Landmark-Aware Visual Navigation (LAVN) Dataset

<p>We present a \textbf{L}andmark-\textbf{A}ware \textbf{V}isual \textbf{N}avigation (LAVN) dataset to allow for supervised learning of human-centric exploration policies. We collect RGB observation and human point-click pairs as a human annotator explores virtual and real world environments with the goal of full coverage exploration of the space. These human point-clicks serve as direct supervision for waypoint prediction when learning to explore in environments. The human annotators also provide distinct landmark examples along each trajectory, which we intuit &nbsp;will simplify the task of map or graph building and localization.&nbsp;</p>