Mosaic: Learning unified multi-sensory object property representations for robot learning via interactive perception

G Tatiya, J Francis, HH Wu, Y Bisk… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
A holistic understanding of object properties across diverse sensory modalities (eg, visual,
audio, and haptic) is essential for tasks ranging from object categorization to complex …

Mosaic: Learning unified multi-sensory object property representations for robot perception

G Tatiya, J Francis, HH Wu, Y Bisk… - arXiv preprint arXiv …, 2023 - arxiv.org
A holistic understanding of object properties across diverse sensory modalities (eg, visual,
audio, and haptic) is essential for tasks ranging from object categorization to complex …

Cross-tool and cross-behavior perceptual knowledge transfer for grounded object recognition

G Tatiya, J Francis, J Sinapov - arXiv preprint arXiv:2303.04023, 2023 - arxiv.org
Humans learn about objects via interaction and using multiple perceptions, such as vision,
sound, and touch. While vision can provide information about an object's appearance, non …

Discovering Object Attributes by Prompting Large Language Models with Perception-Action APIs

A Mavrogiannis, D Yuan, Y Aloimonos - arXiv preprint arXiv:2409.15505, 2024 - arxiv.org
There has been a lot of interest in grounding natural language to physical entities through
visual context. While Vision Language Models (VLMs) can ground linguistic instructions to …

Active Information Gathering for Long-Horizon Navigation Under Uncertainty by Learning the Value of Information

RI Arnob, GJ Stein - arXiv preprint arXiv:2403.03269, 2024 - arxiv.org
We address the task of long-horizon navigation in partially mapped environments for which
active gathering of information about faraway unseen space is essential for good behavior …

Symbol Grounding for Task and Motion Planning in Robotics

X Zhang - 2024 - search.proquest.com
For modern robots that are equipped with a set of skills, such as manipulation and
navigation, it's crucial that they can autonomously make decisions to complete tasks over …