Robot@Home, a robotic dataset for semantic mapping of home environments

The Robot-at-Home dataset (<strong>Robot@Home</strong>, paper here) is a collection of raw and processed data from five domestic settings compiled by a mobile robot equipped with 4 RGB-D cameras and a 2D laser scanner. Its main purpose is to serve as a testbed for semantic mapping algorithms through the categorization of objects and/or rooms. This dataset is unique in three aspects: The provided data were captured with a rig of 4 RGB-D sensors with an overall field of view of 180°H. and 58°V., and with a 2D laser scanner. It comprises diverse and numerous data: <em>sequences of RGB-D images and laser scans</em> from the rooms of five apartments (87,000+ observations were collected), <em>topological information</em> about the connectivity of these rooms, and <em>3D reconstructions</em> and <em>2D geometric maps</em> of the visited rooms. The provided ground truth is dense, including <em>per-point annotations</em> of the categories of the objects and rooms appearing in the reconstructed scenarios, and <em>per-pixel annotations</em> of each RGB-D image within the recorded sequences During the data collection, a total of 36 rooms were completely inspected, so the dataset is rich in contextual information of objects and rooms. This is a valuable feature, missing in most of the state-of-the-art datasets, which can be exploited by, for instance, semantic mapping systems that leverage relationships like <em>pillows are usually on beds</em> or <em>ovens are not in bathrooms</em>.