Performance analysis of a human–robot collaborative target recognition system

This paper presents a comprehensive analysis of time and action operational costs on an objective function developed by Bechar et al. (A. Bechar, J. Meyer and Y. Edan, “An objective function to evaluate performance of human–robot collaboration in target recognition tasks,” IEEE Trans. Syst. Man Cybe...

Full description

Saved in:
Bibliographic Details
Published inRobotica Vol. 30; no. 5; pp. 813 - 826
Main Authors Oren, Y., Bechar, A., Edan, Y.
Format Journal Article
LanguageEnglish
Published Cambridge, UK Cambridge University Press 01.09.2012
Subjects
Costs
False alarms
Human
Mathematical models
Performance evaluation
Target detection
Target recognition
Tasks
Operational cost
Target recognition
Objective function
Performance analysis
Operational level
Human–robot collaboration
Online AccessGet full text

Cover

More Information
Summary:This paper presents a comprehensive analysis of time and action operational costs on an objective function developed by Bechar et al. (A. Bechar, J. Meyer and Y. Edan, “An objective function to evaluate performance of human–robot collaboration in target recognition tasks,” IEEE Trans. Syst. Man Cybern. Part C39(6), 611–620 (2009)) for collaborative target recognition systems. Different task types, system reaction types, and environments were evaluated. Results reveal two types of task and system reactions – one focused on minimizing false alarms, and the second on detecting a target when one is presented. In addition, the analysis reveals a new property of the objective function based on a specific ratio between the weight differences that generalizes the model's objective function and facilitates its analysis. Results indicate that human decision time strongly influences system performance.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0263-5747
1469-8668
DOI:10.1017/S0263574711001020