Home // COGNITIVE 2013, The Fifth International Conference on Advanced Cognitive Technologies and Applications // View article

Specifying Desired Behaviour in Hybrid Central/Self-Organising Multi-Agent Systems

Authors:
Yaser Chaaban
Christian Müller-Schloer

Keywords: Path planning; A*-algorithm; Multi-Agent Systems; autonomous vehicles; Hybrid Coordination; Organic Computing

Abstract:
Path planning for multiple agents in a common environment is a challenging research problem. In previous papers, we introduced a hybrid architecture solving the conflict between a central unit (an observer and a controller) and decentralised autonomous agents. This architecture should have mechanisms for planning, but only as recommendation, and control decisions. In this paper, we focus on planning of the desired behaviour of agents in a shared environment. The scenario used in this work is a traffic intersection without traffic lights. Therefore, an A*-algorithm was adapted for the path planning. Consequently, the designed algorithm calculates collision-free trajectories (central planning) for all agents (vehicles) in a shared environment (the centre of the intersection) enabling them to avoid collisions. The experimental results demonstrated a high performance of our adapted A*-algorithm.

Pages: 1 to 6

Copyright: Copyright (c) IARIA, 2013

Publication date: May 27, 2013

Published in: conference

ISSN: 2308-4197

ISBN: 978-1-61208-273-8

Location: Valencia, Spain

Dates: from May 27, 2013 to June 1, 2013