AUTOPILOT: A Distributed Planner for Air Fleet Control

Abstract

Distributed planning requires both architectures for structuring multiple planners and techniques for planning, communication, and cooperation. We describe a family of systems for distributed control of multiple aircraft, in which each aircraft plans it own flight path and avoids collisions with other aircraft. AUTOPILOT, the kernel planner used by each aircraft, comprises several processing experts that share a common world model. These experts sense the world, plan and evaluate flight paths, communicate with other aircraft, and control plan execution. We discuss four architectures for the distribution of airspace management and planning responsibility among the several aircraft occupying the airspace at any point in time. The architecture differ in the extent of cooperation and communication among aircraft.

Cite

Text

Thorndyke et al. "AUTOPILOT: A Distributed Planner for Air Fleet Control." International Joint Conference on Artificial Intelligence, 1981.

Markdown

[Thorndyke et al. "AUTOPILOT: A Distributed Planner for Air Fleet Control." International Joint Conference on Artificial Intelligence, 1981.](https://mlanthology.org/ijcai/1981/thorndyke1981ijcai-autopilot/)

BibTeX

@inproceedings{thorndyke1981ijcai-autopilot,
  title     = {{AUTOPILOT: A Distributed Planner for Air Fleet Control}},
  author    = {Thorndyke, Perry W. and McArtbur, Dave and Cammarata, Stephanie J.},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {1981},
  pages     = {171-177},
  url       = {https://mlanthology.org/ijcai/1981/thorndyke1981ijcai-autopilot/}
}