Evaluating Multi-Agent Robotic Systems Using Ground Truth

Abstract

A thorough empirical evaluation of multi-agent robotic systems is greatly facilitated if the true state of the world over time can be obtained. The accuracy of the beliefs as well as the overall performance can then be measured objectively and efficiently. In this paper we present a system for determining the ground truth state of the world, similar to the ceiling cameras used in RoboCup small-size league. We have used this ground truth data to evaluate the accuracy of the selfand object-localization of the robots in our RoboCup mid-size league team, the AGILO RoboCuppers. More complex models of the state estimation module have also been learned. These models provide insight into the workings and shortcomings of this module, and can be used to improve it.