There has been an emerging paradigm shift from the era of “internet AI” to “embodied AI,”
where AI algorithms and agents no longer learn from datasets of images, videos or text …

We present the largest and most comprehensive empirical study of pre-trained visual
representations (PVRs) or visual 'foundation models' for Embodied AI. First, we curate …

The ability to accurately locate and navigate to a specific object is a crucial capability for
embodied agents that operate in the real world and interact with objects to complete tasks …

Abstract We introduce Habitat 2.0 (H2. 0), a simulation platform for training virtual robots in
interactive 3D environments and complex physics-enabled scenarios. We make …

Semantic navigation is necessary to deploy mobile robots in uncontrolled environments
such as homes or hospitals. Many learning-based approaches have been proposed in …

We present the Habitat-Matterport 3D (HM3D) dataset. HM3D is a large-scale dataset of
1,000 building-scale 3D reconstructions from a diverse set of real-world locations. Each …

Embodied AI aims to create agents that complete complex tasks by interacting with the
environment. A key problem in this field is embodied navigation which understands multi …

Recent research in language-guided visual navigation has demonstrated a significant
demand for the diversity of traversable environments and the quantity of supervision for …

Contrastive language image pretraining (CLIP) encoders have been shown to be beneficial
for a range of visual tasks from classification and detection to captioning and image …

We present a scalable approach for learning open-world object-goal navigation (ObjectNav)–
the task of asking a virtual robot (agent) to find any instance of an object in an unexplored …