Anticipation as a strategy: a design paradigm for robotics

  • Authors:
  • Mary-Anne Williams;Peter Gärdenfors;Benjamin Johnston;Glenn Wightwick

  • Affiliations:
  • Innovation and Enterprise Research Laboratory, QCIS, University of Technology, Sydney;Innovation and Enterprise Research Laboratory, QCIS, University of Technology, Sydney;Innovation and Enterprise Research Laboratory, QCIS, University of Technology, Sydney;Innovation and Enterprise Research Laboratory, QCIS, University of Technology, Sydney

  • Venue:
  • KSEM'10 Proceedings of the 4th international conference on Knowledge science, engineering and management
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Anticipation plays a crucial role during any action, particularly in agents operating in open, complex and dynamic environments. In this paper we consider the role of anticipation as a strategy from a design perspective. Anticipation is a crucial skill in sporting games like soccer, tennis and cricket. We explore the role of anticipation in robot soccer matches in the context of reaching the RoboCup vision to develop a robot soccer team capable of defeating the FIFA World Champions in 2050. Anticipation in soccer can be planned or emergent but whether planned or emergent, anticipation can be designed. Two key obstacles stand in the way of developing more anticipatory robot systems; an impoverished understanding of the "anticipation" process/capability and a lack of know-how in the design of anticipatory systems. Several teams at RoboCup have developed remarkable preemptive behaviors. The CMU Dive and UTS Dodge are two compelling examples. In this paper we take steps towards designing robots that can adopt anticipatory behaviors by proposing an innovative model of anticipation as a strategy that specifies the key characteristics of anticipation behaviors to be developed. The model can drive the design of autonomous systems by providing a means to explore and to represent anticipation requirements. Our approach is to analyze anticipation as a strategy and then to use the insights obtained to design a reference model that can be used to specify a set of anticipatory requirements for guiding an autonomous robot soccer system.