Autonomous Mapping of Kitchen Environments and Applications

Abstract

Abstract — This paper investigates the problem of acquiring 3D semantic maps of indoor household environments, in particular kitchens. The objects modeled in these maps include cabinets, tables, drawers and shelves, and objects in the environment that have particular relevance for a household robotic assistant. Our mapping approach is based on point cloud representations, and a set of sophisticated interpretation methods operating on these representations. We outline the steps of our mapping approach, explain the key techniques that make it work and present their use for different applications. I.