A framework for automatic multi-agents collaboration in target recognition tasks

Itshak Tkach, Yael Edan, Shimon Y. Nof

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

4 Scopus citations

Abstract

This paper presents a framework for collaboration of agents in a real-time dynamic target recognition system. A methodology was developed to apply "human-in-the-loop" and sensor collaboration for better image understanding in various situations. The proposed system provides a structured framework and set of interaction services between the physical agents (humans and sensors) and software agents; each of the agents (human and sensor) has a set of skills and resources that they contribute to the system. An approach of optimal control methodology through task administration protocols of agents collaboration is developed to optimize system performance. The framework enables better target recognition performance by optimal sensor assignment and human collaboration, with better flexibility by tasks and time management.

Original languageEnglish
Title of host publication21st International Conference on Production Research
Subtitle of host publicationInnovation in Product and Production, ICPR 2011 - Conference Proceedings
EditorsTobias Krause, Dieter Spath, Rolf Ilg
PublisherFraunhofer-Verlag
ISBN (Electronic)9783839602935
StatePublished - 1 Jan 2011
Event21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011 - Stuttgart, Germany
Duration: 31 Jul 20114 Aug 2011

Publication series

Name21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011 - Conference Proceedings

Conference

Conference21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011
Country/TerritoryGermany
CityStuttgart
Period31/07/114/08/11

Keywords

  • Multi-agents
  • Multi-sensors
  • Target recognition
  • Task administration protocols

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'A framework for automatic multi-agents collaboration in target recognition tasks'. Together they form a unique fingerprint.

Cite this