Titlebook: Semantic Labeling of Places with Mobile Robots; Óscar Martínez Mozos Book 2010 Springer-Verlag Berlin Heidelberg 2010 cognition.learning.m

ordain

Conclusion,e information in the maps created by a mobile robot with labels that represent different places in the environment. These places have different functionalities, such as corridors, offices or kitchens. Moreover, throughout this book we have seen how the semantic information about places can improve t

burnish

negligence

Probabilistic Semantic Classification of Trajectories,classes in a trajectory are rather unlikely. For example, if the classification of the current pose is ., then it is rather unlikely that the classification of the next pose is . given the robot moved a short distance only. To get from the kitchen to the office, the robot first has to move through a doorway.

orthopedist

Semantic Information in Sensor Data,servation, we classify the observation itself by assigning a semantic label to each of its measurements. The main idea is to classify each laser beam into the class of the entity it hits. In this way, the data provided by the range sensor contains additional semantic information about the environment.