Reinforcement learning (RL), particularly its combination with deep neural networks,
referred to as deep RL (DRL), has shown tremendous promise across a wide range of …

Understanding and reasoning about spatial relationships is crucial for Visual Question
Answering (VQA) and robotics. Vision Language Models (VLMs) have shown impressive …

We survey applications of pretrained foundation models in robotics. Traditional deep
learning models in robotics are trained on small datasets tailored for specific tasks, which …

The proliferation of Large Language Models (LLMs) has s fueled a shift in robot learning
from automation towards general embodied Artificial Intelligence (AI). Adopting foundation …

Robotic learning for navigation in unfamiliar environments needs to provide policies for both
task-oriented navigation (ie, reaching a goal that the robot has located), and task-agnostic …

We present Habitat 3.0: a simulation platform for studying collaborative human-robot tasks in
home environments. Habitat 3.0 offers contributions across three dimensions:(1) Accurate …

We propose CLIP-Fields, an implicit scene model that can be used for a variety of tasks,
such as segmentation, instance identification, semantic search over space, and view …

Multilingual language models are widely used to extend NLP systems to low-resource
languages. However, concrete evidence for the effects of multilinguality on language …

Abstract We contribute the Habitat Synthetic Scene Dataset a dataset of 211 high-quality 3D
scenes and use it to test navigation agent generalization to realistic 3D environments. Our …