You are on page 1of 2

International Journal of Scientific & Engineering Research, Volume 1, Issue 1, October-2010 1

SWARM INTELLIGENCE FOR CONFLICT DE-


TECTION AND RESOLUTION IN FREE
FLIGHT ENVIRONMENTS
MANIKANDAN VIJAYAKUMAR

Abstract— In this paper we propose the Swarm intelligence (SI) and Free flight environment. Swarm Intelligence, which is a
type of artificial intelligence based on the collective behavior of decentralized, self-organized systems. SI systems are typically
made up of a population of simple agents or boids interacting locally with one another and with their environment. The agents
follow very simple rules, and although there is no centralized control structure dictating how individual agents should behave,
local, and to a certain degree random. On the other way Free flight is a developing air traffic control method that uses no
centralized control (e.g. air traffic controllers). Instead, parts of airspace are reserved dynamically and automatically in a
distributed way using computer communication to ensure the required separation between aircraft. There are some cases
where the conflicts occur in free flight environment leading to chaos. This is been detected and resolved using the Swarm
Intelligence which also helps in optimizing the path, finding the shortest path and also in air traffic control .

Index Terms— Free flight environment, Swarm intelligence (SI), Air Traffic Controllers (ATC), Detecting, Optimizing, Resolving
and Artificial Intelligence (A.I).

1 INTRODUCTION

N ow-a-days air traffic system is reaching its opera-


tional limits, and accommodating future air traffic
growth will be a challenging task for the aviation
Airport and Airspace Simulation Model, etc., have been
developed by industry and government organizations;
however, they are designed around the speci c require-
industry. Radical design changes in the present-day air ments of air traffic service providers. Furthermore, Na-
traffic control system are required to meet this challenge. tional Aeronautics and Space Administration (NASA)
Free ight is one such initiative that is actively being pur- research found them to be inadequate for modeling fu-
sued by government and industry alike, where pilots will ture ATM concepts and to be lacking in several capabili-
have an active role in airborne separation and real-time ties.
route planning. However, there are several safety chal- Based on the projected requirements for free ight we
lenges and design issues to be addressed before free ight established an algorithm to detect and resolve the con-
can become a reality. flicts occurring in the free flight environments. Swarm
Free Flight is an Air Traffic Management (ATM) concept Intelligence is an AI technique that focuses on studying
whereby airspace users are allowed more freedom in se- the collective behavior of a decentralized system made up
lecting routes. This could mean they are no longer re- by a population of simple agents interacting locally with
stricted to airways but are allowed to fly direct routes each other and with the environment. Although there is
from origin to destination at their optimal altitudes, using typically no centralized control dictating the behavior of
favorable winds and avoiding hazards themselves. By no the agents, local interactions among the agents often
longer following airways it could, however, become cause a global pattern to emerge. Examples of systems
harder for Air Traffic Control (ATC) to monitor and con- like this can be found abundant in nature, including ant
trol the traffic. To prevent this and to provide true self- colonies, bird flocking, animal herding, honey bees, bac-
optimization, airborne separation has been proposed as a teria, and many more. This kind of “swarm-like” algo-
part of Free Flight. There have been many potential ATM rithm, such as Ant Colony Optimization (ACO) and Par-
concepts in the past which have aimed at direct routing, ticle Swarm Optimization (PSO), has already been ap-
but airborne separation, even under IFR conditions, is a plied successfully to solve real-world optimization prob-
unique feature of the Free Flight concept. It is a revolutio- lems in engineering and telecommunication. SI models
nary concept that will enable greater traffic volume and have many features in common with Evolutionary Algo-
operational flexibility by distributing some of the functio- rithms. Like EA, SI models are population-based. The
nality, including conflict detection and resolution, to air- system is initialized with a population of individuals (i.e.,
borne systems and pilots. Advanced air traffic manage- potential solutions). These individuals are then manipu-
ment (ATM) concepts that are envisioned in free ight lated over many generations by ways of mimicking social
must be investigated and evaluated before they can be behavior of insects or animals, in an effort to find the op-
operationally tested, without which it can be a risky and tima. Unlike EA, SI models do not use evolutionary oper-
expensive exercise. A wide range of ATM systems, such ators such as crossover and mutation. A potential solution
as the Total Airspace and Airport Modeler, the Opera- simply "flies" through the search space by modifying it-
tional and Supportability Implementation System, the self according to its relationship with other individuals in

IJSER © 2010 Oct 2010


2 International Journal of Scientific & Engineering Research, Volume 1, Issue 1, October-2010

For Complete Paper need to contact:


ijser.editor@ijser.org
IJSER – copyright required from author

You might also like