Page 50 - Innovations in Intelligent Machines

Team, Game, and Negotiation based Intelligent
Autonomous UAV Task Allocation for Wide

Area Applications

1
2
P.B. Sujit , A. Sinha , and D. Ghose 3
1
Department of Electrical and Computer Engineering, Brigham Young University,
Provo, Utah, USA
2
Department of Aerospace Engineering, Indian Institute of Science,
Bangalore, India
3
Department of Aerospace Engineering, Indian Institute of Science,
Bangalore, India
pbsujit@byu.edu, asinha@aero.iisc.ernet.in,dghose@aero.iisc.ernet.in
Abstract. Unmanned aerial vehicles (UAV) have the potential to be used for
search and surveillance missions, and as munitions in the battlefield. The UAVs
are deployed in swarms as they may not have sufficient computational, sensor, and
operational capability to complete the task single-handedly. A desirable feature for
these UAV swarms is the capability of intelligent autonomous decision making and
coordination, with minimal or no centralized control. In this chapter, we present
decentralized and distributed task allocation schemes based on concepts from team
theory, game theory, and from negotiation techniques used in decision-making prob-
lems arising in economics, and apply these to design intelligent decision-making
strategies for multiple UAV systems performing a wide area search and surveillance
mission. We also address the task of searching an unknown environment, which is a
major component in such missions, separately using game theoretical concepts.

1 Introduction

Unmanned aerial vehicles are being extensively used for military and civi-
lian applications, like search, surveillance and as munitions in the battlefield.
They play a crucial role in information gathering from hostile and unknown
regions. These UAVs can also be used as munitions to search, attack and
destroy targets in an unknown region. The UAVs used for these applications
may have limited effectiveness and may not have the required stealth capabil-
ity and munition payload to complete the task single-handedly. Hence, there
is a necessity for such UAVs to be deployed in swarms. A desirable feature for
these UAV swarms is the capability of intelligent autonomous decision making
and coordination. The UAVs operating in an unknown region are expected to

P.B. Sujit et al.: Team, Game, and Negotiation based Intelligent Autonomous UAV Task Allo-
cation for Wide Area Applications, Studies in Computational Intelligence (SCI) 70, 39–75 (2007)
www.springerlink.com c Springer-Verlag Berlin Heidelberg 2007