A Landmark-Aware Visual Navigation Dataset
This provides a new dataset for researchers in visual navigation to train models for human-centric exploration and mapping, though it is incremental as it builds on existing data collection methods.
The authors tackled the lack of real-world human-navigation datasets for visual navigation by introducing the Landmark-Aware Visual Navigation (LAVN) dataset, which includes RGBD observations and human point-click pairs from virtual and real-world environments to support supervised learning of exploration policies and map building.
Map representations learned by expert demonstrations have shown promising research value. However, the field of visual navigation still faces challenges due to the lack of real-world human-navigation datasets that can support efficient, supervised, representation learning of environments. We present a Landmark-Aware Visual Navigation (LAVN) dataset to allow for supervised learning of human-centric exploration policies and map building. We collect RGBD 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. The human annotators also provide distinct landmark examples along each trajectory, which we intuit will simplify the task of map or graph building and localization. These human point-clicks serve as direct supervision for waypoint prediction when learning to explore in environments. Our dataset covers a wide spectrum of scenes, including rooms in indoor environments, as well as walkways outdoors. We release our dataset with detailed documentation at https://huggingface.co/datasets/visnavdataset/lavn (DOI: 10.57967/hf/2386) and a plan for long-term preservation.