A Study of Emergent Computation of Life-like Behavior by Indefinite Observation
This paper describes the action generation of an autonomous animated agent. The agent behaves as if it has subjective motivation that is affected by its experiences. A typical study of this generation uses an ad-hoc method for the subjective action because it focuses on the action selection to solve some task. This paper proposes an indefinite communication architecture (ICA) to generate a subjective action. ICA keeps the experiences of an agent using indefinite observation. In particular, since the indefinite observation gives some chaotic feature to the experience, ICA generates various actions in response to an environment. This paper simulates and discusses the behavior of ICA in our interactive system.
keywordsLife-like Behavior Autonomous Agent Indefinite Observation Emergent Computation Subjective Experience
Unable to display preview. Download preview PDF.
- B. M. Blumberg, P. M. Todd, and P. Maes. No bad dog: Ethological lessons for learning in hamsterdam. In SAB’96, 1996.Google Scholar
- R. A. Brooks. Intelligence without reason. In IJCAI-91, pages 561–595, 1991.Google Scholar
- M. Fujita and K. Kageyama. An open architecture for robot entertainment. In Proc. of Autonomous Agent’97, pages 435–442, 1997.Google Scholar
- Y. P. Gunji. Life, time, protozoan-calculation, and ontological observation. Revue de la pensee drsaujourd’hui, Sep, 1996.Google Scholar
- W. S. N.Reilly. Believable social and emotional agents. Technical Report CMU-CS-96-138, School of Computer Science, Carnegie Mellon University, May 1996.Google Scholar
- C. R. Wren, A. Azarbayejani, T. Darrell, and A. Pentland. Pfinder: Real-time tracking of the human body. In IEEE Tranc. on Pattern Analysis and Machine Intelligence, volume 19(7), pages 780–785, July 1997.Google Scholar