Robot formations using a single camera and entropy-based segmentation

Hyeun Jeong Min, Nikolaos Papanikolopoulos

Research output: Contribution to journalArticlepeer-review

11 Scopus citations

Abstract

This work presents a new problem along with our new algorithm for a multi-robot formation with minimally controlled conditions. For multi-robot cooperation, there have traditionally been prevailing assumptions in order to collect the necessary information. These assumptions include the existence of communication systems among the robots or the use of specialized sensors such as laser scanners or omnidirectional cameras. However, they are not always valid, especially in emergency situations or with miniature robots. We, therefore, need to deal with the conditions that have received less attention in research regarding a multi-robot formation. There are several challenges: (1) less information is available than the well-known formation algorithms assume, (2) following strategies for deformable shapes in a formation with only local information available are needed, and (3) target segmentation without any markers is required. This work presents a formation algorithm based on a visual tracking algorithm, including how to process the image measurements provided by a single monocular camera. Through several experiments with real robots (developed at the University of Minnesota), we show that the proposed algorithms work well with minimal sensing information.

Original languageEnglish (US)
Pages (from-to)21-41
Number of pages21
JournalJournal of Intelligent and Robotic Systems: Theory and Applications
Volume68
Issue number1
DOIs
StatePublished - Sep 1 2012

Keywords

  • Entropy
  • Moving target segmentation
  • Robot formations
  • Robot tracking

Fingerprint Dive into the research topics of 'Robot formations using a single camera and entropy-based segmentation'. Together they form a unique fingerprint.

Cite this