT University)
Partner: Agent Oriented Software Pty. Ltd.

Students involved: Lavindra de Silva


Publications

  1. Sebastian Sardina and Lin Padgham. A BDI agent programming language with failure recovery, declarative goals, and planning. Autonomous Agents and Multi-Agent Systems, 23(1):18-70, 2011.
  2. Sebastian Sardina, Fabio Patrizi, and Giuseppe De Giacomo. Behavior composition in the presence of failure. In Gerhard Brewka and Jerome Lang, editors, Proceedings of Principles of Knowledge Representation and Reasoning (KR), pages 640-650, Sydney, Australia, September 2008. AAAI Press.
  3. Sebastian Sardina and Giuseppe De Giacomo. Realizing multiple autonomous agents through scheduling of shared devices. In Jussi Rintanen and Bernhard Nebel, editors, Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS), pages 304-312, Sydney, Australia, September 2008. AAAI Press.
  4. Stéphane Airiau, Lin Padgham, Sebastian Sardina, and Sandip Sen. Incorporating learning in BDI agents. In Proceedings of the Adaptive Learning Agents and Multi-Agent Systems Workshop (ALAMAS+ALAg-08), Esteroil, Protugal, May 2008.
  5. Massimiliano de Leoni, Andrea Marrella, Massimo Mecella, Stefano Valentini, and Sebastian Sardina. Coordinating mobile actors in pervasive and mobile scenarios: An AI-based approach. In Proceedings of the 17th IEEE International Workshops on Enabling Technologies: Infrastructure for collaboration enterprises (WETICE'08), pages 82-88. IEEE Computer Society, 2008.
  6. Sebastian Sardina, Fabio Patrizi, and Giuseppe De Giacomo. Automatic synthesis of a global behavior from multiple distributed behaviors. In Robert C. Holte and Adele Howe, editors, Proceedings of the National Conference on Artificial Intelligence (AAAI), pages 1063-1069, Vancouver, Canada, July 2007. AAAI Press.
  7. Sebastian Sardina and Lin Padgham. Goals in the context of BDI plan failure and planning. In Edmund H. Durfee, Makoto Yokoo, Michael N. Huhns, and Onn Shehory, editors, Proceedings of Autonomous Agents and Multi-Agent Systems (AAMAS), pages 16-23, Hawaii, USA, May 2007. ACM Press.
  8. Giuseppe De Giacomo and Sebastian Sardina. Automatic synthesis of new behaviors from a library of available behaviors. In Manuela M. Veloso, editor, Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pages 1866-1871, Hyderabad, India, January 2007.
  9. Sebastian Sardina, Giuseppe De Giacomo, Yves Lespérance, and Hector J. Levesque. On the limits of planning over belief states under strict uncertainty. In Proceedings of Principles of Knowledge Representation and Reasoning (KR), pages 463-471, Lake District, UK, June 2006.
  10. Sebastian Sardina, Lavindra P. de Silva, and Lin Padgham. Hierarchical planning in BDI agent programming languages: A formal approach. In Hideyuki Nakashima, Michael P. Wellman, Gerhard Weiss, and Peter Stone, editors, Proceedings of Autonomous Agents and Multi-Agent Systems (AAMAS), pages 1001-1008, Hakodate, Japan, May 2006. ACM Press.
  11. John Thangarajah, Lin Padgham, and Sebastian Sardina. Modelling situations in intelligent agents. In Proceedings of Autonomous Agents and Multi-Agent Systems (AAMAS), pages 1049-1051, Hakodate, Japan, May 2006.