Statistical Evaluation of the Kernel DM+V/W Algorithm for Building Gas Distribution Maps in Uncontrolled Environments

In this paper we present a statistical evaluation of the Kernel DM+V/W algorithm to build two-dimensional gas distribution maps with a mobile robot. In addition to gas sensor measurements from an "e-nose" the Kernel DM+V/W algorithm also takes into account wind information received from an ultrasonic anemometer. We evaluate the method based on real measurements in three uncontrolled environments with very different properties. As a measure for the model quality we compute how well unseen measurements are predicted in terms of the data likelihood. A paired Wilcoxon signed rank test shows a significant improvement (at a confidence level of 95%) of the model quality when using wind information.