Place: Room 621/622, GP South (Building 78)

Time: Thursday 13th Sept, 10:30 morning Tea, 11:00am seminar

Title: Modelling Air Traffic Control Systems using Learning Agents

Speaker: Morgan Smith, PhD Candidate

Abstract

The level of congestion in the airways is becoming an increasing problem.

Several researchers have expressed fears that the current air traffic control systems will not be capable of handling increased future traffic volumes. The current air traffic management system was designed with the fixed route structure, in order to enable the air traffic controllers to perform the separation role effectively. However, this approach leads to inefficient use of airspace and congestion problems as traffic volume increases.

One of the proposed solutions to remedy this situation gaining significant attention is free flight. Based on the idea of free routing, Free flight allows flights to choose their own path, and be responsible for their own separation, potentially increasing utilisation of existing airspace, and decreasing congestion.Free flight is an example of a large-scale system with interacting Components which has several overall goals such as safety. This project will use free flight as the testbed to explore the potential of conflict-free Manoeuvring of agents where no communication is involved. Each agent will act in its own interests, and its navigation will be dictated by an onboard learning classifier system, making it capable of adaptive behaviour.

The goal of the project is to determine whether interacting self-interested learning agents can create emergent properties of safety, efficiency, and effectiveness at the system level.

Dr. Ariel Liebman
Research Fellow
ARC Centre for Complex Systems
School of ITEE, University of Queensland
email: a.liebman@uq.edu.au
tel: +61-7-3365-1623
mobile: +61-(0)414-226-336
room: 78-414, GP South, St Lucia Campus
web: www.accs.edu.au