Home // ADAPTIVE 2015, The Seventh International Conference on Adaptive and Self-Adaptive Systems and Applications // View article

Multi-Agent Model for Leader Identification in Platoon System

Authors:
Dafflon Baudouin
Gechter Franck

Keywords: multi-agent; platoon system; leader identification

Abstract:
In the past decades, the research on autonomous vehicles and transportation systems has performed a great breakthrough. Among the emergent new transportation modes, the development of platoon control solutions seems to be very promising in terms of environmental impact and traffic jam aspects. The two main approaches generally encountered in literature deal with either a global point of view or a local one. In the local approaches, the follower vehicle perceives its environment, identifies a leader and applies a function to calculate a command. This paper deals with the identification task for a local platoon control system. This identification task is made using the reactive multi-agent paradigm. In the proposed system, the identification task can be defined as a selection of one pattern from a set following several criteria. These patterns are emergent structures made of agents which aggregate on specific areas of their environment depending on their perception and their interactions. The agent environment is built using data collected by sensors. The sensors raw data are processed so as to be integrated into agent environment. The association between one physical sensor and a suitable processing algorithm is called an abstract sensor. The paper presents in detail the proposal and its applications in simulated and real environments.

Pages: 74 to 79

Copyright: Copyright (c) IARIA, 2015

Publication date: March 22, 2015

Published in: conference

ISSN: 2308-4146

ISBN: 978-1-61208-391-9

Location: Nice, France

Dates: from March 22, 2015 to March 27, 2015