Distributed Learning in Swarm Systems: A Case Study

Abstract

This thesis investigates several learning issues in swarm systems under a case study--- the stick pulling experiment. This is a strictly collaborative problem where collaboration between non-communicating robots is required to complete the task. We base our experiments on a probabilistic model which is faithful in simulating experiments with real robots. We extend the systematic search with early stopping and get the optimal performances of fully heterogeneous teams consisting of 2--6 robots.