Cooperative Plan Identification: Constructing Concise and Effective Plan Descriptions

Intelligent agents are often called uponto formplans that direct their ownor other agents’ activities. For these systems, the ability to describe plans to people in natural waysis an essential aspect of their interface. In this paper, wepresent the CooperativePlanIdentification (CPI) architecture, a computationalmodelthat generatesconcise, effective textual descriptions of plan data structures. Themodelincorporates previous theoretical workon the comprehension of plan descriptions, using a generate-and-test approachto performefficient search throughthe space of candidate descriptions. Wedescribe an empirical evaluation of the CPIarchitecture in whichsubjects following instructions produced by the CPI architecture performed their tasks with fewer execution errors and achieveda higher percentageof their tasks’ goals than did subjects following instructions producedby alternative methods.

Authors

• R. Michael Young
• North Carolina State University

Keywords

No keywords are indexed for this paper.