Regression-based network monitoring in swarm robotic systems

Mobile ad-hoc networks are becoming more common as robotic swarm technology becomes possible. One issue surrounding swarm technology is communication between robots. Communication costs time and energy, and can impact the performance of a swarm. In order to control the network, network state information must be acquired through network monitoring. We propose a novel REgression-based network Monitoring (REM) algorithm where robots in a swarm receive network state data only when necessary for the task at hand. This simple distributed algorithm will save time and energy in communication by creating predictive models using regressions, minimizing network monitoring overhead.