How things appear to work: Predicting behaviors from device diagrams

N. Hari Narayanan, Masaki Suwa, Hiroshi Motoda

研究成果: Paper査読

13 被引用数 (Scopus)

抄録

This paper introduces a problem solving task involving common sense reasoning that humans are adept at, but one which has not received much attention within the area of cognitive modeling until recently. This is the task of predicting the operation of simple mechanical devices, in terms of behaviors of their components, from labeled schematic diagrams showing the spatial configuration of components and a given initial condition. We describe this task, present a cognitive process model developed from task and protocol analyses, and illustrate it using the example of a pressure gauge. Then the architecture of a corresponding computer model and a control algorithm embodying the cognitive strategy are proposed.

本文言語English
ページ1161-1167
ページ数7
出版ステータスPublished - 1994
外部発表はい
イベントProceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2) - Seattle, WA, USA
継続期間: 1994 7月 311994 8月 4

Other

OtherProceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2)
CitySeattle, WA, USA
Period94/7/3194/8/4

ASJC Scopus subject areas

  • ソフトウェア
  • 人工知能

フィンガープリント

「How things appear to work: Predicting behaviors from device diagrams」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル