Aircraft Swarm Intelligence: An Approach to Coordinated Swarming with Artificial Potential Functions & Gradient Descent

Abstract

This study presents an organized method of swarm coordination with the use of artificial potential functions (APFs) utilizing a first-order optimization gradient descent algorithm. With the emergence of an increasing need for Unmanned Aerial Vehicles (UAVs) system control, swarm coordination presents an approach to eliminate collisions and effectively achieve mission goal parameters. The gradient descent algorithm begins with an initial configuration and implements a step, or iteration, in a direction that is opposite to the gradient. The APFs contain both repulsive and attractive potential functions that contribute to the gradient ultimately determining the states of the agent with respect to the distance from other agents and obstacles. Obstacles or other agents projected to be too close within the path of an individual agent affect the agent’s path and dynamics. Experimental simulations consisted of three, five, and ten agents with two obstacles arranged at different initial positions. Agents’ dynamics were constrained to match the Boeing AH-6 Unmanned Little Bird (ULB). Simulations had shown each agent to effectively travel to a prescribed target location while avoiding obstacles and other agents simultaneously.