Abstract
Our research is linked with the general pattern of computing architecture, dedicated to multi-robots applications. The design of a robot football team needs to realize the different standard layers of an autonomous mobile robot (perception, decision; action). It also includes specific Artificial Intelligence and multi-agent systems problematics. Our study is based on real robots (than we call physical agents). The physical aspect is essential in this work. Indeed, we have to take account of the physical constraints associated to our application. So, the behaviors that we use must be adapted to the technical capacity (the dexterity) of the robots (the precision and the complexity of their actions). Moreover, an experimental platform is developed to validate the theoretical physical agent behaviors. This platform is called MICROB.
In this paper, we propose a flexible Multi-agent ARCHitecture (MARCH) adapted to multi-mobile-robots applications, for the football game purpose. In this architecture, we will propose the notions of phases and roles to select appropriate behavior for each agent. We describe also, the experimental platform and the physical agents.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
M. Asada, E. Uchibe, S. Noda, S. Tawaratsumida, K. Hosoda, “Coordination of multiple behaviors acquired by vision-based reinforcement learning,” Proceedings of the International Conference on Intelligent Robots and systems (IROS), pp 917–924, 1994.
M. Asada, M. Mataric, Y. Kuniyoshi, D. Duhaut, A. Drogoul, P. Stone, H. Asama, H. Kitano, “The RoboCup Physical agent challenge: Phase-I,” The First International Workshop on RoboCup, in Conjunction with IJCAI-97, pp 51–56, 1997.
S. Delaplace, P. Blazevic, J.G. Fontaine, N. Pons, J. Rabit, “Trajectory tracking for mobile robot” S.G. Tzafestas (ed.) Robotic Systems pp 313–320,1992 Kluwer Academic publishers.
A. Drogoul, D. Duhaut, “MICROB: Projet commun de LRP-LAFORIA 1995 de robotique collective,” Internal report, 1995.
H. Kitano, M. Veloso, H. Matsubara, M. Tambe, S. Coradeschi, I. Noda, P. Stone, E. Osawa, M. Asada, “The robocup synthetic agent challenge 97,” The First International Workshop on RoboCup, in Conjunction with IJCAI-97, pp 45–50, 1997.
H. Kitano, Y. Kuniyoshi, I. Noda, M. Asada, H. Matsubara, E. Osawa, “RoboCup: a challenge problem for AI,” Al magazine Vol. 18 N°1, pp 73–85, 1997.
J.L. de la Rosa, A. Oller, J. Veh, J. Puyol, “Soccer team based on agent-oriented programming” Journal of Robotics and Autonomous System Vol. 21, N°2 pp 167–176, 1997.
R. Sargent, B. Bailey, C. Witty, A. Wright, “The importance of fast vision in winning the first micro-robot world cup soccer tournament” Journal of Robotics and Autonomous System Vol. 21, N°2 pp 139–147, 1997.
P. Stone, M. Veloso, “Using decision tree confidence factors for multiagent control,” The First International Workshop on RoboCup, in Conjunction with IJCAI-97, pp 31–36, 1997.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rocher, S., Duhaut, D. (1998). MARCH : A flexible multi-agent architecture, applied to autonomous robots playing football. In: Drogoul, A., Tambe, M., Fukuda, T. (eds) Collective Robotics. CRW 1998. Lecture Notes in Computer Science, vol 1456. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0033377
Download citation
DOI: https://doi.org/10.1007/BFb0033377
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64768-3
Online ISBN: 978-3-540-68723-8
eBook Packages: Springer Book Archive