Response threshold-based task allocation in a reinforcement learning robotic swarm

Abstract

Swarm robotics is a relatively new research area, established as an application of social insects swarm intelligence to multi-robot systems. This paper focuses on the division of labor, and a response threshold model observed in insect societies is applied to a swarm robotic system that performs food foraging. Each robot has a response threshold for leaving their nest and then making a decision by using a reinforcement learning controller for food-searching. In particular, the effect of response threshold reinforcements is investigated.