A Hybrid Evolutionary Probablistic Framework for Developing Robotic Team Behaviors

Edward Newett, Ashraf Saad

2005

Abstract

One of the inherent issues in team-based multiagent robotics is coordinating a cooperative task decomposition. Use of explicit communication models or game theoretic approaches to model teammate behaviors can be costly and error-prone. This paper describes a method of discovering a set of behaviors that allows a team to intrisically function in a collaborative manner. Probabilistic plan- ners based on spreading activation networks that determine these behaviors are implemented in each robot. A genetic algorithm is used to find the appropriate link strengths within each of these networks to produce an overall dynamic team. It is shown that a team controlled by spreading activation networks can perform well as a team by maintaining these behaviors in environmental situations other than the one used for GA evolution. From this framework, a goal-directed task planning approach can be envisioned to deploy a fully functional robot team.

References

  1. Arkin, R., Balch, T.: Cooperative multiagent robotic systems (1998)
  2. Bagchi, S., Biswas, G., Kawamura, K.: Task planning under uncertainty using a spreading activation network. IEEE Transactions on Systems, Man, and Cybernetics, Part A 30 (2000) 639-650
  3. Verschure, P.F.M.J., Althaus, P.: A real-world rational agent: unifying old and new ai. Cognitive Science 27 (2003) 561-590
  4. Panait, L., Luke, S.: Cooperative multi-agent learning: The state of the art. Technical Report GMU-CS-TR-2003-1, Department of Computer Science, George Mason University, 4400 University Drive MS 4A5, Fairfax, VA 22030-4444 USA (2003)
  5. Stanley, K.O., Miikkulainen, R.: Evolving neural network through augmenting topologies. Evolutionary Computation 10 (2002) 99-127
  6. Kortenkamp, D., Chown, E.: A directional spreading activation network for mobile robot navigation. In: Proceedings of the second international conference on From animals to animats 2 : simulation of adaptive behavior, Cambridge, MA, USA, MIT Press (1993) 218-224
  7. Michel, O.: Khepera Simulator version 2.0. User Manual. (1996) Originally downloaded from http://www.i3s.unice.fr/.
  8. Nilsson, T.: Kiks is a khepera simulator. Master's thesis, Ume University (2001)
Download


Paper Citation


in Harvard Style

Newett E. and Saad A. (2005). A Hybrid Evolutionary Probablistic Framework for Developing Robotic Team Behaviors . In Proceedings of the 1st International Workshop on Multi-Agent Robotic Systems - Volume 1: MARS, (ICINCO 2005) ISBN 972-8865-34-1, pages 88-101. DOI: 10.5220/0001196500880101


in Bibtex Style

@conference{mars05,
author={Edward Newett and Ashraf Saad},
title={A Hybrid Evolutionary Probablistic Framework for Developing Robotic Team Behaviors},
booktitle={Proceedings of the 1st International Workshop on Multi-Agent Robotic Systems - Volume 1: MARS, (ICINCO 2005)},
year={2005},
pages={88-101},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001196500880101},
isbn={972-8865-34-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Workshop on Multi-Agent Robotic Systems - Volume 1: MARS, (ICINCO 2005)
TI - A Hybrid Evolutionary Probablistic Framework for Developing Robotic Team Behaviors
SN - 972-8865-34-1
AU - Newett E.
AU - Saad A.
PY - 2005
SP - 88
EP - 101
DO - 10.5220/0001196500880101