Abstract

{bhroleno, sean, ksulliv2, cvo1} @ cs.gmu.edu A classic example of multiagent coordination in a shared environment involves the use of pheromone deposits as a communication mechanism. Due to physical limitations in deploying actual pheromones, we propose a sparse representation of the pheromones using movable beacons. There is no communication between the beacons to propagate pheromones; instead, robots make movement and update decisions based entirely on local pheromone values. Robots deploy the beacons throughout the environment, and subsequently move them and update them using a variation of value iteration. Simulation results show that our approach is effective at finding good trails, locally improving them, and adapting to dynamic changes in the environments.

Citations