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 …

By transferring knowledge from large, diverse, task-agnostic datasets, modern machine
learning models can solve specific downstream tasks either zero-shot or with small task …

In this work, we present a scalable reinforcement learning method for training multi-task
policies from large offline datasets that can leverage both human demonstrations and …

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

Open-vocabulary generalization requires robotic systems to perform tasks involving complex
and diverse environments and task goals. While the recent advances in vision language …

Vision-and-language navigation (VLN) aims to build autonomous visual agents that follow
instructions and navigate in real scenes. To remember previously visited locations and …

Large language models (LLMs) have unlocked new capabilities of task planning from
human instructions. However, prior attempts to apply LLMs to real-world robotic tasks are …

Following language instructions to navigate in unseen environments is a challenging
problem for autonomous embodied agents. The agent not only needs to ground languages …

Understanding crowd motion dynamics is critical to real-world applications, eg, surveillance
systems and autonomous driving. This is challenging because it requires effectively …

State-of-the-art approaches to ObjectGoal navigation (ObjectNav) rely on reinforcement
learning and typically require significant computational resources and time for learning. We …