Automatic behavior pattern classification for social robots

  • Authors:
  • Abraham Prieto;Francisco Bellas;Pilar Caamaño;Richard J. Duro

  • Affiliations:
  • Integrated Group for Engineering Research, Universidade da Coruña, Spain;Integrated Group for Engineering Research, Universidade da Coruña, Spain;Integrated Group for Engineering Research, Universidade da Coruña, Spain;Integrated Group for Engineering Research, Universidade da Coruña, Spain

  • Venue:
  • HAIS'10 Proceedings of the 5th international conference on Hybrid Artificial Intelligence Systems - Volume Part I
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we focus our attention on providing robots with a system that allows them to automatically detect behavior patterns in other robots, as a first step to introducing social responsive robots The system is called ANPAC (Automatic Neural-based Pattern Classification) Its main feature is that ANPAC automatically adjusts the optimal processing window size and obtains the appropriate features through a dimensional transformation process that allow for the classification of behavioral patterns of large groups of entities from perception datasets Here we present the basic elements and operation of ANPAC, and illustrate its applicability through the detection of behavior patterns in the motion of flocks.