Demonstration of Digital Pheromone Swarming Control of Multiple Unmanned Air Vehicles
John Sauter, Robert Matthews, H. Van Dyke Parunak, Sven Brueckner
- Year
- 2005
- Citations
- 16
Abstract
The use of digital pheromones for controlling and coordinating swarms of unmanned vehicles has been studied under various conditions demonstrating their effectiveness in multiple military scenarios in simulation. An experiment was conducted to verify that these same algorithms could effectively coordinate unmanned vehicles in a simulated exercise. Two air vehicles (modified target drones) controlled by digital pheromones and four ground robots controlled by a related stigmergic algorithm successfully executed a two-hour multi-mission surveillance, patrol, target acquisition, and tracking scenario without any scripting. The vehicles were given only high-level instructions, such as “survey this area and identify and track any targets” or “patrol around this convoy”. The air vehicles were able to dynamically adapt to new commands and coordinate their actions with each other and the ground robots to achieve the objectives. The algorithm’s robustness was demonstrated when it dynamically adjusted to the unplanned failure of one of the ground robots without any operator intervention.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002