Proceedings of the KIEE Conference (대한전기학회:학술대회논문집)

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

Action Selection Mechanism for Artificial Life System

인공생명체를 위한 행동선택 구조

  • Kim, Min-Jo (The Graduate school of Information & Communications, Hanyang University) ;
  • Kwon, Woo-Young (The Graduate school of Information & Communications, Hanyang University) ;
  • Lee, Sang-Hoon (Dept. of EECIE., Hanyang University) ;
  • Suh, Il-Hong (The Graduate school of Information & Communications, Hanyang University)
  • 김민조 (한양대학교 정보통신대학원 정보통신공학과) ;
  • 권우영 (한양대학교 정보통신대학원 정보통신공학과) ;
  • 이상훈 (한양대학교 전자전기제어계측공학과) ;
  • 서일홍 (한양대학교 정보통신대학원 정보통신공학과)
  • Published : 2002.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

For action selection as well as teaming, simple associations between stimulus and response have been employed in most of literatures. But, for successful task accomplishment, it is required that artificial life system can team and express behavioral sequences. In this paper, we propose a novel action-selection-mechanism to deal with behavioral sequences. For this, we define behavioral motivation as a primitive node for action selection, and then hierarchically construct a tree with behavioral motivations. The vertical path of the tree represents behavioral sequences. Here, such a tree for our proposed ASM can be newly generated and/or updated, whenever a new behavioral sequence is learned. To show the validity of our proposed ASM, three 2-D grid world simulations will be illustrated.

Keywords