Shanker Keshavdas and Geert-Jan M. Kruijff
Autonomous Robotics, Ontology, Semantic Mapping
Our problem is one of a human-robot team exploring a previously unknown disaster scenario together. The team is building up situation awareness, gathering information about the prescence and structure of specific objects of in- terest like victims or threats. For a robot working with a human team, there are several challenges. From the viewpoint of task-work, there is time-pressure: The exploration needs to be done efficiently, and effectively. From the viewpoint of team-work, the robot needs to perform its tasks together with the human users such that it is apparent to the users why the robot is doing what it is doing. Without that, human users might fail to trust the robot, which can negatively impact overall team performance. In this paper, we present an approach to the field of semantic mapping, as a subset of robotic mapping; aiming to address the problems in both efficiency (task), and apparency (team). The approach models the environment from a geometrical- functional viewpoint, establishing where the robot needs to be, to be in an optimal position to gather particular in- formation relative to a 3D-landmark in the environment. The approach combines top-down logical and probabilistic inferences about 3D-structure and robot morphology, with bottom-up quantitative maps. The inferences result in vantage positions for information gathering which are op- timal in a quantitative sense (effectivity), and which mimic human spatial understanding (apparency). A quantitative evaluation shows that functional mapping leads to significantly better vantage points than a naive approach.
Important Links:
Go Back
