An objective function for performance measurement of human-robot target recognition systems in unstructured environments

Avital Bechar, Yael Edan, Joachim Meyer

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Robotic systems for unstructured environments need to cope with rapid changes in time and space, inherent uncertainty, and generate unpredictable and dynamic situations, resulting in lack of information, due to inadequate sensor accuracy and computational limitations. Introduction of a Human-Operator (HO) into the system can help simplify the robotic system and ensure improved performance. In the current study we developed an objective function for different levels of HO-robot collaboration in a target recognition task. The objective function considers several HO and robot parameters, which contribute to the overall performance in each level of collaboration. Results indicate that HO-robot collaboration improves system performance in many conditions. The optimal collaboration level depends on image complexity and on robot and HO characteristics. Some of the latter have to be assessed through behavioral research on HOs.

Original languageEnglish
Title of host publication2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004
Pages118-123
Number of pages6
DOIs
StatePublished - 1 Dec 2004
Event2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004 - The Hague, Netherlands
Duration: 10 Oct 200413 Oct 2004

Publication series

NameConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Volume1
ISSN (Print)1062-922X

Conference

Conference2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004
Country/TerritoryNetherlands
CityThe Hague
Period10/10/0413/10/04

Keywords

  • Human-robot interaction
  • Levels of automation
  • Objective function
  • Target recognition
  • Unstructured environments

Fingerprint

Dive into the research topics of 'An objective function for performance measurement of human-robot target recognition systems in unstructured environments'. Together they form a unique fingerprint.

Cite this