Ants guide future pilots

  • Authors:

  • Sameer Alam;Minh-Ha Nguyen;Hussein A. Abbass;Michael Barlow

  • Affiliations:

  • The Artificial Life and Adaptive Robotics Laboratory, School of ITEE, University of New South Wales, Australian Defence Force Academy, Canberra, Australia;The Artificial Life and Adaptive Robotics Laboratory, School of ITEE, University of New South Wales, Australian Defence Force Academy, Canberra, Australia;The Artificial Life and Adaptive Robotics Laboratory, School of ITEE, University of New South Wales, Australian Defence Force Academy, Canberra, Australia;The Artificial Life and Adaptive Robotics Laboratory, School of ITEE, University of New South Wales, Australian Defence Force Academy, Canberra, Australia

  • Venue:
  • ACAL'07 Proceedings of the 3rd Australian conference on Progress in artificial life
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper an Ant Colony Optimization (ACO) approach is extended to the safety and time critical domain of air traffic management. This approach is used to generate a set of safe weather avoidance trajectories in a high fidelity air traffic simulation environment. Safety constraints are managed through an enumeration-and-elimination procedure. In this procedure the search space is discretized with each cell forming a state in graph. The arcs of the graph represent possible transition from one state to another. This state space is then manipulated to eliminate those states which violate aircraft performance parameters. To evolve different search behaviour, we used two different approaches (dominance and scalarization) for updating the learned knowledge (pheromone) in the environment. Results shows that our approach generates set of weather avoidance trajectories which are inherently safe.