An object-based semantic world model for long-term change detection and semantic querying

Recent years have seen rising interest in robotic mapping algorithms that operate at the level of objects, rather than two- or three-dimensional occupancy. Such “semantic maps” permit higher-level reasoning than occupancy maps, and are useful for any application that involves dealing with objects, including grasping, change detection, and object search. We describe and experimentally verify such a system aboard a mobile robot equipped with a Microsoft Kinect RGB-D sensor. Our representation is object-based, and makes uniquely weak assumptions about the quality of the perceptual data available; in particular, we perform no explicit object recognition. This allows our system to operate in large, dynamic, and uncon-strained environments, where modeling every object that occurs (or might occur) is impractical. Our dataset, which is publicly available, consists of 67 autonomous runs of our robot over a six-week period in a roughly 1600m² office environment. We demonstrate two applications built on our system: semantic querying and change detection.

I. Introduction

Robotic mapping has been a field of study for more than thirty years [1] and the last ten have seen particular success. With widely-available platforms and sensors, two-dimensional occupancy grid maps can now be built with off-the-shelf tools like DP-SLAM [2] or GMapping [3]. Such maps support navigational planning and building highly accurate plans of buildings. Recent years have seen a focus on maps that operate at a higher level: maps of objects, not just free and occupied space.