Multi-Layered Conceptual Spatial Mapping for Autonomous Mobile Robots.

摘要

This paper presents an approach to spatial mapping for autonomous mobile robots that are to operate among, and interact with, non-expert human users. We ar-gue that our approach of conceptual spatial mapping helps bridge the gap between the representations needed for low-level control of the robot, and the conceptual-topological representations of space humans have. Our approach maintains spatial knowledge on multiple in-terconnected layers. We show that a process for map acquisition, human-augmented mapping, which com-bines bottom-up and top-down influences from differ-ent modalities, will yield a rich multi-layered spatial representation. This representation enables the robot to perform complex actions in a human-populated en-vironment. We show that our approach can be used to establish a notion of situational and functional aware-ness.