The Framework for robotic navigation algorithms evaluation

Abstract

Algorithms for navigation, localization and mapping are core software for almost all mobile robotic systems. There are variety of such algorithms that use different approaches and utilize different robotic equipment. To select a suitable algorithm that fulfill the constraints on equipment, computational complexity, and performance quality we need a framework that allows to perform a large number of tests and simulations in different conditions. In this paper, we evaluate approaches to the creation of such framework, describe initial release of the framework and provide some results on navigation algorithms evaluation with it.